diff options
author | 2017-05-01 15:34:01 -0400 | |
---|---|---|
committer | 2017-05-01 20:59:45 +0000 | |
commit | 879a08ac146acb2518363cc9d2d8aa6dce04528d (patch) | |
tree | 5c0c0370b00db7c26d12d4d89596f838cfc090c2 /src/jumper | |
parent | 6ab223e0f0203225c9cf019b56561489027e4b0d (diff) |
refactor hsl_to_rgb a touch
This rewrites the existing logic to expose more of the symmetries,
and especially to make them clearly identical subexpressions.
I think it's clear that the intent in hue_to_rgb is to wrap the t value
back into 0-1... that's t = fract(t).
No GM diffs.
Change-Id: I9d62d8f80bcb45711ee334f953d3f6410e068ce4
Reviewed-on: https://skia-review.googlesource.com/14940
Reviewed-by: Herb Derby <herb@google.com>
Diffstat (limited to 'src/jumper')
-rw-r--r-- | src/jumper/SkJumper_generated.S | 4200 | ||||
-rw-r--r-- | src/jumper/SkJumper_generated_win.S | 3883 | ||||
-rw-r--r-- | src/jumper/SkJumper_stages.cpp | 14 |
3 files changed, 3894 insertions, 4203 deletions
diff --git a/src/jumper/SkJumper_generated.S b/src/jumper/SkJumper_generated.S index 48530e5576..df34f28a18 100644 --- a/src/jumper/SkJumper_generated.S +++ b/src/jumper/SkJumper_generated.S @@ -1030,91 +1030,78 @@ FUNCTION(_sk_hsl_to_rgb_aarch64) _sk_hsl_to_rgb_aarch64: .long 0x52a7d548 // mov w8, #0x3eaa0000 .long 0x72955568 // movk w8, #0xaaab - .long 0x4e040d18 // dup v24.4s, w8 + .long 0x4e040d15 // dup v21.4s, w8 .long 0x52a7c548 // mov w8, #0x3e2a0000 .long 0x72955568 // movk w8, #0xaaab - .long 0x4f03f613 // fmov v19.4s, #1.000000000000000000e+00 - .long 0x4e040d15 // dup v21.4s, w8 + .long 0x4e040d12 // dup v18.4s, w8 .long 0x52a7e548 // mov w8, #0x3f2a0000 - .long 0x4f0167f2 // movi v18.4s, #0x3f, lsl #24 - .long 0x4e22d439 // fadd v25.4s, v1.4s, v2.4s .long 0x72955568 // movk w8, #0xaaab - .long 0x4e33d43d // fadd v29.4s, v1.4s, v19.4s - .long 0x4ea0d830 // fcmeq v16.4s, v1.4s, #0.0 - .long 0x4f07f616 // fmov v22.4s, #-1.000000000000000000e+00 - .long 0x4e040d1a // dup v26.4s, w8 + .long 0x4f0167f1 // movi v17.4s, #0x3f, lsl #24 + .long 0x6e22dc33 // fmul v19.4s, v1.4s, v2.4s + .long 0x4e040d19 // dup v25.4s, w8 .long 0x52b7d548 // mov w8, #0xbeaa0000 - .long 0x6ea2e65c // fcmgt v28.4s, v18.4s, v2.4s - .long 0x4ea2cc39 // fmls v25.4s, v1.4s, v2.4s - .long 0x6e22dfa1 // fmul v1.4s, v29.4s, v2.4s + .long 0x4ea0d830 // fcmeq v16.4s, v1.4s, #0.0 .long 0x72955568 // movk w8, #0xaaab - .long 0x6eb3e41f // fcmgt v31.4s, v0.4s, v19.4s - .long 0x6e791c3c // bsl v28.16b, v1.16b, v25.16b - .long 0x4e36d419 // fadd v25.4s, v0.4s, v22.4s - .long 0x4ea0e81b // fcmlt v27.4s, v0.4s, #0.0 - .long 0x4e33d41e // fadd v30.4s, v0.4s, v19.4s - .long 0x6e601f3f // bsl v31.16b, v25.16b, v0.16b - .long 0x4e040d19 // dup v25.4s, w8 - .long 0x4e38d418 // fadd v24.4s, v0.4s, v24.4s - .long 0x4e39d400 // fadd v0.4s, v0.4s, v25.4s - .long 0x6e7f1fdb // bsl v27.16b, v30.16b, v31.16b - .long 0x6eb3e71d // fcmgt v29.4s, v24.4s, v19.4s - .long 0x4e36d71e // fadd v30.4s, v24.4s, v22.4s - .long 0x6e781fdd // bsl v29.16b, v30.16b, v24.16b - .long 0x6eb3e41e // fcmgt v30.4s, v0.4s, v19.4s - .long 0x4e36d416 // fadd v22.4s, v0.4s, v22.4s + .long 0x6ea2e63a // fcmgt v26.4s, v17.4s, v2.4s + .long 0x4eb3d421 // fsub v1.4s, v1.4s, v19.4s + .long 0x4e219818 // frintm v24.4s, v0.4s + .long 0x4e040d1b // dup v27.4s, w8 + .long 0x6e611e7a // bsl v26.16b, v19.16b, v1.16b + .long 0x4e35d401 // fadd v1.4s, v0.4s, v21.4s + .long 0x4eb8d418 // fsub v24.4s, v0.4s, v24.4s + .long 0x4e3bd400 // fadd v0.4s, v0.4s, v27.4s + .long 0x4e22d755 // fadd v21.4s, v26.4s, v2.4s + .long 0x4e21983a // frintm v26.4s, v1.4s .long 0x4f026414 // movi v20.4s, #0x40, lsl #24 - .long 0x4ea0eb19 // fcmlt v25.4s, v24.4s, #0.0 - .long 0x4e33d718 // fadd v24.4s, v24.4s, v19.4s - .long 0x6e601ede // bsl v30.16b, v22.16b, v0.16b - .long 0x4ea0e816 // fcmlt v22.4s, v0.4s, #0.0 - .long 0x4e33d400 // fadd v0.4s, v0.4s, v19.4s - .long 0x6ea0fb93 // fneg v19.4s, v28.4s - .long 0x4e22ce93 // fmla v19.4s, v20.4s, v2.4s - .long 0x4f00f717 // fmov v23.4s, #6.000000000000000000e+00 - .long 0x6e7d1f19 // bsl v25.16b, v24.16b, v29.16b - .long 0x6e7e1c16 // bsl v22.16b, v0.16b, v30.16b - .long 0x4eb3d780 // fsub v0.4s, v28.4s, v19.4s - .long 0x4ebbd75d // fsub v29.4s, v26.4s, v27.4s - .long 0x4eb9d754 // fsub v20.4s, v26.4s, v25.4s - .long 0x4eb31e7e // mov v30.16b, v19.16b - .long 0x6e37dc00 // fmul v0.4s, v0.4s, v23.4s - .long 0x4eb31e77 // mov v23.16b, v19.16b - .long 0x4e34cc1e // fmla v30.4s, v0.4s, v20.4s - .long 0x4eb6d754 // fsub v20.4s, v26.4s, v22.4s - .long 0x4e3dcc17 // fmla v23.4s, v0.4s, v29.4s - .long 0x4eb31e7d // mov v29.16b, v19.16b - .long 0x4e34cc1d // fmla v29.4s, v0.4s, v20.4s - .long 0x6eb9e754 // fcmgt v20.4s, v26.4s, v25.4s - .long 0x6e731fd4 // bsl v20.16b, v30.16b, v19.16b - .long 0x6ebbe75e // fcmgt v30.4s, v26.4s, v27.4s - .long 0x6eb6e75a // fcmgt v26.4s, v26.4s, v22.4s - .long 0x6e731efe // bsl v30.16b, v23.16b, v19.16b - .long 0x4eb31e77 // mov v23.16b, v19.16b - .long 0x6e731fba // bsl v26.16b, v29.16b, v19.16b - .long 0x4eb31e7d // mov v29.16b, v19.16b - .long 0x6ebbe6b8 // fcmgt v24.4s, v21.4s, v27.4s - .long 0x4e3bcc17 // fmla v23.4s, v0.4s, v27.4s - .long 0x6ebbe65b // fcmgt v27.4s, v18.4s, v27.4s - .long 0x4e36cc1d // fmla v29.4s, v0.4s, v22.4s - .long 0x4e39cc13 // fmla v19.4s, v0.4s, v25.4s - .long 0x6eb9e6a0 // fcmgt v0.4s, v21.4s, v25.4s - .long 0x6eb9e659 // fcmgt v25.4s, v18.4s, v25.4s - .long 0x6eb6e652 // fcmgt v18.4s, v18.4s, v22.4s + .long 0x4f00f716 // fmov v22.4s, #6.000000000000000000e+00 + .long 0x4e21981c // frintm v28.4s, v0.4s + .long 0x6ea0fabd // fneg v29.4s, v21.4s + .long 0x4ebad43a // fsub v26.4s, v1.4s, v26.4s + .long 0x4f00f617 // fmov v23.4s, #4.000000000000000000e+00 + .long 0x4ebcd41c // fsub v28.4s, v0.4s, v28.4s + .long 0x4e22ce9d // fmla v29.4s, v20.4s, v2.4s + .long 0x6e36df54 // fmul v20.4s, v26.4s, v22.4s + .long 0x6e36df13 // fmul v19.4s, v24.4s, v22.4s + .long 0x6e36df80 // fmul v0.4s, v28.4s, v22.4s + .long 0x4ebdd6b6 // fsub v22.4s, v21.4s, v29.4s + .long 0x4eb4d6e1 // fsub v1.4s, v23.4s, v20.4s + .long 0x4ebd1fbe // mov v30.16b, v29.16b + .long 0x4eb3d6fb // fsub v27.4s, v23.4s, v19.4s + .long 0x4e21cede // fmla v30.4s, v22.4s, v1.4s + .long 0x4ebd1fa1 // mov v1.16b, v29.16b + .long 0x4e3bcec1 // fmla v1.4s, v22.4s, v27.4s + .long 0x4ea0d6f7 // fsub v23.4s, v23.4s, v0.4s + .long 0x4ebd1fbb // mov v27.16b, v29.16b + .long 0x4ebd1fbf // mov v31.16b, v29.16b + .long 0x4e37cedb // fmla v27.4s, v22.4s, v23.4s + .long 0x6ebae737 // fcmgt v23.4s, v25.4s, v26.4s + .long 0x4e33cedf // fmla v31.4s, v22.4s, v19.4s + .long 0x4ebd1fb3 // mov v19.16b, v29.16b + .long 0x6e7d1fd7 // bsl v23.16b, v30.16b, v29.16b + .long 0x6eb8e73e // fcmgt v30.4s, v25.4s, v24.4s + .long 0x6ebce739 // fcmgt v25.4s, v25.4s, v28.4s + .long 0x4e20ced3 // fmla v19.4s, v22.4s, v0.4s + .long 0x6e7d1c3e // bsl v30.16b, v1.16b, v29.16b + .long 0x6e7d1f79 // bsl v25.16b, v27.16b, v29.16b + .long 0x4e34cedd // fmla v29.4s, v22.4s, v20.4s + .long 0x6eb8e654 // fcmgt v20.4s, v18.4s, v24.4s + .long 0x6eb8e636 // fcmgt v22.4s, v17.4s, v24.4s + .long 0x6ebae658 // fcmgt v24.4s, v18.4s, v26.4s + .long 0x6ebae63a // fcmgt v26.4s, v17.4s, v26.4s + .long 0x6ebce631 // fcmgt v17.4s, v17.4s, v28.4s .long 0xf8408423 // ldr x3, [x1], #8 - .long 0x6eb6e6b5 // fcmgt v21.4s, v21.4s, v22.4s - .long 0x6e741f99 // bsl v25.16b, v28.16b, v20.16b - .long 0x6e7a1f92 // bsl v18.16b, v28.16b, v26.16b - .long 0x4eb01e11 // mov v17.16b, v16.16b - .long 0x6e7e1f9b // bsl v27.16b, v28.16b, v30.16b - .long 0x6e791e60 // bsl v0.16b, v19.16b, v25.16b - .long 0x6e721fb5 // bsl v21.16b, v29.16b, v18.16b + .long 0x6ebce652 // fcmgt v18.4s, v18.4s, v28.4s + .long 0x6e791eb1 // bsl v17.16b, v21.16b, v25.16b + .long 0x6e771eba // bsl v26.16b, v21.16b, v23.16b + .long 0x6e7e1eb6 // bsl v22.16b, v21.16b, v30.16b + .long 0x6e711e72 // bsl v18.16b, v19.16b, v17.16b + .long 0x4eb01e00 // mov v0.16b, v16.16b .long 0x4eb01e01 // mov v1.16b, v16.16b - .long 0x6e7b1ef8 // bsl v24.16b, v23.16b, v27.16b - .long 0x6e601c51 // bsl v17.16b, v2.16b, v0.16b - .long 0x6e751c50 // bsl v16.16b, v2.16b, v21.16b - .long 0x6e781c41 // bsl v1.16b, v2.16b, v24.16b - .long 0x4eb11e20 // mov v0.16b, v17.16b + .long 0x6e7a1fb8 // bsl v24.16b, v29.16b, v26.16b + .long 0x6e761ff4 // bsl v20.16b, v31.16b, v22.16b + .long 0x6e721c50 // bsl v16.16b, v2.16b, v18.16b + .long 0x6e781c40 // bsl v0.16b, v2.16b, v24.16b + .long 0x6e741c41 // bsl v1.16b, v2.16b, v20.16b .long 0x4eb01e02 // mov v2.16b, v16.16b .long 0xd61f0060 // br x3 @@ -2217,9 +2204,9 @@ FUNCTION(_sk_gather_i8_aarch64) _sk_gather_i8_aarch64: .long 0xaa0103e8 // mov x8, x1 .long 0xf8408429 // ldr x9, [x1], #8 - .long 0xb4000069 // cbz x9, 1d2c <sk_gather_i8_aarch64+0x14> + .long 0xb4000069 // cbz x9, 1cf8 <sk_gather_i8_aarch64+0x14> .long 0xaa0903ea // mov x10, x9 - .long 0x14000003 // b 1d34 <sk_gather_i8_aarch64+0x1c> + .long 0x14000003 // b 1d00 <sk_gather_i8_aarch64+0x1c> .long 0xf940050a // ldr x10, [x8, #8] .long 0x91004101 // add x1, x8, #0x10 .long 0xf8410548 // ldr x8, [x10], #16 @@ -3068,7 +3055,7 @@ _sk_linear_gradient_aarch64: .long 0x4d40c902 // ld1r {v2.4s}, [x8] .long 0xf9400128 // ldr x8, [x9] .long 0x4d40c943 // ld1r {v3.4s}, [x10] - .long 0xb40006c8 // cbz x8, 2900 <sk_linear_gradient_aarch64+0x100> + .long 0xb40006c8 // cbz x8, 28cc <sk_linear_gradient_aarch64+0x100> .long 0x6dbf23e9 // stp d9, d8, [sp, #-16]! .long 0xf9400529 // ldr x9, [x9, #8] .long 0x6f00e413 // movi v19.2d, #0x0 @@ -3119,9 +3106,9 @@ _sk_linear_gradient_aarch64: .long 0xd1000508 // sub x8, x8, #0x1 .long 0x6e771fd0 // bsl v16.16b, v30.16b, v23.16b .long 0x91009129 // add x9, x9, #0x24 - .long 0xb5fffaa8 // cbnz x8, 2848 <sk_linear_gradient_aarch64+0x48> + .long 0xb5fffaa8 // cbnz x8, 2814 <sk_linear_gradient_aarch64+0x48> .long 0x6cc123e9 // ldp d9, d8, [sp], #16 - .long 0x14000005 // b 2910 <sk_linear_gradient_aarch64+0x110> + .long 0x14000005 // b 28dc <sk_linear_gradient_aarch64+0x110> .long 0x6f00e414 // movi v20.2d, #0x0 .long 0x6f00e412 // movi v18.2d, #0x0 .long 0x6f00e411 // movi v17.2d, #0x0 @@ -4582,93 +4569,95 @@ HIDDEN _sk_hsl_to_rgb_vfp4 FUNCTION(_sk_hsl_to_rgb_vfp4) _sk_hsl_to_rgb_vfp4: .long 0xed2d8b02 // vpush {d8} - .long 0xf2c71f10 // vmov.f32 d17, #1 - .long 0xeddf0b50 // vldr d16, [pc, #320] - .long 0xf2c3261f // vmov.i32 d18, #1056964608 - .long 0xeddf9b50 // vldr d25, [pc, #320] - .long 0xf2415d21 // vadd.f32 d21, d1, d17 - .long 0xed9f8b52 // vldr d8, [pc, #328] - .long 0xf3414d12 // vmul.f32 d20, d1, d2 + .long 0xeddf0b51 // vldr d16, [pc, #324] + .long 0xf3fb2700 // vcvt.s32.f32 d18, d0 + .long 0xf2400d20 // vadd.f32 d16, d0, d16 + .long 0xeddf1b50 // vldr d17, [pc, #320] + .long 0xf2401d21 // vadd.f32 d17, d0, d17 + .long 0xeddfab50 // vldr d26, [pc, #320] + .long 0xf2c3661f // vmov.i32 d22, #1056964608 + .long 0xeddfdb50 // vldr d29, [pc, #320] + .long 0xf3fb2622 // vcvt.f32.s32 d18, d18 + .long 0xed9f8b50 // vldr d8, [pc, #320] + .long 0xf3fb3720 // vcvt.s32.f32 d19, d16 .long 0xe4913004 // ldr r3, [r1], #4 - .long 0xf2416d02 // vadd.f32 d22, d1, d2 - .long 0xf2407d20 // vadd.f32 d23, d0, d16 - .long 0xf3620e82 // vcgt.f32 d16, d18, d2 - .long 0xf3455d92 // vmul.f32 d21, d21, d2 - .long 0xf2664da4 // vsub.f32 d20, d22, d20 - .long 0xf2426d02 // vadd.f32 d22, d2, d2 - .long 0xf3c73f10 // vmov.f32 d19, #-1 - .long 0xf35501b4 // vbsl d16, d21, d20 - .long 0xf2409d29 // vadd.f32 d25, d0, d25 - .long 0xf2408d23 // vadd.f32 d24, d0, d19 - .long 0xf360ae21 // vcgt.f32 d26, d0, d17 - .long 0xf247cda3 // vadd.f32 d28, d23, d19 - .long 0xf367dea1 // vcgt.f32 d29, d23, d17 - .long 0xf240bd21 // vadd.f32 d27, d0, d17 - .long 0xf2666da0 // vsub.f32 d22, d22, d16 - .long 0xf2474da1 // vadd.f32 d20, d23, d17 - .long 0xf358a190 // vbsl d26, d24, d0 - .long 0xf3f98600 // vclt.f32 d24, d0, #0 - .long 0xf3695ea1 // vcgt.f32 d21, d25, d17 - .long 0xf2493da3 // vadd.f32 d19, d25, d19 - .long 0xf35b81ba // vbsl d24, d27, d26 - .long 0xeddfbb38 // vldr d27, [pc, #224] - .long 0xf35cd1b7 // vbsl d29, d28, d23 - .long 0xf3f97627 // vclt.f32 d23, d23, #0 - .long 0xf2491da1 // vadd.f32 d17, d25, d17 - .long 0xf260ada6 // vsub.f32 d26, d16, d22 - .long 0xf35471bd // vbsl d23, d20, d29 - .long 0xf2c14f18 // vmov.f32 d20, #6 - .long 0xf35351b9 // vbsl d21, d19, d25 - .long 0xf3f99629 // vclt.f32 d25, d25, #0 - .long 0xf26bcda7 // vsub.f32 d28, d27, d23 - .long 0xf35191b5 // vbsl d25, d17, d21 - .long 0xf34a1db4 // vmul.f32 d17, d26, d20 - .long 0xf26b3da8 // vsub.f32 d19, d27, d24 - .long 0xf26b4da9 // vsub.f32 d20, d27, d25 - .long 0xf36beea8 // vcgt.f32 d30, d27, d24 - .long 0xf3415dbc // vmul.f32 d21, d17, d28 - .long 0xf36bcea7 // vcgt.f32 d28, d27, d23 - .long 0xf3413db3 // vmul.f32 d19, d17, d19 - .long 0xf3444db1 // vmul.f32 d20, d20, d17 - .long 0xf2465da5 // vadd.f32 d21, d22, d21 - .long 0xf341ddb8 // vmul.f32 d29, d17, d24 - .long 0xf341adb7 // vmul.f32 d26, d17, d23 - .long 0xf2463da3 // vadd.f32 d19, d22, d19 - .long 0xf3220ea8 // vcgt.f32 d0, d18, d24 - .long 0xf3491db1 // vmul.f32 d17, d25, d17 - .long 0xf355c1b6 // vbsl d28, d21, d22 - .long 0xf3685e28 // vcgt.f32 d21, d8, d24 - .long 0xf36bbea9 // vcgt.f32 d27, d27, d25 - .long 0xf2464da4 // vadd.f32 d20, d22, d20 - .long 0xf2468dad // vadd.f32 d24, d22, d29 - .long 0xf362fea7 // vcgt.f32 d31, d18, d23 - .long 0xf3622ea9 // vcgt.f32 d18, d18, d25 - .long 0xf353e1b6 // vbsl d30, d19, d22 - .long 0xf3687e27 // vcgt.f32 d23, d8, d23 - .long 0xf246adaa // vadd.f32 d26, d22, d26 - .long 0xf31001be // vbsl d0, d16, d30 - .long 0xf354b1b6 // vbsl d27, d20, d22 - .long 0xf3585190 // vbsl d21, d24, d0 - .long 0xf3b90501 // vceq.f32 d0, d1, #0 - .long 0xf3683e29 // vcgt.f32 d19, d8, d25 - .long 0xf2461da1 // vadd.f32 d17, d22, d17 - .long 0xf350f1bc // vbsl d31, d16, d28 - .long 0xf35021bb // vbsl d18, d16, d27 - .long 0xf2600110 // vorr d16, d0, d0 - .long 0xf35a71bf // vbsl d23, d26, d31 - .long 0xf2201110 // vorr d1, d0, d0 - .long 0xf3520137 // vbsl d16, d2, d23 - .long 0xf35131b2 // vbsl d19, d17, d18 - .long 0xf3121135 // vbsl d1, d2, d21 - .long 0xf3120133 // vbsl d0, d2, d19 + .long 0xf3fb4721 // vcvt.s32.f32 d20, d17 + .long 0xf2c07010 // vmov.i32 d23, #0 + .long 0xf3625e80 // vcgt.f32 d21, d18, d0 + .long 0xf3fb3623 // vcvt.f32.s32 d19, d19 + .long 0xf3fb4624 // vcvt.f32.s32 d20, d20 + .long 0xf3418d12 // vmul.f32 d24, d1, d2 + .long 0xf35a51b7 // vbsl d21, d26, d23 + .long 0xf3639ea0 // vcgt.f32 d25, d19, d16 + .long 0xf364bea1 // vcgt.f32 d27, d20, d17 + .long 0xf366ce82 // vcgt.f32 d28, d22, d2 + .long 0xf2622da5 // vsub.f32 d18, d18, d21 + .long 0xf35a91b7 // vbsl d25, d26, d23 + .long 0xf35ab1b7 // vbsl d27, d26, d23 + .long 0xf2615d28 // vsub.f32 d21, d1, d24 + .long 0xf2633da9 // vsub.f32 d19, d19, d25 + .long 0xf358c1b5 // vbsl d28, d24, d21 + .long 0xf2644dab // vsub.f32 d20, d20, d27 + .long 0xf2602d22 // vsub.f32 d18, d0, d18 + .long 0xf2c15f18 // vmov.f32 d21, #6 + .long 0xf2427d02 // vadd.f32 d23, d2, d2 + .long 0xf24c8d82 // vadd.f32 d24, d28, d2 + .long 0xf2600da3 // vsub.f32 d16, d16, d19 + .long 0xf2611da4 // vsub.f32 d17, d17, d20 + .long 0xf3423db5 // vmul.f32 d19, d18, d21 + .long 0xf2674da8 // vsub.f32 d20, d23, d24 + .long 0xf2c17f10 // vmov.f32 d23, #4 + .long 0xf3409db5 // vmul.f32 d25, d16, d21 + .long 0xf3415db5 // vmul.f32 d21, d17, d21 + .long 0xf267ada3 // vsub.f32 d26, d23, d19 + .long 0xf268bda4 // vsub.f32 d27, d24, d20 + .long 0xf267cda9 // vsub.f32 d28, d23, d25 + .long 0xf2677da5 // vsub.f32 d23, d23, d21 + .long 0xf36deea2 // vcgt.f32 d30, d29, d18 + .long 0xf34badba // vmul.f32 d26, d27, d26 + .long 0xf34b9db9 // vmul.f32 d25, d27, d25 + .long 0xf34bcdbc // vmul.f32 d28, d27, d28 + .long 0xf34b7db7 // vmul.f32 d23, d27, d23 + .long 0xf244adaa // vadd.f32 d26, d20, d26 + .long 0xf34b3db3 // vmul.f32 d19, d27, d19 + .long 0xf34b5db5 // vmul.f32 d21, d27, d21 + .long 0xf36dfea0 // vcgt.f32 d31, d29, d16 + .long 0xf244cdac // vadd.f32 d28, d20, d28 + .long 0xf3260ea0 // vcgt.f32 d0, d22, d16 + .long 0xf36dbea1 // vcgt.f32 d27, d29, d17 + .long 0xf2447da7 // vadd.f32 d23, d20, d23 + .long 0xf35ae1b4 // vbsl d30, d26, d20 + .long 0xf368ae20 // vcgt.f32 d26, d8, d16 + .long 0xf2440da9 // vadd.f32 d16, d20, d25 + .long 0xf366dea2 // vcgt.f32 d29, d22, d18 + .long 0xf3666ea1 // vcgt.f32 d22, d22, d17 + .long 0xf35cf1b4 // vbsl d31, d28, d20 + .long 0xf3682e22 // vcgt.f32 d18, d8, d18 + .long 0xf2443da3 // vadd.f32 d19, d20, d19 + .long 0xf3681e21 // vcgt.f32 d17, d8, d17 + .long 0xf2445da5 // vadd.f32 d21, d20, d21 + .long 0xf31801bf // vbsl d0, d24, d31 + .long 0xf357b1b4 // vbsl d27, d23, d20 + .long 0xf350a190 // vbsl d26, d16, d0 + .long 0xf3f90501 // vceq.f32 d16, d1, #0 + .long 0xf358d1be // vbsl d29, d24, d30 + .long 0xf35861bb // vbsl d22, d24, d27 + .long 0xf22011b0 // vorr d1, d16, d16 + .long 0xf22001b0 // vorr d0, d16, d16 + .long 0xf352013a // vbsl d16, d2, d26 + .long 0xf35321bd // vbsl d18, d19, d29 + .long 0xf35511b6 // vbsl d17, d21, d22 + .long 0xf3121132 // vbsl d1, d2, d18 + .long 0xf3120131 // vbsl d0, d2, d17 .long 0xf22021b0 // vorr d2, d16, d16 .long 0xecbd8b02 // vpop {d8} .long 0xe12fff13 // bx r3 - .long 0xe320f000 // nop {0} .long 0xbeaaaaab // .word 0xbeaaaaab .long 0xbeaaaaab // .word 0xbeaaaaab .long 0x3eaaaaab // .word 0x3eaaaaab .long 0x3eaaaaab // .word 0x3eaaaaab + .long 0x3f800000 // .word 0x3f800000 + .long 0x3f800000 // .word 0x3f800000 .long 0x3f2aaaab // .word 0x3f2aaaab .long 0x3f2aaaab // .word 0x3f2aaaab .long 0x3e2aaaab // .word 0x3e2aaaab @@ -6815,7 +6804,7 @@ _sk_linear_gradient_vfp4: .long 0xe494c00c // ldr ip, [r4], #12 .long 0xf4a41c9f // vld1.32 {d1[]}, [r4 :32] .long 0xe35c0000 // cmp ip, #0 - .long 0x0a000036 // beq 2d78 <sk_linear_gradient_vfp4+0x110> + .long 0x0a000036 // beq 2d80 <sk_linear_gradient_vfp4+0x110> .long 0xe59e3004 // ldr r3, [lr, #4] .long 0xf2c01010 // vmov.i32 d17, #0 .long 0xf2c07010 // vmov.i32 d23, #0 @@ -6865,12 +6854,12 @@ _sk_linear_gradient_vfp4: .long 0xf26371b3 // vorr d23, d19, d19 .long 0xf26481b4 // vorr d24, d20, d20 .long 0xf26561b5 // vorr d22, d21, d21 - .long 0x1affffd3 // bne 2cb4 <sk_linear_gradient_vfp4+0x4c> + .long 0x1affffd3 // bne 2cbc <sk_linear_gradient_vfp4+0x4c> .long 0xf26c01bc // vorr d16, d28, d28 .long 0xf22b11bb // vorr d1, d27, d27 .long 0xf22a21ba // vorr d2, d26, d26 .long 0xf22931b9 // vorr d3, d25, d25 - .long 0xea000003 // b 2d88 <sk_linear_gradient_vfp4+0x120> + .long 0xea000003 // b 2d90 <sk_linear_gradient_vfp4+0x120> .long 0xf2c05010 // vmov.i32 d21, #0 .long 0xf2c04010 // vmov.i32 d20, #0 .long 0xf2c03010 // vmov.i32 d19, #0 @@ -7350,14 +7339,14 @@ _sk_seed_shader_hsw: .byte 197,249,110,199 // vmovd %edi,%xmm0 .byte 196,226,125,88,192 // vpbroadcastd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,165,60,0,0 // vbroadcastss 0x3ca5(%rip),%ymm1 # 3d68 <_sk_callback_hsw+0x125> + .byte 196,226,125,24,13,53,60,0,0 // vbroadcastss 0x3c35(%rip),%ymm1 # 3cf8 <_sk_callback_hsw+0x125> .byte 197,252,88,193 // vaddps %ymm1,%ymm0,%ymm0 .byte 197,252,88,2 // vaddps (%rdx),%ymm0,%ymm0 .byte 196,226,125,24,16 // vbroadcastss (%rax),%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 197,236,88,201 // vaddps %ymm1,%ymm2,%ymm1 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,21,137,60,0,0 // vbroadcastss 0x3c89(%rip),%ymm2 # 3d6c <_sk_callback_hsw+0x129> + .byte 196,226,125,24,21,25,60,0,0 // vbroadcastss 0x3c19(%rip),%ymm2 # 3cfc <_sk_callback_hsw+0x129> .byte 197,228,87,219 // vxorps %ymm3,%ymm3,%ymm3 .byte 197,220,87,228 // vxorps %ymm4,%ymm4,%ymm4 .byte 197,212,87,237 // vxorps %ymm5,%ymm5,%ymm5 @@ -7393,7 +7382,7 @@ HIDDEN _sk_srcatop_hsw FUNCTION(_sk_srcatop_hsw) _sk_srcatop_hsw: .byte 197,252,89,199 // vmulps %ymm7,%ymm0,%ymm0 - .byte 196,98,125,24,5,57,60,0,0 // vbroadcastss 0x3c39(%rip),%ymm8 # 3d70 <_sk_callback_hsw+0x12d> + .byte 196,98,125,24,5,201,59,0,0 // vbroadcastss 0x3bc9(%rip),%ymm8 # 3d00 <_sk_callback_hsw+0x12d> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,226,61,184,196 // vfmadd231ps %ymm4,%ymm8,%ymm0 .byte 197,244,89,207 // vmulps %ymm7,%ymm1,%ymm1 @@ -7409,7 +7398,7 @@ HIDDEN _sk_dstatop_hsw .globl _sk_dstatop_hsw FUNCTION(_sk_dstatop_hsw) _sk_dstatop_hsw: - .byte 196,98,125,24,5,12,60,0,0 // vbroadcastss 0x3c0c(%rip),%ymm8 # 3d74 <_sk_callback_hsw+0x131> + .byte 196,98,125,24,5,156,59,0,0 // vbroadcastss 0x3b9c(%rip),%ymm8 # 3d04 <_sk_callback_hsw+0x131> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 196,226,101,184,196 // vfmadd231ps %ymm4,%ymm3,%ymm0 @@ -7448,7 +7437,7 @@ HIDDEN _sk_srcout_hsw .globl _sk_srcout_hsw FUNCTION(_sk_srcout_hsw) _sk_srcout_hsw: - .byte 196,98,125,24,5,179,59,0,0 // vbroadcastss 0x3bb3(%rip),%ymm8 # 3d78 <_sk_callback_hsw+0x135> + .byte 196,98,125,24,5,67,59,0,0 // vbroadcastss 0x3b43(%rip),%ymm8 # 3d08 <_sk_callback_hsw+0x135> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 @@ -7461,7 +7450,7 @@ HIDDEN _sk_dstout_hsw .globl _sk_dstout_hsw FUNCTION(_sk_dstout_hsw) _sk_dstout_hsw: - .byte 196,226,125,24,5,150,59,0,0 // vbroadcastss 0x3b96(%rip),%ymm0 # 3d7c <_sk_callback_hsw+0x139> + .byte 196,226,125,24,5,38,59,0,0 // vbroadcastss 0x3b26(%rip),%ymm0 # 3d0c <_sk_callback_hsw+0x139> .byte 197,252,92,219 // vsubps %ymm3,%ymm0,%ymm3 .byte 197,228,89,196 // vmulps %ymm4,%ymm3,%ymm0 .byte 197,228,89,205 // vmulps %ymm5,%ymm3,%ymm1 @@ -7474,7 +7463,7 @@ HIDDEN _sk_srcover_hsw .globl _sk_srcover_hsw FUNCTION(_sk_srcover_hsw) _sk_srcover_hsw: - .byte 196,98,125,24,5,121,59,0,0 // vbroadcastss 0x3b79(%rip),%ymm8 # 3d80 <_sk_callback_hsw+0x13d> + .byte 196,98,125,24,5,9,59,0,0 // vbroadcastss 0x3b09(%rip),%ymm8 # 3d10 <_sk_callback_hsw+0x13d> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,93,184,192 // vfmadd231ps %ymm8,%ymm4,%ymm0 .byte 196,194,85,184,200 // vfmadd231ps %ymm8,%ymm5,%ymm1 @@ -7487,7 +7476,7 @@ HIDDEN _sk_dstover_hsw .globl _sk_dstover_hsw FUNCTION(_sk_dstover_hsw) _sk_dstover_hsw: - .byte 196,98,125,24,5,88,59,0,0 // vbroadcastss 0x3b58(%rip),%ymm8 # 3d84 <_sk_callback_hsw+0x141> + .byte 196,98,125,24,5,232,58,0,0 // vbroadcastss 0x3ae8(%rip),%ymm8 # 3d14 <_sk_callback_hsw+0x141> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 196,226,61,168,196 // vfmadd213ps %ymm4,%ymm8,%ymm0 .byte 196,226,61,168,205 // vfmadd213ps %ymm5,%ymm8,%ymm1 @@ -7511,7 +7500,7 @@ HIDDEN _sk_multiply_hsw .globl _sk_multiply_hsw FUNCTION(_sk_multiply_hsw) _sk_multiply_hsw: - .byte 196,98,125,24,5,35,59,0,0 // vbroadcastss 0x3b23(%rip),%ymm8 # 3d88 <_sk_callback_hsw+0x145> + .byte 196,98,125,24,5,179,58,0,0 // vbroadcastss 0x3ab3(%rip),%ymm8 # 3d18 <_sk_callback_hsw+0x145> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,52,89,208 // vmulps %ymm0,%ymm9,%ymm10 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -7559,7 +7548,7 @@ HIDDEN _sk_xor__hsw .globl _sk_xor__hsw FUNCTION(_sk_xor__hsw) _sk_xor__hsw: - .byte 196,98,125,24,5,158,58,0,0 // vbroadcastss 0x3a9e(%rip),%ymm8 # 3d8c <_sk_callback_hsw+0x149> + .byte 196,98,125,24,5,46,58,0,0 // vbroadcastss 0x3a2e(%rip),%ymm8 # 3d1c <_sk_callback_hsw+0x149> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,180,89,192 // vmulps %ymm0,%ymm9,%ymm0 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -7593,7 +7582,7 @@ _sk_darken_hsw: .byte 197,100,89,206 // vmulps %ymm6,%ymm3,%ymm9 .byte 196,193,108,95,209 // vmaxps %ymm9,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,38,58,0,0 // vbroadcastss 0x3a26(%rip),%ymm8 # 3d90 <_sk_callback_hsw+0x14d> + .byte 196,98,125,24,5,182,57,0,0 // vbroadcastss 0x39b6(%rip),%ymm8 # 3d20 <_sk_callback_hsw+0x14d> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,69,184,216 // vfmadd231ps %ymm8,%ymm7,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -7618,7 +7607,7 @@ _sk_lighten_hsw: .byte 197,100,89,206 // vmulps %ymm6,%ymm3,%ymm9 .byte 196,193,108,93,209 // vminps %ymm9,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,213,57,0,0 // vbroadcastss 0x39d5(%rip),%ymm8 # 3d94 <_sk_callback_hsw+0x151> + .byte 196,98,125,24,5,101,57,0,0 // vbroadcastss 0x3965(%rip),%ymm8 # 3d24 <_sk_callback_hsw+0x151> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,69,184,216 // vfmadd231ps %ymm8,%ymm7,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -7646,7 +7635,7 @@ _sk_difference_hsw: .byte 196,193,108,93,209 // vminps %ymm9,%ymm2,%ymm2 .byte 197,236,88,210 // vaddps %ymm2,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,120,57,0,0 // vbroadcastss 0x3978(%rip),%ymm8 # 3d98 <_sk_callback_hsw+0x155> + .byte 196,98,125,24,5,8,57,0,0 // vbroadcastss 0x3908(%rip),%ymm8 # 3d28 <_sk_callback_hsw+0x155> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,69,184,216 // vfmadd231ps %ymm8,%ymm7,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -7668,7 +7657,7 @@ _sk_exclusion_hsw: .byte 197,236,89,214 // vmulps %ymm6,%ymm2,%ymm2 .byte 197,236,88,210 // vaddps %ymm2,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,54,57,0,0 // vbroadcastss 0x3936(%rip),%ymm8 # 3d9c <_sk_callback_hsw+0x159> + .byte 196,98,125,24,5,198,56,0,0 // vbroadcastss 0x38c6(%rip),%ymm8 # 3d2c <_sk_callback_hsw+0x159> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 196,194,69,184,216 // vfmadd231ps %ymm8,%ymm7,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -7678,7 +7667,7 @@ HIDDEN _sk_colorburn_hsw .globl _sk_colorburn_hsw FUNCTION(_sk_colorburn_hsw) _sk_colorburn_hsw: - .byte 196,98,125,24,5,36,57,0,0 // vbroadcastss 0x3924(%rip),%ymm8 # 3da0 <_sk_callback_hsw+0x15d> + .byte 196,98,125,24,5,180,56,0,0 // vbroadcastss 0x38b4(%rip),%ymm8 # 3d30 <_sk_callback_hsw+0x15d> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,52,89,216 // vmulps %ymm0,%ymm9,%ymm11 .byte 196,65,44,87,210 // vxorps %ymm10,%ymm10,%ymm10 @@ -7736,7 +7725,7 @@ HIDDEN _sk_colordodge_hsw FUNCTION(_sk_colordodge_hsw) _sk_colordodge_hsw: .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 - .byte 196,98,125,24,13,47,56,0,0 // vbroadcastss 0x382f(%rip),%ymm9 # 3da4 <_sk_callback_hsw+0x161> + .byte 196,98,125,24,13,191,55,0,0 // vbroadcastss 0x37bf(%rip),%ymm9 # 3d34 <_sk_callback_hsw+0x161> .byte 197,52,92,215 // vsubps %ymm7,%ymm9,%ymm10 .byte 197,44,89,216 // vmulps %ymm0,%ymm10,%ymm11 .byte 197,52,92,203 // vsubps %ymm3,%ymm9,%ymm9 @@ -7789,7 +7778,7 @@ HIDDEN _sk_hardlight_hsw .globl _sk_hardlight_hsw FUNCTION(_sk_hardlight_hsw) _sk_hardlight_hsw: - .byte 196,98,125,24,5,80,55,0,0 // vbroadcastss 0x3750(%rip),%ymm8 # 3da8 <_sk_callback_hsw+0x165> + .byte 196,98,125,24,5,224,54,0,0 // vbroadcastss 0x36e0(%rip),%ymm8 # 3d38 <_sk_callback_hsw+0x165> .byte 197,60,92,215 // vsubps %ymm7,%ymm8,%ymm10 .byte 197,44,89,216 // vmulps %ymm0,%ymm10,%ymm11 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -7840,7 +7829,7 @@ HIDDEN _sk_overlay_hsw .globl _sk_overlay_hsw FUNCTION(_sk_overlay_hsw) _sk_overlay_hsw: - .byte 196,98,125,24,5,136,54,0,0 // vbroadcastss 0x3688(%rip),%ymm8 # 3dac <_sk_callback_hsw+0x169> + .byte 196,98,125,24,5,24,54,0,0 // vbroadcastss 0x3618(%rip),%ymm8 # 3d3c <_sk_callback_hsw+0x169> .byte 197,60,92,215 // vsubps %ymm7,%ymm8,%ymm10 .byte 197,44,89,216 // vmulps %ymm0,%ymm10,%ymm11 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -7901,10 +7890,10 @@ _sk_softlight_hsw: .byte 196,65,20,88,197 // vaddps %ymm13,%ymm13,%ymm8 .byte 196,65,60,88,192 // vaddps %ymm8,%ymm8,%ymm8 .byte 196,66,61,168,192 // vfmadd213ps %ymm8,%ymm8,%ymm8 - .byte 196,98,125,24,29,147,53,0,0 // vbroadcastss 0x3593(%rip),%ymm11 # 3db4 <_sk_callback_hsw+0x171> + .byte 196,98,125,24,29,35,53,0,0 // vbroadcastss 0x3523(%rip),%ymm11 # 3d44 <_sk_callback_hsw+0x171> .byte 196,65,20,88,227 // vaddps %ymm11,%ymm13,%ymm12 .byte 196,65,28,89,192 // vmulps %ymm8,%ymm12,%ymm8 - .byte 196,98,125,24,37,132,53,0,0 // vbroadcastss 0x3584(%rip),%ymm12 # 3db8 <_sk_callback_hsw+0x175> + .byte 196,98,125,24,37,20,53,0,0 // vbroadcastss 0x3514(%rip),%ymm12 # 3d48 <_sk_callback_hsw+0x175> .byte 196,66,21,184,196 // vfmadd231ps %ymm12,%ymm13,%ymm8 .byte 196,65,124,82,245 // vrsqrtps %ymm13,%ymm14 .byte 196,65,124,83,246 // vrcpps %ymm14,%ymm14 @@ -7914,7 +7903,7 @@ _sk_softlight_hsw: .byte 197,4,194,255,2 // vcmpleps %ymm7,%ymm15,%ymm15 .byte 196,67,13,74,240,240 // vblendvps %ymm15,%ymm8,%ymm14,%ymm14 .byte 197,116,88,249 // vaddps %ymm1,%ymm1,%ymm15 - .byte 196,98,125,24,5,71,53,0,0 // vbroadcastss 0x3547(%rip),%ymm8 # 3db0 <_sk_callback_hsw+0x16d> + .byte 196,98,125,24,5,215,52,0,0 // vbroadcastss 0x34d7(%rip),%ymm8 # 3d40 <_sk_callback_hsw+0x16d> .byte 196,65,60,92,237 // vsubps %ymm13,%ymm8,%ymm13 .byte 197,132,92,195 // vsubps %ymm3,%ymm15,%ymm0 .byte 196,98,125,168,235 // vfmadd213ps %ymm3,%ymm0,%ymm13 @@ -8007,7 +7996,7 @@ HIDDEN _sk_clamp_1_hsw .globl _sk_clamp_1_hsw FUNCTION(_sk_clamp_1_hsw) _sk_clamp_1_hsw: - .byte 196,98,125,24,5,204,51,0,0 // vbroadcastss 0x33cc(%rip),%ymm8 # 3dbc <_sk_callback_hsw+0x179> + .byte 196,98,125,24,5,92,51,0,0 // vbroadcastss 0x335c(%rip),%ymm8 # 3d4c <_sk_callback_hsw+0x179> .byte 196,193,124,93,192 // vminps %ymm8,%ymm0,%ymm0 .byte 196,193,116,93,200 // vminps %ymm8,%ymm1,%ymm1 .byte 196,193,108,93,208 // vminps %ymm8,%ymm2,%ymm2 @@ -8019,7 +8008,7 @@ HIDDEN _sk_clamp_a_hsw .globl _sk_clamp_a_hsw FUNCTION(_sk_clamp_a_hsw) _sk_clamp_a_hsw: - .byte 196,98,125,24,5,175,51,0,0 // vbroadcastss 0x33af(%rip),%ymm8 # 3dc0 <_sk_callback_hsw+0x17d> + .byte 196,98,125,24,5,63,51,0,0 // vbroadcastss 0x333f(%rip),%ymm8 # 3d50 <_sk_callback_hsw+0x17d> .byte 196,193,100,93,216 // vminps %ymm8,%ymm3,%ymm3 .byte 197,252,93,195 // vminps %ymm3,%ymm0,%ymm0 .byte 197,244,93,203 // vminps %ymm3,%ymm1,%ymm1 @@ -8105,7 +8094,7 @@ FUNCTION(_sk_unpremul_hsw) _sk_unpremul_hsw: .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,65,100,194,200,0 // vcmpeqps %ymm8,%ymm3,%ymm9 - .byte 196,98,125,24,21,247,50,0,0 // vbroadcastss 0x32f7(%rip),%ymm10 # 3dc4 <_sk_callback_hsw+0x181> + .byte 196,98,125,24,21,135,50,0,0 // vbroadcastss 0x3287(%rip),%ymm10 # 3d54 <_sk_callback_hsw+0x181> .byte 197,44,94,211 // vdivps %ymm3,%ymm10,%ymm10 .byte 196,67,45,74,192,144 // vblendvps %ymm9,%ymm8,%ymm10,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 @@ -8118,16 +8107,16 @@ HIDDEN _sk_from_srgb_hsw .globl _sk_from_srgb_hsw FUNCTION(_sk_from_srgb_hsw) _sk_from_srgb_hsw: - .byte 196,98,125,24,5,216,50,0,0 // vbroadcastss 0x32d8(%rip),%ymm8 # 3dc8 <_sk_callback_hsw+0x185> + .byte 196,98,125,24,5,104,50,0,0 // vbroadcastss 0x3268(%rip),%ymm8 # 3d58 <_sk_callback_hsw+0x185> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 197,124,89,208 // vmulps %ymm0,%ymm0,%ymm10 - .byte 196,98,125,24,29,202,50,0,0 // vbroadcastss 0x32ca(%rip),%ymm11 # 3dcc <_sk_callback_hsw+0x189> - .byte 196,98,125,24,37,197,50,0,0 // vbroadcastss 0x32c5(%rip),%ymm12 # 3dd0 <_sk_callback_hsw+0x18d> + .byte 196,98,125,24,29,90,50,0,0 // vbroadcastss 0x325a(%rip),%ymm11 # 3d5c <_sk_callback_hsw+0x189> + .byte 196,98,125,24,37,85,50,0,0 // vbroadcastss 0x3255(%rip),%ymm12 # 3d60 <_sk_callback_hsw+0x18d> .byte 196,65,124,40,236 // vmovaps %ymm12,%ymm13 .byte 196,66,125,168,235 // vfmadd213ps %ymm11,%ymm0,%ymm13 - .byte 196,98,125,24,53,182,50,0,0 // vbroadcastss 0x32b6(%rip),%ymm14 # 3dd4 <_sk_callback_hsw+0x191> + .byte 196,98,125,24,53,70,50,0,0 // vbroadcastss 0x3246(%rip),%ymm14 # 3d64 <_sk_callback_hsw+0x191> .byte 196,66,45,168,238 // vfmadd213ps %ymm14,%ymm10,%ymm13 - .byte 196,98,125,24,21,172,50,0,0 // vbroadcastss 0x32ac(%rip),%ymm10 # 3dd8 <_sk_callback_hsw+0x195> + .byte 196,98,125,24,21,60,50,0,0 // vbroadcastss 0x323c(%rip),%ymm10 # 3d68 <_sk_callback_hsw+0x195> .byte 196,193,124,194,194,1 // vcmpltps %ymm10,%ymm0,%ymm0 .byte 196,195,21,74,193,0 // vblendvps %ymm0,%ymm9,%ymm13,%ymm0 .byte 196,65,116,89,200 // vmulps %ymm8,%ymm1,%ymm9 @@ -8153,16 +8142,16 @@ _sk_to_srgb_hsw: .byte 197,124,82,192 // vrsqrtps %ymm0,%ymm8 .byte 196,65,124,83,200 // vrcpps %ymm8,%ymm9 .byte 196,65,124,82,208 // vrsqrtps %ymm8,%ymm10 - .byte 196,98,125,24,5,70,50,0,0 // vbroadcastss 0x3246(%rip),%ymm8 # 3ddc <_sk_callback_hsw+0x199> + .byte 196,98,125,24,5,214,49,0,0 // vbroadcastss 0x31d6(%rip),%ymm8 # 3d6c <_sk_callback_hsw+0x199> .byte 196,65,124,89,216 // vmulps %ymm8,%ymm0,%ymm11 - .byte 196,98,125,24,37,60,50,0,0 // vbroadcastss 0x323c(%rip),%ymm12 # 3de0 <_sk_callback_hsw+0x19d> - .byte 196,98,125,24,45,55,50,0,0 // vbroadcastss 0x3237(%rip),%ymm13 # 3de4 <_sk_callback_hsw+0x1a1> + .byte 196,98,125,24,37,204,49,0,0 // vbroadcastss 0x31cc(%rip),%ymm12 # 3d70 <_sk_callback_hsw+0x19d> + .byte 196,98,125,24,45,199,49,0,0 // vbroadcastss 0x31c7(%rip),%ymm13 # 3d74 <_sk_callback_hsw+0x1a1> .byte 196,66,21,168,204 // vfmadd213ps %ymm12,%ymm13,%ymm9 - .byte 196,98,125,24,53,45,50,0,0 // vbroadcastss 0x322d(%rip),%ymm14 # 3de8 <_sk_callback_hsw+0x1a5> + .byte 196,98,125,24,53,189,49,0,0 // vbroadcastss 0x31bd(%rip),%ymm14 # 3d78 <_sk_callback_hsw+0x1a5> .byte 196,66,13,184,202 // vfmadd231ps %ymm10,%ymm14,%ymm9 - .byte 196,98,125,24,21,35,50,0,0 // vbroadcastss 0x3223(%rip),%ymm10 # 3dec <_sk_callback_hsw+0x1a9> + .byte 196,98,125,24,21,179,49,0,0 // vbroadcastss 0x31b3(%rip),%ymm10 # 3d7c <_sk_callback_hsw+0x1a9> .byte 196,65,44,93,201 // vminps %ymm9,%ymm10,%ymm9 - .byte 196,98,125,24,61,25,50,0,0 // vbroadcastss 0x3219(%rip),%ymm15 # 3df0 <_sk_callback_hsw+0x1ad> + .byte 196,98,125,24,61,169,49,0,0 // vbroadcastss 0x31a9(%rip),%ymm15 # 3d80 <_sk_callback_hsw+0x1ad> .byte 196,193,124,194,199,1 // vcmpltps %ymm15,%ymm0,%ymm0 .byte 196,195,53,74,195,0 // vblendvps %ymm0,%ymm11,%ymm9,%ymm0 .byte 197,124,82,201 // vrsqrtps %ymm1,%ymm9 @@ -8195,26 +8184,26 @@ _sk_rgb_to_hsl_hsw: .byte 197,124,93,201 // vminps %ymm1,%ymm0,%ymm9 .byte 197,52,93,202 // vminps %ymm2,%ymm9,%ymm9 .byte 196,65,60,92,209 // vsubps %ymm9,%ymm8,%ymm10 - .byte 196,98,125,24,29,147,49,0,0 // vbroadcastss 0x3193(%rip),%ymm11 # 3df4 <_sk_callback_hsw+0x1b1> + .byte 196,98,125,24,29,35,49,0,0 // vbroadcastss 0x3123(%rip),%ymm11 # 3d84 <_sk_callback_hsw+0x1b1> .byte 196,65,36,94,218 // vdivps %ymm10,%ymm11,%ymm11 .byte 197,116,92,226 // vsubps %ymm2,%ymm1,%ymm12 .byte 197,116,194,234,1 // vcmpltps %ymm2,%ymm1,%ymm13 - .byte 196,98,125,24,53,128,49,0,0 // vbroadcastss 0x3180(%rip),%ymm14 # 3df8 <_sk_callback_hsw+0x1b5> + .byte 196,98,125,24,53,16,49,0,0 // vbroadcastss 0x3110(%rip),%ymm14 # 3d88 <_sk_callback_hsw+0x1b5> .byte 196,65,4,87,255 // vxorps %ymm15,%ymm15,%ymm15 .byte 196,67,5,74,238,208 // vblendvps %ymm13,%ymm14,%ymm15,%ymm13 .byte 196,66,37,168,229 // vfmadd213ps %ymm13,%ymm11,%ymm12 .byte 197,236,92,208 // vsubps %ymm0,%ymm2,%ymm2 .byte 197,124,92,233 // vsubps %ymm1,%ymm0,%ymm13 - .byte 196,98,125,24,53,103,49,0,0 // vbroadcastss 0x3167(%rip),%ymm14 # 3e00 <_sk_callback_hsw+0x1bd> + .byte 196,98,125,24,53,247,48,0,0 // vbroadcastss 0x30f7(%rip),%ymm14 # 3d90 <_sk_callback_hsw+0x1bd> .byte 196,66,37,168,238 // vfmadd213ps %ymm14,%ymm11,%ymm13 - .byte 196,98,125,24,53,85,49,0,0 // vbroadcastss 0x3155(%rip),%ymm14 # 3dfc <_sk_callback_hsw+0x1b9> + .byte 196,98,125,24,53,229,48,0,0 // vbroadcastss 0x30e5(%rip),%ymm14 # 3d8c <_sk_callback_hsw+0x1b9> .byte 196,194,37,168,214 // vfmadd213ps %ymm14,%ymm11,%ymm2 .byte 197,188,194,201,0 // vcmpeqps %ymm1,%ymm8,%ymm1 .byte 196,227,21,74,202,16 // vblendvps %ymm1,%ymm2,%ymm13,%ymm1 .byte 197,188,194,192,0 // vcmpeqps %ymm0,%ymm8,%ymm0 .byte 196,195,117,74,196,0 // vblendvps %ymm0,%ymm12,%ymm1,%ymm0 .byte 196,193,60,88,201 // vaddps %ymm9,%ymm8,%ymm1 - .byte 196,98,125,24,29,56,49,0,0 // vbroadcastss 0x3138(%rip),%ymm11 # 3e08 <_sk_callback_hsw+0x1c5> + .byte 196,98,125,24,29,200,48,0,0 // vbroadcastss 0x30c8(%rip),%ymm11 # 3d98 <_sk_callback_hsw+0x1c5> .byte 196,193,116,89,211 // vmulps %ymm11,%ymm1,%ymm2 .byte 197,36,194,218,1 // vcmpltps %ymm2,%ymm11,%ymm11 .byte 196,65,12,92,224 // vsubps %ymm8,%ymm14,%ymm12 @@ -8224,7 +8213,7 @@ _sk_rgb_to_hsl_hsw: .byte 197,172,94,201 // vdivps %ymm1,%ymm10,%ymm1 .byte 196,195,125,74,199,128 // vblendvps %ymm8,%ymm15,%ymm0,%ymm0 .byte 196,195,117,74,207,128 // vblendvps %ymm8,%ymm15,%ymm1,%ymm1 - .byte 196,98,125,24,5,251,48,0,0 // vbroadcastss 0x30fb(%rip),%ymm8 # 3e04 <_sk_callback_hsw+0x1c1> + .byte 196,98,125,24,5,139,48,0,0 // vbroadcastss 0x308b(%rip),%ymm8 # 3d94 <_sk_callback_hsw+0x1c1> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -8233,106 +8222,86 @@ HIDDEN _sk_hsl_to_rgb_hsw .globl _sk_hsl_to_rgb_hsw FUNCTION(_sk_hsl_to_rgb_hsw) _sk_hsl_to_rgb_hsw: - .byte 72,131,236,120 // sub $0x78,%rsp - .byte 197,252,17,124,36,64 // vmovups %ymm7,0x40(%rsp) - .byte 197,252,17,116,36,32 // vmovups %ymm6,0x20(%rsp) - .byte 197,252,17,44,36 // vmovups %ymm5,(%rsp) - .byte 197,252,17,100,36,224 // vmovups %ymm4,-0x20(%rsp) - .byte 197,252,17,92,36,192 // vmovups %ymm3,-0x40(%rsp) - .byte 197,252,17,76,36,160 // vmovups %ymm1,-0x60(%rsp) + .byte 72,131,236,56 // sub $0x38,%rsp + .byte 197,252,17,60,36 // vmovups %ymm7,(%rsp) + .byte 197,252,17,116,36,224 // vmovups %ymm6,-0x20(%rsp) + .byte 197,252,17,108,36,192 // vmovups %ymm5,-0x40(%rsp) + .byte 197,252,17,100,36,160 // vmovups %ymm4,-0x60(%rsp) + .byte 197,252,17,92,36,128 // vmovups %ymm3,-0x80(%rsp) + .byte 197,252,40,217 // vmovaps %ymm1,%ymm3 + .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 184,0,0,0,63 // mov $0x3f000000,%eax - .byte 197,249,110,216 // vmovd %eax,%xmm3 - .byte 196,98,125,88,195 // vpbroadcastd %xmm3,%ymm8 - .byte 196,193,108,194,232,1 // vcmpltps %ymm8,%ymm2,%ymm5 - .byte 196,98,125,24,21,182,48,0,0 // vbroadcastss 0x30b6(%rip),%ymm10 # 3e0c <_sk_callback_hsw+0x1c9> - .byte 196,193,116,88,218 // vaddps %ymm10,%ymm1,%ymm3 - .byte 197,228,89,218 // vmulps %ymm2,%ymm3,%ymm3 - .byte 197,244,88,226 // vaddps %ymm2,%ymm1,%ymm4 - .byte 196,226,117,188,226 // vfnmadd231ps %ymm2,%ymm1,%ymm4 - .byte 196,99,93,74,203,80 // vblendvps %ymm5,%ymm3,%ymm4,%ymm9 - .byte 196,226,125,24,13,157,48,0,0 // vbroadcastss 0x309d(%rip),%ymm1 # 3e14 <_sk_callback_hsw+0x1d1> - .byte 197,252,88,201 // vaddps %ymm1,%ymm0,%ymm1 - .byte 65,184,0,0,0,0 // mov $0x0,%r8d - .byte 184,0,0,128,63 // mov $0x3f800000,%eax - .byte 197,249,110,216 // vmovd %eax,%xmm3 - .byte 196,98,125,88,227 // vpbroadcastd %xmm3,%ymm12 - .byte 197,156,194,217,1 // vcmpltps %ymm1,%ymm12,%ymm3 - .byte 196,98,125,24,45,123,48,0,0 // vbroadcastss 0x307b(%rip),%ymm13 # 3e18 <_sk_callback_hsw+0x1d5> - .byte 196,193,116,88,229 // vaddps %ymm13,%ymm1,%ymm4 - .byte 196,227,117,74,220,48 // vblendvps %ymm3,%ymm4,%ymm1,%ymm3 - .byte 196,193,121,110,224 // vmovd %r8d,%xmm4 - .byte 196,98,125,88,252 // vpbroadcastd %xmm4,%ymm15 - .byte 196,193,116,194,231,1 // vcmpltps %ymm15,%ymm1,%ymm4 - .byte 196,193,116,88,202 // vaddps %ymm10,%ymm1,%ymm1 - .byte 196,227,101,74,241,64 // vblendvps %ymm4,%ymm1,%ymm3,%ymm6 - .byte 196,98,125,24,29,68,48,0,0 // vbroadcastss 0x3044(%rip),%ymm11 # 3e10 <_sk_callback_hsw+0x1cd> - .byte 196,66,109,170,217 // vfmsub213ps %ymm9,%ymm2,%ymm11 - .byte 196,193,52,92,203 // vsubps %ymm11,%ymm9,%ymm1 - .byte 196,226,125,24,29,61,48,0,0 // vbroadcastss 0x303d(%rip),%ymm3 # 3e1c <_sk_callback_hsw+0x1d9> - .byte 197,116,89,243 // vmulps %ymm3,%ymm1,%ymm14 + .byte 197,121,110,192 // vmovd %eax,%xmm8 + .byte 196,66,125,88,192 // vpbroadcastd %xmm8,%ymm8 + .byte 196,65,108,194,200,1 // vcmpltps %ymm8,%ymm2,%ymm9 + .byte 197,100,89,210 // vmulps %ymm2,%ymm3,%ymm10 + .byte 196,65,100,92,218 // vsubps %ymm10,%ymm3,%ymm11 + .byte 196,67,37,74,202,144 // vblendvps %ymm9,%ymm10,%ymm11,%ymm9 + .byte 197,52,88,202 // vaddps %ymm2,%ymm9,%ymm9 + .byte 196,98,125,24,21,49,48,0,0 // vbroadcastss 0x3031(%rip),%ymm10 # 3d9c <_sk_callback_hsw+0x1c9> + .byte 196,66,109,170,209 // vfmsub213ps %ymm9,%ymm2,%ymm10 + .byte 196,98,125,24,29,39,48,0,0 // vbroadcastss 0x3027(%rip),%ymm11 # 3da0 <_sk_callback_hsw+0x1cd> + .byte 196,65,116,88,219 // vaddps %ymm11,%ymm1,%ymm11 + .byte 196,67,125,8,227,1 // vroundps $0x1,%ymm11,%ymm12 + .byte 196,65,36,92,236 // vsubps %ymm12,%ymm11,%ymm13 + .byte 196,65,52,92,218 // vsubps %ymm10,%ymm9,%ymm11 + .byte 196,98,125,24,37,13,48,0,0 // vbroadcastss 0x300d(%rip),%ymm12 # 3da4 <_sk_callback_hsw+0x1d1> + .byte 196,65,20,89,244 // vmulps %ymm12,%ymm13,%ymm14 + .byte 196,65,124,40,251 // vmovaps %ymm11,%ymm15 + .byte 196,66,13,168,250 // vfmadd213ps %ymm10,%ymm14,%ymm15 + .byte 196,226,125,24,5,249,47,0,0 // vbroadcastss 0x2ff9(%rip),%ymm0 # 3da8 <_sk_callback_hsw+0x1d5> + .byte 196,65,124,92,246 // vsubps %ymm14,%ymm0,%ymm14 + .byte 196,66,37,168,242 // vfmadd213ps %ymm10,%ymm11,%ymm14 .byte 65,184,171,170,42,62 // mov $0x3e2aaaab,%r8d .byte 184,171,170,42,63 // mov $0x3f2aaaab,%eax - .byte 197,249,110,200 // vmovd %eax,%xmm1 - .byte 196,226,125,88,233 // vpbroadcastd %xmm1,%ymm5 - .byte 196,226,125,24,37,32,48,0,0 // vbroadcastss 0x3020(%rip),%ymm4 # 3e20 <_sk_callback_hsw+0x1dd> - .byte 197,220,92,206 // vsubps %ymm6,%ymm4,%ymm1 - .byte 196,194,13,168,203 // vfmadd213ps %ymm11,%ymm14,%ymm1 - .byte 197,204,194,253,1 // vcmpltps %ymm5,%ymm6,%ymm7 - .byte 196,227,37,74,201,112 // vblendvps %ymm7,%ymm1,%ymm11,%ymm1 - .byte 196,193,76,194,248,1 // vcmpltps %ymm8,%ymm6,%ymm7 - .byte 196,195,117,74,249,112 // vblendvps %ymm7,%ymm9,%ymm1,%ymm7 - .byte 196,193,121,110,200 // vmovd %r8d,%xmm1 - .byte 196,226,125,88,217 // vpbroadcastd %xmm1,%ymm3 - .byte 197,204,194,203,1 // vcmpltps %ymm3,%ymm6,%ymm1 - .byte 196,194,13,168,243 // vfmadd213ps %ymm11,%ymm14,%ymm6 - .byte 196,227,69,74,206,16 // vblendvps %ymm1,%ymm6,%ymm7,%ymm1 - .byte 197,252,17,76,36,128 // vmovups %ymm1,-0x80(%rsp) - .byte 197,156,194,200,1 // vcmpltps %ymm0,%ymm12,%ymm1 - .byte 196,193,124,88,253 // vaddps %ymm13,%ymm0,%ymm7 - .byte 196,227,125,74,207,16 // vblendvps %ymm1,%ymm7,%ymm0,%ymm1 - .byte 196,193,124,194,255,1 // vcmpltps %ymm15,%ymm0,%ymm7 - .byte 196,193,124,88,242 // vaddps %ymm10,%ymm0,%ymm6 - .byte 196,227,117,74,206,112 // vblendvps %ymm7,%ymm6,%ymm1,%ymm1 - .byte 197,220,92,241 // vsubps %ymm1,%ymm4,%ymm6 - .byte 196,194,13,168,243 // vfmadd213ps %ymm11,%ymm14,%ymm6 - .byte 197,244,194,253,1 // vcmpltps %ymm5,%ymm1,%ymm7 - .byte 196,227,37,74,246,112 // vblendvps %ymm7,%ymm6,%ymm11,%ymm6 + .byte 197,249,110,248 // vmovd %eax,%xmm7 + .byte 196,226,125,88,255 // vpbroadcastd %xmm7,%ymm7 + .byte 197,148,194,247,1 // vcmpltps %ymm7,%ymm13,%ymm6 + .byte 196,195,45,74,246,96 // vblendvps %ymm6,%ymm14,%ymm10,%ymm6 + .byte 196,65,20,194,240,1 // vcmpltps %ymm8,%ymm13,%ymm14 + .byte 196,195,77,74,241,224 // vblendvps %ymm14,%ymm9,%ymm6,%ymm6 + .byte 196,193,121,110,232 // vmovd %r8d,%xmm5 + .byte 196,226,125,88,237 // vpbroadcastd %xmm5,%ymm5 + .byte 197,20,194,237,1 // vcmpltps %ymm5,%ymm13,%ymm13 + .byte 196,195,77,74,247,208 // vblendvps %ymm13,%ymm15,%ymm6,%ymm6 + .byte 196,99,125,8,233,1 // vroundps $0x1,%ymm1,%ymm13 + .byte 196,65,116,92,237 // vsubps %ymm13,%ymm1,%ymm13 + .byte 196,65,20,89,244 // vmulps %ymm12,%ymm13,%ymm14 + .byte 196,65,124,92,254 // vsubps %ymm14,%ymm0,%ymm15 + .byte 196,66,37,168,250 // vfmadd213ps %ymm10,%ymm11,%ymm15 + .byte 197,148,194,231,1 // vcmpltps %ymm7,%ymm13,%ymm4 + .byte 196,195,45,74,231,64 // vblendvps %ymm4,%ymm15,%ymm10,%ymm4 + .byte 196,65,20,194,248,1 // vcmpltps %ymm8,%ymm13,%ymm15 + .byte 196,195,93,74,225,240 // vblendvps %ymm15,%ymm9,%ymm4,%ymm4 + .byte 196,66,37,168,242 // vfmadd213ps %ymm10,%ymm11,%ymm14 + .byte 197,20,194,237,1 // vcmpltps %ymm5,%ymm13,%ymm13 + .byte 196,195,93,74,230,208 // vblendvps %ymm13,%ymm14,%ymm4,%ymm4 + .byte 196,98,125,24,45,105,47,0,0 // vbroadcastss 0x2f69(%rip),%ymm13 # 3dac <_sk_callback_hsw+0x1d9> + .byte 196,193,116,88,205 // vaddps %ymm13,%ymm1,%ymm1 + .byte 196,99,125,8,233,1 // vroundps $0x1,%ymm1,%ymm13 + .byte 196,193,116,92,205 // vsubps %ymm13,%ymm1,%ymm1 + .byte 196,65,116,89,228 // vmulps %ymm12,%ymm1,%ymm12 + .byte 196,193,124,92,196 // vsubps %ymm12,%ymm0,%ymm0 + .byte 196,66,37,168,226 // vfmadd213ps %ymm10,%ymm11,%ymm12 + .byte 196,194,37,168,194 // vfmadd213ps %ymm10,%ymm11,%ymm0 + .byte 197,244,194,255,1 // vcmpltps %ymm7,%ymm1,%ymm7 + .byte 196,227,45,74,192,112 // vblendvps %ymm7,%ymm0,%ymm10,%ymm0 .byte 196,193,116,194,248,1 // vcmpltps %ymm8,%ymm1,%ymm7 - .byte 196,195,77,74,241,112 // vblendvps %ymm7,%ymm9,%ymm6,%ymm6 - .byte 197,244,194,251,1 // vcmpltps %ymm3,%ymm1,%ymm7 - .byte 196,194,13,168,203 // vfmadd213ps %ymm11,%ymm14,%ymm1 - .byte 196,227,77,74,201,112 // vblendvps %ymm7,%ymm1,%ymm6,%ymm1 - .byte 196,226,125,24,53,138,47,0,0 // vbroadcastss 0x2f8a(%rip),%ymm6 # 3e24 <_sk_callback_hsw+0x1e1> - .byte 197,252,88,198 // vaddps %ymm6,%ymm0,%ymm0 - .byte 197,156,194,240,1 // vcmpltps %ymm0,%ymm12,%ymm6 - .byte 196,193,124,88,253 // vaddps %ymm13,%ymm0,%ymm7 - .byte 196,227,125,74,247,96 // vblendvps %ymm6,%ymm7,%ymm0,%ymm6 - .byte 196,193,124,194,255,1 // vcmpltps %ymm15,%ymm0,%ymm7 - .byte 196,193,124,88,194 // vaddps %ymm10,%ymm0,%ymm0 - .byte 196,227,77,74,192,112 // vblendvps %ymm7,%ymm0,%ymm6,%ymm0 - .byte 197,220,92,224 // vsubps %ymm0,%ymm4,%ymm4 - .byte 197,252,40,240 // vmovaps %ymm0,%ymm6 - .byte 196,194,13,168,243 // vfmadd213ps %ymm11,%ymm14,%ymm6 - .byte 196,194,13,168,227 // vfmadd213ps %ymm11,%ymm14,%ymm4 - .byte 197,252,194,237,1 // vcmpltps %ymm5,%ymm0,%ymm5 - .byte 196,227,37,74,228,80 // vblendvps %ymm5,%ymm4,%ymm11,%ymm4 - .byte 196,193,124,194,232,1 // vcmpltps %ymm8,%ymm0,%ymm5 - .byte 196,195,93,74,225,80 // vblendvps %ymm5,%ymm9,%ymm4,%ymm4 - .byte 197,252,194,195,1 // vcmpltps %ymm3,%ymm0,%ymm0 - .byte 196,227,93,74,222,0 // vblendvps %ymm0,%ymm6,%ymm4,%ymm3 + .byte 196,195,125,74,193,112 // vblendvps %ymm7,%ymm9,%ymm0,%ymm0 + .byte 197,244,194,205,1 // vcmpltps %ymm5,%ymm1,%ymm1 + .byte 196,195,125,74,236,16 // vblendvps %ymm1,%ymm12,%ymm0,%ymm5 .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 - .byte 197,252,194,100,36,160,0 // vcmpeqps -0x60(%rsp),%ymm0,%ymm4 - .byte 197,252,16,68,36,128 // vmovups -0x80(%rsp),%ymm0 - .byte 196,227,125,74,194,64 // vblendvps %ymm4,%ymm2,%ymm0,%ymm0 - .byte 196,227,117,74,202,64 // vblendvps %ymm4,%ymm2,%ymm1,%ymm1 - .byte 196,227,101,74,210,64 // vblendvps %ymm4,%ymm2,%ymm3,%ymm2 + .byte 197,228,194,216,0 // vcmpeqps %ymm0,%ymm3,%ymm3 + .byte 196,227,77,74,194,48 // vblendvps %ymm3,%ymm2,%ymm6,%ymm0 + .byte 196,227,93,74,202,48 // vblendvps %ymm3,%ymm2,%ymm4,%ymm1 + .byte 196,227,85,74,210,48 // vblendvps %ymm3,%ymm2,%ymm5,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 197,252,16,92,36,192 // vmovups -0x40(%rsp),%ymm3 - .byte 197,252,16,100,36,224 // vmovups -0x20(%rsp),%ymm4 - .byte 197,252,16,44,36 // vmovups (%rsp),%ymm5 - .byte 197,252,16,116,36,32 // vmovups 0x20(%rsp),%ymm6 - .byte 197,252,16,124,36,64 // vmovups 0x40(%rsp),%ymm7 - .byte 72,131,196,120 // add $0x78,%rsp + .byte 197,252,16,92,36,128 // vmovups -0x80(%rsp),%ymm3 + .byte 197,252,16,100,36,160 // vmovups -0x60(%rsp),%ymm4 + .byte 197,252,16,108,36,192 // vmovups -0x40(%rsp),%ymm5 + .byte 197,252,16,116,36,224 // vmovups -0x20(%rsp),%ymm6 + .byte 197,252,16,60,36 // vmovups (%rsp),%ymm7 + .byte 72,131,196,56 // add $0x38,%rsp .byte 255,224 // jmpq *%rax HIDDEN _sk_scale_1_float_hsw @@ -8357,11 +8326,11 @@ _sk_scale_u8_hsw: .byte 72,139,0 // mov (%rax),%rax .byte 72,1,248 // add %rdi,%rax .byte 77,133,192 // test %r8,%r8 - .byte 117,51 // jne f99 <_sk_scale_u8_hsw+0x43> + .byte 117,51 // jne f27 <_sk_scale_u8_hsw+0x43> .byte 197,122,126,0 // vmovq (%rax),%xmm8 .byte 196,66,125,49,192 // vpmovzxbd %xmm8,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,171,46,0,0 // vbroadcastss 0x2eab(%rip),%ymm9 # 3e28 <_sk_callback_hsw+0x1e5> + .byte 196,98,125,24,13,165,46,0,0 // vbroadcastss 0x2ea5(%rip),%ymm9 # 3db0 <_sk_callback_hsw+0x1dd> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 @@ -8379,9 +8348,9 @@ _sk_scale_u8_hsw: .byte 77,9,217 // or %r11,%r9 .byte 72,131,193,8 // add $0x8,%rcx .byte 73,255,202 // dec %r10 - .byte 117,234 // jne fa1 <_sk_scale_u8_hsw+0x4b> + .byte 117,234 // jne f2f <_sk_scale_u8_hsw+0x4b> .byte 196,65,249,110,193 // vmovq %r9,%xmm8 - .byte 235,172 // jmp f6a <_sk_scale_u8_hsw+0x14> + .byte 235,172 // jmp ef8 <_sk_scale_u8_hsw+0x14> HIDDEN _sk_lerp_1_float_hsw .globl _sk_lerp_1_float_hsw @@ -8409,11 +8378,11 @@ _sk_lerp_u8_hsw: .byte 72,139,0 // mov (%rax),%rax .byte 72,1,248 // add %rdi,%rax .byte 77,133,192 // test %r8,%r8 - .byte 117,71 // jne 1044 <_sk_lerp_u8_hsw+0x57> + .byte 117,71 // jne fd2 <_sk_lerp_u8_hsw+0x57> .byte 197,122,126,0 // vmovq (%rax),%xmm8 .byte 196,66,125,49,192 // vpmovzxbd %xmm8,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,24,46,0,0 // vbroadcastss 0x2e18(%rip),%ymm9 # 3e2c <_sk_callback_hsw+0x1e9> + .byte 196,98,125,24,13,18,46,0,0 // vbroadcastss 0x2e12(%rip),%ymm9 # 3db4 <_sk_callback_hsw+0x1e1> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 .byte 197,252,92,196 // vsubps %ymm4,%ymm0,%ymm0 .byte 196,226,61,168,196 // vfmadd213ps %ymm4,%ymm8,%ymm0 @@ -8435,9 +8404,9 @@ _sk_lerp_u8_hsw: .byte 77,9,217 // or %r11,%r9 .byte 72,131,193,8 // add $0x8,%rcx .byte 73,255,202 // dec %r10 - .byte 117,234 // jne 104c <_sk_lerp_u8_hsw+0x5f> + .byte 117,234 // jne fda <_sk_lerp_u8_hsw+0x5f> .byte 196,65,249,110,193 // vmovq %r9,%xmm8 - .byte 235,152 // jmp 1001 <_sk_lerp_u8_hsw+0x14> + .byte 235,152 // jmp f8f <_sk_lerp_u8_hsw+0x14> HIDDEN _sk_lerp_565_hsw .globl _sk_lerp_565_hsw @@ -8446,23 +8415,23 @@ _sk_lerp_565_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,149,0,0,0 // jne 110c <_sk_lerp_565_hsw+0xa3> + .byte 15,133,149,0,0,0 // jne 109a <_sk_lerp_565_hsw+0xa3> .byte 196,193,122,111,28,122 // vmovdqu (%r10,%rdi,2),%xmm3 .byte 196,226,125,51,219 // vpmovzxwd %xmm3,%ymm3 - .byte 196,98,125,88,5,165,45,0,0 // vpbroadcastd 0x2da5(%rip),%ymm8 # 3e30 <_sk_callback_hsw+0x1ed> + .byte 196,98,125,88,5,159,45,0,0 // vpbroadcastd 0x2d9f(%rip),%ymm8 # 3db8 <_sk_callback_hsw+0x1e5> .byte 196,65,101,219,192 // vpand %ymm8,%ymm3,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,150,45,0,0 // vbroadcastss 0x2d96(%rip),%ymm9 # 3e34 <_sk_callback_hsw+0x1f1> + .byte 196,98,125,24,13,144,45,0,0 // vbroadcastss 0x2d90(%rip),%ymm9 # 3dbc <_sk_callback_hsw+0x1e9> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 - .byte 196,98,125,88,13,140,45,0,0 // vpbroadcastd 0x2d8c(%rip),%ymm9 # 3e38 <_sk_callback_hsw+0x1f5> + .byte 196,98,125,88,13,134,45,0,0 // vpbroadcastd 0x2d86(%rip),%ymm9 # 3dc0 <_sk_callback_hsw+0x1ed> .byte 196,65,101,219,201 // vpand %ymm9,%ymm3,%ymm9 .byte 196,65,124,91,201 // vcvtdq2ps %ymm9,%ymm9 - .byte 196,98,125,24,21,125,45,0,0 // vbroadcastss 0x2d7d(%rip),%ymm10 # 3e3c <_sk_callback_hsw+0x1f9> + .byte 196,98,125,24,21,119,45,0,0 // vbroadcastss 0x2d77(%rip),%ymm10 # 3dc4 <_sk_callback_hsw+0x1f1> .byte 196,65,52,89,202 // vmulps %ymm10,%ymm9,%ymm9 - .byte 196,98,125,88,21,115,45,0,0 // vpbroadcastd 0x2d73(%rip),%ymm10 # 3e40 <_sk_callback_hsw+0x1fd> + .byte 196,98,125,88,21,109,45,0,0 // vpbroadcastd 0x2d6d(%rip),%ymm10 # 3dc8 <_sk_callback_hsw+0x1f5> .byte 196,193,101,219,218 // vpand %ymm10,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,21,101,45,0,0 // vbroadcastss 0x2d65(%rip),%ymm10 # 3e44 <_sk_callback_hsw+0x201> + .byte 196,98,125,24,21,95,45,0,0 // vbroadcastss 0x2d5f(%rip),%ymm10 # 3dcc <_sk_callback_hsw+0x1f9> .byte 196,193,100,89,218 // vmulps %ymm10,%ymm3,%ymm3 .byte 197,252,92,196 // vsubps %ymm4,%ymm0,%ymm0 .byte 196,226,61,168,196 // vfmadd213ps %ymm4,%ymm8,%ymm0 @@ -8471,16 +8440,16 @@ _sk_lerp_565_hsw: .byte 197,236,92,214 // vsubps %ymm6,%ymm2,%ymm2 .byte 196,226,101,168,214 // vfmadd213ps %ymm6,%ymm3,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,62,45,0,0 // vbroadcastss 0x2d3e(%rip),%ymm3 # 3e48 <_sk_callback_hsw+0x205> + .byte 196,226,125,24,29,56,45,0,0 // vbroadcastss 0x2d38(%rip),%ymm3 # 3dd0 <_sk_callback_hsw+0x1fd> .byte 255,224 // jmpq *%rax .byte 65,137,200 // mov %ecx,%r8d .byte 65,128,224,7 // and $0x7,%r8b .byte 197,225,239,219 // vpxor %xmm3,%xmm3,%xmm3 .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 15,135,89,255,255,255 // ja 107d <_sk_lerp_565_hsw+0x14> + .byte 15,135,89,255,255,255 // ja 100b <_sk_lerp_565_hsw+0x14> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,73,0,0,0 // lea 0x49(%rip),%r9 # 1178 <_sk_lerp_565_hsw+0x10f> + .byte 76,141,13,75,0,0,0 // lea 0x4b(%rip),%r9 # 1108 <_sk_lerp_565_hsw+0x111> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -8492,27 +8461,28 @@ _sk_lerp_565_hsw: .byte 196,193,97,196,92,122,4,2 // vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm3,%xmm3 .byte 196,193,97,196,92,122,2,1 // vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm3,%xmm3 .byte 196,193,97,196,28,122,0 // vpinsrw $0x0,(%r10,%rdi,2),%xmm3,%xmm3 - .byte 233,5,255,255,255 // jmpq 107d <_sk_lerp_565_hsw+0x14> - .byte 244 // hlt + .byte 233,5,255,255,255 // jmpq 100b <_sk_lerp_565_hsw+0x14> + .byte 102,144 // xchg %ax,%ax + .byte 242,255 // repnz (bad) .byte 255 // (bad) .byte 255 // (bad) + .byte 234 // (bad) .byte 255 // (bad) - .byte 236 // in (%dx),%al .byte 255 // (bad) + .byte 255,226 // jmpq *%rdx .byte 255 // (bad) - .byte 255,228 // jmpq *%rsp .byte 255 // (bad) .byte 255 // (bad) + .byte 218,255 // (bad) .byte 255 // (bad) - .byte 220,255 // fdivr %st,%st(7) + .byte 255,210 // callq *%rdx .byte 255 // (bad) - .byte 255,212 // callq *%rsp .byte 255 // (bad) + .byte 255,202 // dec %edx .byte 255 // (bad) - .byte 255,204 // dec %esp .byte 255 // (bad) .byte 255 // (bad) - .byte 255,192 // inc %eax + .byte 190 // .byte 0xbe .byte 255 // (bad) .byte 255 // (bad) .byte 255 // .byte 0xff @@ -8526,23 +8496,23 @@ _sk_load_tables_hsw: .byte 76,141,12,189,0,0,0,0 // lea 0x0(,%rdi,4),%r9 .byte 76,3,8 // add (%rax),%r9 .byte 77,133,192 // test %r8,%r8 - .byte 117,105 // jne 1212 <_sk_load_tables_hsw+0x7e> + .byte 117,105 // jne 11a2 <_sk_load_tables_hsw+0x7e> .byte 196,193,126,111,25 // vmovdqu (%r9),%ymm3 - .byte 197,229,219,13,42,47,0,0 // vpand 0x2f2a(%rip),%ymm3,%ymm1 # 40e0 <_sk_callback_hsw+0x49d> + .byte 197,229,219,13,26,47,0,0 // vpand 0x2f1a(%rip),%ymm3,%ymm1 # 4060 <_sk_callback_hsw+0x48d> .byte 196,65,61,118,192 // vpcmpeqd %ymm8,%ymm8,%ymm8 .byte 72,139,72,8 // mov 0x8(%rax),%rcx .byte 76,139,72,16 // mov 0x10(%rax),%r9 .byte 197,237,118,210 // vpcmpeqd %ymm2,%ymm2,%ymm2 .byte 196,226,109,146,4,137 // vgatherdps %ymm2,(%rcx,%ymm1,4),%ymm0 - .byte 196,226,101,0,21,42,47,0,0 // vpshufb 0x2f2a(%rip),%ymm3,%ymm2 # 4100 <_sk_callback_hsw+0x4bd> + .byte 196,226,101,0,21,26,47,0,0 // vpshufb 0x2f1a(%rip),%ymm3,%ymm2 # 4080 <_sk_callback_hsw+0x4ad> .byte 196,65,53,118,201 // vpcmpeqd %ymm9,%ymm9,%ymm9 .byte 196,194,53,146,12,145 // vgatherdps %ymm9,(%r9,%ymm2,4),%ymm1 .byte 72,139,64,24 // mov 0x18(%rax),%rax - .byte 196,98,101,0,13,50,47,0,0 // vpshufb 0x2f32(%rip),%ymm3,%ymm9 # 4120 <_sk_callback_hsw+0x4dd> + .byte 196,98,101,0,13,34,47,0,0 // vpshufb 0x2f22(%rip),%ymm3,%ymm9 # 40a0 <_sk_callback_hsw+0x4cd> .byte 196,162,61,146,20,136 // vgatherdps %ymm8,(%rax,%ymm9,4),%ymm2 .byte 197,229,114,211,24 // vpsrld $0x18,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,70,44,0,0 // vbroadcastss 0x2c46(%rip),%ymm8 # 3e4c <_sk_callback_hsw+0x209> + .byte 196,98,125,24,5,62,44,0,0 // vbroadcastss 0x2c3e(%rip),%ymm8 # 3dd4 <_sk_callback_hsw+0x201> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,137,193 // mov %r8,%rcx @@ -8555,7 +8525,7 @@ _sk_load_tables_hsw: .byte 196,193,249,110,194 // vmovq %r10,%xmm0 .byte 196,226,125,33,192 // vpmovsxbd %xmm0,%ymm0 .byte 196,194,125,140,25 // vpmaskmovd (%r9),%ymm0,%ymm3 - .byte 233,115,255,255,255 // jmpq 11ae <_sk_load_tables_hsw+0x1a> + .byte 233,115,255,255,255 // jmpq 113e <_sk_load_tables_hsw+0x1a> HIDDEN _sk_load_tables_u16_be_hsw .globl _sk_load_tables_u16_be_hsw @@ -8565,7 +8535,7 @@ _sk_load_tables_u16_be_hsw: .byte 76,139,0 // mov (%rax),%r8 .byte 76,141,12,189,0,0,0,0 // lea 0x0(,%rdi,4),%r9 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,201,0,0,0 // jne 131a <_sk_load_tables_u16_be_hsw+0xdf> + .byte 15,133,201,0,0,0 // jne 12aa <_sk_load_tables_u16_be_hsw+0xdf> .byte 196,1,121,16,4,72 // vmovupd (%r8,%r9,2),%xmm8 .byte 196,129,121,16,84,72,16 // vmovupd 0x10(%r8,%r9,2),%xmm2 .byte 196,129,121,16,92,72,32 // vmovupd 0x20(%r8,%r9,2),%xmm3 @@ -8581,7 +8551,7 @@ _sk_load_tables_u16_be_hsw: .byte 197,185,108,200 // vpunpcklqdq %xmm0,%xmm8,%xmm1 .byte 197,185,109,208 // vpunpckhqdq %xmm0,%xmm8,%xmm2 .byte 197,49,108,195 // vpunpcklqdq %xmm3,%xmm9,%xmm8 - .byte 197,121,111,21,190,47,0,0 // vmovdqa 0x2fbe(%rip),%xmm10 # 4260 <_sk_callback_hsw+0x61d> + .byte 197,121,111,21,174,47,0,0 // vmovdqa 0x2fae(%rip),%xmm10 # 41e0 <_sk_callback_hsw+0x60d> .byte 196,193,113,219,194 // vpand %xmm10,%xmm1,%xmm0 .byte 196,226,125,51,200 // vpmovzxwd %xmm0,%ymm1 .byte 196,65,37,118,219 // vpcmpeqd %ymm11,%ymm11,%ymm11 @@ -8603,36 +8573,36 @@ _sk_load_tables_u16_be_hsw: .byte 197,185,235,219 // vpor %xmm3,%xmm8,%xmm3 .byte 196,226,125,51,219 // vpmovzxwd %xmm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,63,43,0,0 // vbroadcastss 0x2b3f(%rip),%ymm8 # 3e50 <_sk_callback_hsw+0x20d> + .byte 196,98,125,24,5,55,43,0,0 // vbroadcastss 0x2b37(%rip),%ymm8 # 3dd8 <_sk_callback_hsw+0x205> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax .byte 196,1,123,16,4,72 // vmovsd (%r8,%r9,2),%xmm8 .byte 196,65,49,239,201 // vpxor %xmm9,%xmm9,%xmm9 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,85 // je 1380 <_sk_load_tables_u16_be_hsw+0x145> + .byte 116,85 // je 1310 <_sk_load_tables_u16_be_hsw+0x145> .byte 196,1,57,22,68,72,8 // vmovhpd 0x8(%r8,%r9,2),%xmm8,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,72 // jb 1380 <_sk_load_tables_u16_be_hsw+0x145> + .byte 114,72 // jb 1310 <_sk_load_tables_u16_be_hsw+0x145> .byte 196,129,123,16,84,72,16 // vmovsd 0x10(%r8,%r9,2),%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 116,72 // je 138d <_sk_load_tables_u16_be_hsw+0x152> + .byte 116,72 // je 131d <_sk_load_tables_u16_be_hsw+0x152> .byte 196,129,105,22,84,72,24 // vmovhpd 0x18(%r8,%r9,2),%xmm2,%xmm2 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,59 // jb 138d <_sk_load_tables_u16_be_hsw+0x152> + .byte 114,59 // jb 131d <_sk_load_tables_u16_be_hsw+0x152> .byte 196,129,123,16,92,72,32 // vmovsd 0x20(%r8,%r9,2),%xmm3 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 15,132,9,255,255,255 // je 126c <_sk_load_tables_u16_be_hsw+0x31> + .byte 15,132,9,255,255,255 // je 11fc <_sk_load_tables_u16_be_hsw+0x31> .byte 196,129,97,22,92,72,40 // vmovhpd 0x28(%r8,%r9,2),%xmm3,%xmm3 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 15,130,248,254,255,255 // jb 126c <_sk_load_tables_u16_be_hsw+0x31> + .byte 15,130,248,254,255,255 // jb 11fc <_sk_load_tables_u16_be_hsw+0x31> .byte 196,1,122,126,76,72,48 // vmovq 0x30(%r8,%r9,2),%xmm9 - .byte 233,236,254,255,255 // jmpq 126c <_sk_load_tables_u16_be_hsw+0x31> + .byte 233,236,254,255,255 // jmpq 11fc <_sk_load_tables_u16_be_hsw+0x31> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 .byte 197,233,87,210 // vxorpd %xmm2,%xmm2,%xmm2 - .byte 233,223,254,255,255 // jmpq 126c <_sk_load_tables_u16_be_hsw+0x31> + .byte 233,223,254,255,255 // jmpq 11fc <_sk_load_tables_u16_be_hsw+0x31> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 - .byte 233,214,254,255,255 // jmpq 126c <_sk_load_tables_u16_be_hsw+0x31> + .byte 233,214,254,255,255 // jmpq 11fc <_sk_load_tables_u16_be_hsw+0x31> HIDDEN _sk_load_tables_rgb_u16_be_hsw .globl _sk_load_tables_rgb_u16_be_hsw @@ -8642,7 +8612,7 @@ _sk_load_tables_rgb_u16_be_hsw: .byte 76,139,0 // mov (%rax),%r8 .byte 76,141,12,127 // lea (%rdi,%rdi,2),%r9 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,193,0,0,0 // jne 1469 <_sk_load_tables_rgb_u16_be_hsw+0xd3> + .byte 15,133,193,0,0,0 // jne 13f9 <_sk_load_tables_rgb_u16_be_hsw+0xd3> .byte 196,129,122,111,4,72 // vmovdqu (%r8,%r9,2),%xmm0 .byte 196,129,122,111,84,72,12 // vmovdqu 0xc(%r8,%r9,2),%xmm2 .byte 196,129,122,111,76,72,24 // vmovdqu 0x18(%r8,%r9,2),%xmm1 @@ -8663,7 +8633,7 @@ _sk_load_tables_rgb_u16_be_hsw: .byte 197,185,108,218 // vpunpcklqdq %xmm2,%xmm8,%xmm3 .byte 197,185,109,210 // vpunpckhqdq %xmm2,%xmm8,%xmm2 .byte 197,121,108,193 // vpunpcklqdq %xmm1,%xmm0,%xmm8 - .byte 197,121,111,13,94,46,0,0 // vmovdqa 0x2e5e(%rip),%xmm9 # 4270 <_sk_callback_hsw+0x62d> + .byte 197,121,111,13,78,46,0,0 // vmovdqa 0x2e4e(%rip),%xmm9 # 41f0 <_sk_callback_hsw+0x61d> .byte 196,193,97,219,193 // vpand %xmm9,%xmm3,%xmm0 .byte 196,226,125,51,200 // vpmovzxwd %xmm0,%ymm1 .byte 197,229,118,219 // vpcmpeqd %ymm3,%ymm3,%ymm3 @@ -8680,41 +8650,41 @@ _sk_load_tables_rgb_u16_be_hsw: .byte 196,98,125,51,194 // vpmovzxwd %xmm2,%ymm8 .byte 196,162,101,146,20,128 // vgatherdps %ymm3,(%rax,%ymm8,4),%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,237,41,0,0 // vbroadcastss 0x29ed(%rip),%ymm3 # 3e54 <_sk_callback_hsw+0x211> + .byte 196,226,125,24,29,229,41,0,0 // vbroadcastss 0x29e5(%rip),%ymm3 # 3ddc <_sk_callback_hsw+0x209> .byte 255,224 // jmpq *%rax .byte 196,129,121,110,4,72 // vmovd (%r8,%r9,2),%xmm0 .byte 196,129,121,196,68,72,4,2 // vpinsrw $0x2,0x4(%r8,%r9,2),%xmm0,%xmm0 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 117,5 // jne 1482 <_sk_load_tables_rgb_u16_be_hsw+0xec> - .byte 233,90,255,255,255 // jmpq 13dc <_sk_load_tables_rgb_u16_be_hsw+0x46> + .byte 117,5 // jne 1412 <_sk_load_tables_rgb_u16_be_hsw+0xec> + .byte 233,90,255,255,255 // jmpq 136c <_sk_load_tables_rgb_u16_be_hsw+0x46> .byte 196,129,121,110,76,72,6 // vmovd 0x6(%r8,%r9,2),%xmm1 .byte 196,1,113,196,68,72,10,2 // vpinsrw $0x2,0xa(%r8,%r9,2),%xmm1,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,26 // jb 14b1 <_sk_load_tables_rgb_u16_be_hsw+0x11b> + .byte 114,26 // jb 1441 <_sk_load_tables_rgb_u16_be_hsw+0x11b> .byte 196,129,121,110,76,72,12 // vmovd 0xc(%r8,%r9,2),%xmm1 .byte 196,129,113,196,84,72,16,2 // vpinsrw $0x2,0x10(%r8,%r9,2),%xmm1,%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 117,10 // jne 14b6 <_sk_load_tables_rgb_u16_be_hsw+0x120> - .byte 233,43,255,255,255 // jmpq 13dc <_sk_load_tables_rgb_u16_be_hsw+0x46> - .byte 233,38,255,255,255 // jmpq 13dc <_sk_load_tables_rgb_u16_be_hsw+0x46> + .byte 117,10 // jne 1446 <_sk_load_tables_rgb_u16_be_hsw+0x120> + .byte 233,43,255,255,255 // jmpq 136c <_sk_load_tables_rgb_u16_be_hsw+0x46> + .byte 233,38,255,255,255 // jmpq 136c <_sk_load_tables_rgb_u16_be_hsw+0x46> .byte 196,129,121,110,76,72,18 // vmovd 0x12(%r8,%r9,2),%xmm1 .byte 196,1,113,196,76,72,22,2 // vpinsrw $0x2,0x16(%r8,%r9,2),%xmm1,%xmm9 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,26 // jb 14e5 <_sk_load_tables_rgb_u16_be_hsw+0x14f> + .byte 114,26 // jb 1475 <_sk_load_tables_rgb_u16_be_hsw+0x14f> .byte 196,129,121,110,76,72,24 // vmovd 0x18(%r8,%r9,2),%xmm1 .byte 196,129,113,196,76,72,28,2 // vpinsrw $0x2,0x1c(%r8,%r9,2),%xmm1,%xmm1 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 117,10 // jne 14ea <_sk_load_tables_rgb_u16_be_hsw+0x154> - .byte 233,247,254,255,255 // jmpq 13dc <_sk_load_tables_rgb_u16_be_hsw+0x46> - .byte 233,242,254,255,255 // jmpq 13dc <_sk_load_tables_rgb_u16_be_hsw+0x46> + .byte 117,10 // jne 147a <_sk_load_tables_rgb_u16_be_hsw+0x154> + .byte 233,247,254,255,255 // jmpq 136c <_sk_load_tables_rgb_u16_be_hsw+0x46> + .byte 233,242,254,255,255 // jmpq 136c <_sk_load_tables_rgb_u16_be_hsw+0x46> .byte 196,129,121,110,92,72,30 // vmovd 0x1e(%r8,%r9,2),%xmm3 .byte 196,1,97,196,92,72,34,2 // vpinsrw $0x2,0x22(%r8,%r9,2),%xmm3,%xmm11 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,20 // jb 1513 <_sk_load_tables_rgb_u16_be_hsw+0x17d> + .byte 114,20 // jb 14a3 <_sk_load_tables_rgb_u16_be_hsw+0x17d> .byte 196,129,121,110,92,72,36 // vmovd 0x24(%r8,%r9,2),%xmm3 .byte 196,129,97,196,92,72,40,2 // vpinsrw $0x2,0x28(%r8,%r9,2),%xmm3,%xmm3 - .byte 233,201,254,255,255 // jmpq 13dc <_sk_load_tables_rgb_u16_be_hsw+0x46> - .byte 233,196,254,255,255 // jmpq 13dc <_sk_load_tables_rgb_u16_be_hsw+0x46> + .byte 233,201,254,255,255 // jmpq 136c <_sk_load_tables_rgb_u16_be_hsw+0x46> + .byte 233,196,254,255,255 // jmpq 136c <_sk_load_tables_rgb_u16_be_hsw+0x46> HIDDEN _sk_byte_tables_hsw .globl _sk_byte_tables_hsw @@ -8727,7 +8697,7 @@ _sk_byte_tables_hsw: .byte 65,84 // push %r12 .byte 83 // push %rbx .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,43,41,0,0 // vbroadcastss 0x292b(%rip),%ymm8 # 3e58 <_sk_callback_hsw+0x215> + .byte 196,98,125,24,5,35,41,0,0 // vbroadcastss 0x2923(%rip),%ymm8 # 3de0 <_sk_callback_hsw+0x20d> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 197,253,91,192 // vcvtps2dq %ymm0,%ymm0 .byte 196,195,249,22,192,1 // vpextrq $0x1,%xmm0,%r8 @@ -8764,7 +8734,7 @@ _sk_byte_tables_hsw: .byte 196,227,121,32,197,7 // vpinsrb $0x7,%ebp,%xmm0,%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,124,40,0,0 // vbroadcastss 0x287c(%rip),%ymm9 # 3e5c <_sk_callback_hsw+0x219> + .byte 196,98,125,24,13,116,40,0,0 // vbroadcastss 0x2874(%rip),%ymm9 # 3de4 <_sk_callback_hsw+0x211> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 @@ -8925,7 +8895,7 @@ _sk_byte_tables_rgb_hsw: .byte 196,227,121,32,197,7 // vpinsrb $0x7,%ebp,%xmm0,%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,181,37,0,0 // vbroadcastss 0x25b5(%rip),%ymm9 # 3e60 <_sk_callback_hsw+0x21d> + .byte 196,98,125,24,13,173,37,0,0 // vbroadcastss 0x25ad(%rip),%ymm9 # 3de8 <_sk_callback_hsw+0x215> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 @@ -9088,33 +9058,33 @@ _sk_parametric_r_hsw: .byte 196,66,125,168,211 // vfmadd213ps %ymm11,%ymm0,%ymm10 .byte 196,226,125,24,0 // vbroadcastss (%rax),%ymm0 .byte 196,65,124,91,218 // vcvtdq2ps %ymm10,%ymm11 - .byte 196,98,125,24,37,104,35,0,0 // vbroadcastss 0x2368(%rip),%ymm12 # 3e64 <_sk_callback_hsw+0x221> - .byte 196,98,125,24,45,99,35,0,0 // vbroadcastss 0x2363(%rip),%ymm13 # 3e68 <_sk_callback_hsw+0x225> + .byte 196,98,125,24,37,96,35,0,0 // vbroadcastss 0x2360(%rip),%ymm12 # 3dec <_sk_callback_hsw+0x219> + .byte 196,98,125,24,45,91,35,0,0 // vbroadcastss 0x235b(%rip),%ymm13 # 3df0 <_sk_callback_hsw+0x21d> .byte 196,65,44,84,213 // vandps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,89,35,0,0 // vbroadcastss 0x2359(%rip),%ymm13 # 3e6c <_sk_callback_hsw+0x229> + .byte 196,98,125,24,45,81,35,0,0 // vbroadcastss 0x2351(%rip),%ymm13 # 3df4 <_sk_callback_hsw+0x221> .byte 196,65,44,86,213 // vorps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,79,35,0,0 // vbroadcastss 0x234f(%rip),%ymm13 # 3e70 <_sk_callback_hsw+0x22d> + .byte 196,98,125,24,45,71,35,0,0 // vbroadcastss 0x2347(%rip),%ymm13 # 3df8 <_sk_callback_hsw+0x225> .byte 196,66,37,184,236 // vfmadd231ps %ymm12,%ymm11,%ymm13 - .byte 196,98,125,24,29,69,35,0,0 // vbroadcastss 0x2345(%rip),%ymm11 # 3e74 <_sk_callback_hsw+0x231> + .byte 196,98,125,24,29,61,35,0,0 // vbroadcastss 0x233d(%rip),%ymm11 # 3dfc <_sk_callback_hsw+0x229> .byte 196,66,45,172,221 // vfnmadd213ps %ymm13,%ymm10,%ymm11 - .byte 196,98,125,24,37,59,35,0,0 // vbroadcastss 0x233b(%rip),%ymm12 # 3e78 <_sk_callback_hsw+0x235> + .byte 196,98,125,24,37,51,35,0,0 // vbroadcastss 0x2333(%rip),%ymm12 # 3e00 <_sk_callback_hsw+0x22d> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,49,35,0,0 // vbroadcastss 0x2331(%rip),%ymm12 # 3e7c <_sk_callback_hsw+0x239> + .byte 196,98,125,24,37,41,35,0,0 // vbroadcastss 0x2329(%rip),%ymm12 # 3e04 <_sk_callback_hsw+0x231> .byte 196,65,28,94,210 // vdivps %ymm10,%ymm12,%ymm10 .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 196,99,125,8,208,1 // vroundps $0x1,%ymm0,%ymm10 .byte 196,65,124,92,210 // vsubps %ymm10,%ymm0,%ymm10 - .byte 196,98,125,24,29,18,35,0,0 // vbroadcastss 0x2312(%rip),%ymm11 # 3e80 <_sk_callback_hsw+0x23d> + .byte 196,98,125,24,29,10,35,0,0 // vbroadcastss 0x230a(%rip),%ymm11 # 3e08 <_sk_callback_hsw+0x235> .byte 196,193,124,88,195 // vaddps %ymm11,%ymm0,%ymm0 - .byte 196,98,125,24,29,8,35,0,0 // vbroadcastss 0x2308(%rip),%ymm11 # 3e84 <_sk_callback_hsw+0x241> + .byte 196,98,125,24,29,0,35,0,0 // vbroadcastss 0x2300(%rip),%ymm11 # 3e0c <_sk_callback_hsw+0x239> .byte 196,98,45,172,216 // vfnmadd213ps %ymm0,%ymm10,%ymm11 - .byte 196,226,125,24,5,254,34,0,0 // vbroadcastss 0x22fe(%rip),%ymm0 # 3e88 <_sk_callback_hsw+0x245> + .byte 196,226,125,24,5,246,34,0,0 // vbroadcastss 0x22f6(%rip),%ymm0 # 3e10 <_sk_callback_hsw+0x23d> .byte 196,193,124,92,194 // vsubps %ymm10,%ymm0,%ymm0 - .byte 196,98,125,24,21,244,34,0,0 // vbroadcastss 0x22f4(%rip),%ymm10 # 3e8c <_sk_callback_hsw+0x249> + .byte 196,98,125,24,21,236,34,0,0 // vbroadcastss 0x22ec(%rip),%ymm10 # 3e14 <_sk_callback_hsw+0x241> .byte 197,172,94,192 // vdivps %ymm0,%ymm10,%ymm0 .byte 197,164,88,192 // vaddps %ymm0,%ymm11,%ymm0 - .byte 196,98,125,24,21,231,34,0,0 // vbroadcastss 0x22e7(%rip),%ymm10 # 3e90 <_sk_callback_hsw+0x24d> + .byte 196,98,125,24,21,223,34,0,0 // vbroadcastss 0x22df(%rip),%ymm10 # 3e18 <_sk_callback_hsw+0x245> .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 197,253,91,192 // vcvtps2dq %ymm0,%ymm0 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -9122,7 +9092,7 @@ _sk_parametric_r_hsw: .byte 196,195,125,74,193,128 // vblendvps %ymm8,%ymm9,%ymm0,%ymm0 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,124,95,192 // vmaxps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,190,34,0,0 // vbroadcastss 0x22be(%rip),%ymm8 # 3e94 <_sk_callback_hsw+0x251> + .byte 196,98,125,24,5,182,34,0,0 // vbroadcastss 0x22b6(%rip),%ymm8 # 3e1c <_sk_callback_hsw+0x249> .byte 196,193,124,93,192 // vminps %ymm8,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -9142,33 +9112,33 @@ _sk_parametric_g_hsw: .byte 196,66,117,168,211 // vfmadd213ps %ymm11,%ymm1,%ymm10 .byte 196,226,125,24,8 // vbroadcastss (%rax),%ymm1 .byte 196,65,124,91,218 // vcvtdq2ps %ymm10,%ymm11 - .byte 196,98,125,24,37,118,34,0,0 // vbroadcastss 0x2276(%rip),%ymm12 # 3e98 <_sk_callback_hsw+0x255> - .byte 196,98,125,24,45,113,34,0,0 // vbroadcastss 0x2271(%rip),%ymm13 # 3e9c <_sk_callback_hsw+0x259> + .byte 196,98,125,24,37,110,34,0,0 // vbroadcastss 0x226e(%rip),%ymm12 # 3e20 <_sk_callback_hsw+0x24d> + .byte 196,98,125,24,45,105,34,0,0 // vbroadcastss 0x2269(%rip),%ymm13 # 3e24 <_sk_callback_hsw+0x251> .byte 196,65,44,84,213 // vandps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,103,34,0,0 // vbroadcastss 0x2267(%rip),%ymm13 # 3ea0 <_sk_callback_hsw+0x25d> + .byte 196,98,125,24,45,95,34,0,0 // vbroadcastss 0x225f(%rip),%ymm13 # 3e28 <_sk_callback_hsw+0x255> .byte 196,65,44,86,213 // vorps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,93,34,0,0 // vbroadcastss 0x225d(%rip),%ymm13 # 3ea4 <_sk_callback_hsw+0x261> + .byte 196,98,125,24,45,85,34,0,0 // vbroadcastss 0x2255(%rip),%ymm13 # 3e2c <_sk_callback_hsw+0x259> .byte 196,66,37,184,236 // vfmadd231ps %ymm12,%ymm11,%ymm13 - .byte 196,98,125,24,29,83,34,0,0 // vbroadcastss 0x2253(%rip),%ymm11 # 3ea8 <_sk_callback_hsw+0x265> + .byte 196,98,125,24,29,75,34,0,0 // vbroadcastss 0x224b(%rip),%ymm11 # 3e30 <_sk_callback_hsw+0x25d> .byte 196,66,45,172,221 // vfnmadd213ps %ymm13,%ymm10,%ymm11 - .byte 196,98,125,24,37,73,34,0,0 // vbroadcastss 0x2249(%rip),%ymm12 # 3eac <_sk_callback_hsw+0x269> + .byte 196,98,125,24,37,65,34,0,0 // vbroadcastss 0x2241(%rip),%ymm12 # 3e34 <_sk_callback_hsw+0x261> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,63,34,0,0 // vbroadcastss 0x223f(%rip),%ymm12 # 3eb0 <_sk_callback_hsw+0x26d> + .byte 196,98,125,24,37,55,34,0,0 // vbroadcastss 0x2237(%rip),%ymm12 # 3e38 <_sk_callback_hsw+0x265> .byte 196,65,28,94,210 // vdivps %ymm10,%ymm12,%ymm10 .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 .byte 196,193,116,89,202 // vmulps %ymm10,%ymm1,%ymm1 .byte 196,99,125,8,209,1 // vroundps $0x1,%ymm1,%ymm10 .byte 196,65,116,92,210 // vsubps %ymm10,%ymm1,%ymm10 - .byte 196,98,125,24,29,32,34,0,0 // vbroadcastss 0x2220(%rip),%ymm11 # 3eb4 <_sk_callback_hsw+0x271> + .byte 196,98,125,24,29,24,34,0,0 // vbroadcastss 0x2218(%rip),%ymm11 # 3e3c <_sk_callback_hsw+0x269> .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,22,34,0,0 // vbroadcastss 0x2216(%rip),%ymm11 # 3eb8 <_sk_callback_hsw+0x275> + .byte 196,98,125,24,29,14,34,0,0 // vbroadcastss 0x220e(%rip),%ymm11 # 3e40 <_sk_callback_hsw+0x26d> .byte 196,98,45,172,217 // vfnmadd213ps %ymm1,%ymm10,%ymm11 - .byte 196,226,125,24,13,12,34,0,0 // vbroadcastss 0x220c(%rip),%ymm1 # 3ebc <_sk_callback_hsw+0x279> + .byte 196,226,125,24,13,4,34,0,0 // vbroadcastss 0x2204(%rip),%ymm1 # 3e44 <_sk_callback_hsw+0x271> .byte 196,193,116,92,202 // vsubps %ymm10,%ymm1,%ymm1 - .byte 196,98,125,24,21,2,34,0,0 // vbroadcastss 0x2202(%rip),%ymm10 # 3ec0 <_sk_callback_hsw+0x27d> + .byte 196,98,125,24,21,250,33,0,0 // vbroadcastss 0x21fa(%rip),%ymm10 # 3e48 <_sk_callback_hsw+0x275> .byte 197,172,94,201 // vdivps %ymm1,%ymm10,%ymm1 .byte 197,164,88,201 // vaddps %ymm1,%ymm11,%ymm1 - .byte 196,98,125,24,21,245,33,0,0 // vbroadcastss 0x21f5(%rip),%ymm10 # 3ec4 <_sk_callback_hsw+0x281> + .byte 196,98,125,24,21,237,33,0,0 // vbroadcastss 0x21ed(%rip),%ymm10 # 3e4c <_sk_callback_hsw+0x279> .byte 196,193,116,89,202 // vmulps %ymm10,%ymm1,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -9176,7 +9146,7 @@ _sk_parametric_g_hsw: .byte 196,195,117,74,201,128 // vblendvps %ymm8,%ymm9,%ymm1,%ymm1 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,116,95,200 // vmaxps %ymm8,%ymm1,%ymm1 - .byte 196,98,125,24,5,204,33,0,0 // vbroadcastss 0x21cc(%rip),%ymm8 # 3ec8 <_sk_callback_hsw+0x285> + .byte 196,98,125,24,5,196,33,0,0 // vbroadcastss 0x21c4(%rip),%ymm8 # 3e50 <_sk_callback_hsw+0x27d> .byte 196,193,116,93,200 // vminps %ymm8,%ymm1,%ymm1 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -9196,33 +9166,33 @@ _sk_parametric_b_hsw: .byte 196,66,109,168,211 // vfmadd213ps %ymm11,%ymm2,%ymm10 .byte 196,226,125,24,16 // vbroadcastss (%rax),%ymm2 .byte 196,65,124,91,218 // vcvtdq2ps %ymm10,%ymm11 - .byte 196,98,125,24,37,132,33,0,0 // vbroadcastss 0x2184(%rip),%ymm12 # 3ecc <_sk_callback_hsw+0x289> - .byte 196,98,125,24,45,127,33,0,0 // vbroadcastss 0x217f(%rip),%ymm13 # 3ed0 <_sk_callback_hsw+0x28d> + .byte 196,98,125,24,37,124,33,0,0 // vbroadcastss 0x217c(%rip),%ymm12 # 3e54 <_sk_callback_hsw+0x281> + .byte 196,98,125,24,45,119,33,0,0 // vbroadcastss 0x2177(%rip),%ymm13 # 3e58 <_sk_callback_hsw+0x285> .byte 196,65,44,84,213 // vandps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,117,33,0,0 // vbroadcastss 0x2175(%rip),%ymm13 # 3ed4 <_sk_callback_hsw+0x291> + .byte 196,98,125,24,45,109,33,0,0 // vbroadcastss 0x216d(%rip),%ymm13 # 3e5c <_sk_callback_hsw+0x289> .byte 196,65,44,86,213 // vorps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,107,33,0,0 // vbroadcastss 0x216b(%rip),%ymm13 # 3ed8 <_sk_callback_hsw+0x295> + .byte 196,98,125,24,45,99,33,0,0 // vbroadcastss 0x2163(%rip),%ymm13 # 3e60 <_sk_callback_hsw+0x28d> .byte 196,66,37,184,236 // vfmadd231ps %ymm12,%ymm11,%ymm13 - .byte 196,98,125,24,29,97,33,0,0 // vbroadcastss 0x2161(%rip),%ymm11 # 3edc <_sk_callback_hsw+0x299> + .byte 196,98,125,24,29,89,33,0,0 // vbroadcastss 0x2159(%rip),%ymm11 # 3e64 <_sk_callback_hsw+0x291> .byte 196,66,45,172,221 // vfnmadd213ps %ymm13,%ymm10,%ymm11 - .byte 196,98,125,24,37,87,33,0,0 // vbroadcastss 0x2157(%rip),%ymm12 # 3ee0 <_sk_callback_hsw+0x29d> + .byte 196,98,125,24,37,79,33,0,0 // vbroadcastss 0x214f(%rip),%ymm12 # 3e68 <_sk_callback_hsw+0x295> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,77,33,0,0 // vbroadcastss 0x214d(%rip),%ymm12 # 3ee4 <_sk_callback_hsw+0x2a1> + .byte 196,98,125,24,37,69,33,0,0 // vbroadcastss 0x2145(%rip),%ymm12 # 3e6c <_sk_callback_hsw+0x299> .byte 196,65,28,94,210 // vdivps %ymm10,%ymm12,%ymm10 .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 .byte 196,193,108,89,210 // vmulps %ymm10,%ymm2,%ymm2 .byte 196,99,125,8,210,1 // vroundps $0x1,%ymm2,%ymm10 .byte 196,65,108,92,210 // vsubps %ymm10,%ymm2,%ymm10 - .byte 196,98,125,24,29,46,33,0,0 // vbroadcastss 0x212e(%rip),%ymm11 # 3ee8 <_sk_callback_hsw+0x2a5> + .byte 196,98,125,24,29,38,33,0,0 // vbroadcastss 0x2126(%rip),%ymm11 # 3e70 <_sk_callback_hsw+0x29d> .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 - .byte 196,98,125,24,29,36,33,0,0 // vbroadcastss 0x2124(%rip),%ymm11 # 3eec <_sk_callback_hsw+0x2a9> + .byte 196,98,125,24,29,28,33,0,0 // vbroadcastss 0x211c(%rip),%ymm11 # 3e74 <_sk_callback_hsw+0x2a1> .byte 196,98,45,172,218 // vfnmadd213ps %ymm2,%ymm10,%ymm11 - .byte 196,226,125,24,21,26,33,0,0 // vbroadcastss 0x211a(%rip),%ymm2 # 3ef0 <_sk_callback_hsw+0x2ad> + .byte 196,226,125,24,21,18,33,0,0 // vbroadcastss 0x2112(%rip),%ymm2 # 3e78 <_sk_callback_hsw+0x2a5> .byte 196,193,108,92,210 // vsubps %ymm10,%ymm2,%ymm2 - .byte 196,98,125,24,21,16,33,0,0 // vbroadcastss 0x2110(%rip),%ymm10 # 3ef4 <_sk_callback_hsw+0x2b1> + .byte 196,98,125,24,21,8,33,0,0 // vbroadcastss 0x2108(%rip),%ymm10 # 3e7c <_sk_callback_hsw+0x2a9> .byte 197,172,94,210 // vdivps %ymm2,%ymm10,%ymm2 .byte 197,164,88,210 // vaddps %ymm2,%ymm11,%ymm2 - .byte 196,98,125,24,21,3,33,0,0 // vbroadcastss 0x2103(%rip),%ymm10 # 3ef8 <_sk_callback_hsw+0x2b5> + .byte 196,98,125,24,21,251,32,0,0 // vbroadcastss 0x20fb(%rip),%ymm10 # 3e80 <_sk_callback_hsw+0x2ad> .byte 196,193,108,89,210 // vmulps %ymm10,%ymm2,%ymm2 .byte 197,253,91,210 // vcvtps2dq %ymm2,%ymm2 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -9230,7 +9200,7 @@ _sk_parametric_b_hsw: .byte 196,195,109,74,209,128 // vblendvps %ymm8,%ymm9,%ymm2,%ymm2 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,108,95,208 // vmaxps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,218,32,0,0 // vbroadcastss 0x20da(%rip),%ymm8 # 3efc <_sk_callback_hsw+0x2b9> + .byte 196,98,125,24,5,210,32,0,0 // vbroadcastss 0x20d2(%rip),%ymm8 # 3e84 <_sk_callback_hsw+0x2b1> .byte 196,193,108,93,208 // vminps %ymm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -9250,33 +9220,33 @@ _sk_parametric_a_hsw: .byte 196,66,101,168,211 // vfmadd213ps %ymm11,%ymm3,%ymm10 .byte 196,226,125,24,24 // vbroadcastss (%rax),%ymm3 .byte 196,65,124,91,218 // vcvtdq2ps %ymm10,%ymm11 - .byte 196,98,125,24,37,146,32,0,0 // vbroadcastss 0x2092(%rip),%ymm12 # 3f00 <_sk_callback_hsw+0x2bd> - .byte 196,98,125,24,45,141,32,0,0 // vbroadcastss 0x208d(%rip),%ymm13 # 3f04 <_sk_callback_hsw+0x2c1> + .byte 196,98,125,24,37,138,32,0,0 // vbroadcastss 0x208a(%rip),%ymm12 # 3e88 <_sk_callback_hsw+0x2b5> + .byte 196,98,125,24,45,133,32,0,0 // vbroadcastss 0x2085(%rip),%ymm13 # 3e8c <_sk_callback_hsw+0x2b9> .byte 196,65,44,84,213 // vandps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,131,32,0,0 // vbroadcastss 0x2083(%rip),%ymm13 # 3f08 <_sk_callback_hsw+0x2c5> + .byte 196,98,125,24,45,123,32,0,0 // vbroadcastss 0x207b(%rip),%ymm13 # 3e90 <_sk_callback_hsw+0x2bd> .byte 196,65,44,86,213 // vorps %ymm13,%ymm10,%ymm10 - .byte 196,98,125,24,45,121,32,0,0 // vbroadcastss 0x2079(%rip),%ymm13 # 3f0c <_sk_callback_hsw+0x2c9> + .byte 196,98,125,24,45,113,32,0,0 // vbroadcastss 0x2071(%rip),%ymm13 # 3e94 <_sk_callback_hsw+0x2c1> .byte 196,66,37,184,236 // vfmadd231ps %ymm12,%ymm11,%ymm13 - .byte 196,98,125,24,29,111,32,0,0 // vbroadcastss 0x206f(%rip),%ymm11 # 3f10 <_sk_callback_hsw+0x2cd> + .byte 196,98,125,24,29,103,32,0,0 // vbroadcastss 0x2067(%rip),%ymm11 # 3e98 <_sk_callback_hsw+0x2c5> .byte 196,66,45,172,221 // vfnmadd213ps %ymm13,%ymm10,%ymm11 - .byte 196,98,125,24,37,101,32,0,0 // vbroadcastss 0x2065(%rip),%ymm12 # 3f14 <_sk_callback_hsw+0x2d1> + .byte 196,98,125,24,37,93,32,0,0 // vbroadcastss 0x205d(%rip),%ymm12 # 3e9c <_sk_callback_hsw+0x2c9> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,91,32,0,0 // vbroadcastss 0x205b(%rip),%ymm12 # 3f18 <_sk_callback_hsw+0x2d5> + .byte 196,98,125,24,37,83,32,0,0 // vbroadcastss 0x2053(%rip),%ymm12 # 3ea0 <_sk_callback_hsw+0x2cd> .byte 196,65,28,94,210 // vdivps %ymm10,%ymm12,%ymm10 .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 .byte 196,193,100,89,218 // vmulps %ymm10,%ymm3,%ymm3 .byte 196,99,125,8,211,1 // vroundps $0x1,%ymm3,%ymm10 .byte 196,65,100,92,210 // vsubps %ymm10,%ymm3,%ymm10 - .byte 196,98,125,24,29,60,32,0,0 // vbroadcastss 0x203c(%rip),%ymm11 # 3f1c <_sk_callback_hsw+0x2d9> + .byte 196,98,125,24,29,52,32,0,0 // vbroadcastss 0x2034(%rip),%ymm11 # 3ea4 <_sk_callback_hsw+0x2d1> .byte 196,193,100,88,219 // vaddps %ymm11,%ymm3,%ymm3 - .byte 196,98,125,24,29,50,32,0,0 // vbroadcastss 0x2032(%rip),%ymm11 # 3f20 <_sk_callback_hsw+0x2dd> + .byte 196,98,125,24,29,42,32,0,0 // vbroadcastss 0x202a(%rip),%ymm11 # 3ea8 <_sk_callback_hsw+0x2d5> .byte 196,98,45,172,219 // vfnmadd213ps %ymm3,%ymm10,%ymm11 - .byte 196,226,125,24,29,40,32,0,0 // vbroadcastss 0x2028(%rip),%ymm3 # 3f24 <_sk_callback_hsw+0x2e1> + .byte 196,226,125,24,29,32,32,0,0 // vbroadcastss 0x2020(%rip),%ymm3 # 3eac <_sk_callback_hsw+0x2d9> .byte 196,193,100,92,218 // vsubps %ymm10,%ymm3,%ymm3 - .byte 196,98,125,24,21,30,32,0,0 // vbroadcastss 0x201e(%rip),%ymm10 # 3f28 <_sk_callback_hsw+0x2e5> + .byte 196,98,125,24,21,22,32,0,0 // vbroadcastss 0x2016(%rip),%ymm10 # 3eb0 <_sk_callback_hsw+0x2dd> .byte 197,172,94,219 // vdivps %ymm3,%ymm10,%ymm3 .byte 197,164,88,219 // vaddps %ymm3,%ymm11,%ymm3 - .byte 196,98,125,24,21,17,32,0,0 // vbroadcastss 0x2011(%rip),%ymm10 # 3f2c <_sk_callback_hsw+0x2e9> + .byte 196,98,125,24,21,9,32,0,0 // vbroadcastss 0x2009(%rip),%ymm10 # 3eb4 <_sk_callback_hsw+0x2e1> .byte 196,193,100,89,218 // vmulps %ymm10,%ymm3,%ymm3 .byte 197,253,91,219 // vcvtps2dq %ymm3,%ymm3 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -9284,7 +9254,7 @@ _sk_parametric_a_hsw: .byte 196,195,101,74,217,128 // vblendvps %ymm8,%ymm9,%ymm3,%ymm3 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,100,95,216 // vmaxps %ymm8,%ymm3,%ymm3 - .byte 196,98,125,24,5,232,31,0,0 // vbroadcastss 0x1fe8(%rip),%ymm8 # 3f30 <_sk_callback_hsw+0x2ed> + .byte 196,98,125,24,5,224,31,0,0 // vbroadcastss 0x1fe0(%rip),%ymm8 # 3eb8 <_sk_callback_hsw+0x2e5> .byte 196,193,100,93,216 // vminps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -9293,26 +9263,26 @@ HIDDEN _sk_lab_to_xyz_hsw .globl _sk_lab_to_xyz_hsw FUNCTION(_sk_lab_to_xyz_hsw) _sk_lab_to_xyz_hsw: - .byte 196,98,125,24,5,218,31,0,0 // vbroadcastss 0x1fda(%rip),%ymm8 # 3f34 <_sk_callback_hsw+0x2f1> - .byte 196,98,125,24,13,213,31,0,0 // vbroadcastss 0x1fd5(%rip),%ymm9 # 3f38 <_sk_callback_hsw+0x2f5> - .byte 196,98,125,24,21,208,31,0,0 // vbroadcastss 0x1fd0(%rip),%ymm10 # 3f3c <_sk_callback_hsw+0x2f9> + .byte 196,98,125,24,5,210,31,0,0 // vbroadcastss 0x1fd2(%rip),%ymm8 # 3ebc <_sk_callback_hsw+0x2e9> + .byte 196,98,125,24,13,205,31,0,0 // vbroadcastss 0x1fcd(%rip),%ymm9 # 3ec0 <_sk_callback_hsw+0x2ed> + .byte 196,98,125,24,21,200,31,0,0 // vbroadcastss 0x1fc8(%rip),%ymm10 # 3ec4 <_sk_callback_hsw+0x2f1> .byte 196,194,53,168,202 // vfmadd213ps %ymm10,%ymm9,%ymm1 .byte 196,194,53,168,210 // vfmadd213ps %ymm10,%ymm9,%ymm2 - .byte 196,98,125,24,13,193,31,0,0 // vbroadcastss 0x1fc1(%rip),%ymm9 # 3f40 <_sk_callback_hsw+0x2fd> + .byte 196,98,125,24,13,185,31,0,0 // vbroadcastss 0x1fb9(%rip),%ymm9 # 3ec8 <_sk_callback_hsw+0x2f5> .byte 196,66,125,184,200 // vfmadd231ps %ymm8,%ymm0,%ymm9 - .byte 196,226,125,24,5,183,31,0,0 // vbroadcastss 0x1fb7(%rip),%ymm0 # 3f44 <_sk_callback_hsw+0x301> + .byte 196,226,125,24,5,175,31,0,0 // vbroadcastss 0x1faf(%rip),%ymm0 # 3ecc <_sk_callback_hsw+0x2f9> .byte 197,180,89,192 // vmulps %ymm0,%ymm9,%ymm0 - .byte 196,98,125,24,5,174,31,0,0 // vbroadcastss 0x1fae(%rip),%ymm8 # 3f48 <_sk_callback_hsw+0x305> + .byte 196,98,125,24,5,166,31,0,0 // vbroadcastss 0x1fa6(%rip),%ymm8 # 3ed0 <_sk_callback_hsw+0x2fd> .byte 196,98,117,168,192 // vfmadd213ps %ymm0,%ymm1,%ymm8 - .byte 196,98,125,24,13,164,31,0,0 // vbroadcastss 0x1fa4(%rip),%ymm9 # 3f4c <_sk_callback_hsw+0x309> + .byte 196,98,125,24,13,156,31,0,0 // vbroadcastss 0x1f9c(%rip),%ymm9 # 3ed4 <_sk_callback_hsw+0x301> .byte 196,98,109,172,200 // vfnmadd213ps %ymm0,%ymm2,%ymm9 .byte 196,193,60,89,200 // vmulps %ymm8,%ymm8,%ymm1 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 - .byte 196,226,125,24,21,145,31,0,0 // vbroadcastss 0x1f91(%rip),%ymm2 # 3f50 <_sk_callback_hsw+0x30d> + .byte 196,226,125,24,21,137,31,0,0 // vbroadcastss 0x1f89(%rip),%ymm2 # 3ed8 <_sk_callback_hsw+0x305> .byte 197,108,194,209,1 // vcmpltps %ymm1,%ymm2,%ymm10 - .byte 196,98,125,24,29,135,31,0,0 // vbroadcastss 0x1f87(%rip),%ymm11 # 3f54 <_sk_callback_hsw+0x311> + .byte 196,98,125,24,29,127,31,0,0 // vbroadcastss 0x1f7f(%rip),%ymm11 # 3edc <_sk_callback_hsw+0x309> .byte 196,65,60,88,195 // vaddps %ymm11,%ymm8,%ymm8 - .byte 196,98,125,24,37,125,31,0,0 // vbroadcastss 0x1f7d(%rip),%ymm12 # 3f58 <_sk_callback_hsw+0x315> + .byte 196,98,125,24,37,117,31,0,0 // vbroadcastss 0x1f75(%rip),%ymm12 # 3ee0 <_sk_callback_hsw+0x30d> .byte 196,65,60,89,196 // vmulps %ymm12,%ymm8,%ymm8 .byte 196,99,61,74,193,160 // vblendvps %ymm10,%ymm1,%ymm8,%ymm8 .byte 197,252,89,200 // vmulps %ymm0,%ymm0,%ymm1 @@ -9327,9 +9297,9 @@ _sk_lab_to_xyz_hsw: .byte 196,65,52,88,203 // vaddps %ymm11,%ymm9,%ymm9 .byte 196,65,52,89,204 // vmulps %ymm12,%ymm9,%ymm9 .byte 196,227,53,74,208,32 // vblendvps %ymm2,%ymm0,%ymm9,%ymm2 - .byte 196,226,125,24,5,50,31,0,0 // vbroadcastss 0x1f32(%rip),%ymm0 # 3f5c <_sk_callback_hsw+0x319> + .byte 196,226,125,24,5,42,31,0,0 // vbroadcastss 0x1f2a(%rip),%ymm0 # 3ee4 <_sk_callback_hsw+0x311> .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 - .byte 196,98,125,24,5,41,31,0,0 // vbroadcastss 0x1f29(%rip),%ymm8 # 3f60 <_sk_callback_hsw+0x31d> + .byte 196,98,125,24,5,33,31,0,0 // vbroadcastss 0x1f21(%rip),%ymm8 # 3ee8 <_sk_callback_hsw+0x315> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -9343,11 +9313,11 @@ _sk_load_a8_hsw: .byte 72,139,0 // mov (%rax),%rax .byte 72,1,248 // add %rdi,%rax .byte 77,133,192 // test %r8,%r8 - .byte 117,45 // jne 207d <_sk_load_a8_hsw+0x3d> + .byte 117,45 // jne 200d <_sk_load_a8_hsw+0x3d> .byte 197,250,126,0 // vmovq (%rax),%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,254,30,0,0 // vbroadcastss 0x1efe(%rip),%ymm1 # 3f64 <_sk_callback_hsw+0x321> + .byte 196,226,125,24,13,246,30,0,0 // vbroadcastss 0x1ef6(%rip),%ymm1 # 3eec <_sk_callback_hsw+0x319> .byte 197,252,89,217 // vmulps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -9364,9 +9334,9 @@ _sk_load_a8_hsw: .byte 77,9,217 // or %r11,%r9 .byte 72,131,193,8 // add $0x8,%rcx .byte 73,255,202 // dec %r10 - .byte 117,234 // jne 2085 <_sk_load_a8_hsw+0x45> + .byte 117,234 // jne 2015 <_sk_load_a8_hsw+0x45> .byte 196,193,249,110,193 // vmovq %r9,%xmm0 - .byte 235,178 // jmp 2054 <_sk_load_a8_hsw+0x14> + .byte 235,178 // jmp 1fe4 <_sk_load_a8_hsw+0x14> HIDDEN _sk_gather_a8_hsw .globl _sk_gather_a8_hsw @@ -9412,7 +9382,7 @@ _sk_gather_a8_hsw: .byte 196,227,121,32,192,7 // vpinsrb $0x7,%eax,%xmm0,%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,9,30,0,0 // vbroadcastss 0x1e09(%rip),%ymm1 # 3f68 <_sk_callback_hsw+0x325> + .byte 196,226,125,24,13,1,30,0,0 // vbroadcastss 0x1e01(%rip),%ymm1 # 3ef0 <_sk_callback_hsw+0x31d> .byte 197,252,89,217 // vmulps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -9430,14 +9400,14 @@ FUNCTION(_sk_store_a8_hsw) _sk_store_a8_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,228,29,0,0 // vbroadcastss 0x1de4(%rip),%ymm8 # 3f6c <_sk_callback_hsw+0x329> + .byte 196,98,125,24,5,220,29,0,0 // vbroadcastss 0x1ddc(%rip),%ymm8 # 3ef4 <_sk_callback_hsw+0x321> .byte 196,65,100,89,192 // vmulps %ymm8,%ymm3,%ymm8 .byte 196,65,125,91,192 // vcvtps2dq %ymm8,%ymm8 .byte 196,67,125,25,193,1 // vextractf128 $0x1,%ymm8,%xmm9 .byte 196,66,57,43,193 // vpackusdw %xmm9,%xmm8,%xmm8 .byte 196,65,57,103,192 // vpackuswb %xmm8,%xmm8,%xmm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,10 // jne 21b1 <_sk_store_a8_hsw+0x37> + .byte 117,10 // jne 2141 <_sk_store_a8_hsw+0x37> .byte 196,65,123,17,4,58 // vmovsd %xmm8,(%r10,%rdi,1) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -9445,10 +9415,10 @@ _sk_store_a8_hsw: .byte 65,128,224,7 // and $0x7,%r8b .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 119,236 // ja 21ad <_sk_store_a8_hsw+0x33> + .byte 119,236 // ja 213d <_sk_store_a8_hsw+0x33> .byte 196,66,121,48,192 // vpmovzxbw %xmm8,%xmm8 .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,67,0,0,0 // lea 0x43(%rip),%r9 # 2214 <_sk_store_a8_hsw+0x9a> + .byte 76,141,13,67,0,0,0 // lea 0x43(%rip),%r9 # 21a4 <_sk_store_a8_hsw+0x9a> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -9459,7 +9429,7 @@ _sk_store_a8_hsw: .byte 196,67,121,20,68,58,2,4 // vpextrb $0x4,%xmm8,0x2(%r10,%rdi,1) .byte 196,67,121,20,68,58,1,2 // vpextrb $0x2,%xmm8,0x1(%r10,%rdi,1) .byte 196,67,121,20,4,58,0 // vpextrb $0x0,%xmm8,(%r10,%rdi,1) - .byte 235,154 // jmp 21ad <_sk_store_a8_hsw+0x33> + .byte 235,154 // jmp 213d <_sk_store_a8_hsw+0x33> .byte 144 // nop .byte 246,255 // idiv %bh .byte 255 // (bad) @@ -9493,14 +9463,14 @@ _sk_load_g8_hsw: .byte 72,139,0 // mov (%rax),%rax .byte 72,1,248 // add %rdi,%rax .byte 77,133,192 // test %r8,%r8 - .byte 117,50 // jne 2272 <_sk_load_g8_hsw+0x42> + .byte 117,50 // jne 2202 <_sk_load_g8_hsw+0x42> .byte 197,250,126,0 // vmovq (%rax),%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,26,29,0,0 // vbroadcastss 0x1d1a(%rip),%ymm1 # 3f70 <_sk_callback_hsw+0x32d> + .byte 196,226,125,24,13,18,29,0,0 // vbroadcastss 0x1d12(%rip),%ymm1 # 3ef8 <_sk_callback_hsw+0x325> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,15,29,0,0 // vbroadcastss 0x1d0f(%rip),%ymm3 # 3f74 <_sk_callback_hsw+0x331> + .byte 196,226,125,24,29,7,29,0,0 // vbroadcastss 0x1d07(%rip),%ymm3 # 3efc <_sk_callback_hsw+0x329> .byte 76,137,193 // mov %r8,%rcx .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 @@ -9514,9 +9484,9 @@ _sk_load_g8_hsw: .byte 77,9,217 // or %r11,%r9 .byte 72,131,193,8 // add $0x8,%rcx .byte 73,255,202 // dec %r10 - .byte 117,234 // jne 227a <_sk_load_g8_hsw+0x4a> + .byte 117,234 // jne 220a <_sk_load_g8_hsw+0x4a> .byte 196,193,249,110,193 // vmovq %r9,%xmm0 - .byte 235,173 // jmp 2244 <_sk_load_g8_hsw+0x14> + .byte 235,173 // jmp 21d4 <_sk_load_g8_hsw+0x14> HIDDEN _sk_gather_g8_hsw .globl _sk_gather_g8_hsw @@ -9562,10 +9532,10 @@ _sk_gather_g8_hsw: .byte 196,227,121,32,192,7 // vpinsrb $0x7,%eax,%xmm0,%xmm0 .byte 196,226,125,49,192 // vpmovzxbd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,36,28,0,0 // vbroadcastss 0x1c24(%rip),%ymm1 # 3f78 <_sk_callback_hsw+0x335> + .byte 196,226,125,24,13,28,28,0,0 // vbroadcastss 0x1c1c(%rip),%ymm1 # 3f00 <_sk_callback_hsw+0x32d> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,25,28,0,0 // vbroadcastss 0x1c19(%rip),%ymm3 # 3f7c <_sk_callback_hsw+0x339> + .byte 196,226,125,24,29,17,28,0,0 // vbroadcastss 0x1c11(%rip),%ymm3 # 3f04 <_sk_callback_hsw+0x331> .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 .byte 91 // pop %rbx @@ -9581,9 +9551,9 @@ _sk_gather_i8_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 73,137,192 // mov %rax,%r8 .byte 77,133,192 // test %r8,%r8 - .byte 116,5 // je 2383 <_sk_gather_i8_hsw+0xf> + .byte 116,5 // je 2313 <_sk_gather_i8_hsw+0xf> .byte 76,137,192 // mov %r8,%rax - .byte 235,2 // jmp 2385 <_sk_gather_i8_hsw+0x11> + .byte 235,2 // jmp 2315 <_sk_gather_i8_hsw+0x11> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,87 // push %r15 .byte 65,86 // push %r14 @@ -9621,14 +9591,14 @@ _sk_gather_i8_hsw: .byte 73,139,64,8 // mov 0x8(%r8),%rax .byte 197,245,118,201 // vpcmpeqd %ymm1,%ymm1,%ymm1 .byte 196,226,117,144,28,128 // vpgatherdd %ymm1,(%rax,%ymm0,4),%ymm3 - .byte 197,229,219,5,13,29,0,0 // vpand 0x1d0d(%rip),%ymm3,%ymm0 # 4140 <_sk_callback_hsw+0x4fd> + .byte 197,229,219,5,253,28,0,0 // vpand 0x1cfd(%rip),%ymm3,%ymm0 # 40c0 <_sk_callback_hsw+0x4ed> .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,5,64,27,0,0 // vbroadcastss 0x1b40(%rip),%ymm8 # 3f80 <_sk_callback_hsw+0x33d> + .byte 196,98,125,24,5,56,27,0,0 // vbroadcastss 0x1b38(%rip),%ymm8 # 3f08 <_sk_callback_hsw+0x335> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,226,101,0,13,18,29,0,0 // vpshufb 0x1d12(%rip),%ymm3,%ymm1 # 4160 <_sk_callback_hsw+0x51d> + .byte 196,226,101,0,13,2,29,0,0 // vpshufb 0x1d02(%rip),%ymm3,%ymm1 # 40e0 <_sk_callback_hsw+0x50d> .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 - .byte 196,226,101,0,21,32,29,0,0 // vpshufb 0x1d20(%rip),%ymm3,%ymm2 # 4180 <_sk_callback_hsw+0x53d> + .byte 196,226,101,0,21,16,29,0,0 // vpshufb 0x1d10(%rip),%ymm3,%ymm2 # 4100 <_sk_callback_hsw+0x52d> .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 197,229,114,211,24 // vpsrld $0x18,%ymm3,%ymm3 @@ -9649,35 +9619,35 @@ _sk_load_565_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 .byte 72,133,201 // test %rcx,%rcx - .byte 117,114 // jne 2500 <_sk_load_565_hsw+0x7c> + .byte 117,114 // jne 2490 <_sk_load_565_hsw+0x7c> .byte 196,193,122,111,4,122 // vmovdqu (%r10,%rdi,2),%xmm0 .byte 196,226,125,51,208 // vpmovzxwd %xmm0,%ymm2 - .byte 196,226,125,88,5,226,26,0,0 // vpbroadcastd 0x1ae2(%rip),%ymm0 # 3f84 <_sk_callback_hsw+0x341> + .byte 196,226,125,88,5,218,26,0,0 // vpbroadcastd 0x1ada(%rip),%ymm0 # 3f0c <_sk_callback_hsw+0x339> .byte 197,237,219,192 // vpand %ymm0,%ymm2,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,213,26,0,0 // vbroadcastss 0x1ad5(%rip),%ymm1 # 3f88 <_sk_callback_hsw+0x345> + .byte 196,226,125,24,13,205,26,0,0 // vbroadcastss 0x1acd(%rip),%ymm1 # 3f10 <_sk_callback_hsw+0x33d> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,88,13,204,26,0,0 // vpbroadcastd 0x1acc(%rip),%ymm1 # 3f8c <_sk_callback_hsw+0x349> + .byte 196,226,125,88,13,196,26,0,0 // vpbroadcastd 0x1ac4(%rip),%ymm1 # 3f14 <_sk_callback_hsw+0x341> .byte 197,237,219,201 // vpand %ymm1,%ymm2,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,29,191,26,0,0 // vbroadcastss 0x1abf(%rip),%ymm3 # 3f90 <_sk_callback_hsw+0x34d> + .byte 196,226,125,24,29,183,26,0,0 // vbroadcastss 0x1ab7(%rip),%ymm3 # 3f18 <_sk_callback_hsw+0x345> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 - .byte 196,226,125,88,29,182,26,0,0 // vpbroadcastd 0x1ab6(%rip),%ymm3 # 3f94 <_sk_callback_hsw+0x351> + .byte 196,226,125,88,29,174,26,0,0 // vpbroadcastd 0x1aae(%rip),%ymm3 # 3f1c <_sk_callback_hsw+0x349> .byte 197,237,219,211 // vpand %ymm3,%ymm2,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,226,125,24,29,169,26,0,0 // vbroadcastss 0x1aa9(%rip),%ymm3 # 3f98 <_sk_callback_hsw+0x355> + .byte 196,226,125,24,29,161,26,0,0 // vbroadcastss 0x1aa1(%rip),%ymm3 # 3f20 <_sk_callback_hsw+0x34d> .byte 197,236,89,211 // vmulps %ymm3,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,158,26,0,0 // vbroadcastss 0x1a9e(%rip),%ymm3 # 3f9c <_sk_callback_hsw+0x359> + .byte 196,226,125,24,29,150,26,0,0 // vbroadcastss 0x1a96(%rip),%ymm3 # 3f24 <_sk_callback_hsw+0x351> .byte 255,224 // jmpq *%rax .byte 65,137,200 // mov %ecx,%r8d .byte 65,128,224,7 // and $0x7,%r8b .byte 197,249,239,192 // vpxor %xmm0,%xmm0,%xmm0 .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 119,128 // ja 2494 <_sk_load_565_hsw+0x10> + .byte 119,128 // ja 2424 <_sk_load_565_hsw+0x10> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,73,0,0,0 // lea 0x49(%rip),%r9 # 2568 <_sk_load_565_hsw+0xe4> + .byte 76,141,13,73,0,0,0 // lea 0x49(%rip),%r9 # 24f8 <_sk_load_565_hsw+0xe4> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -9689,7 +9659,7 @@ _sk_load_565_hsw: .byte 196,193,121,196,68,122,4,2 // vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm0,%xmm0 .byte 196,193,121,196,68,122,2,1 // vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm0,%xmm0 .byte 196,193,121,196,4,122,0 // vpinsrw $0x0,(%r10,%rdi,2),%xmm0,%xmm0 - .byte 233,44,255,255,255 // jmpq 2494 <_sk_load_565_hsw+0x10> + .byte 233,44,255,255,255 // jmpq 2424 <_sk_load_565_hsw+0x10> .byte 244 // hlt .byte 255 // (bad) .byte 255 // (bad) @@ -9759,23 +9729,23 @@ _sk_gather_565_hsw: .byte 65,15,183,4,88 // movzwl (%r8,%rbx,2),%eax .byte 197,249,196,192,7 // vpinsrw $0x7,%eax,%xmm0,%xmm0 .byte 196,226,125,51,208 // vpmovzxwd %xmm0,%ymm2 - .byte 196,226,125,88,5,97,25,0,0 // vpbroadcastd 0x1961(%rip),%ymm0 # 3fa0 <_sk_callback_hsw+0x35d> + .byte 196,226,125,88,5,89,25,0,0 // vpbroadcastd 0x1959(%rip),%ymm0 # 3f28 <_sk_callback_hsw+0x355> .byte 197,237,219,192 // vpand %ymm0,%ymm2,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,84,25,0,0 // vbroadcastss 0x1954(%rip),%ymm1 # 3fa4 <_sk_callback_hsw+0x361> + .byte 196,226,125,24,13,76,25,0,0 // vbroadcastss 0x194c(%rip),%ymm1 # 3f2c <_sk_callback_hsw+0x359> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,88,13,75,25,0,0 // vpbroadcastd 0x194b(%rip),%ymm1 # 3fa8 <_sk_callback_hsw+0x365> + .byte 196,226,125,88,13,67,25,0,0 // vpbroadcastd 0x1943(%rip),%ymm1 # 3f30 <_sk_callback_hsw+0x35d> .byte 197,237,219,201 // vpand %ymm1,%ymm2,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,29,62,25,0,0 // vbroadcastss 0x193e(%rip),%ymm3 # 3fac <_sk_callback_hsw+0x369> + .byte 196,226,125,24,29,54,25,0,0 // vbroadcastss 0x1936(%rip),%ymm3 # 3f34 <_sk_callback_hsw+0x361> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 - .byte 196,226,125,88,29,53,25,0,0 // vpbroadcastd 0x1935(%rip),%ymm3 # 3fb0 <_sk_callback_hsw+0x36d> + .byte 196,226,125,88,29,45,25,0,0 // vpbroadcastd 0x192d(%rip),%ymm3 # 3f38 <_sk_callback_hsw+0x365> .byte 197,237,219,211 // vpand %ymm3,%ymm2,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,226,125,24,29,40,25,0,0 // vbroadcastss 0x1928(%rip),%ymm3 # 3fb4 <_sk_callback_hsw+0x371> + .byte 196,226,125,24,29,32,25,0,0 // vbroadcastss 0x1920(%rip),%ymm3 # 3f3c <_sk_callback_hsw+0x369> .byte 197,236,89,211 // vmulps %ymm3,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,29,25,0,0 // vbroadcastss 0x191d(%rip),%ymm3 # 3fb8 <_sk_callback_hsw+0x375> + .byte 196,226,125,24,29,21,25,0,0 // vbroadcastss 0x1915(%rip),%ymm3 # 3f40 <_sk_callback_hsw+0x36d> .byte 91 // pop %rbx .byte 65,92 // pop %r12 .byte 65,94 // pop %r14 @@ -9788,11 +9758,11 @@ FUNCTION(_sk_store_565_hsw) _sk_store_565_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,10,25,0,0 // vbroadcastss 0x190a(%rip),%ymm8 # 3fbc <_sk_callback_hsw+0x379> + .byte 196,98,125,24,5,2,25,0,0 // vbroadcastss 0x1902(%rip),%ymm8 # 3f44 <_sk_callback_hsw+0x371> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,193,53,114,241,11 // vpslld $0xb,%ymm9,%ymm9 - .byte 196,98,125,24,21,245,24,0,0 // vbroadcastss 0x18f5(%rip),%ymm10 # 3fc0 <_sk_callback_hsw+0x37d> + .byte 196,98,125,24,21,237,24,0,0 // vbroadcastss 0x18ed(%rip),%ymm10 # 3f48 <_sk_callback_hsw+0x375> .byte 196,65,116,89,210 // vmulps %ymm10,%ymm1,%ymm10 .byte 196,65,125,91,210 // vcvtps2dq %ymm10,%ymm10 .byte 196,193,45,114,242,5 // vpslld $0x5,%ymm10,%ymm10 @@ -9803,7 +9773,7 @@ _sk_store_565_hsw: .byte 196,67,125,57,193,1 // vextracti128 $0x1,%ymm8,%xmm9 .byte 196,66,57,43,193 // vpackusdw %xmm9,%xmm8,%xmm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,10 // jne 2709 <_sk_store_565_hsw+0x65> + .byte 117,10 // jne 2699 <_sk_store_565_hsw+0x65> .byte 196,65,122,127,4,122 // vmovdqu %xmm8,(%r10,%rdi,2) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -9811,9 +9781,9 @@ _sk_store_565_hsw: .byte 65,128,224,7 // and $0x7,%r8b .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 119,236 // ja 2705 <_sk_store_565_hsw+0x61> + .byte 119,236 // ja 2695 <_sk_store_565_hsw+0x61> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,68,0,0,0 // lea 0x44(%rip),%r9 # 2768 <_sk_store_565_hsw+0xc4> + .byte 76,141,13,68,0,0,0 // lea 0x44(%rip),%r9 # 26f8 <_sk_store_565_hsw+0xc4> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -9824,7 +9794,7 @@ _sk_store_565_hsw: .byte 196,67,121,21,68,122,4,2 // vpextrw $0x2,%xmm8,0x4(%r10,%rdi,2) .byte 196,67,121,21,68,122,2,1 // vpextrw $0x1,%xmm8,0x2(%r10,%rdi,2) .byte 196,67,121,21,4,122,0 // vpextrw $0x0,%xmm8,(%r10,%rdi,2) - .byte 235,159 // jmp 2705 <_sk_store_565_hsw+0x61> + .byte 235,159 // jmp 2695 <_sk_store_565_hsw+0x61> .byte 102,144 // xchg %ax,%ax .byte 245 // cmc .byte 255 // (bad) @@ -9857,28 +9827,28 @@ _sk_load_4444_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,138,0,0,0 // jne 281c <_sk_load_4444_hsw+0x98> + .byte 15,133,138,0,0,0 // jne 27ac <_sk_load_4444_hsw+0x98> .byte 196,193,122,111,4,122 // vmovdqu (%r10,%rdi,2),%xmm0 .byte 196,226,125,51,216 // vpmovzxwd %xmm0,%ymm3 - .byte 196,226,125,88,5,30,24,0,0 // vpbroadcastd 0x181e(%rip),%ymm0 # 3fc4 <_sk_callback_hsw+0x381> + .byte 196,226,125,88,5,22,24,0,0 // vpbroadcastd 0x1816(%rip),%ymm0 # 3f4c <_sk_callback_hsw+0x379> .byte 197,229,219,192 // vpand %ymm0,%ymm3,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,17,24,0,0 // vbroadcastss 0x1811(%rip),%ymm1 # 3fc8 <_sk_callback_hsw+0x385> + .byte 196,226,125,24,13,9,24,0,0 // vbroadcastss 0x1809(%rip),%ymm1 # 3f50 <_sk_callback_hsw+0x37d> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,88,13,8,24,0,0 // vpbroadcastd 0x1808(%rip),%ymm1 # 3fcc <_sk_callback_hsw+0x389> + .byte 196,226,125,88,13,0,24,0,0 // vpbroadcastd 0x1800(%rip),%ymm1 # 3f54 <_sk_callback_hsw+0x381> .byte 197,229,219,201 // vpand %ymm1,%ymm3,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,21,251,23,0,0 // vbroadcastss 0x17fb(%rip),%ymm2 # 3fd0 <_sk_callback_hsw+0x38d> + .byte 196,226,125,24,21,243,23,0,0 // vbroadcastss 0x17f3(%rip),%ymm2 # 3f58 <_sk_callback_hsw+0x385> .byte 197,244,89,202 // vmulps %ymm2,%ymm1,%ymm1 - .byte 196,226,125,88,21,242,23,0,0 // vpbroadcastd 0x17f2(%rip),%ymm2 # 3fd4 <_sk_callback_hsw+0x391> + .byte 196,226,125,88,21,234,23,0,0 // vpbroadcastd 0x17ea(%rip),%ymm2 # 3f5c <_sk_callback_hsw+0x389> .byte 197,229,219,210 // vpand %ymm2,%ymm3,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,98,125,24,5,229,23,0,0 // vbroadcastss 0x17e5(%rip),%ymm8 # 3fd8 <_sk_callback_hsw+0x395> + .byte 196,98,125,24,5,221,23,0,0 // vbroadcastss 0x17dd(%rip),%ymm8 # 3f60 <_sk_callback_hsw+0x38d> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,88,5,219,23,0,0 // vpbroadcastd 0x17db(%rip),%ymm8 # 3fdc <_sk_callback_hsw+0x399> + .byte 196,98,125,88,5,211,23,0,0 // vpbroadcastd 0x17d3(%rip),%ymm8 # 3f64 <_sk_callback_hsw+0x391> .byte 196,193,101,219,216 // vpand %ymm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,205,23,0,0 // vbroadcastss 0x17cd(%rip),%ymm8 # 3fe0 <_sk_callback_hsw+0x39d> + .byte 196,98,125,24,5,197,23,0,0 // vbroadcastss 0x17c5(%rip),%ymm8 # 3f68 <_sk_callback_hsw+0x395> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -9887,9 +9857,9 @@ _sk_load_4444_hsw: .byte 197,249,239,192 // vpxor %xmm0,%xmm0,%xmm0 .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 15,135,100,255,255,255 // ja 2798 <_sk_load_4444_hsw+0x14> + .byte 15,135,100,255,255,255 // ja 2728 <_sk_load_4444_hsw+0x14> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,73,0,0,0 // lea 0x49(%rip),%r9 # 2888 <_sk_load_4444_hsw+0x104> + .byte 76,141,13,73,0,0,0 // lea 0x49(%rip),%r9 # 2818 <_sk_load_4444_hsw+0x104> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -9901,7 +9871,7 @@ _sk_load_4444_hsw: .byte 196,193,121,196,68,122,4,2 // vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm0,%xmm0 .byte 196,193,121,196,68,122,2,1 // vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm0,%xmm0 .byte 196,193,121,196,4,122,0 // vpinsrw $0x0,(%r10,%rdi,2),%xmm0,%xmm0 - .byte 233,16,255,255,255 // jmpq 2798 <_sk_load_4444_hsw+0x14> + .byte 233,16,255,255,255 // jmpq 2728 <_sk_load_4444_hsw+0x14> .byte 244 // hlt .byte 255 // (bad) .byte 255 // (bad) @@ -9971,25 +9941,25 @@ _sk_gather_4444_hsw: .byte 65,15,183,4,88 // movzwl (%r8,%rbx,2),%eax .byte 197,249,196,192,7 // vpinsrw $0x7,%eax,%xmm0,%xmm0 .byte 196,226,125,51,216 // vpmovzxwd %xmm0,%ymm3 - .byte 196,226,125,88,5,133,22,0,0 // vpbroadcastd 0x1685(%rip),%ymm0 # 3fe4 <_sk_callback_hsw+0x3a1> + .byte 196,226,125,88,5,125,22,0,0 // vpbroadcastd 0x167d(%rip),%ymm0 # 3f6c <_sk_callback_hsw+0x399> .byte 197,229,219,192 // vpand %ymm0,%ymm3,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,120,22,0,0 // vbroadcastss 0x1678(%rip),%ymm1 # 3fe8 <_sk_callback_hsw+0x3a5> + .byte 196,226,125,24,13,112,22,0,0 // vbroadcastss 0x1670(%rip),%ymm1 # 3f70 <_sk_callback_hsw+0x39d> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,88,13,111,22,0,0 // vpbroadcastd 0x166f(%rip),%ymm1 # 3fec <_sk_callback_hsw+0x3a9> + .byte 196,226,125,88,13,103,22,0,0 // vpbroadcastd 0x1667(%rip),%ymm1 # 3f74 <_sk_callback_hsw+0x3a1> .byte 197,229,219,201 // vpand %ymm1,%ymm3,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,21,98,22,0,0 // vbroadcastss 0x1662(%rip),%ymm2 # 3ff0 <_sk_callback_hsw+0x3ad> + .byte 196,226,125,24,21,90,22,0,0 // vbroadcastss 0x165a(%rip),%ymm2 # 3f78 <_sk_callback_hsw+0x3a5> .byte 197,244,89,202 // vmulps %ymm2,%ymm1,%ymm1 - .byte 196,226,125,88,21,89,22,0,0 // vpbroadcastd 0x1659(%rip),%ymm2 # 3ff4 <_sk_callback_hsw+0x3b1> + .byte 196,226,125,88,21,81,22,0,0 // vpbroadcastd 0x1651(%rip),%ymm2 # 3f7c <_sk_callback_hsw+0x3a9> .byte 197,229,219,210 // vpand %ymm2,%ymm3,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,98,125,24,5,76,22,0,0 // vbroadcastss 0x164c(%rip),%ymm8 # 3ff8 <_sk_callback_hsw+0x3b5> + .byte 196,98,125,24,5,68,22,0,0 // vbroadcastss 0x1644(%rip),%ymm8 # 3f80 <_sk_callback_hsw+0x3ad> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,88,5,66,22,0,0 // vpbroadcastd 0x1642(%rip),%ymm8 # 3ffc <_sk_callback_hsw+0x3b9> + .byte 196,98,125,88,5,58,22,0,0 // vpbroadcastd 0x163a(%rip),%ymm8 # 3f84 <_sk_callback_hsw+0x3b1> .byte 196,193,101,219,216 // vpand %ymm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,52,22,0,0 // vbroadcastss 0x1634(%rip),%ymm8 # 4000 <_sk_callback_hsw+0x3bd> + .byte 196,98,125,24,5,44,22,0,0 // vbroadcastss 0x162c(%rip),%ymm8 # 3f88 <_sk_callback_hsw+0x3b5> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 91 // pop %rbx @@ -10004,7 +9974,7 @@ FUNCTION(_sk_store_4444_hsw) _sk_store_4444_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,26,22,0,0 // vbroadcastss 0x161a(%rip),%ymm8 # 4004 <_sk_callback_hsw+0x3c1> + .byte 196,98,125,24,5,18,22,0,0 // vbroadcastss 0x1612(%rip),%ymm8 # 3f8c <_sk_callback_hsw+0x3b9> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,193,53,114,241,12 // vpslld $0xc,%ymm9,%ymm9 @@ -10022,7 +9992,7 @@ _sk_store_4444_hsw: .byte 196,67,125,57,193,1 // vextracti128 $0x1,%ymm8,%xmm9 .byte 196,66,57,43,193 // vpackusdw %xmm9,%xmm8,%xmm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,10 // jne 2a4d <_sk_store_4444_hsw+0x71> + .byte 117,10 // jne 29dd <_sk_store_4444_hsw+0x71> .byte 196,65,122,127,4,122 // vmovdqu %xmm8,(%r10,%rdi,2) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -10030,9 +10000,9 @@ _sk_store_4444_hsw: .byte 65,128,224,7 // and $0x7,%r8b .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 119,236 // ja 2a49 <_sk_store_4444_hsw+0x6d> + .byte 119,236 // ja 29d9 <_sk_store_4444_hsw+0x6d> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,68,0,0,0 // lea 0x44(%rip),%r9 # 2aac <_sk_store_4444_hsw+0xd0> + .byte 76,141,13,68,0,0,0 // lea 0x44(%rip),%r9 # 2a3c <_sk_store_4444_hsw+0xd0> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -10043,7 +10013,7 @@ _sk_store_4444_hsw: .byte 196,67,121,21,68,122,4,2 // vpextrw $0x2,%xmm8,0x4(%r10,%rdi,2) .byte 196,67,121,21,68,122,2,1 // vpextrw $0x1,%xmm8,0x2(%r10,%rdi,2) .byte 196,67,121,21,4,122,0 // vpextrw $0x0,%xmm8,(%r10,%rdi,2) - .byte 235,159 // jmp 2a49 <_sk_store_4444_hsw+0x6d> + .byte 235,159 // jmp 29d9 <_sk_store_4444_hsw+0x6d> .byte 102,144 // xchg %ax,%ax .byte 245 // cmc .byte 255 // (bad) @@ -10078,16 +10048,16 @@ _sk_load_8888_hsw: .byte 76,141,12,189,0,0,0,0 // lea 0x0(,%rdi,4),%r9 .byte 76,3,8 // add (%rax),%r9 .byte 77,133,192 // test %r8,%r8 - .byte 117,88 // jne 2b35 <_sk_load_8888_hsw+0x6d> + .byte 117,88 // jne 2ac5 <_sk_load_8888_hsw+0x6d> .byte 196,193,126,111,25 // vmovdqu (%r9),%ymm3 - .byte 197,229,219,5,182,22,0,0 // vpand 0x16b6(%rip),%ymm3,%ymm0 # 41a0 <_sk_callback_hsw+0x55d> + .byte 197,229,219,5,166,22,0,0 // vpand 0x16a6(%rip),%ymm3,%ymm0 # 4120 <_sk_callback_hsw+0x54d> .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,5,17,21,0,0 // vbroadcastss 0x1511(%rip),%ymm8 # 4008 <_sk_callback_hsw+0x3c5> + .byte 196,98,125,24,5,9,21,0,0 // vbroadcastss 0x1509(%rip),%ymm8 # 3f90 <_sk_callback_hsw+0x3bd> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,226,101,0,13,187,22,0,0 // vpshufb 0x16bb(%rip),%ymm3,%ymm1 # 41c0 <_sk_callback_hsw+0x57d> + .byte 196,226,101,0,13,171,22,0,0 // vpshufb 0x16ab(%rip),%ymm3,%ymm1 # 4140 <_sk_callback_hsw+0x56d> .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 - .byte 196,226,101,0,21,201,22,0,0 // vpshufb 0x16c9(%rip),%ymm3,%ymm2 # 41e0 <_sk_callback_hsw+0x59d> + .byte 196,226,101,0,21,185,22,0,0 // vpshufb 0x16b9(%rip),%ymm3,%ymm2 # 4160 <_sk_callback_hsw+0x58d> .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 197,229,114,211,24 // vpsrld $0x18,%ymm3,%ymm3 @@ -10104,7 +10074,7 @@ _sk_load_8888_hsw: .byte 196,225,249,110,192 // vmovq %rax,%xmm0 .byte 196,226,125,33,192 // vpmovsxbd %xmm0,%ymm0 .byte 196,194,125,140,25 // vpmaskmovd (%r9),%ymm0,%ymm3 - .byte 235,135 // jmp 2ae2 <_sk_load_8888_hsw+0x1a> + .byte 235,135 // jmp 2a72 <_sk_load_8888_hsw+0x1a> HIDDEN _sk_gather_8888_hsw .globl _sk_gather_8888_hsw @@ -10119,14 +10089,14 @@ _sk_gather_8888_hsw: .byte 197,245,254,192 // vpaddd %ymm0,%ymm1,%ymm0 .byte 197,245,118,201 // vpcmpeqd %ymm1,%ymm1,%ymm1 .byte 196,194,117,144,28,128 // vpgatherdd %ymm1,(%r8,%ymm0,4),%ymm3 - .byte 197,229,219,5,119,22,0,0 // vpand 0x1677(%rip),%ymm3,%ymm0 # 4200 <_sk_callback_hsw+0x5bd> + .byte 197,229,219,5,103,22,0,0 // vpand 0x1667(%rip),%ymm3,%ymm0 # 4180 <_sk_callback_hsw+0x5ad> .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,5,118,20,0,0 // vbroadcastss 0x1476(%rip),%ymm8 # 400c <_sk_callback_hsw+0x3c9> + .byte 196,98,125,24,5,110,20,0,0 // vbroadcastss 0x146e(%rip),%ymm8 # 3f94 <_sk_callback_hsw+0x3c1> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,226,101,0,13,124,22,0,0 // vpshufb 0x167c(%rip),%ymm3,%ymm1 # 4220 <_sk_callback_hsw+0x5dd> + .byte 196,226,101,0,13,108,22,0,0 // vpshufb 0x166c(%rip),%ymm3,%ymm1 # 41a0 <_sk_callback_hsw+0x5cd> .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 - .byte 196,226,101,0,21,138,22,0,0 // vpshufb 0x168a(%rip),%ymm3,%ymm2 # 4240 <_sk_callback_hsw+0x5fd> + .byte 196,226,101,0,21,122,22,0,0 // vpshufb 0x167a(%rip),%ymm3,%ymm2 # 41c0 <_sk_callback_hsw+0x5ed> .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 197,229,114,211,24 // vpsrld $0x18,%ymm3,%ymm3 @@ -10143,7 +10113,7 @@ _sk_store_8888_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,141,12,189,0,0,0,0 // lea 0x0(,%rdi,4),%r9 .byte 76,3,8 // add (%rax),%r9 - .byte 196,98,125,24,5,38,20,0,0 // vbroadcastss 0x1426(%rip),%ymm8 # 4010 <_sk_callback_hsw+0x3cd> + .byte 196,98,125,24,5,30,20,0,0 // vbroadcastss 0x141e(%rip),%ymm8 # 3f98 <_sk_callback_hsw+0x3c5> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,65,116,89,208 // vmulps %ymm8,%ymm1,%ymm10 @@ -10159,7 +10129,7 @@ _sk_store_8888_hsw: .byte 196,65,45,235,192 // vpor %ymm8,%ymm10,%ymm8 .byte 196,65,53,235,192 // vpor %ymm8,%ymm9,%ymm8 .byte 77,133,192 // test %r8,%r8 - .byte 117,12 // jne 2c44 <_sk_store_8888_hsw+0x73> + .byte 117,12 // jne 2bd4 <_sk_store_8888_hsw+0x73> .byte 196,65,126,127,1 // vmovdqu %ymm8,(%r9) .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,137,193 // mov %r8,%rcx @@ -10172,7 +10142,7 @@ _sk_store_8888_hsw: .byte 196,97,249,110,200 // vmovq %rax,%xmm9 .byte 196,66,125,33,201 // vpmovsxbd %xmm9,%ymm9 .byte 196,66,53,142,1 // vpmaskmovd %ymm8,%ymm9,(%r9) - .byte 235,211 // jmp 2c3d <_sk_store_8888_hsw+0x6c> + .byte 235,211 // jmp 2bcd <_sk_store_8888_hsw+0x6c> HIDDEN _sk_load_f16_hsw .globl _sk_load_f16_hsw @@ -10181,7 +10151,7 @@ _sk_load_f16_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 72,133,201 // test %rcx,%rcx - .byte 117,97 // jne 2cd5 <_sk_load_f16_hsw+0x6b> + .byte 117,97 // jne 2c65 <_sk_load_f16_hsw+0x6b> .byte 197,121,16,4,248 // vmovupd (%rax,%rdi,8),%xmm8 .byte 197,249,16,84,248,16 // vmovupd 0x10(%rax,%rdi,8),%xmm2 .byte 197,249,16,92,248,32 // vmovupd 0x20(%rax,%rdi,8),%xmm3 @@ -10207,29 +10177,29 @@ _sk_load_f16_hsw: .byte 197,123,16,4,248 // vmovsd (%rax,%rdi,8),%xmm8 .byte 196,65,49,239,201 // vpxor %xmm9,%xmm9,%xmm9 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,79 // je 2d34 <_sk_load_f16_hsw+0xca> + .byte 116,79 // je 2cc4 <_sk_load_f16_hsw+0xca> .byte 197,57,22,68,248,8 // vmovhpd 0x8(%rax,%rdi,8),%xmm8,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,67 // jb 2d34 <_sk_load_f16_hsw+0xca> + .byte 114,67 // jb 2cc4 <_sk_load_f16_hsw+0xca> .byte 197,251,16,84,248,16 // vmovsd 0x10(%rax,%rdi,8),%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 116,68 // je 2d41 <_sk_load_f16_hsw+0xd7> + .byte 116,68 // je 2cd1 <_sk_load_f16_hsw+0xd7> .byte 197,233,22,84,248,24 // vmovhpd 0x18(%rax,%rdi,8),%xmm2,%xmm2 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,56 // jb 2d41 <_sk_load_f16_hsw+0xd7> + .byte 114,56 // jb 2cd1 <_sk_load_f16_hsw+0xd7> .byte 197,251,16,92,248,32 // vmovsd 0x20(%rax,%rdi,8),%xmm3 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 15,132,114,255,255,255 // je 2c8b <_sk_load_f16_hsw+0x21> + .byte 15,132,114,255,255,255 // je 2c1b <_sk_load_f16_hsw+0x21> .byte 197,225,22,92,248,40 // vmovhpd 0x28(%rax,%rdi,8),%xmm3,%xmm3 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 15,130,98,255,255,255 // jb 2c8b <_sk_load_f16_hsw+0x21> + .byte 15,130,98,255,255,255 // jb 2c1b <_sk_load_f16_hsw+0x21> .byte 197,122,126,76,248,48 // vmovq 0x30(%rax,%rdi,8),%xmm9 - .byte 233,87,255,255,255 // jmpq 2c8b <_sk_load_f16_hsw+0x21> + .byte 233,87,255,255,255 // jmpq 2c1b <_sk_load_f16_hsw+0x21> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 .byte 197,233,87,210 // vxorpd %xmm2,%xmm2,%xmm2 - .byte 233,74,255,255,255 // jmpq 2c8b <_sk_load_f16_hsw+0x21> + .byte 233,74,255,255,255 // jmpq 2c1b <_sk_load_f16_hsw+0x21> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 - .byte 233,65,255,255,255 // jmpq 2c8b <_sk_load_f16_hsw+0x21> + .byte 233,65,255,255,255 // jmpq 2c1b <_sk_load_f16_hsw+0x21> HIDDEN _sk_gather_f16_hsw .globl _sk_gather_f16_hsw @@ -10287,7 +10257,7 @@ _sk_store_f16_hsw: .byte 196,65,57,98,205 // vpunpckldq %xmm13,%xmm8,%xmm9 .byte 196,65,57,106,197 // vpunpckhdq %xmm13,%xmm8,%xmm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,27 // jne 2e39 <_sk_store_f16_hsw+0x65> + .byte 117,27 // jne 2dc9 <_sk_store_f16_hsw+0x65> .byte 197,120,17,28,248 // vmovups %xmm11,(%rax,%rdi,8) .byte 197,120,17,84,248,16 // vmovups %xmm10,0x10(%rax,%rdi,8) .byte 197,120,17,76,248,32 // vmovups %xmm9,0x20(%rax,%rdi,8) @@ -10296,22 +10266,22 @@ _sk_store_f16_hsw: .byte 255,224 // jmpq *%rax .byte 197,121,214,28,248 // vmovq %xmm11,(%rax,%rdi,8) .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,241 // je 2e35 <_sk_store_f16_hsw+0x61> + .byte 116,241 // je 2dc5 <_sk_store_f16_hsw+0x61> .byte 197,121,23,92,248,8 // vmovhpd %xmm11,0x8(%rax,%rdi,8) .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,229 // jb 2e35 <_sk_store_f16_hsw+0x61> + .byte 114,229 // jb 2dc5 <_sk_store_f16_hsw+0x61> .byte 197,121,214,84,248,16 // vmovq %xmm10,0x10(%rax,%rdi,8) - .byte 116,221 // je 2e35 <_sk_store_f16_hsw+0x61> + .byte 116,221 // je 2dc5 <_sk_store_f16_hsw+0x61> .byte 197,121,23,84,248,24 // vmovhpd %xmm10,0x18(%rax,%rdi,8) .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,209 // jb 2e35 <_sk_store_f16_hsw+0x61> + .byte 114,209 // jb 2dc5 <_sk_store_f16_hsw+0x61> .byte 197,121,214,76,248,32 // vmovq %xmm9,0x20(%rax,%rdi,8) - .byte 116,201 // je 2e35 <_sk_store_f16_hsw+0x61> + .byte 116,201 // je 2dc5 <_sk_store_f16_hsw+0x61> .byte 197,121,23,76,248,40 // vmovhpd %xmm9,0x28(%rax,%rdi,8) .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,189 // jb 2e35 <_sk_store_f16_hsw+0x61> + .byte 114,189 // jb 2dc5 <_sk_store_f16_hsw+0x61> .byte 197,121,214,68,248,48 // vmovq %xmm8,0x30(%rax,%rdi,8) - .byte 235,181 // jmp 2e35 <_sk_store_f16_hsw+0x61> + .byte 235,181 // jmp 2dc5 <_sk_store_f16_hsw+0x61> HIDDEN _sk_load_u16_be_hsw .globl _sk_load_u16_be_hsw @@ -10321,7 +10291,7 @@ _sk_load_u16_be_hsw: .byte 76,139,0 // mov (%rax),%r8 .byte 72,141,4,189,0,0,0,0 // lea 0x0(,%rdi,4),%rax .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,204,0,0,0 // jne 2f62 <_sk_load_u16_be_hsw+0xe2> + .byte 15,133,204,0,0,0 // jne 2ef2 <_sk_load_u16_be_hsw+0xe2> .byte 196,65,121,16,4,64 // vmovupd (%r8,%rax,2),%xmm8 .byte 196,193,121,16,84,64,16 // vmovupd 0x10(%r8,%rax,2),%xmm2 .byte 196,193,121,16,92,64,32 // vmovupd 0x20(%r8,%rax,2),%xmm3 @@ -10340,7 +10310,7 @@ _sk_load_u16_be_hsw: .byte 197,241,235,192 // vpor %xmm0,%xmm1,%xmm0 .byte 196,226,125,51,192 // vpmovzxwd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,21,29,17,0,0 // vbroadcastss 0x111d(%rip),%ymm10 # 4014 <_sk_callback_hsw+0x3d1> + .byte 196,98,125,24,21,21,17,0,0 // vbroadcastss 0x1115(%rip),%ymm10 # 3f9c <_sk_callback_hsw+0x3c9> .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 197,185,109,202 // vpunpckhqdq %xmm2,%xmm8,%xmm1 .byte 197,233,113,241,8 // vpsllw $0x8,%xmm1,%xmm2 @@ -10368,29 +10338,29 @@ _sk_load_u16_be_hsw: .byte 196,65,123,16,4,64 // vmovsd (%r8,%rax,2),%xmm8 .byte 196,65,49,239,201 // vpxor %xmm9,%xmm9,%xmm9 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,85 // je 2fc8 <_sk_load_u16_be_hsw+0x148> + .byte 116,85 // je 2f58 <_sk_load_u16_be_hsw+0x148> .byte 196,65,57,22,68,64,8 // vmovhpd 0x8(%r8,%rax,2),%xmm8,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,72 // jb 2fc8 <_sk_load_u16_be_hsw+0x148> + .byte 114,72 // jb 2f58 <_sk_load_u16_be_hsw+0x148> .byte 196,193,123,16,84,64,16 // vmovsd 0x10(%r8,%rax,2),%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 116,72 // je 2fd5 <_sk_load_u16_be_hsw+0x155> + .byte 116,72 // je 2f65 <_sk_load_u16_be_hsw+0x155> .byte 196,193,105,22,84,64,24 // vmovhpd 0x18(%r8,%rax,2),%xmm2,%xmm2 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,59 // jb 2fd5 <_sk_load_u16_be_hsw+0x155> + .byte 114,59 // jb 2f65 <_sk_load_u16_be_hsw+0x155> .byte 196,193,123,16,92,64,32 // vmovsd 0x20(%r8,%rax,2),%xmm3 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 15,132,6,255,255,255 // je 2eb1 <_sk_load_u16_be_hsw+0x31> + .byte 15,132,6,255,255,255 // je 2e41 <_sk_load_u16_be_hsw+0x31> .byte 196,193,97,22,92,64,40 // vmovhpd 0x28(%r8,%rax,2),%xmm3,%xmm3 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 15,130,245,254,255,255 // jb 2eb1 <_sk_load_u16_be_hsw+0x31> + .byte 15,130,245,254,255,255 // jb 2e41 <_sk_load_u16_be_hsw+0x31> .byte 196,65,122,126,76,64,48 // vmovq 0x30(%r8,%rax,2),%xmm9 - .byte 233,233,254,255,255 // jmpq 2eb1 <_sk_load_u16_be_hsw+0x31> + .byte 233,233,254,255,255 // jmpq 2e41 <_sk_load_u16_be_hsw+0x31> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 .byte 197,233,87,210 // vxorpd %xmm2,%xmm2,%xmm2 - .byte 233,220,254,255,255 // jmpq 2eb1 <_sk_load_u16_be_hsw+0x31> + .byte 233,220,254,255,255 // jmpq 2e41 <_sk_load_u16_be_hsw+0x31> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 - .byte 233,211,254,255,255 // jmpq 2eb1 <_sk_load_u16_be_hsw+0x31> + .byte 233,211,254,255,255 // jmpq 2e41 <_sk_load_u16_be_hsw+0x31> HIDDEN _sk_load_rgb_u16_be_hsw .globl _sk_load_rgb_u16_be_hsw @@ -10400,7 +10370,7 @@ _sk_load_rgb_u16_be_hsw: .byte 76,139,0 // mov (%rax),%r8 .byte 72,141,4,127 // lea (%rdi,%rdi,2),%rax .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,204,0,0,0 // jne 30bc <_sk_load_rgb_u16_be_hsw+0xde> + .byte 15,133,204,0,0,0 // jne 304c <_sk_load_rgb_u16_be_hsw+0xde> .byte 196,193,122,111,4,64 // vmovdqu (%r8,%rax,2),%xmm0 .byte 196,193,122,111,84,64,12 // vmovdqu 0xc(%r8,%rax,2),%xmm2 .byte 196,193,122,111,76,64,24 // vmovdqu 0x18(%r8,%rax,2),%xmm1 @@ -10424,7 +10394,7 @@ _sk_load_rgb_u16_be_hsw: .byte 197,241,235,192 // vpor %xmm0,%xmm1,%xmm0 .byte 196,226,125,51,192 // vpmovzxwd %xmm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,21,174,15,0,0 // vbroadcastss 0xfae(%rip),%ymm10 # 4018 <_sk_callback_hsw+0x3d5> + .byte 196,98,125,24,21,166,15,0,0 // vbroadcastss 0xfa6(%rip),%ymm10 # 3fa0 <_sk_callback_hsw+0x3cd> .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 197,185,109,202 // vpunpckhqdq %xmm2,%xmm8,%xmm1 .byte 197,233,113,241,8 // vpsllw $0x8,%xmm1,%xmm2 @@ -10441,41 +10411,41 @@ _sk_load_rgb_u16_be_hsw: .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,210 // vmulps %ymm10,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,98,15,0,0 // vbroadcastss 0xf62(%rip),%ymm3 # 401c <_sk_callback_hsw+0x3d9> + .byte 196,226,125,24,29,90,15,0,0 // vbroadcastss 0xf5a(%rip),%ymm3 # 3fa4 <_sk_callback_hsw+0x3d1> .byte 255,224 // jmpq *%rax .byte 196,193,121,110,4,64 // vmovd (%r8,%rax,2),%xmm0 .byte 196,193,121,196,68,64,4,2 // vpinsrw $0x2,0x4(%r8,%rax,2),%xmm0,%xmm0 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 117,5 // jne 30d5 <_sk_load_rgb_u16_be_hsw+0xf7> - .byte 233,79,255,255,255 // jmpq 3024 <_sk_load_rgb_u16_be_hsw+0x46> + .byte 117,5 // jne 3065 <_sk_load_rgb_u16_be_hsw+0xf7> + .byte 233,79,255,255,255 // jmpq 2fb4 <_sk_load_rgb_u16_be_hsw+0x46> .byte 196,193,121,110,76,64,6 // vmovd 0x6(%r8,%rax,2),%xmm1 .byte 196,65,113,196,68,64,10,2 // vpinsrw $0x2,0xa(%r8,%rax,2),%xmm1,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,26 // jb 3104 <_sk_load_rgb_u16_be_hsw+0x126> + .byte 114,26 // jb 3094 <_sk_load_rgb_u16_be_hsw+0x126> .byte 196,193,121,110,76,64,12 // vmovd 0xc(%r8,%rax,2),%xmm1 .byte 196,193,113,196,84,64,16,2 // vpinsrw $0x2,0x10(%r8,%rax,2),%xmm1,%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 117,10 // jne 3109 <_sk_load_rgb_u16_be_hsw+0x12b> - .byte 233,32,255,255,255 // jmpq 3024 <_sk_load_rgb_u16_be_hsw+0x46> - .byte 233,27,255,255,255 // jmpq 3024 <_sk_load_rgb_u16_be_hsw+0x46> + .byte 117,10 // jne 3099 <_sk_load_rgb_u16_be_hsw+0x12b> + .byte 233,32,255,255,255 // jmpq 2fb4 <_sk_load_rgb_u16_be_hsw+0x46> + .byte 233,27,255,255,255 // jmpq 2fb4 <_sk_load_rgb_u16_be_hsw+0x46> .byte 196,193,121,110,76,64,18 // vmovd 0x12(%r8,%rax,2),%xmm1 .byte 196,65,113,196,76,64,22,2 // vpinsrw $0x2,0x16(%r8,%rax,2),%xmm1,%xmm9 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,26 // jb 3138 <_sk_load_rgb_u16_be_hsw+0x15a> + .byte 114,26 // jb 30c8 <_sk_load_rgb_u16_be_hsw+0x15a> .byte 196,193,121,110,76,64,24 // vmovd 0x18(%r8,%rax,2),%xmm1 .byte 196,193,113,196,76,64,28,2 // vpinsrw $0x2,0x1c(%r8,%rax,2),%xmm1,%xmm1 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 117,10 // jne 313d <_sk_load_rgb_u16_be_hsw+0x15f> - .byte 233,236,254,255,255 // jmpq 3024 <_sk_load_rgb_u16_be_hsw+0x46> - .byte 233,231,254,255,255 // jmpq 3024 <_sk_load_rgb_u16_be_hsw+0x46> + .byte 117,10 // jne 30cd <_sk_load_rgb_u16_be_hsw+0x15f> + .byte 233,236,254,255,255 // jmpq 2fb4 <_sk_load_rgb_u16_be_hsw+0x46> + .byte 233,231,254,255,255 // jmpq 2fb4 <_sk_load_rgb_u16_be_hsw+0x46> .byte 196,193,121,110,92,64,30 // vmovd 0x1e(%r8,%rax,2),%xmm3 .byte 196,65,97,196,92,64,34,2 // vpinsrw $0x2,0x22(%r8,%rax,2),%xmm3,%xmm11 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,20 // jb 3166 <_sk_load_rgb_u16_be_hsw+0x188> + .byte 114,20 // jb 30f6 <_sk_load_rgb_u16_be_hsw+0x188> .byte 196,193,121,110,92,64,36 // vmovd 0x24(%r8,%rax,2),%xmm3 .byte 196,193,97,196,92,64,40,2 // vpinsrw $0x2,0x28(%r8,%rax,2),%xmm3,%xmm3 - .byte 233,190,254,255,255 // jmpq 3024 <_sk_load_rgb_u16_be_hsw+0x46> - .byte 233,185,254,255,255 // jmpq 3024 <_sk_load_rgb_u16_be_hsw+0x46> + .byte 233,190,254,255,255 // jmpq 2fb4 <_sk_load_rgb_u16_be_hsw+0x46> + .byte 233,185,254,255,255 // jmpq 2fb4 <_sk_load_rgb_u16_be_hsw+0x46> HIDDEN _sk_store_u16_be_hsw .globl _sk_store_u16_be_hsw @@ -10484,7 +10454,7 @@ _sk_store_u16_be_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,0 // mov (%rax),%r8 .byte 72,141,4,189,0,0,0,0 // lea 0x0(,%rdi,4),%rax - .byte 196,98,125,24,5,159,14,0,0 // vbroadcastss 0xe9f(%rip),%ymm8 # 4020 <_sk_callback_hsw+0x3dd> + .byte 196,98,125,24,5,151,14,0,0 // vbroadcastss 0xe97(%rip),%ymm8 # 3fa8 <_sk_callback_hsw+0x3d5> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,67,125,25,202,1 // vextractf128 $0x1,%ymm9,%xmm10 @@ -10522,7 +10492,7 @@ _sk_store_u16_be_hsw: .byte 196,65,17,98,200 // vpunpckldq %xmm8,%xmm13,%xmm9 .byte 196,65,17,106,192 // vpunpckhdq %xmm8,%xmm13,%xmm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,31 // jne 3265 <_sk_store_u16_be_hsw+0xfa> + .byte 117,31 // jne 31f5 <_sk_store_u16_be_hsw+0xfa> .byte 196,65,120,17,28,64 // vmovups %xmm11,(%r8,%rax,2) .byte 196,65,120,17,84,64,16 // vmovups %xmm10,0x10(%r8,%rax,2) .byte 196,65,120,17,76,64,32 // vmovups %xmm9,0x20(%r8,%rax,2) @@ -10531,22 +10501,22 @@ _sk_store_u16_be_hsw: .byte 255,224 // jmpq *%rax .byte 196,65,121,214,28,64 // vmovq %xmm11,(%r8,%rax,2) .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,240 // je 3261 <_sk_store_u16_be_hsw+0xf6> + .byte 116,240 // je 31f1 <_sk_store_u16_be_hsw+0xf6> .byte 196,65,121,23,92,64,8 // vmovhpd %xmm11,0x8(%r8,%rax,2) .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,227 // jb 3261 <_sk_store_u16_be_hsw+0xf6> + .byte 114,227 // jb 31f1 <_sk_store_u16_be_hsw+0xf6> .byte 196,65,121,214,84,64,16 // vmovq %xmm10,0x10(%r8,%rax,2) - .byte 116,218 // je 3261 <_sk_store_u16_be_hsw+0xf6> + .byte 116,218 // je 31f1 <_sk_store_u16_be_hsw+0xf6> .byte 196,65,121,23,84,64,24 // vmovhpd %xmm10,0x18(%r8,%rax,2) .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,205 // jb 3261 <_sk_store_u16_be_hsw+0xf6> + .byte 114,205 // jb 31f1 <_sk_store_u16_be_hsw+0xf6> .byte 196,65,121,214,76,64,32 // vmovq %xmm9,0x20(%r8,%rax,2) - .byte 116,196 // je 3261 <_sk_store_u16_be_hsw+0xf6> + .byte 116,196 // je 31f1 <_sk_store_u16_be_hsw+0xf6> .byte 196,65,121,23,76,64,40 // vmovhpd %xmm9,0x28(%r8,%rax,2) .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,183 // jb 3261 <_sk_store_u16_be_hsw+0xf6> + .byte 114,183 // jb 31f1 <_sk_store_u16_be_hsw+0xf6> .byte 196,65,121,214,68,64,48 // vmovq %xmm8,0x30(%r8,%rax,2) - .byte 235,174 // jmp 3261 <_sk_store_u16_be_hsw+0xf6> + .byte 235,174 // jmp 31f1 <_sk_store_u16_be_hsw+0xf6> HIDDEN _sk_load_f32_hsw .globl _sk_load_f32_hsw @@ -10554,10 +10524,10 @@ FUNCTION(_sk_load_f32_hsw) _sk_load_f32_hsw: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 119,110 // ja 3329 <_sk_load_f32_hsw+0x76> + .byte 119,110 // ja 32b9 <_sk_load_f32_hsw+0x76> .byte 76,139,0 // mov (%rax),%r8 .byte 76,141,12,189,0,0,0,0 // lea 0x0(,%rdi,4),%r9 - .byte 76,141,21,135,0,0,0 // lea 0x87(%rip),%r10 # 3354 <_sk_load_f32_hsw+0xa1> + .byte 76,141,21,135,0,0,0 // lea 0x87(%rip),%r10 # 32e4 <_sk_load_f32_hsw+0xa1> .byte 73,99,4,138 // movslq (%r10,%rcx,4),%rax .byte 76,1,208 // add %r10,%rax .byte 255,224 // jmpq *%rax @@ -10618,7 +10588,7 @@ _sk_store_f32_hsw: .byte 196,65,37,20,196 // vunpcklpd %ymm12,%ymm11,%ymm8 .byte 196,65,37,21,220 // vunpckhpd %ymm12,%ymm11,%ymm11 .byte 72,133,201 // test %rcx,%rcx - .byte 117,55 // jne 33e1 <_sk_store_f32_hsw+0x6d> + .byte 117,55 // jne 3371 <_sk_store_f32_hsw+0x6d> .byte 196,67,45,24,225,1 // vinsertf128 $0x1,%xmm9,%ymm10,%ymm12 .byte 196,67,61,24,235,1 // vinsertf128 $0x1,%xmm11,%ymm8,%ymm13 .byte 196,67,45,6,201,49 // vperm2f128 $0x31,%ymm9,%ymm10,%ymm9 @@ -10631,22 +10601,22 @@ _sk_store_f32_hsw: .byte 255,224 // jmpq *%rax .byte 196,65,121,17,20,128 // vmovupd %xmm10,(%r8,%rax,4) .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,240 // je 33dd <_sk_store_f32_hsw+0x69> + .byte 116,240 // je 336d <_sk_store_f32_hsw+0x69> .byte 196,65,121,17,76,128,16 // vmovupd %xmm9,0x10(%r8,%rax,4) .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,227 // jb 33dd <_sk_store_f32_hsw+0x69> + .byte 114,227 // jb 336d <_sk_store_f32_hsw+0x69> .byte 196,65,121,17,68,128,32 // vmovupd %xmm8,0x20(%r8,%rax,4) - .byte 116,218 // je 33dd <_sk_store_f32_hsw+0x69> + .byte 116,218 // je 336d <_sk_store_f32_hsw+0x69> .byte 196,65,121,17,92,128,48 // vmovupd %xmm11,0x30(%r8,%rax,4) .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,205 // jb 33dd <_sk_store_f32_hsw+0x69> + .byte 114,205 // jb 336d <_sk_store_f32_hsw+0x69> .byte 196,67,125,25,84,128,64,1 // vextractf128 $0x1,%ymm10,0x40(%r8,%rax,4) - .byte 116,195 // je 33dd <_sk_store_f32_hsw+0x69> + .byte 116,195 // je 336d <_sk_store_f32_hsw+0x69> .byte 196,67,125,25,76,128,80,1 // vextractf128 $0x1,%ymm9,0x50(%r8,%rax,4) .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,181 // jb 33dd <_sk_store_f32_hsw+0x69> + .byte 114,181 // jb 336d <_sk_store_f32_hsw+0x69> .byte 196,67,125,25,68,128,96,1 // vextractf128 $0x1,%ymm8,0x60(%r8,%rax,4) - .byte 235,171 // jmp 33dd <_sk_store_f32_hsw+0x69> + .byte 235,171 // jmp 336d <_sk_store_f32_hsw+0x69> HIDDEN _sk_clamp_x_hsw .globl _sk_clamp_x_hsw @@ -10756,11 +10726,11 @@ HIDDEN _sk_luminance_to_alpha_hsw .globl _sk_luminance_to_alpha_hsw FUNCTION(_sk_luminance_to_alpha_hsw) _sk_luminance_to_alpha_hsw: - .byte 196,226,125,24,29,185,10,0,0 // vbroadcastss 0xab9(%rip),%ymm3 # 4024 <_sk_callback_hsw+0x3e1> - .byte 196,98,125,24,5,180,10,0,0 // vbroadcastss 0xab4(%rip),%ymm8 # 4028 <_sk_callback_hsw+0x3e5> + .byte 196,226,125,24,29,177,10,0,0 // vbroadcastss 0xab1(%rip),%ymm3 # 3fac <_sk_callback_hsw+0x3d9> + .byte 196,98,125,24,5,172,10,0,0 // vbroadcastss 0xaac(%rip),%ymm8 # 3fb0 <_sk_callback_hsw+0x3dd> .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 .byte 196,226,125,184,203 // vfmadd231ps %ymm3,%ymm0,%ymm1 - .byte 196,226,125,24,29,165,10,0,0 // vbroadcastss 0xaa5(%rip),%ymm3 # 402c <_sk_callback_hsw+0x3e9> + .byte 196,226,125,24,29,157,10,0,0 // vbroadcastss 0xa9d(%rip),%ymm3 # 3fb4 <_sk_callback_hsw+0x3e1> .byte 196,226,109,168,217 // vfmadd213ps %ymm1,%ymm2,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -10905,7 +10875,7 @@ _sk_linear_gradient_hsw: .byte 196,98,125,24,72,28 // vbroadcastss 0x1c(%rax),%ymm9 .byte 76,139,0 // mov (%rax),%r8 .byte 77,133,192 // test %r8,%r8 - .byte 15,132,143,0,0,0 // je 385f <_sk_linear_gradient_hsw+0xb5> + .byte 15,132,143,0,0,0 // je 37ef <_sk_linear_gradient_hsw+0xb5> .byte 72,139,64,8 // mov 0x8(%rax),%rax .byte 72,131,192,32 // add $0x20,%rax .byte 196,65,28,87,228 // vxorps %ymm12,%ymm12,%ymm12 @@ -10932,8 +10902,8 @@ _sk_linear_gradient_hsw: .byte 196,67,13,74,201,208 // vblendvps %ymm13,%ymm9,%ymm14,%ymm9 .byte 72,131,192,36 // add $0x24,%rax .byte 73,255,200 // dec %r8 - .byte 117,140 // jne 37e9 <_sk_linear_gradient_hsw+0x3f> - .byte 235,17 // jmp 3870 <_sk_linear_gradient_hsw+0xc6> + .byte 117,140 // jne 3779 <_sk_linear_gradient_hsw+0x3f> + .byte 235,17 // jmp 3800 <_sk_linear_gradient_hsw+0xc6> .byte 197,244,87,201 // vxorps %ymm1,%ymm1,%ymm1 .byte 197,236,87,210 // vxorps %ymm2,%ymm2,%ymm2 .byte 197,228,87,219 // vxorps %ymm3,%ymm3,%ymm3 @@ -10972,7 +10942,7 @@ HIDDEN _sk_save_xy_hsw FUNCTION(_sk_save_xy_hsw) _sk_save_xy_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,76,7,0,0 // vbroadcastss 0x74c(%rip),%ymm8 # 4030 <_sk_callback_hsw+0x3ed> + .byte 196,98,125,24,5,68,7,0,0 // vbroadcastss 0x744(%rip),%ymm8 # 3fb8 <_sk_callback_hsw+0x3e5> .byte 196,65,124,88,200 // vaddps %ymm8,%ymm0,%ymm9 .byte 196,67,125,8,209,1 // vroundps $0x1,%ymm9,%ymm10 .byte 196,65,52,92,202 // vsubps %ymm10,%ymm9,%ymm9 @@ -11006,9 +10976,9 @@ HIDDEN _sk_bilinear_nx_hsw FUNCTION(_sk_bilinear_nx_hsw) _sk_bilinear_nx_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,224,6,0,0 // vbroadcastss 0x6e0(%rip),%ymm0 # 4034 <_sk_callback_hsw+0x3f1> + .byte 196,226,125,24,5,216,6,0,0 // vbroadcastss 0x6d8(%rip),%ymm0 # 3fbc <_sk_callback_hsw+0x3e9> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,215,6,0,0 // vbroadcastss 0x6d7(%rip),%ymm8 # 4038 <_sk_callback_hsw+0x3f5> + .byte 196,98,125,24,5,207,6,0,0 // vbroadcastss 0x6cf(%rip),%ymm8 # 3fc0 <_sk_callback_hsw+0x3ed> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -11019,7 +10989,7 @@ HIDDEN _sk_bilinear_px_hsw FUNCTION(_sk_bilinear_px_hsw) _sk_bilinear_px_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,191,6,0,0 // vbroadcastss 0x6bf(%rip),%ymm0 # 403c <_sk_callback_hsw+0x3f9> + .byte 196,226,125,24,5,183,6,0,0 // vbroadcastss 0x6b7(%rip),%ymm0 # 3fc4 <_sk_callback_hsw+0x3f1> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 .byte 197,124,16,64,64 // vmovups 0x40(%rax),%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -11031,9 +11001,9 @@ HIDDEN _sk_bilinear_ny_hsw FUNCTION(_sk_bilinear_ny_hsw) _sk_bilinear_ny_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,163,6,0,0 // vbroadcastss 0x6a3(%rip),%ymm1 # 4040 <_sk_callback_hsw+0x3fd> + .byte 196,226,125,24,13,155,6,0,0 // vbroadcastss 0x69b(%rip),%ymm1 # 3fc8 <_sk_callback_hsw+0x3f5> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,153,6,0,0 // vbroadcastss 0x699(%rip),%ymm8 # 4044 <_sk_callback_hsw+0x401> + .byte 196,98,125,24,5,145,6,0,0 // vbroadcastss 0x691(%rip),%ymm8 # 3fcc <_sk_callback_hsw+0x3f9> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -11044,7 +11014,7 @@ HIDDEN _sk_bilinear_py_hsw FUNCTION(_sk_bilinear_py_hsw) _sk_bilinear_py_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,129,6,0,0 // vbroadcastss 0x681(%rip),%ymm1 # 4048 <_sk_callback_hsw+0x405> + .byte 196,226,125,24,13,121,6,0,0 // vbroadcastss 0x679(%rip),%ymm1 # 3fd0 <_sk_callback_hsw+0x3fd> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 .byte 197,124,16,64,96 // vmovups 0x60(%rax),%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -11056,13 +11026,13 @@ HIDDEN _sk_bicubic_n3x_hsw FUNCTION(_sk_bicubic_n3x_hsw) _sk_bicubic_n3x_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,100,6,0,0 // vbroadcastss 0x664(%rip),%ymm0 # 404c <_sk_callback_hsw+0x409> + .byte 196,226,125,24,5,92,6,0,0 // vbroadcastss 0x65c(%rip),%ymm0 # 3fd4 <_sk_callback_hsw+0x401> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,91,6,0,0 // vbroadcastss 0x65b(%rip),%ymm8 # 4050 <_sk_callback_hsw+0x40d> + .byte 196,98,125,24,5,83,6,0,0 // vbroadcastss 0x653(%rip),%ymm8 # 3fd8 <_sk_callback_hsw+0x405> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,76,6,0,0 // vbroadcastss 0x64c(%rip),%ymm10 # 4054 <_sk_callback_hsw+0x411> - .byte 196,98,125,24,29,71,6,0,0 // vbroadcastss 0x647(%rip),%ymm11 # 4058 <_sk_callback_hsw+0x415> + .byte 196,98,125,24,21,68,6,0,0 // vbroadcastss 0x644(%rip),%ymm10 # 3fdc <_sk_callback_hsw+0x409> + .byte 196,98,125,24,29,63,6,0,0 // vbroadcastss 0x63f(%rip),%ymm11 # 3fe0 <_sk_callback_hsw+0x40d> .byte 196,66,61,168,218 // vfmadd213ps %ymm10,%ymm8,%ymm11 .byte 196,65,36,89,193 // vmulps %ymm9,%ymm11,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -11074,16 +11044,16 @@ HIDDEN _sk_bicubic_n1x_hsw FUNCTION(_sk_bicubic_n1x_hsw) _sk_bicubic_n1x_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,42,6,0,0 // vbroadcastss 0x62a(%rip),%ymm0 # 405c <_sk_callback_hsw+0x419> + .byte 196,226,125,24,5,34,6,0,0 // vbroadcastss 0x622(%rip),%ymm0 # 3fe4 <_sk_callback_hsw+0x411> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,33,6,0,0 // vbroadcastss 0x621(%rip),%ymm8 # 4060 <_sk_callback_hsw+0x41d> + .byte 196,98,125,24,5,25,6,0,0 // vbroadcastss 0x619(%rip),%ymm8 # 3fe8 <_sk_callback_hsw+0x415> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 - .byte 196,98,125,24,13,23,6,0,0 // vbroadcastss 0x617(%rip),%ymm9 # 4064 <_sk_callback_hsw+0x421> - .byte 196,98,125,24,21,18,6,0,0 // vbroadcastss 0x612(%rip),%ymm10 # 4068 <_sk_callback_hsw+0x425> + .byte 196,98,125,24,13,15,6,0,0 // vbroadcastss 0x60f(%rip),%ymm9 # 3fec <_sk_callback_hsw+0x419> + .byte 196,98,125,24,21,10,6,0,0 // vbroadcastss 0x60a(%rip),%ymm10 # 3ff0 <_sk_callback_hsw+0x41d> .byte 196,66,61,168,209 // vfmadd213ps %ymm9,%ymm8,%ymm10 - .byte 196,98,125,24,13,8,6,0,0 // vbroadcastss 0x608(%rip),%ymm9 # 406c <_sk_callback_hsw+0x429> + .byte 196,98,125,24,13,0,6,0,0 // vbroadcastss 0x600(%rip),%ymm9 # 3ff4 <_sk_callback_hsw+0x421> .byte 196,66,61,184,202 // vfmadd231ps %ymm10,%ymm8,%ymm9 - .byte 196,98,125,24,21,254,5,0,0 // vbroadcastss 0x5fe(%rip),%ymm10 # 4070 <_sk_callback_hsw+0x42d> + .byte 196,98,125,24,21,246,5,0,0 // vbroadcastss 0x5f6(%rip),%ymm10 # 3ff8 <_sk_callback_hsw+0x425> .byte 196,66,61,184,209 // vfmadd231ps %ymm9,%ymm8,%ymm10 .byte 197,124,17,144,128,0,0,0 // vmovups %ymm10,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -11094,14 +11064,14 @@ HIDDEN _sk_bicubic_p1x_hsw FUNCTION(_sk_bicubic_p1x_hsw) _sk_bicubic_p1x_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,230,5,0,0 // vbroadcastss 0x5e6(%rip),%ymm8 # 4074 <_sk_callback_hsw+0x431> + .byte 196,98,125,24,5,222,5,0,0 // vbroadcastss 0x5de(%rip),%ymm8 # 3ffc <_sk_callback_hsw+0x429> .byte 197,188,88,0 // vaddps (%rax),%ymm8,%ymm0 .byte 197,124,16,72,64 // vmovups 0x40(%rax),%ymm9 - .byte 196,98,125,24,21,216,5,0,0 // vbroadcastss 0x5d8(%rip),%ymm10 # 4078 <_sk_callback_hsw+0x435> - .byte 196,98,125,24,29,211,5,0,0 // vbroadcastss 0x5d3(%rip),%ymm11 # 407c <_sk_callback_hsw+0x439> + .byte 196,98,125,24,21,208,5,0,0 // vbroadcastss 0x5d0(%rip),%ymm10 # 4000 <_sk_callback_hsw+0x42d> + .byte 196,98,125,24,29,203,5,0,0 // vbroadcastss 0x5cb(%rip),%ymm11 # 4004 <_sk_callback_hsw+0x431> .byte 196,66,53,168,218 // vfmadd213ps %ymm10,%ymm9,%ymm11 .byte 196,66,53,168,216 // vfmadd213ps %ymm8,%ymm9,%ymm11 - .byte 196,98,125,24,5,196,5,0,0 // vbroadcastss 0x5c4(%rip),%ymm8 # 4080 <_sk_callback_hsw+0x43d> + .byte 196,98,125,24,5,188,5,0,0 // vbroadcastss 0x5bc(%rip),%ymm8 # 4008 <_sk_callback_hsw+0x435> .byte 196,66,53,184,195 // vfmadd231ps %ymm11,%ymm9,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -11112,12 +11082,12 @@ HIDDEN _sk_bicubic_p3x_hsw FUNCTION(_sk_bicubic_p3x_hsw) _sk_bicubic_p3x_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,172,5,0,0 // vbroadcastss 0x5ac(%rip),%ymm0 # 4084 <_sk_callback_hsw+0x441> + .byte 196,226,125,24,5,164,5,0,0 // vbroadcastss 0x5a4(%rip),%ymm0 # 400c <_sk_callback_hsw+0x439> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 .byte 197,124,16,64,64 // vmovups 0x40(%rax),%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,153,5,0,0 // vbroadcastss 0x599(%rip),%ymm10 # 4088 <_sk_callback_hsw+0x445> - .byte 196,98,125,24,29,148,5,0,0 // vbroadcastss 0x594(%rip),%ymm11 # 408c <_sk_callback_hsw+0x449> + .byte 196,98,125,24,21,145,5,0,0 // vbroadcastss 0x591(%rip),%ymm10 # 4010 <_sk_callback_hsw+0x43d> + .byte 196,98,125,24,29,140,5,0,0 // vbroadcastss 0x58c(%rip),%ymm11 # 4014 <_sk_callback_hsw+0x441> .byte 196,66,61,168,218 // vfmadd213ps %ymm10,%ymm8,%ymm11 .byte 196,65,52,89,195 // vmulps %ymm11,%ymm9,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -11129,13 +11099,13 @@ HIDDEN _sk_bicubic_n3y_hsw FUNCTION(_sk_bicubic_n3y_hsw) _sk_bicubic_n3y_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,119,5,0,0 // vbroadcastss 0x577(%rip),%ymm1 # 4090 <_sk_callback_hsw+0x44d> + .byte 196,226,125,24,13,111,5,0,0 // vbroadcastss 0x56f(%rip),%ymm1 # 4018 <_sk_callback_hsw+0x445> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,109,5,0,0 // vbroadcastss 0x56d(%rip),%ymm8 # 4094 <_sk_callback_hsw+0x451> + .byte 196,98,125,24,5,101,5,0,0 // vbroadcastss 0x565(%rip),%ymm8 # 401c <_sk_callback_hsw+0x449> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,94,5,0,0 // vbroadcastss 0x55e(%rip),%ymm10 # 4098 <_sk_callback_hsw+0x455> - .byte 196,98,125,24,29,89,5,0,0 // vbroadcastss 0x559(%rip),%ymm11 # 409c <_sk_callback_hsw+0x459> + .byte 196,98,125,24,21,86,5,0,0 // vbroadcastss 0x556(%rip),%ymm10 # 4020 <_sk_callback_hsw+0x44d> + .byte 196,98,125,24,29,81,5,0,0 // vbroadcastss 0x551(%rip),%ymm11 # 4024 <_sk_callback_hsw+0x451> .byte 196,66,61,168,218 // vfmadd213ps %ymm10,%ymm8,%ymm11 .byte 196,65,36,89,193 // vmulps %ymm9,%ymm11,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -11147,16 +11117,16 @@ HIDDEN _sk_bicubic_n1y_hsw FUNCTION(_sk_bicubic_n1y_hsw) _sk_bicubic_n1y_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,60,5,0,0 // vbroadcastss 0x53c(%rip),%ymm1 # 40a0 <_sk_callback_hsw+0x45d> + .byte 196,226,125,24,13,52,5,0,0 // vbroadcastss 0x534(%rip),%ymm1 # 4028 <_sk_callback_hsw+0x455> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,50,5,0,0 // vbroadcastss 0x532(%rip),%ymm8 # 40a4 <_sk_callback_hsw+0x461> + .byte 196,98,125,24,5,42,5,0,0 // vbroadcastss 0x52a(%rip),%ymm8 # 402c <_sk_callback_hsw+0x459> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 - .byte 196,98,125,24,13,40,5,0,0 // vbroadcastss 0x528(%rip),%ymm9 # 40a8 <_sk_callback_hsw+0x465> - .byte 196,98,125,24,21,35,5,0,0 // vbroadcastss 0x523(%rip),%ymm10 # 40ac <_sk_callback_hsw+0x469> + .byte 196,98,125,24,13,32,5,0,0 // vbroadcastss 0x520(%rip),%ymm9 # 4030 <_sk_callback_hsw+0x45d> + .byte 196,98,125,24,21,27,5,0,0 // vbroadcastss 0x51b(%rip),%ymm10 # 4034 <_sk_callback_hsw+0x461> .byte 196,66,61,168,209 // vfmadd213ps %ymm9,%ymm8,%ymm10 - .byte 196,98,125,24,13,25,5,0,0 // vbroadcastss 0x519(%rip),%ymm9 # 40b0 <_sk_callback_hsw+0x46d> + .byte 196,98,125,24,13,17,5,0,0 // vbroadcastss 0x511(%rip),%ymm9 # 4038 <_sk_callback_hsw+0x465> .byte 196,66,61,184,202 // vfmadd231ps %ymm10,%ymm8,%ymm9 - .byte 196,98,125,24,21,15,5,0,0 // vbroadcastss 0x50f(%rip),%ymm10 # 40b4 <_sk_callback_hsw+0x471> + .byte 196,98,125,24,21,7,5,0,0 // vbroadcastss 0x507(%rip),%ymm10 # 403c <_sk_callback_hsw+0x469> .byte 196,66,61,184,209 // vfmadd231ps %ymm9,%ymm8,%ymm10 .byte 197,124,17,144,160,0,0,0 // vmovups %ymm10,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -11167,14 +11137,14 @@ HIDDEN _sk_bicubic_p1y_hsw FUNCTION(_sk_bicubic_p1y_hsw) _sk_bicubic_p1y_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,247,4,0,0 // vbroadcastss 0x4f7(%rip),%ymm8 # 40b8 <_sk_callback_hsw+0x475> + .byte 196,98,125,24,5,239,4,0,0 // vbroadcastss 0x4ef(%rip),%ymm8 # 4040 <_sk_callback_hsw+0x46d> .byte 197,188,88,72,32 // vaddps 0x20(%rax),%ymm8,%ymm1 .byte 197,124,16,72,96 // vmovups 0x60(%rax),%ymm9 - .byte 196,98,125,24,21,232,4,0,0 // vbroadcastss 0x4e8(%rip),%ymm10 # 40bc <_sk_callback_hsw+0x479> - .byte 196,98,125,24,29,227,4,0,0 // vbroadcastss 0x4e3(%rip),%ymm11 # 40c0 <_sk_callback_hsw+0x47d> + .byte 196,98,125,24,21,224,4,0,0 // vbroadcastss 0x4e0(%rip),%ymm10 # 4044 <_sk_callback_hsw+0x471> + .byte 196,98,125,24,29,219,4,0,0 // vbroadcastss 0x4db(%rip),%ymm11 # 4048 <_sk_callback_hsw+0x475> .byte 196,66,53,168,218 // vfmadd213ps %ymm10,%ymm9,%ymm11 .byte 196,66,53,168,216 // vfmadd213ps %ymm8,%ymm9,%ymm11 - .byte 196,98,125,24,5,212,4,0,0 // vbroadcastss 0x4d4(%rip),%ymm8 # 40c4 <_sk_callback_hsw+0x481> + .byte 196,98,125,24,5,204,4,0,0 // vbroadcastss 0x4cc(%rip),%ymm8 # 404c <_sk_callback_hsw+0x479> .byte 196,66,53,184,195 // vfmadd231ps %ymm11,%ymm9,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -11185,12 +11155,12 @@ HIDDEN _sk_bicubic_p3y_hsw FUNCTION(_sk_bicubic_p3y_hsw) _sk_bicubic_p3y_hsw: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,188,4,0,0 // vbroadcastss 0x4bc(%rip),%ymm1 # 40c8 <_sk_callback_hsw+0x485> + .byte 196,226,125,24,13,180,4,0,0 // vbroadcastss 0x4b4(%rip),%ymm1 # 4050 <_sk_callback_hsw+0x47d> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 .byte 197,124,16,64,96 // vmovups 0x60(%rax),%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,168,4,0,0 // vbroadcastss 0x4a8(%rip),%ymm10 # 40cc <_sk_callback_hsw+0x489> - .byte 196,98,125,24,29,163,4,0,0 // vbroadcastss 0x4a3(%rip),%ymm11 # 40d0 <_sk_callback_hsw+0x48d> + .byte 196,98,125,24,21,160,4,0,0 // vbroadcastss 0x4a0(%rip),%ymm10 # 4054 <_sk_callback_hsw+0x481> + .byte 196,98,125,24,29,155,4,0,0 // vbroadcastss 0x49b(%rip),%ymm11 # 4058 <_sk_callback_hsw+0x485> .byte 196,66,61,168,218 // vfmadd213ps %ymm10,%ymm8,%ymm11 .byte 196,65,52,89,195 // vmulps %ymm11,%ymm9,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -11331,22 +11301,17 @@ BALIGN4 .byte 62,0,0 // add %al,%ds:(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) - .byte 128,63,0 // cmpb $0x0,(%rdi) - .byte 0,0 // add %al,(%rax) - .byte 64,171 // rex stos %eax,%es:(%rdi) + .byte 0,64,171 // add %al,-0x55(%rax) .byte 170 // stos %al,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) .byte 62,0,0 // add %al,%ds:(%rax) - .byte 128,191,0,0,192,64,171 // cmpb $0xab,0x40c00000(%rdi) - .byte 170 // stos %al,%es:(%rdi) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) + .byte 192,64,0,0 // rolb $0x0,0x0(%rax) + .byte 128,64,171,170 // addb $0xaa,-0x55(%rax) .byte 170 // stos %al,%es:(%rdi) .byte 190,129,128,128,59 // mov $0x3b808081,%esi .byte 129,128,128,59,0,248,0,0,8,33 // addl $0x21080000,-0x7ffc480(%rax) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 3e41 <.literal4+0xd9> + .byte 224,7 // loopne 3dc9 <.literal4+0xd1> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -11360,10 +11325,10 @@ BALIGN4 .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) .byte 0,52,255 // add %dh,(%rdi,%rdi,8) .byte 255 // (bad) - .byte 127,0 // jg 3e6c <.literal4+0x104> + .byte 127,0 // jg 3df4 <.literal4+0xfc> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 3ee5 <.literal4+0x17d> + .byte 119,115 // ja 3e6d <.literal4+0x175> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -11377,10 +11342,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 3ea0 <.literal4+0x138> + .byte 127,0 // jg 3e28 <.literal4+0x130> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 3f19 <.literal4+0x1b1> + .byte 119,115 // ja 3ea1 <.literal4+0x1a9> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -11394,10 +11359,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 3ed4 <.literal4+0x16c> + .byte 127,0 // jg 3e5c <.literal4+0x164> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 3f4d <.literal4+0x1e5> + .byte 119,115 // ja 3ed5 <.literal4+0x1dd> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -11411,10 +11376,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 3f08 <.literal4+0x1a0> + .byte 127,0 // jg 3e90 <.literal4+0x198> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 3f81 <.literal4+0x219> + .byte 119,115 // ja 3f09 <.literal4+0x211> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -11427,7 +11392,7 @@ BALIGN4 .byte 0,75,0 // add %cl,0x0(%rbx) .byte 0,128,63,0,0,200 // add %al,-0x37ffffc1(%rax) .byte 66,0,0 // rex.X add %al,(%rax) - .byte 127,67 // jg 3f7f <.literal4+0x217> + .byte 127,67 // jg 3f07 <.literal4+0x20f> .byte 0,0 // add %al,(%rax) .byte 0,195 // add %al,%bl .byte 0,0 // add %al,(%rax) @@ -11439,10 +11404,10 @@ BALIGN4 .byte 190,80,128,3,62 // mov $0x3e038050,%esi .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 3f9f <.literal4+0x237> + .byte 118,63 // jbe 3f27 <.literal4+0x22f> .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) - .byte 127,67 // jg 3fb3 <.literal4+0x24b> + .byte 127,67 // jg 3f3b <.literal4+0x243> .byte 129,128,128,59,0,0,128,63,129,128 // addl $0x80813f80,0x3b80(%rax) .byte 128,59,0 // cmpb $0x0,(%rbx) .byte 0,128,63,129,128,128 // add %al,-0x7f7f7ec1(%rax) @@ -11451,7 +11416,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 3f95 <.literal4+0x22d> + .byte 224,7 // loopne 3f1d <.literal4+0x225> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -11463,7 +11428,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 3fb1 <.literal4+0x249> + .byte 224,7 // loopne 3f39 <.literal4+0x241> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -11474,7 +11439,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 248 // clc .byte 65,0,0 // add %al,(%r8) - .byte 124,66 // jl 4006 <.literal4+0x29e> + .byte 124,66 // jl 3f8e <.literal4+0x296> .byte 0,240 // add %dh,%al .byte 0,0 // add %al,(%rax) .byte 137,136,136,55,0,15 // mov %ecx,0xf003788(%rax) @@ -11492,9 +11457,9 @@ BALIGN4 .byte 137,136,136,59,15,0 // mov %ecx,0xf3b88(%rax) .byte 0,0 // add %al,(%rax) .byte 137,136,136,61,0,0 // mov %ecx,0x3d88(%rax) - .byte 112,65 // jo 4049 <.literal4+0x2e1> + .byte 112,65 // jo 3fd1 <.literal4+0x2d9> .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) - .byte 127,67 // jg 4057 <.literal4+0x2ef> + .byte 127,67 // jg 3fdf <.literal4+0x2e7> .byte 128,0,128 // addb $0x80,(%rax) .byte 55 // (bad) .byte 128,0,128 // addb $0x80,(%rax) @@ -11502,7 +11467,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 255 // (bad) - .byte 127,71 // jg 406b <.literal4+0x303> + .byte 127,71 // jg 3ff3 <.literal4+0x2fb> .byte 208 // (bad) .byte 179,89 // mov $0x59,%bl .byte 62,89 // ds pop %rcx @@ -11588,16 +11553,16 @@ BALIGN32 .byte 0,0 // add %al,(%rax) .byte 1,255 // add %edi,%edi .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004108 <_sk_callback_hsw+0xa0004c5> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004088 <_sk_callback_hsw+0xa0004b5> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004110 <_sk_callback_hsw+0x120004cd> + .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004090 <_sk_callback_hsw+0x120004bd> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004118 <_sk_callback_hsw+0x1a0004d5> + .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004098 <_sk_callback_hsw+0x1a0004c5> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004120 <_sk_callback_hsw+0x30004dd> + .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 30040a0 <_sk_callback_hsw+0x30004cd> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -11640,16 +11605,16 @@ BALIGN32 .byte 0,0 // add %al,(%rax) .byte 1,255 // add %edi,%edi .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004168 <_sk_callback_hsw+0xa000525> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a0040e8 <_sk_callback_hsw+0xa000515> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004170 <_sk_callback_hsw+0x1200052d> + .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 120040f0 <_sk_callback_hsw+0x1200051d> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004178 <_sk_callback_hsw+0x1a000535> + .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a0040f8 <_sk_callback_hsw+0x1a000525> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004180 <_sk_callback_hsw+0x300053d> + .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004100 <_sk_callback_hsw+0x300052d> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -11692,16 +11657,16 @@ BALIGN32 .byte 0,0 // add %al,(%rax) .byte 1,255 // add %edi,%edi .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a0041c8 <_sk_callback_hsw+0xa000585> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004148 <_sk_callback_hsw+0xa000575> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 120041d0 <_sk_callback_hsw+0x1200058d> + .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004150 <_sk_callback_hsw+0x1200057d> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a0041d8 <_sk_callback_hsw+0x1a000595> + .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004158 <_sk_callback_hsw+0x1a000585> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 30041e0 <_sk_callback_hsw+0x300059d> + .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004160 <_sk_callback_hsw+0x300058d> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -11744,16 +11709,16 @@ BALIGN32 .byte 0,0 // add %al,(%rax) .byte 1,255 // add %edi,%edi .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a004228 <_sk_callback_hsw+0xa0005e5> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a0041a8 <_sk_callback_hsw+0xa0005d5> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 12004230 <_sk_callback_hsw+0x120005ed> + .byte 255,13,255,255,255,17 // decl 0x11ffffff(%rip) # 120041b0 <_sk_callback_hsw+0x120005dd> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a004238 <_sk_callback_hsw+0x1a0005f5> + .byte 255,21,255,255,255,25 // callq *0x19ffffff(%rip) # 1a0041b8 <_sk_callback_hsw+0x1a0005e5> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 3004240 <_sk_callback_hsw+0x30005fd> + .byte 255,29,255,255,255,2 // lcall *0x2ffffff(%rip) # 30041c0 <_sk_callback_hsw+0x30005ed> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -11874,14 +11839,14 @@ _sk_seed_shader_avx: .byte 197,249,112,192,0 // vpshufd $0x0,%xmm0,%xmm0 .byte 196,227,125,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,111,83,0,0 // vbroadcastss 0x536f(%rip),%ymm1 # 5438 <_sk_callback_avx+0x126> + .byte 196,226,125,24,13,231,82,0,0 // vbroadcastss 0x52e7(%rip),%ymm1 # 53b0 <_sk_callback_avx+0x126> .byte 197,252,88,193 // vaddps %ymm1,%ymm0,%ymm0 .byte 197,252,88,2 // vaddps (%rdx),%ymm0,%ymm0 .byte 196,226,125,24,16 // vbroadcastss (%rax),%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 197,236,88,201 // vaddps %ymm1,%ymm2,%ymm1 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,21,83,83,0,0 // vbroadcastss 0x5353(%rip),%ymm2 # 543c <_sk_callback_avx+0x12a> + .byte 196,226,125,24,21,203,82,0,0 // vbroadcastss 0x52cb(%rip),%ymm2 # 53b4 <_sk_callback_avx+0x12a> .byte 197,228,87,219 // vxorps %ymm3,%ymm3,%ymm3 .byte 197,220,87,228 // vxorps %ymm4,%ymm4,%ymm4 .byte 197,212,87,237 // vxorps %ymm5,%ymm5,%ymm5 @@ -11917,7 +11882,7 @@ HIDDEN _sk_srcatop_avx FUNCTION(_sk_srcatop_avx) _sk_srcatop_avx: .byte 197,252,89,199 // vmulps %ymm7,%ymm0,%ymm0 - .byte 196,98,125,24,5,3,83,0,0 // vbroadcastss 0x5303(%rip),%ymm8 # 5440 <_sk_callback_avx+0x12e> + .byte 196,98,125,24,5,123,82,0,0 // vbroadcastss 0x527b(%rip),%ymm8 # 53b8 <_sk_callback_avx+0x12e> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,204 // vmulps %ymm4,%ymm8,%ymm9 .byte 197,180,88,192 // vaddps %ymm0,%ymm9,%ymm0 @@ -11938,7 +11903,7 @@ HIDDEN _sk_dstatop_avx FUNCTION(_sk_dstatop_avx) _sk_dstatop_avx: .byte 197,100,89,196 // vmulps %ymm4,%ymm3,%ymm8 - .byte 196,98,125,24,13,197,82,0,0 // vbroadcastss 0x52c5(%rip),%ymm9 # 5444 <_sk_callback_avx+0x132> + .byte 196,98,125,24,13,61,82,0,0 // vbroadcastss 0x523d(%rip),%ymm9 # 53bc <_sk_callback_avx+0x132> .byte 197,52,92,207 // vsubps %ymm7,%ymm9,%ymm9 .byte 197,180,89,192 // vmulps %ymm0,%ymm9,%ymm0 .byte 197,188,88,192 // vaddps %ymm0,%ymm8,%ymm0 @@ -11980,7 +11945,7 @@ HIDDEN _sk_srcout_avx .globl _sk_srcout_avx FUNCTION(_sk_srcout_avx) _sk_srcout_avx: - .byte 196,98,125,24,5,100,82,0,0 // vbroadcastss 0x5264(%rip),%ymm8 # 5448 <_sk_callback_avx+0x136> + .byte 196,98,125,24,5,220,81,0,0 // vbroadcastss 0x51dc(%rip),%ymm8 # 53c0 <_sk_callback_avx+0x136> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 @@ -11993,7 +11958,7 @@ HIDDEN _sk_dstout_avx .globl _sk_dstout_avx FUNCTION(_sk_dstout_avx) _sk_dstout_avx: - .byte 196,226,125,24,5,71,82,0,0 // vbroadcastss 0x5247(%rip),%ymm0 # 544c <_sk_callback_avx+0x13a> + .byte 196,226,125,24,5,191,81,0,0 // vbroadcastss 0x51bf(%rip),%ymm0 # 53c4 <_sk_callback_avx+0x13a> .byte 197,252,92,219 // vsubps %ymm3,%ymm0,%ymm3 .byte 197,228,89,196 // vmulps %ymm4,%ymm3,%ymm0 .byte 197,228,89,205 // vmulps %ymm5,%ymm3,%ymm1 @@ -12006,7 +11971,7 @@ HIDDEN _sk_srcover_avx .globl _sk_srcover_avx FUNCTION(_sk_srcover_avx) _sk_srcover_avx: - .byte 196,98,125,24,5,42,82,0,0 // vbroadcastss 0x522a(%rip),%ymm8 # 5450 <_sk_callback_avx+0x13e> + .byte 196,98,125,24,5,162,81,0,0 // vbroadcastss 0x51a2(%rip),%ymm8 # 53c8 <_sk_callback_avx+0x13e> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,204 // vmulps %ymm4,%ymm8,%ymm9 .byte 197,180,88,192 // vaddps %ymm0,%ymm9,%ymm0 @@ -12023,7 +11988,7 @@ HIDDEN _sk_dstover_avx .globl _sk_dstover_avx FUNCTION(_sk_dstover_avx) _sk_dstover_avx: - .byte 196,98,125,24,5,253,81,0,0 // vbroadcastss 0x51fd(%rip),%ymm8 # 5454 <_sk_callback_avx+0x142> + .byte 196,98,125,24,5,117,81,0,0 // vbroadcastss 0x5175(%rip),%ymm8 # 53cc <_sk_callback_avx+0x142> .byte 197,60,92,199 // vsubps %ymm7,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,252,88,196 // vaddps %ymm4,%ymm0,%ymm0 @@ -12051,7 +12016,7 @@ HIDDEN _sk_multiply_avx .globl _sk_multiply_avx FUNCTION(_sk_multiply_avx) _sk_multiply_avx: - .byte 196,98,125,24,5,188,81,0,0 // vbroadcastss 0x51bc(%rip),%ymm8 # 5458 <_sk_callback_avx+0x146> + .byte 196,98,125,24,5,52,81,0,0 // vbroadcastss 0x5134(%rip),%ymm8 # 53d0 <_sk_callback_avx+0x146> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,52,89,208 // vmulps %ymm0,%ymm9,%ymm10 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -12111,7 +12076,7 @@ HIDDEN _sk_xor__avx .globl _sk_xor__avx FUNCTION(_sk_xor__avx) _sk_xor__avx: - .byte 196,98,125,24,5,11,81,0,0 // vbroadcastss 0x510b(%rip),%ymm8 # 545c <_sk_callback_avx+0x14a> + .byte 196,98,125,24,5,131,80,0,0 // vbroadcastss 0x5083(%rip),%ymm8 # 53d4 <_sk_callback_avx+0x14a> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,180,89,192 // vmulps %ymm0,%ymm9,%ymm0 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -12148,7 +12113,7 @@ _sk_darken_avx: .byte 197,100,89,206 // vmulps %ymm6,%ymm3,%ymm9 .byte 196,193,108,95,209 // vmaxps %ymm9,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,139,80,0,0 // vbroadcastss 0x508b(%rip),%ymm8 # 5460 <_sk_callback_avx+0x14e> + .byte 196,98,125,24,5,3,80,0,0 // vbroadcastss 0x5003(%rip),%ymm8 # 53d8 <_sk_callback_avx+0x14e> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,199 // vmulps %ymm7,%ymm8,%ymm8 .byte 197,188,88,219 // vaddps %ymm3,%ymm8,%ymm3 @@ -12174,7 +12139,7 @@ _sk_lighten_avx: .byte 197,100,89,206 // vmulps %ymm6,%ymm3,%ymm9 .byte 196,193,108,93,209 // vminps %ymm9,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,55,80,0,0 // vbroadcastss 0x5037(%rip),%ymm8 # 5464 <_sk_callback_avx+0x152> + .byte 196,98,125,24,5,175,79,0,0 // vbroadcastss 0x4faf(%rip),%ymm8 # 53dc <_sk_callback_avx+0x152> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,199 // vmulps %ymm7,%ymm8,%ymm8 .byte 197,188,88,219 // vaddps %ymm3,%ymm8,%ymm3 @@ -12203,7 +12168,7 @@ _sk_difference_avx: .byte 196,193,108,93,209 // vminps %ymm9,%ymm2,%ymm2 .byte 197,236,88,210 // vaddps %ymm2,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,215,79,0,0 // vbroadcastss 0x4fd7(%rip),%ymm8 # 5468 <_sk_callback_avx+0x156> + .byte 196,98,125,24,5,79,79,0,0 // vbroadcastss 0x4f4f(%rip),%ymm8 # 53e0 <_sk_callback_avx+0x156> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,199 // vmulps %ymm7,%ymm8,%ymm8 .byte 197,188,88,219 // vaddps %ymm3,%ymm8,%ymm3 @@ -12226,7 +12191,7 @@ _sk_exclusion_avx: .byte 197,236,89,214 // vmulps %ymm6,%ymm2,%ymm2 .byte 197,236,88,210 // vaddps %ymm2,%ymm2,%ymm2 .byte 197,188,92,210 // vsubps %ymm2,%ymm8,%ymm2 - .byte 196,98,125,24,5,146,79,0,0 // vbroadcastss 0x4f92(%rip),%ymm8 # 546c <_sk_callback_avx+0x15a> + .byte 196,98,125,24,5,10,79,0,0 // vbroadcastss 0x4f0a(%rip),%ymm8 # 53e4 <_sk_callback_avx+0x15a> .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 .byte 197,60,89,199 // vmulps %ymm7,%ymm8,%ymm8 .byte 197,188,88,219 // vaddps %ymm3,%ymm8,%ymm3 @@ -12237,7 +12202,7 @@ HIDDEN _sk_colorburn_avx .globl _sk_colorburn_avx FUNCTION(_sk_colorburn_avx) _sk_colorburn_avx: - .byte 196,98,125,24,5,125,79,0,0 // vbroadcastss 0x4f7d(%rip),%ymm8 # 5470 <_sk_callback_avx+0x15e> + .byte 196,98,125,24,5,245,78,0,0 // vbroadcastss 0x4ef5(%rip),%ymm8 # 53e8 <_sk_callback_avx+0x15e> .byte 197,60,92,207 // vsubps %ymm7,%ymm8,%ymm9 .byte 197,52,89,216 // vmulps %ymm0,%ymm9,%ymm11 .byte 196,65,44,87,210 // vxorps %ymm10,%ymm10,%ymm10 @@ -12299,7 +12264,7 @@ HIDDEN _sk_colordodge_avx FUNCTION(_sk_colordodge_avx) _sk_colordodge_avx: .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 - .byte 196,98,125,24,13,121,78,0,0 // vbroadcastss 0x4e79(%rip),%ymm9 # 5474 <_sk_callback_avx+0x162> + .byte 196,98,125,24,13,241,77,0,0 // vbroadcastss 0x4df1(%rip),%ymm9 # 53ec <_sk_callback_avx+0x162> .byte 197,52,92,215 // vsubps %ymm7,%ymm9,%ymm10 .byte 197,44,89,216 // vmulps %ymm0,%ymm10,%ymm11 .byte 197,52,92,203 // vsubps %ymm3,%ymm9,%ymm9 @@ -12356,7 +12321,7 @@ HIDDEN _sk_hardlight_avx .globl _sk_hardlight_avx FUNCTION(_sk_hardlight_avx) _sk_hardlight_avx: - .byte 196,98,125,24,5,139,77,0,0 // vbroadcastss 0x4d8b(%rip),%ymm8 # 5478 <_sk_callback_avx+0x166> + .byte 196,98,125,24,5,3,77,0,0 // vbroadcastss 0x4d03(%rip),%ymm8 # 53f0 <_sk_callback_avx+0x166> .byte 197,60,92,215 // vsubps %ymm7,%ymm8,%ymm10 .byte 197,44,89,200 // vmulps %ymm0,%ymm10,%ymm9 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -12411,7 +12376,7 @@ HIDDEN _sk_overlay_avx .globl _sk_overlay_avx FUNCTION(_sk_overlay_avx) _sk_overlay_avx: - .byte 196,98,125,24,5,180,76,0,0 // vbroadcastss 0x4cb4(%rip),%ymm8 # 547c <_sk_callback_avx+0x16a> + .byte 196,98,125,24,5,44,76,0,0 // vbroadcastss 0x4c2c(%rip),%ymm8 # 53f4 <_sk_callback_avx+0x16a> .byte 197,60,92,215 // vsubps %ymm7,%ymm8,%ymm10 .byte 197,44,89,200 // vmulps %ymm0,%ymm10,%ymm9 .byte 197,60,92,195 // vsubps %ymm3,%ymm8,%ymm8 @@ -12477,10 +12442,10 @@ _sk_softlight_avx: .byte 196,65,60,88,192 // vaddps %ymm8,%ymm8,%ymm8 .byte 196,65,60,89,216 // vmulps %ymm8,%ymm8,%ymm11 .byte 196,65,60,88,195 // vaddps %ymm11,%ymm8,%ymm8 - .byte 196,98,125,24,29,171,75,0,0 // vbroadcastss 0x4bab(%rip),%ymm11 # 5484 <_sk_callback_avx+0x172> + .byte 196,98,125,24,29,35,75,0,0 // vbroadcastss 0x4b23(%rip),%ymm11 # 53fc <_sk_callback_avx+0x172> .byte 196,65,28,88,235 // vaddps %ymm11,%ymm12,%ymm13 .byte 196,65,20,89,192 // vmulps %ymm8,%ymm13,%ymm8 - .byte 196,98,125,24,45,156,75,0,0 // vbroadcastss 0x4b9c(%rip),%ymm13 # 5488 <_sk_callback_avx+0x176> + .byte 196,98,125,24,45,20,75,0,0 // vbroadcastss 0x4b14(%rip),%ymm13 # 5400 <_sk_callback_avx+0x176> .byte 196,65,28,89,245 // vmulps %ymm13,%ymm12,%ymm14 .byte 196,65,12,88,192 // vaddps %ymm8,%ymm14,%ymm8 .byte 196,65,124,82,244 // vrsqrtps %ymm12,%ymm14 @@ -12491,7 +12456,7 @@ _sk_softlight_avx: .byte 197,4,194,255,2 // vcmpleps %ymm7,%ymm15,%ymm15 .byte 196,67,13,74,240,240 // vblendvps %ymm15,%ymm8,%ymm14,%ymm14 .byte 197,116,88,249 // vaddps %ymm1,%ymm1,%ymm15 - .byte 196,98,125,24,5,90,75,0,0 // vbroadcastss 0x4b5a(%rip),%ymm8 # 5480 <_sk_callback_avx+0x16e> + .byte 196,98,125,24,5,210,74,0,0 // vbroadcastss 0x4ad2(%rip),%ymm8 # 53f8 <_sk_callback_avx+0x16e> .byte 196,65,60,92,228 // vsubps %ymm12,%ymm8,%ymm12 .byte 197,132,92,195 // vsubps %ymm3,%ymm15,%ymm0 .byte 196,65,124,89,228 // vmulps %ymm12,%ymm0,%ymm12 @@ -12598,7 +12563,7 @@ HIDDEN _sk_clamp_1_avx .globl _sk_clamp_1_avx FUNCTION(_sk_clamp_1_avx) _sk_clamp_1_avx: - .byte 196,98,125,24,5,170,73,0,0 // vbroadcastss 0x49aa(%rip),%ymm8 # 548c <_sk_callback_avx+0x17a> + .byte 196,98,125,24,5,34,73,0,0 // vbroadcastss 0x4922(%rip),%ymm8 # 5404 <_sk_callback_avx+0x17a> .byte 196,193,124,93,192 // vminps %ymm8,%ymm0,%ymm0 .byte 196,193,116,93,200 // vminps %ymm8,%ymm1,%ymm1 .byte 196,193,108,93,208 // vminps %ymm8,%ymm2,%ymm2 @@ -12610,7 +12575,7 @@ HIDDEN _sk_clamp_a_avx .globl _sk_clamp_a_avx FUNCTION(_sk_clamp_a_avx) _sk_clamp_a_avx: - .byte 196,98,125,24,5,141,73,0,0 // vbroadcastss 0x498d(%rip),%ymm8 # 5490 <_sk_callback_avx+0x17e> + .byte 196,98,125,24,5,5,73,0,0 // vbroadcastss 0x4905(%rip),%ymm8 # 5408 <_sk_callback_avx+0x17e> .byte 196,193,100,93,216 // vminps %ymm8,%ymm3,%ymm3 .byte 197,252,93,195 // vminps %ymm3,%ymm0,%ymm0 .byte 197,244,93,203 // vminps %ymm3,%ymm1,%ymm1 @@ -12696,7 +12661,7 @@ FUNCTION(_sk_unpremul_avx) _sk_unpremul_avx: .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,65,100,194,200,0 // vcmpeqps %ymm8,%ymm3,%ymm9 - .byte 196,98,125,24,21,213,72,0,0 // vbroadcastss 0x48d5(%rip),%ymm10 # 5494 <_sk_callback_avx+0x182> + .byte 196,98,125,24,21,77,72,0,0 // vbroadcastss 0x484d(%rip),%ymm10 # 540c <_sk_callback_avx+0x182> .byte 197,44,94,211 // vdivps %ymm3,%ymm10,%ymm10 .byte 196,67,45,74,192,144 // vblendvps %ymm9,%ymm8,%ymm10,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 @@ -12709,17 +12674,17 @@ HIDDEN _sk_from_srgb_avx .globl _sk_from_srgb_avx FUNCTION(_sk_from_srgb_avx) _sk_from_srgb_avx: - .byte 196,98,125,24,5,182,72,0,0 // vbroadcastss 0x48b6(%rip),%ymm8 # 5498 <_sk_callback_avx+0x186> + .byte 196,98,125,24,5,46,72,0,0 // vbroadcastss 0x482e(%rip),%ymm8 # 5410 <_sk_callback_avx+0x186> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 197,124,89,208 // vmulps %ymm0,%ymm0,%ymm10 - .byte 196,98,125,24,29,168,72,0,0 // vbroadcastss 0x48a8(%rip),%ymm11 # 549c <_sk_callback_avx+0x18a> + .byte 196,98,125,24,29,32,72,0,0 // vbroadcastss 0x4820(%rip),%ymm11 # 5414 <_sk_callback_avx+0x18a> .byte 196,65,124,89,227 // vmulps %ymm11,%ymm0,%ymm12 - .byte 196,98,125,24,45,158,72,0,0 // vbroadcastss 0x489e(%rip),%ymm13 # 54a0 <_sk_callback_avx+0x18e> + .byte 196,98,125,24,45,22,72,0,0 // vbroadcastss 0x4816(%rip),%ymm13 # 5418 <_sk_callback_avx+0x18e> .byte 196,65,28,88,229 // vaddps %ymm13,%ymm12,%ymm12 .byte 196,65,44,89,212 // vmulps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,37,143,72,0,0 // vbroadcastss 0x488f(%rip),%ymm12 # 54a4 <_sk_callback_avx+0x192> + .byte 196,98,125,24,37,7,72,0,0 // vbroadcastss 0x4807(%rip),%ymm12 # 541c <_sk_callback_avx+0x192> .byte 196,65,44,88,212 // vaddps %ymm12,%ymm10,%ymm10 - .byte 196,98,125,24,53,133,72,0,0 // vbroadcastss 0x4885(%rip),%ymm14 # 54a8 <_sk_callback_avx+0x196> + .byte 196,98,125,24,53,253,71,0,0 // vbroadcastss 0x47fd(%rip),%ymm14 # 5420 <_sk_callback_avx+0x196> .byte 196,193,124,194,198,1 // vcmpltps %ymm14,%ymm0,%ymm0 .byte 196,195,45,74,193,0 // vblendvps %ymm0,%ymm9,%ymm10,%ymm0 .byte 196,65,116,89,200 // vmulps %ymm8,%ymm1,%ymm9 @@ -12748,18 +12713,18 @@ _sk_to_srgb_avx: .byte 197,124,82,192 // vrsqrtps %ymm0,%ymm8 .byte 196,65,124,83,200 // vrcpps %ymm8,%ymm9 .byte 196,65,124,82,208 // vrsqrtps %ymm8,%ymm10 - .byte 196,98,125,24,5,16,72,0,0 // vbroadcastss 0x4810(%rip),%ymm8 # 54ac <_sk_callback_avx+0x19a> + .byte 196,98,125,24,5,136,71,0,0 // vbroadcastss 0x4788(%rip),%ymm8 # 5424 <_sk_callback_avx+0x19a> .byte 196,65,124,89,216 // vmulps %ymm8,%ymm0,%ymm11 - .byte 196,98,125,24,37,6,72,0,0 // vbroadcastss 0x4806(%rip),%ymm12 # 54b0 <_sk_callback_avx+0x19e> + .byte 196,98,125,24,37,126,71,0,0 // vbroadcastss 0x477e(%rip),%ymm12 # 5428 <_sk_callback_avx+0x19e> .byte 196,65,52,89,204 // vmulps %ymm12,%ymm9,%ymm9 - .byte 196,98,125,24,45,252,71,0,0 // vbroadcastss 0x47fc(%rip),%ymm13 # 54b4 <_sk_callback_avx+0x1a2> + .byte 196,98,125,24,45,116,71,0,0 // vbroadcastss 0x4774(%rip),%ymm13 # 542c <_sk_callback_avx+0x1a2> .byte 196,65,52,88,205 // vaddps %ymm13,%ymm9,%ymm9 - .byte 196,98,125,24,53,242,71,0,0 // vbroadcastss 0x47f2(%rip),%ymm14 # 54b8 <_sk_callback_avx+0x1a6> + .byte 196,98,125,24,53,106,71,0,0 // vbroadcastss 0x476a(%rip),%ymm14 # 5430 <_sk_callback_avx+0x1a6> .byte 196,65,44,89,214 // vmulps %ymm14,%ymm10,%ymm10 .byte 196,65,44,88,201 // vaddps %ymm9,%ymm10,%ymm9 - .byte 196,98,125,24,21,227,71,0,0 // vbroadcastss 0x47e3(%rip),%ymm10 # 54bc <_sk_callback_avx+0x1aa> + .byte 196,98,125,24,21,91,71,0,0 // vbroadcastss 0x475b(%rip),%ymm10 # 5434 <_sk_callback_avx+0x1aa> .byte 196,65,44,93,201 // vminps %ymm9,%ymm10,%ymm9 - .byte 196,98,125,24,61,217,71,0,0 // vbroadcastss 0x47d9(%rip),%ymm15 # 54c0 <_sk_callback_avx+0x1ae> + .byte 196,98,125,24,61,81,71,0,0 // vbroadcastss 0x4751(%rip),%ymm15 # 5438 <_sk_callback_avx+0x1ae> .byte 196,193,124,194,199,1 // vcmpltps %ymm15,%ymm0,%ymm0 .byte 196,195,53,74,195,0 // vblendvps %ymm0,%ymm11,%ymm9,%ymm0 .byte 197,124,82,201 // vrsqrtps %ymm1,%ymm9 @@ -12796,7 +12761,7 @@ _sk_rgb_to_hsl_avx: .byte 197,124,93,201 // vminps %ymm1,%ymm0,%ymm9 .byte 197,52,93,202 // vminps %ymm2,%ymm9,%ymm9 .byte 196,65,60,92,209 // vsubps %ymm9,%ymm8,%ymm10 - .byte 196,98,125,24,29,63,71,0,0 // vbroadcastss 0x473f(%rip),%ymm11 # 54c4 <_sk_callback_avx+0x1b2> + .byte 196,98,125,24,29,183,70,0,0 // vbroadcastss 0x46b7(%rip),%ymm11 # 543c <_sk_callback_avx+0x1b2> .byte 196,65,36,94,218 // vdivps %ymm10,%ymm11,%ymm11 .byte 197,116,92,226 // vsubps %ymm2,%ymm1,%ymm12 .byte 196,65,28,89,227 // vmulps %ymm11,%ymm12,%ymm12 @@ -12806,19 +12771,19 @@ _sk_rgb_to_hsl_avx: .byte 196,193,108,89,211 // vmulps %ymm11,%ymm2,%ymm2 .byte 197,252,92,201 // vsubps %ymm1,%ymm0,%ymm1 .byte 196,193,116,89,203 // vmulps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,24,71,0,0 // vbroadcastss 0x4718(%rip),%ymm11 # 54d0 <_sk_callback_avx+0x1be> + .byte 196,98,125,24,29,144,70,0,0 // vbroadcastss 0x4690(%rip),%ymm11 # 5448 <_sk_callback_avx+0x1be> .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,6,71,0,0 // vbroadcastss 0x4706(%rip),%ymm11 # 54cc <_sk_callback_avx+0x1ba> + .byte 196,98,125,24,29,126,70,0,0 // vbroadcastss 0x467e(%rip),%ymm11 # 5444 <_sk_callback_avx+0x1ba> .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 .byte 196,227,117,74,202,224 // vblendvps %ymm14,%ymm2,%ymm1,%ymm1 - .byte 196,226,125,24,21,238,70,0,0 // vbroadcastss 0x46ee(%rip),%ymm2 # 54c8 <_sk_callback_avx+0x1b6> + .byte 196,226,125,24,21,102,70,0,0 // vbroadcastss 0x4666(%rip),%ymm2 # 5440 <_sk_callback_avx+0x1b6> .byte 196,65,12,87,246 // vxorps %ymm14,%ymm14,%ymm14 .byte 196,227,13,74,210,208 // vblendvps %ymm13,%ymm2,%ymm14,%ymm2 .byte 197,188,194,192,0 // vcmpeqps %ymm0,%ymm8,%ymm0 .byte 196,193,108,88,212 // vaddps %ymm12,%ymm2,%ymm2 .byte 196,227,117,74,194,0 // vblendvps %ymm0,%ymm2,%ymm1,%ymm0 .byte 196,193,60,88,201 // vaddps %ymm9,%ymm8,%ymm1 - .byte 196,98,125,24,37,213,70,0,0 // vbroadcastss 0x46d5(%rip),%ymm12 # 54d8 <_sk_callback_avx+0x1c6> + .byte 196,98,125,24,37,77,70,0,0 // vbroadcastss 0x464d(%rip),%ymm12 # 5450 <_sk_callback_avx+0x1c6> .byte 196,193,116,89,212 // vmulps %ymm12,%ymm1,%ymm2 .byte 197,28,194,226,1 // vcmpltps %ymm2,%ymm12,%ymm12 .byte 196,65,36,92,216 // vsubps %ymm8,%ymm11,%ymm11 @@ -12828,7 +12793,7 @@ _sk_rgb_to_hsl_avx: .byte 197,172,94,201 // vdivps %ymm1,%ymm10,%ymm1 .byte 196,195,125,74,198,128 // vblendvps %ymm8,%ymm14,%ymm0,%ymm0 .byte 196,195,117,74,206,128 // vblendvps %ymm8,%ymm14,%ymm1,%ymm1 - .byte 196,98,125,24,5,152,70,0,0 // vbroadcastss 0x4698(%rip),%ymm8 # 54d4 <_sk_callback_avx+0x1c2> + .byte 196,98,125,24,5,16,70,0,0 // vbroadcastss 0x4610(%rip),%ymm8 # 544c <_sk_callback_avx+0x1c2> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -12837,119 +12802,94 @@ HIDDEN _sk_hsl_to_rgb_avx .globl _sk_hsl_to_rgb_avx FUNCTION(_sk_hsl_to_rgb_avx) _sk_hsl_to_rgb_avx: - .byte 72,131,236,120 // sub $0x78,%rsp - .byte 197,252,17,124,36,64 // vmovups %ymm7,0x40(%rsp) - .byte 197,252,17,116,36,32 // vmovups %ymm6,0x20(%rsp) - .byte 197,252,17,44,36 // vmovups %ymm5,(%rsp) - .byte 197,252,17,100,36,224 // vmovups %ymm4,-0x20(%rsp) - .byte 197,252,17,92,36,192 // vmovups %ymm3,-0x40(%rsp) - .byte 197,252,40,234 // vmovaps %ymm2,%ymm5 - .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 + .byte 72,131,236,56 // sub $0x38,%rsp + .byte 197,252,17,60,36 // vmovups %ymm7,(%rsp) + .byte 197,252,17,116,36,224 // vmovups %ymm6,-0x20(%rsp) + .byte 197,252,17,108,36,192 // vmovups %ymm5,-0x40(%rsp) + .byte 197,252,17,100,36,160 // vmovups %ymm4,-0x60(%rsp) + .byte 197,252,17,92,36,128 // vmovups %ymm3,-0x80(%rsp) + .byte 197,252,40,217 // vmovaps %ymm1,%ymm3 + .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 184,0,0,0,63 // mov $0x3f000000,%eax - .byte 197,249,110,192 // vmovd %eax,%xmm0 - .byte 196,227,121,4,192,0 // vpermilps $0x0,%xmm0,%xmm0 - .byte 196,99,125,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm0,%ymm8 - .byte 196,193,84,194,192,1 // vcmpltps %ymm8,%ymm5,%ymm0 - .byte 196,98,125,24,21,74,70,0,0 // vbroadcastss 0x464a(%rip),%ymm10 # 54dc <_sk_callback_avx+0x1ca> - .byte 197,252,17,76,36,160 // vmovups %ymm1,-0x60(%rsp) - .byte 196,193,116,88,218 // vaddps %ymm10,%ymm1,%ymm3 - .byte 197,228,89,221 // vmulps %ymm5,%ymm3,%ymm3 - .byte 197,244,88,229 // vaddps %ymm5,%ymm1,%ymm4 - .byte 197,244,89,245 // vmulps %ymm5,%ymm1,%ymm6 - .byte 197,220,92,230 // vsubps %ymm6,%ymm4,%ymm4 - .byte 196,99,93,74,203,0 // vblendvps %ymm0,%ymm3,%ymm4,%ymm9 - .byte 196,226,125,24,13,36,70,0,0 // vbroadcastss 0x4624(%rip),%ymm1 # 54e0 <_sk_callback_avx+0x1ce> - .byte 197,236,88,201 // vaddps %ymm1,%ymm2,%ymm1 - .byte 65,184,0,0,0,0 // mov $0x0,%r8d - .byte 184,0,0,128,63 // mov $0x3f800000,%eax - .byte 197,249,110,216 // vmovd %eax,%xmm3 - .byte 196,227,121,4,219,0 // vpermilps $0x0,%xmm3,%xmm3 - .byte 196,99,101,24,227,1 // vinsertf128 $0x1,%xmm3,%ymm3,%ymm12 - .byte 197,156,194,217,1 // vcmpltps %ymm1,%ymm12,%ymm3 - .byte 196,98,125,24,53,251,69,0,0 // vbroadcastss 0x45fb(%rip),%ymm14 # 54e4 <_sk_callback_avx+0x1d2> - .byte 196,193,116,88,230 // vaddps %ymm14,%ymm1,%ymm4 - .byte 196,227,117,74,220,48 // vblendvps %ymm3,%ymm4,%ymm1,%ymm3 - .byte 196,193,121,110,224 // vmovd %r8d,%xmm4 - .byte 196,227,121,4,228,0 // vpermilps $0x0,%xmm4,%xmm4 - .byte 196,99,93,24,252,1 // vinsertf128 $0x1,%xmm4,%ymm4,%ymm15 - .byte 196,193,116,194,231,1 // vcmpltps %ymm15,%ymm1,%ymm4 - .byte 196,193,116,88,202 // vaddps %ymm10,%ymm1,%ymm1 - .byte 196,227,101,74,241,64 // vblendvps %ymm4,%ymm1,%ymm3,%ymm6 - .byte 197,212,88,205 // vaddps %ymm5,%ymm5,%ymm1 - .byte 196,65,116,92,217 // vsubps %ymm9,%ymm1,%ymm11 - .byte 196,193,52,92,203 // vsubps %ymm11,%ymm9,%ymm1 - .byte 196,226,125,24,29,187,69,0,0 // vbroadcastss 0x45bb(%rip),%ymm3 # 54e8 <_sk_callback_avx+0x1d6> - .byte 197,116,89,235 // vmulps %ymm3,%ymm1,%ymm13 + .byte 197,121,110,192 // vmovd %eax,%xmm8 .byte 65,184,171,170,42,62 // mov $0x3e2aaaab,%r8d .byte 184,171,170,42,63 // mov $0x3f2aaaab,%eax - .byte 197,249,110,200 // vmovd %eax,%xmm1 - .byte 196,227,121,4,201,0 // vpermilps $0x0,%xmm1,%xmm1 - .byte 196,227,117,24,225,1 // vinsertf128 $0x1,%xmm1,%ymm1,%ymm4 - .byte 196,226,125,24,29,151,69,0,0 // vbroadcastss 0x4597(%rip),%ymm3 # 54ec <_sk_callback_avx+0x1da> - .byte 197,228,92,206 // vsubps %ymm6,%ymm3,%ymm1 - .byte 197,148,89,201 // vmulps %ymm1,%ymm13,%ymm1 - .byte 197,164,88,201 // vaddps %ymm1,%ymm11,%ymm1 - .byte 197,204,194,252,1 // vcmpltps %ymm4,%ymm6,%ymm7 - .byte 196,227,37,74,201,112 // vblendvps %ymm7,%ymm1,%ymm11,%ymm1 - .byte 196,193,76,194,248,1 // vcmpltps %ymm8,%ymm6,%ymm7 - .byte 196,195,117,74,249,112 // vblendvps %ymm7,%ymm9,%ymm1,%ymm7 - .byte 196,193,121,110,200 // vmovd %r8d,%xmm1 - .byte 196,227,121,4,201,0 // vpermilps $0x0,%xmm1,%xmm1 - .byte 196,227,117,24,201,1 // vinsertf128 $0x1,%xmm1,%ymm1,%ymm1 - .byte 197,204,194,193,1 // vcmpltps %ymm1,%ymm6,%ymm0 - .byte 197,148,89,246 // vmulps %ymm6,%ymm13,%ymm6 - .byte 197,164,88,246 // vaddps %ymm6,%ymm11,%ymm6 - .byte 196,227,69,74,198,0 // vblendvps %ymm0,%ymm6,%ymm7,%ymm0 - .byte 197,252,17,68,36,128 // vmovups %ymm0,-0x80(%rsp) - .byte 197,156,194,194,1 // vcmpltps %ymm2,%ymm12,%ymm0 - .byte 196,193,108,88,254 // vaddps %ymm14,%ymm2,%ymm7 - .byte 196,227,109,74,199,0 // vblendvps %ymm0,%ymm7,%ymm2,%ymm0 - .byte 196,193,108,194,255,1 // vcmpltps %ymm15,%ymm2,%ymm7 - .byte 196,193,108,88,242 // vaddps %ymm10,%ymm2,%ymm6 - .byte 196,227,125,74,198,112 // vblendvps %ymm7,%ymm6,%ymm0,%ymm0 - .byte 197,228,92,240 // vsubps %ymm0,%ymm3,%ymm6 - .byte 197,148,89,246 // vmulps %ymm6,%ymm13,%ymm6 - .byte 197,164,88,246 // vaddps %ymm6,%ymm11,%ymm6 - .byte 197,252,194,252,1 // vcmpltps %ymm4,%ymm0,%ymm7 - .byte 196,227,37,74,246,112 // vblendvps %ymm7,%ymm6,%ymm11,%ymm6 - .byte 196,193,124,194,248,1 // vcmpltps %ymm8,%ymm0,%ymm7 - .byte 196,195,77,74,241,112 // vblendvps %ymm7,%ymm9,%ymm6,%ymm6 - .byte 197,252,194,249,1 // vcmpltps %ymm1,%ymm0,%ymm7 - .byte 197,148,89,192 // vmulps %ymm0,%ymm13,%ymm0 - .byte 197,164,88,192 // vaddps %ymm0,%ymm11,%ymm0 - .byte 196,227,77,74,240,112 // vblendvps %ymm7,%ymm0,%ymm6,%ymm6 - .byte 196,226,125,24,5,238,68,0,0 // vbroadcastss 0x44ee(%rip),%ymm0 # 54f0 <_sk_callback_avx+0x1de> - .byte 197,236,88,192 // vaddps %ymm0,%ymm2,%ymm0 - .byte 197,156,194,208,1 // vcmpltps %ymm0,%ymm12,%ymm2 - .byte 196,193,124,88,254 // vaddps %ymm14,%ymm0,%ymm7 - .byte 196,227,125,74,215,32 // vblendvps %ymm2,%ymm7,%ymm0,%ymm2 - .byte 196,193,124,194,255,1 // vcmpltps %ymm15,%ymm0,%ymm7 - .byte 196,193,124,88,194 // vaddps %ymm10,%ymm0,%ymm0 - .byte 196,227,109,74,192,112 // vblendvps %ymm7,%ymm0,%ymm2,%ymm0 - .byte 197,252,194,212,1 // vcmpltps %ymm4,%ymm0,%ymm2 - .byte 197,228,92,216 // vsubps %ymm0,%ymm3,%ymm3 - .byte 197,148,89,219 // vmulps %ymm3,%ymm13,%ymm3 - .byte 197,164,88,219 // vaddps %ymm3,%ymm11,%ymm3 - .byte 196,227,37,74,211,32 // vblendvps %ymm2,%ymm3,%ymm11,%ymm2 - .byte 196,193,124,194,216,1 // vcmpltps %ymm8,%ymm0,%ymm3 - .byte 196,195,109,74,209,48 // vblendvps %ymm3,%ymm9,%ymm2,%ymm2 - .byte 197,252,194,201,1 // vcmpltps %ymm1,%ymm0,%ymm1 - .byte 197,148,89,192 // vmulps %ymm0,%ymm13,%ymm0 - .byte 197,164,88,192 // vaddps %ymm0,%ymm11,%ymm0 - .byte 196,227,109,74,208,16 // vblendvps %ymm1,%ymm0,%ymm2,%ymm2 + .byte 197,121,110,224 // vmovd %eax,%xmm12 + .byte 196,67,121,4,192,0 // vpermilps $0x0,%xmm8,%xmm8 + .byte 196,67,61,24,192,1 // vinsertf128 $0x1,%xmm8,%ymm8,%ymm8 + .byte 196,65,108,194,200,1 // vcmpltps %ymm8,%ymm2,%ymm9 + .byte 197,100,89,210 // vmulps %ymm2,%ymm3,%ymm10 + .byte 196,65,100,92,218 // vsubps %ymm10,%ymm3,%ymm11 + .byte 196,67,37,74,202,144 // vblendvps %ymm9,%ymm10,%ymm11,%ymm9 + .byte 197,52,88,210 // vaddps %ymm2,%ymm9,%ymm10 + .byte 197,108,88,202 // vaddps %ymm2,%ymm2,%ymm9 + .byte 196,65,52,92,202 // vsubps %ymm10,%ymm9,%ymm9 + .byte 196,98,125,24,29,151,69,0,0 // vbroadcastss 0x4597(%rip),%ymm11 # 5454 <_sk_callback_avx+0x1ca> + .byte 196,65,116,88,219 // vaddps %ymm11,%ymm1,%ymm11 + .byte 196,67,125,8,235,1 // vroundps $0x1,%ymm11,%ymm13 + .byte 196,65,36,92,237 // vsubps %ymm13,%ymm11,%ymm13 + .byte 196,65,44,92,217 // vsubps %ymm9,%ymm10,%ymm11 + .byte 196,98,125,24,53,125,69,0,0 // vbroadcastss 0x457d(%rip),%ymm14 # 5458 <_sk_callback_avx+0x1ce> + .byte 196,65,20,89,254 // vmulps %ymm14,%ymm13,%ymm15 + .byte 196,67,121,4,228,0 // vpermilps $0x0,%xmm12,%xmm12 + .byte 196,67,29,24,228,1 // vinsertf128 $0x1,%xmm12,%ymm12,%ymm12 + .byte 196,226,125,24,5,103,69,0,0 // vbroadcastss 0x4567(%rip),%ymm0 # 545c <_sk_callback_avx+0x1d2> + .byte 196,193,124,92,255 // vsubps %ymm15,%ymm0,%ymm7 + .byte 197,164,89,255 // vmulps %ymm7,%ymm11,%ymm7 + .byte 197,180,88,255 // vaddps %ymm7,%ymm9,%ymm7 + .byte 196,193,20,194,244,1 // vcmpltps %ymm12,%ymm13,%ymm6 + .byte 196,227,53,74,247,96 // vblendvps %ymm6,%ymm7,%ymm9,%ymm6 + .byte 196,193,20,194,248,1 // vcmpltps %ymm8,%ymm13,%ymm7 + .byte 196,195,77,74,242,112 // vblendvps %ymm7,%ymm10,%ymm6,%ymm6 + .byte 196,193,121,110,248 // vmovd %r8d,%xmm7 + .byte 196,227,121,4,255,0 // vpermilps $0x0,%xmm7,%xmm7 + .byte 196,227,69,24,255,1 // vinsertf128 $0x1,%xmm7,%ymm7,%ymm7 + .byte 197,20,194,239,1 // vcmpltps %ymm7,%ymm13,%ymm13 + .byte 196,65,4,89,251 // vmulps %ymm11,%ymm15,%ymm15 + .byte 196,65,52,88,255 // vaddps %ymm15,%ymm9,%ymm15 + .byte 196,195,77,74,247,208 // vblendvps %ymm13,%ymm15,%ymm6,%ymm6 + .byte 196,99,125,8,233,1 // vroundps $0x1,%ymm1,%ymm13 + .byte 196,65,116,92,237 // vsubps %ymm13,%ymm1,%ymm13 + .byte 196,65,20,89,254 // vmulps %ymm14,%ymm13,%ymm15 + .byte 196,193,124,92,239 // vsubps %ymm15,%ymm0,%ymm5 + .byte 197,164,89,237 // vmulps %ymm5,%ymm11,%ymm5 + .byte 197,180,88,237 // vaddps %ymm5,%ymm9,%ymm5 + .byte 196,193,20,194,228,1 // vcmpltps %ymm12,%ymm13,%ymm4 + .byte 196,227,53,74,229,64 // vblendvps %ymm4,%ymm5,%ymm9,%ymm4 + .byte 196,193,20,194,232,1 // vcmpltps %ymm8,%ymm13,%ymm5 + .byte 196,195,93,74,226,80 // vblendvps %ymm5,%ymm10,%ymm4,%ymm4 + .byte 197,148,194,239,1 // vcmpltps %ymm7,%ymm13,%ymm5 + .byte 196,65,36,89,239 // vmulps %ymm15,%ymm11,%ymm13 + .byte 196,65,52,88,237 // vaddps %ymm13,%ymm9,%ymm13 + .byte 196,195,93,74,229,80 // vblendvps %ymm5,%ymm13,%ymm4,%ymm4 + .byte 196,226,125,24,45,205,68,0,0 // vbroadcastss 0x44cd(%rip),%ymm5 # 5460 <_sk_callback_avx+0x1d6> + .byte 197,244,88,205 // vaddps %ymm5,%ymm1,%ymm1 + .byte 196,227,125,8,233,1 // vroundps $0x1,%ymm1,%ymm5 + .byte 197,244,92,205 // vsubps %ymm5,%ymm1,%ymm1 + .byte 196,193,116,89,238 // vmulps %ymm14,%ymm1,%ymm5 + .byte 196,65,116,194,228,1 // vcmpltps %ymm12,%ymm1,%ymm12 + .byte 197,252,92,197 // vsubps %ymm5,%ymm0,%ymm0 + .byte 197,164,89,192 // vmulps %ymm0,%ymm11,%ymm0 + .byte 197,180,88,192 // vaddps %ymm0,%ymm9,%ymm0 + .byte 196,227,53,74,192,192 // vblendvps %ymm12,%ymm0,%ymm9,%ymm0 + .byte 196,65,116,194,192,1 // vcmpltps %ymm8,%ymm1,%ymm8 + .byte 196,195,125,74,194,128 // vblendvps %ymm8,%ymm10,%ymm0,%ymm0 + .byte 197,244,194,207,1 // vcmpltps %ymm7,%ymm1,%ymm1 + .byte 197,164,89,237 // vmulps %ymm5,%ymm11,%ymm5 + .byte 197,180,88,237 // vaddps %ymm5,%ymm9,%ymm5 + .byte 196,227,125,74,237,16 // vblendvps %ymm1,%ymm5,%ymm0,%ymm5 .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 - .byte 197,252,194,92,36,160,0 // vcmpeqps -0x60(%rsp),%ymm0,%ymm3 - .byte 197,252,16,68,36,128 // vmovups -0x80(%rsp),%ymm0 - .byte 196,227,125,74,197,48 // vblendvps %ymm3,%ymm5,%ymm0,%ymm0 - .byte 196,227,77,74,205,48 // vblendvps %ymm3,%ymm5,%ymm6,%ymm1 - .byte 196,227,109,74,213,48 // vblendvps %ymm3,%ymm5,%ymm2,%ymm2 + .byte 197,228,194,216,0 // vcmpeqps %ymm0,%ymm3,%ymm3 + .byte 196,227,77,74,194,48 // vblendvps %ymm3,%ymm2,%ymm6,%ymm0 + .byte 196,227,93,74,202,48 // vblendvps %ymm3,%ymm2,%ymm4,%ymm1 + .byte 196,227,85,74,210,48 // vblendvps %ymm3,%ymm2,%ymm5,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 197,252,16,92,36,192 // vmovups -0x40(%rsp),%ymm3 - .byte 197,252,16,100,36,224 // vmovups -0x20(%rsp),%ymm4 - .byte 197,252,16,44,36 // vmovups (%rsp),%ymm5 - .byte 197,252,16,116,36,32 // vmovups 0x20(%rsp),%ymm6 - .byte 197,252,16,124,36,64 // vmovups 0x40(%rsp),%ymm7 - .byte 72,131,196,120 // add $0x78,%rsp + .byte 197,252,16,92,36,128 // vmovups -0x80(%rsp),%ymm3 + .byte 197,252,16,100,36,160 // vmovups -0x60(%rsp),%ymm4 + .byte 197,252,16,108,36,192 // vmovups -0x40(%rsp),%ymm5 + .byte 197,252,16,116,36,224 // vmovups -0x20(%rsp),%ymm6 + .byte 197,252,16,60,36 // vmovups (%rsp),%ymm7 + .byte 72,131,196,56 // add $0x38,%rsp .byte 255,224 // jmpq *%rax HIDDEN _sk_scale_1_float_avx @@ -12974,14 +12914,14 @@ _sk_scale_u8_avx: .byte 72,139,0 // mov (%rax),%rax .byte 72,1,248 // add %rdi,%rax .byte 77,133,192 // test %r8,%r8 - .byte 117,68 // jne 1114 <_sk_scale_u8_avx+0x54> + .byte 117,68 // jne 108c <_sk_scale_u8_avx+0x54> .byte 197,122,126,0 // vmovq (%rax),%xmm8 .byte 196,66,121,49,200 // vpmovzxbd %xmm8,%xmm9 .byte 196,67,121,4,192,229 // vpermilps $0xe5,%xmm8,%xmm8 .byte 196,66,121,49,192 // vpmovzxbd %xmm8,%xmm8 .byte 196,67,53,24,192,1 // vinsertf128 $0x1,%xmm8,%ymm9,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,252,67,0,0 // vbroadcastss 0x43fc(%rip),%ymm9 # 54f4 <_sk_callback_avx+0x1e2> + .byte 196,98,125,24,13,244,67,0,0 // vbroadcastss 0x43f4(%rip),%ymm9 # 5464 <_sk_callback_avx+0x1da> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 @@ -12999,9 +12939,9 @@ _sk_scale_u8_avx: .byte 77,9,217 // or %r11,%r9 .byte 72,131,193,8 // add $0x8,%rcx .byte 73,255,202 // dec %r10 - .byte 117,234 // jne 111c <_sk_scale_u8_avx+0x5c> + .byte 117,234 // jne 1094 <_sk_scale_u8_avx+0x5c> .byte 196,65,249,110,193 // vmovq %r9,%xmm8 - .byte 235,155 // jmp 10d4 <_sk_scale_u8_avx+0x14> + .byte 235,155 // jmp 104c <_sk_scale_u8_avx+0x14> HIDDEN _sk_lerp_1_float_avx .globl _sk_lerp_1_float_avx @@ -13033,14 +12973,14 @@ _sk_lerp_u8_avx: .byte 72,139,0 // mov (%rax),%rax .byte 72,1,248 // add %rdi,%rax .byte 77,133,192 // test %r8,%r8 - .byte 117,104 // jne 11f0 <_sk_lerp_u8_avx+0x78> + .byte 117,104 // jne 1168 <_sk_lerp_u8_avx+0x78> .byte 197,122,126,0 // vmovq (%rax),%xmm8 .byte 196,66,121,49,200 // vpmovzxbd %xmm8,%xmm9 .byte 196,67,121,4,192,229 // vpermilps $0xe5,%xmm8,%xmm8 .byte 196,66,121,49,192 // vpmovzxbd %xmm8,%xmm8 .byte 196,67,53,24,192,1 // vinsertf128 $0x1,%xmm8,%ymm9,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,72,67,0,0 // vbroadcastss 0x4348(%rip),%ymm9 # 54f8 <_sk_callback_avx+0x1e6> + .byte 196,98,125,24,13,64,67,0,0 // vbroadcastss 0x4340(%rip),%ymm9 # 5468 <_sk_callback_avx+0x1de> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 .byte 197,252,92,196 // vsubps %ymm4,%ymm0,%ymm0 .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 @@ -13066,9 +13006,9 @@ _sk_lerp_u8_avx: .byte 77,9,217 // or %r11,%r9 .byte 72,131,193,8 // add $0x8,%rcx .byte 73,255,202 // dec %r10 - .byte 117,234 // jne 11f8 <_sk_lerp_u8_avx+0x80> + .byte 117,234 // jne 1170 <_sk_lerp_u8_avx+0x80> .byte 196,65,249,110,193 // vmovq %r9,%xmm8 - .byte 233,116,255,255,255 // jmpq 118c <_sk_lerp_u8_avx+0x14> + .byte 233,116,255,255,255 // jmpq 1104 <_sk_lerp_u8_avx+0x14> HIDDEN _sk_lerp_565_avx .globl _sk_lerp_565_avx @@ -13077,26 +13017,26 @@ _sk_lerp_565_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,174,0,0,0 // jne 12d4 <_sk_lerp_565_avx+0xbc> + .byte 15,133,174,0,0,0 // jne 124c <_sk_lerp_565_avx+0xbc> .byte 196,65,122,111,4,122 // vmovdqu (%r10,%rdi,2),%xmm8 .byte 197,225,239,219 // vpxor %xmm3,%xmm3,%xmm3 .byte 197,185,105,219 // vpunpckhwd %xmm3,%xmm8,%xmm3 .byte 196,66,121,51,192 // vpmovzxwd %xmm8,%xmm8 .byte 196,227,61,24,219,1 // vinsertf128 $0x1,%xmm3,%ymm8,%ymm3 - .byte 196,98,125,24,5,180,66,0,0 // vbroadcastss 0x42b4(%rip),%ymm8 # 54fc <_sk_callback_avx+0x1ea> + .byte 196,98,125,24,5,172,66,0,0 // vbroadcastss 0x42ac(%rip),%ymm8 # 546c <_sk_callback_avx+0x1e2> .byte 196,65,100,84,192 // vandps %ymm8,%ymm3,%ymm8 .byte 196,65,124,91,192 // vcvtdq2ps %ymm8,%ymm8 - .byte 196,98,125,24,13,165,66,0,0 // vbroadcastss 0x42a5(%rip),%ymm9 # 5500 <_sk_callback_avx+0x1ee> + .byte 196,98,125,24,13,157,66,0,0 // vbroadcastss 0x429d(%rip),%ymm9 # 5470 <_sk_callback_avx+0x1e6> .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 - .byte 196,98,125,24,13,155,66,0,0 // vbroadcastss 0x429b(%rip),%ymm9 # 5504 <_sk_callback_avx+0x1f2> + .byte 196,98,125,24,13,147,66,0,0 // vbroadcastss 0x4293(%rip),%ymm9 # 5474 <_sk_callback_avx+0x1ea> .byte 196,65,100,84,201 // vandps %ymm9,%ymm3,%ymm9 .byte 196,65,124,91,201 // vcvtdq2ps %ymm9,%ymm9 - .byte 196,98,125,24,21,140,66,0,0 // vbroadcastss 0x428c(%rip),%ymm10 # 5508 <_sk_callback_avx+0x1f6> + .byte 196,98,125,24,21,132,66,0,0 // vbroadcastss 0x4284(%rip),%ymm10 # 5478 <_sk_callback_avx+0x1ee> .byte 196,65,52,89,202 // vmulps %ymm10,%ymm9,%ymm9 - .byte 196,98,125,24,21,130,66,0,0 // vbroadcastss 0x4282(%rip),%ymm10 # 550c <_sk_callback_avx+0x1fa> + .byte 196,98,125,24,21,122,66,0,0 // vbroadcastss 0x427a(%rip),%ymm10 # 547c <_sk_callback_avx+0x1f2> .byte 196,193,100,84,218 // vandps %ymm10,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,21,116,66,0,0 // vbroadcastss 0x4274(%rip),%ymm10 # 5510 <_sk_callback_avx+0x1fe> + .byte 196,98,125,24,21,108,66,0,0 // vbroadcastss 0x426c(%rip),%ymm10 # 5480 <_sk_callback_avx+0x1f6> .byte 196,193,100,89,218 // vmulps %ymm10,%ymm3,%ymm3 .byte 197,252,92,196 // vsubps %ymm4,%ymm0,%ymm0 .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 @@ -13108,16 +13048,16 @@ _sk_lerp_565_avx: .byte 197,236,89,211 // vmulps %ymm3,%ymm2,%ymm2 .byte 197,236,88,214 // vaddps %ymm6,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,66,66,0,0 // vbroadcastss 0x4242(%rip),%ymm3 # 5514 <_sk_callback_avx+0x202> + .byte 196,226,125,24,29,58,66,0,0 // vbroadcastss 0x423a(%rip),%ymm3 # 5484 <_sk_callback_avx+0x1fa> .byte 255,224 // jmpq *%rax .byte 65,137,200 // mov %ecx,%r8d .byte 65,128,224,7 // and $0x7,%r8b .byte 196,65,57,239,192 // vpxor %xmm8,%xmm8,%xmm8 .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 15,135,63,255,255,255 // ja 122c <_sk_lerp_565_avx+0x14> + .byte 15,135,63,255,255,255 // ja 11a4 <_sk_lerp_565_avx+0x14> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,76,0,0,0 // lea 0x4c(%rip),%r9 # 1344 <_sk_lerp_565_avx+0x12c> + .byte 76,141,13,76,0,0,0 // lea 0x4c(%rip),%r9 # 12bc <_sk_lerp_565_avx+0x12c> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -13129,13 +13069,13 @@ _sk_lerp_565_avx: .byte 196,65,57,196,68,122,4,2 // vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm8,%xmm8 .byte 196,65,57,196,68,122,2,1 // vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm8,%xmm8 .byte 196,65,57,196,4,122,0 // vpinsrw $0x0,(%r10,%rdi,2),%xmm8,%xmm8 - .byte 233,235,254,255,255 // jmpq 122c <_sk_lerp_565_avx+0x14> + .byte 233,235,254,255,255 // jmpq 11a4 <_sk_lerp_565_avx+0x14> .byte 15,31,0 // nopl (%rax) .byte 241 // icebp .byte 255 // (bad) .byte 255 // (bad) .byte 255 // (bad) - .byte 233,255,255,255,225 // jmpq ffffffffe200134c <_sk_callback_avx+0xffffffffe1ffc03a> + .byte 233,255,255,255,225 // jmpq ffffffffe20012c4 <_sk_callback_avx+0xffffffffe1ffc03a> .byte 255 // (bad) .byte 255 // (bad) .byte 255 // (bad) @@ -13160,7 +13100,7 @@ _sk_load_tables_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,0 // mov (%rax),%r8 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,26,2,0,0 // jne 1588 <_sk_load_tables_avx+0x228> + .byte 15,133,26,2,0,0 // jne 1500 <_sk_load_tables_avx+0x228> .byte 196,65,124,16,4,184 // vmovups (%r8,%rdi,4),%ymm8 .byte 85 // push %rbp .byte 65,87 // push %r15 @@ -13168,7 +13108,7 @@ _sk_load_tables_avx: .byte 65,85 // push %r13 .byte 65,84 // push %r12 .byte 83 // push %rbx - .byte 197,124,40,13,90,68,0,0 // vmovaps 0x445a(%rip),%ymm9 # 57e0 <_sk_callback_avx+0x4ce> + .byte 197,124,40,13,66,68,0,0 // vmovaps 0x4442(%rip),%ymm9 # 5740 <_sk_callback_avx+0x4b6> .byte 196,193,60,84,193 // vandps %ymm9,%ymm8,%ymm0 .byte 196,193,249,126,193 // vmovq %xmm0,%r9 .byte 69,137,203 // mov %r9d,%r11d @@ -13260,7 +13200,7 @@ _sk_load_tables_avx: .byte 196,193,97,114,210,24 // vpsrld $0x18,%xmm10,%xmm3 .byte 196,227,61,24,219,1 // vinsertf128 $0x1,%xmm3,%ymm8,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,163,63,0,0 // vbroadcastss 0x3fa3(%rip),%ymm8 # 5518 <_sk_callback_avx+0x206> + .byte 196,98,125,24,5,155,63,0,0 // vbroadcastss 0x3f9b(%rip),%ymm8 # 5488 <_sk_callback_avx+0x1fe> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 91 // pop %rbx @@ -13275,9 +13215,9 @@ _sk_load_tables_avx: .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 65,254,201 // dec %r9b .byte 65,128,249,6 // cmp $0x6,%r9b - .byte 15,135,211,253,255,255 // ja 1374 <_sk_load_tables_avx+0x14> + .byte 15,135,211,253,255,255 // ja 12ec <_sk_load_tables_avx+0x14> .byte 69,15,182,201 // movzbl %r9b,%r9d - .byte 76,141,21,140,0,0,0 // lea 0x8c(%rip),%r10 # 1638 <_sk_load_tables_avx+0x2d8> + .byte 76,141,21,140,0,0,0 // lea 0x8c(%rip),%r10 # 15b0 <_sk_load_tables_avx+0x2d8> .byte 79,99,12,138 // movslq (%r10,%r9,4),%r9 .byte 77,1,209 // add %r10,%r9 .byte 65,255,225 // jmpq *%r9 @@ -13300,7 +13240,7 @@ _sk_load_tables_avx: .byte 196,99,61,12,192,15 // vblendps $0xf,%ymm0,%ymm8,%ymm8 .byte 196,195,57,34,4,184,0 // vpinsrd $0x0,(%r8,%rdi,4),%xmm8,%xmm0 .byte 196,99,61,12,192,15 // vblendps $0xf,%ymm0,%ymm8,%ymm8 - .byte 233,62,253,255,255 // jmpq 1374 <_sk_load_tables_avx+0x14> + .byte 233,62,253,255,255 // jmpq 12ec <_sk_load_tables_avx+0x14> .byte 102,144 // xchg %ax,%ax .byte 236 // in (%dx),%al .byte 255 // (bad) @@ -13318,7 +13258,7 @@ _sk_load_tables_avx: .byte 255 // (bad) .byte 255 // (bad) .byte 255 // (bad) - .byte 126,255 // jle 1651 <_sk_load_tables_avx+0x2f1> + .byte 126,255 // jle 15c9 <_sk_load_tables_avx+0x2f1> .byte 255 // (bad) .byte 255 // .byte 0xff @@ -13330,7 +13270,7 @@ _sk_load_tables_u16_be_avx: .byte 76,139,0 // mov (%rax),%r8 .byte 76,141,12,189,0,0,0,0 // lea 0x0(,%rdi,4),%r9 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,113,2,0,0 // jne 18db <_sk_load_tables_u16_be_avx+0x287> + .byte 15,133,113,2,0,0 // jne 1853 <_sk_load_tables_u16_be_avx+0x287> .byte 196,1,121,16,4,72 // vmovupd (%r8,%r9,2),%xmm8 .byte 196,129,121,16,84,72,16 // vmovupd 0x10(%r8,%r9,2),%xmm2 .byte 196,129,121,16,92,72,32 // vmovupd 0x20(%r8,%r9,2),%xmm3 @@ -13352,7 +13292,7 @@ _sk_load_tables_u16_be_avx: .byte 197,177,108,208 // vpunpcklqdq %xmm0,%xmm9,%xmm2 .byte 197,177,109,200 // vpunpckhqdq %xmm0,%xmm9,%xmm1 .byte 196,65,57,108,212 // vpunpcklqdq %xmm12,%xmm8,%xmm10 - .byte 197,121,111,29,154,65,0,0 // vmovdqa 0x419a(%rip),%xmm11 # 5860 <_sk_callback_avx+0x54e> + .byte 197,121,111,29,130,65,0,0 // vmovdqa 0x4182(%rip),%xmm11 # 57c0 <_sk_callback_avx+0x536> .byte 196,193,105,219,195 // vpand %xmm11,%xmm2,%xmm0 .byte 196,65,49,239,201 // vpxor %xmm9,%xmm9,%xmm9 .byte 196,193,121,105,209 // vpunpckhwd %xmm9,%xmm0,%xmm2 @@ -13451,7 +13391,7 @@ _sk_load_tables_u16_be_avx: .byte 196,226,121,51,219 // vpmovzxwd %xmm3,%xmm3 .byte 196,195,101,24,216,1 // vinsertf128 $0x1,%xmm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,84,60,0,0 // vbroadcastss 0x3c54(%rip),%ymm8 # 551c <_sk_callback_avx+0x20a> + .byte 196,98,125,24,5,76,60,0,0 // vbroadcastss 0x3c4c(%rip),%ymm8 # 548c <_sk_callback_avx+0x202> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 91 // pop %rbx @@ -13464,29 +13404,29 @@ _sk_load_tables_u16_be_avx: .byte 196,1,123,16,4,72 // vmovsd (%r8,%r9,2),%xmm8 .byte 196,65,49,239,201 // vpxor %xmm9,%xmm9,%xmm9 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,85 // je 1941 <_sk_load_tables_u16_be_avx+0x2ed> + .byte 116,85 // je 18b9 <_sk_load_tables_u16_be_avx+0x2ed> .byte 196,1,57,22,68,72,8 // vmovhpd 0x8(%r8,%r9,2),%xmm8,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,72 // jb 1941 <_sk_load_tables_u16_be_avx+0x2ed> + .byte 114,72 // jb 18b9 <_sk_load_tables_u16_be_avx+0x2ed> .byte 196,129,123,16,84,72,16 // vmovsd 0x10(%r8,%r9,2),%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 116,72 // je 194e <_sk_load_tables_u16_be_avx+0x2fa> + .byte 116,72 // je 18c6 <_sk_load_tables_u16_be_avx+0x2fa> .byte 196,129,105,22,84,72,24 // vmovhpd 0x18(%r8,%r9,2),%xmm2,%xmm2 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,59 // jb 194e <_sk_load_tables_u16_be_avx+0x2fa> + .byte 114,59 // jb 18c6 <_sk_load_tables_u16_be_avx+0x2fa> .byte 196,129,123,16,92,72,32 // vmovsd 0x20(%r8,%r9,2),%xmm3 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 15,132,97,253,255,255 // je 1685 <_sk_load_tables_u16_be_avx+0x31> + .byte 15,132,97,253,255,255 // je 15fd <_sk_load_tables_u16_be_avx+0x31> .byte 196,129,97,22,92,72,40 // vmovhpd 0x28(%r8,%r9,2),%xmm3,%xmm3 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 15,130,80,253,255,255 // jb 1685 <_sk_load_tables_u16_be_avx+0x31> + .byte 15,130,80,253,255,255 // jb 15fd <_sk_load_tables_u16_be_avx+0x31> .byte 196,1,122,126,76,72,48 // vmovq 0x30(%r8,%r9,2),%xmm9 - .byte 233,68,253,255,255 // jmpq 1685 <_sk_load_tables_u16_be_avx+0x31> + .byte 233,68,253,255,255 // jmpq 15fd <_sk_load_tables_u16_be_avx+0x31> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 .byte 197,233,87,210 // vxorpd %xmm2,%xmm2,%xmm2 - .byte 233,55,253,255,255 // jmpq 1685 <_sk_load_tables_u16_be_avx+0x31> + .byte 233,55,253,255,255 // jmpq 15fd <_sk_load_tables_u16_be_avx+0x31> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 - .byte 233,46,253,255,255 // jmpq 1685 <_sk_load_tables_u16_be_avx+0x31> + .byte 233,46,253,255,255 // jmpq 15fd <_sk_load_tables_u16_be_avx+0x31> HIDDEN _sk_load_tables_rgb_u16_be_avx .globl _sk_load_tables_rgb_u16_be_avx @@ -13496,7 +13436,7 @@ _sk_load_tables_rgb_u16_be_avx: .byte 76,139,0 // mov (%rax),%r8 .byte 76,141,12,127 // lea (%rdi,%rdi,2),%r9 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,93,2,0,0 // jne 1bc6 <_sk_load_tables_rgb_u16_be_avx+0x26f> + .byte 15,133,93,2,0,0 // jne 1b3e <_sk_load_tables_rgb_u16_be_avx+0x26f> .byte 196,129,122,111,4,72 // vmovdqu (%r8,%r9,2),%xmm0 .byte 196,129,122,111,84,72,12 // vmovdqu 0xc(%r8,%r9,2),%xmm2 .byte 196,129,122,111,76,72,24 // vmovdqu 0x18(%r8,%r9,2),%xmm1 @@ -13523,7 +13463,7 @@ _sk_load_tables_rgb_u16_be_avx: .byte 197,185,108,202 // vpunpcklqdq %xmm2,%xmm8,%xmm1 .byte 197,185,109,210 // vpunpckhqdq %xmm2,%xmm8,%xmm2 .byte 197,121,108,195 // vpunpcklqdq %xmm3,%xmm0,%xmm8 - .byte 197,121,111,13,147,62,0,0 // vmovdqa 0x3e93(%rip),%xmm9 # 5870 <_sk_callback_avx+0x55e> + .byte 197,121,111,13,123,62,0,0 // vmovdqa 0x3e7b(%rip),%xmm9 # 57d0 <_sk_callback_avx+0x546> .byte 196,193,113,219,193 // vpand %xmm9,%xmm1,%xmm0 .byte 196,65,41,239,210 // vpxor %xmm10,%xmm10,%xmm10 .byte 196,193,121,105,202 // vpunpckhwd %xmm10,%xmm0,%xmm1 @@ -13615,7 +13555,7 @@ _sk_load_tables_rgb_u16_be_avx: .byte 196,227,105,33,211,48 // vinsertps $0x30,%xmm3,%xmm2,%xmm2 .byte 196,195,109,24,208,1 // vinsertf128 $0x1,%xmm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,102,57,0,0 // vbroadcastss 0x3966(%rip),%ymm3 # 5520 <_sk_callback_avx+0x20e> + .byte 196,226,125,24,29,94,57,0,0 // vbroadcastss 0x395e(%rip),%ymm3 # 5490 <_sk_callback_avx+0x206> .byte 91 // pop %rbx .byte 65,92 // pop %r12 .byte 65,93 // pop %r13 @@ -13626,36 +13566,36 @@ _sk_load_tables_rgb_u16_be_avx: .byte 196,129,121,110,4,72 // vmovd (%r8,%r9,2),%xmm0 .byte 196,129,121,196,68,72,4,2 // vpinsrw $0x2,0x4(%r8,%r9,2),%xmm0,%xmm0 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 117,5 // jne 1bdf <_sk_load_tables_rgb_u16_be_avx+0x288> - .byte 233,190,253,255,255 // jmpq 199d <_sk_load_tables_rgb_u16_be_avx+0x46> + .byte 117,5 // jne 1b57 <_sk_load_tables_rgb_u16_be_avx+0x288> + .byte 233,190,253,255,255 // jmpq 1915 <_sk_load_tables_rgb_u16_be_avx+0x46> .byte 196,129,121,110,76,72,6 // vmovd 0x6(%r8,%r9,2),%xmm1 .byte 196,1,113,196,68,72,10,2 // vpinsrw $0x2,0xa(%r8,%r9,2),%xmm1,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,26 // jb 1c0e <_sk_load_tables_rgb_u16_be_avx+0x2b7> + .byte 114,26 // jb 1b86 <_sk_load_tables_rgb_u16_be_avx+0x2b7> .byte 196,129,121,110,76,72,12 // vmovd 0xc(%r8,%r9,2),%xmm1 .byte 196,129,113,196,84,72,16,2 // vpinsrw $0x2,0x10(%r8,%r9,2),%xmm1,%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 117,10 // jne 1c13 <_sk_load_tables_rgb_u16_be_avx+0x2bc> - .byte 233,143,253,255,255 // jmpq 199d <_sk_load_tables_rgb_u16_be_avx+0x46> - .byte 233,138,253,255,255 // jmpq 199d <_sk_load_tables_rgb_u16_be_avx+0x46> + .byte 117,10 // jne 1b8b <_sk_load_tables_rgb_u16_be_avx+0x2bc> + .byte 233,143,253,255,255 // jmpq 1915 <_sk_load_tables_rgb_u16_be_avx+0x46> + .byte 233,138,253,255,255 // jmpq 1915 <_sk_load_tables_rgb_u16_be_avx+0x46> .byte 196,129,121,110,76,72,18 // vmovd 0x12(%r8,%r9,2),%xmm1 .byte 196,1,113,196,76,72,22,2 // vpinsrw $0x2,0x16(%r8,%r9,2),%xmm1,%xmm9 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,26 // jb 1c42 <_sk_load_tables_rgb_u16_be_avx+0x2eb> + .byte 114,26 // jb 1bba <_sk_load_tables_rgb_u16_be_avx+0x2eb> .byte 196,129,121,110,76,72,24 // vmovd 0x18(%r8,%r9,2),%xmm1 .byte 196,129,113,196,76,72,28,2 // vpinsrw $0x2,0x1c(%r8,%r9,2),%xmm1,%xmm1 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 117,10 // jne 1c47 <_sk_load_tables_rgb_u16_be_avx+0x2f0> - .byte 233,91,253,255,255 // jmpq 199d <_sk_load_tables_rgb_u16_be_avx+0x46> - .byte 233,86,253,255,255 // jmpq 199d <_sk_load_tables_rgb_u16_be_avx+0x46> + .byte 117,10 // jne 1bbf <_sk_load_tables_rgb_u16_be_avx+0x2f0> + .byte 233,91,253,255,255 // jmpq 1915 <_sk_load_tables_rgb_u16_be_avx+0x46> + .byte 233,86,253,255,255 // jmpq 1915 <_sk_load_tables_rgb_u16_be_avx+0x46> .byte 196,129,121,110,92,72,30 // vmovd 0x1e(%r8,%r9,2),%xmm3 .byte 196,1,97,196,92,72,34,2 // vpinsrw $0x2,0x22(%r8,%r9,2),%xmm3,%xmm11 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,20 // jb 1c70 <_sk_load_tables_rgb_u16_be_avx+0x319> + .byte 114,20 // jb 1be8 <_sk_load_tables_rgb_u16_be_avx+0x319> .byte 196,129,121,110,92,72,36 // vmovd 0x24(%r8,%r9,2),%xmm3 .byte 196,129,97,196,92,72,40,2 // vpinsrw $0x2,0x28(%r8,%r9,2),%xmm3,%xmm3 - .byte 233,45,253,255,255 // jmpq 199d <_sk_load_tables_rgb_u16_be_avx+0x46> - .byte 233,40,253,255,255 // jmpq 199d <_sk_load_tables_rgb_u16_be_avx+0x46> + .byte 233,45,253,255,255 // jmpq 1915 <_sk_load_tables_rgb_u16_be_avx+0x46> + .byte 233,40,253,255,255 // jmpq 1915 <_sk_load_tables_rgb_u16_be_avx+0x46> HIDDEN _sk_byte_tables_avx .globl _sk_byte_tables_avx @@ -13668,7 +13608,7 @@ _sk_byte_tables_avx: .byte 65,84 // push %r12 .byte 83 // push %rbx .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,154,56,0,0 // vbroadcastss 0x389a(%rip),%ymm8 # 5524 <_sk_callback_avx+0x212> + .byte 196,98,125,24,5,146,56,0,0 // vbroadcastss 0x3892(%rip),%ymm8 # 5494 <_sk_callback_avx+0x20a> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 197,253,91,192 // vcvtps2dq %ymm0,%ymm0 .byte 196,195,249,22,192,1 // vpextrq $0x1,%xmm0,%r8 @@ -13705,7 +13645,7 @@ _sk_byte_tables_avx: .byte 196,226,121,49,192 // vpmovzxbd %xmm0,%xmm0 .byte 196,227,53,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm9,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,232,55,0,0 // vbroadcastss 0x37e8(%rip),%ymm9 # 5528 <_sk_callback_avx+0x216> + .byte 196,98,125,24,13,224,55,0,0 // vbroadcastss 0x37e0(%rip),%ymm9 # 5498 <_sk_callback_avx+0x20e> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 @@ -13867,7 +13807,7 @@ _sk_byte_tables_rgb_avx: .byte 196,226,121,49,192 // vpmovzxbd %xmm0,%xmm0 .byte 196,227,53,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm9,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,14,53,0,0 // vbroadcastss 0x350e(%rip),%ymm9 # 552c <_sk_callback_avx+0x21a> + .byte 196,98,125,24,13,6,53,0,0 // vbroadcastss 0x3506(%rip),%ymm9 # 549c <_sk_callback_avx+0x212> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 197,188,89,201 // vmulps %ymm1,%ymm8,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 @@ -14164,36 +14104,36 @@ _sk_parametric_r_avx: .byte 196,193,124,88,195 // vaddps %ymm11,%ymm0,%ymm0 .byte 196,98,125,24,16 // vbroadcastss (%rax),%ymm10 .byte 197,124,91,216 // vcvtdq2ps %ymm0,%ymm11 - .byte 196,98,125,24,37,108,48,0,0 // vbroadcastss 0x306c(%rip),%ymm12 # 5530 <_sk_callback_avx+0x21e> + .byte 196,98,125,24,37,100,48,0,0 // vbroadcastss 0x3064(%rip),%ymm12 # 54a0 <_sk_callback_avx+0x216> .byte 196,65,36,89,220 // vmulps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,98,48,0,0 // vbroadcastss 0x3062(%rip),%ymm12 # 5534 <_sk_callback_avx+0x222> + .byte 196,98,125,24,37,90,48,0,0 // vbroadcastss 0x305a(%rip),%ymm12 # 54a4 <_sk_callback_avx+0x21a> .byte 196,193,124,84,196 // vandps %ymm12,%ymm0,%ymm0 - .byte 196,98,125,24,37,88,48,0,0 // vbroadcastss 0x3058(%rip),%ymm12 # 5538 <_sk_callback_avx+0x226> + .byte 196,98,125,24,37,80,48,0,0 // vbroadcastss 0x3050(%rip),%ymm12 # 54a8 <_sk_callback_avx+0x21e> .byte 196,193,124,86,196 // vorps %ymm12,%ymm0,%ymm0 - .byte 196,98,125,24,37,78,48,0,0 // vbroadcastss 0x304e(%rip),%ymm12 # 553c <_sk_callback_avx+0x22a> + .byte 196,98,125,24,37,70,48,0,0 // vbroadcastss 0x3046(%rip),%ymm12 # 54ac <_sk_callback_avx+0x222> .byte 196,65,36,88,220 // vaddps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,68,48,0,0 // vbroadcastss 0x3044(%rip),%ymm12 # 5540 <_sk_callback_avx+0x22e> + .byte 196,98,125,24,37,60,48,0,0 // vbroadcastss 0x303c(%rip),%ymm12 # 54b0 <_sk_callback_avx+0x226> .byte 196,65,124,89,228 // vmulps %ymm12,%ymm0,%ymm12 .byte 196,65,36,92,220 // vsubps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,53,48,0,0 // vbroadcastss 0x3035(%rip),%ymm12 # 5544 <_sk_callback_avx+0x232> + .byte 196,98,125,24,37,45,48,0,0 // vbroadcastss 0x302d(%rip),%ymm12 # 54b4 <_sk_callback_avx+0x22a> .byte 196,193,124,88,196 // vaddps %ymm12,%ymm0,%ymm0 - .byte 196,98,125,24,37,43,48,0,0 // vbroadcastss 0x302b(%rip),%ymm12 # 5548 <_sk_callback_avx+0x236> + .byte 196,98,125,24,37,35,48,0,0 // vbroadcastss 0x3023(%rip),%ymm12 # 54b8 <_sk_callback_avx+0x22e> .byte 197,156,94,192 // vdivps %ymm0,%ymm12,%ymm0 .byte 197,164,92,192 // vsubps %ymm0,%ymm11,%ymm0 .byte 197,172,89,192 // vmulps %ymm0,%ymm10,%ymm0 .byte 196,99,125,8,208,1 // vroundps $0x1,%ymm0,%ymm10 .byte 196,65,124,92,210 // vsubps %ymm10,%ymm0,%ymm10 - .byte 196,98,125,24,29,15,48,0,0 // vbroadcastss 0x300f(%rip),%ymm11 # 554c <_sk_callback_avx+0x23a> + .byte 196,98,125,24,29,7,48,0,0 // vbroadcastss 0x3007(%rip),%ymm11 # 54bc <_sk_callback_avx+0x232> .byte 196,193,124,88,195 // vaddps %ymm11,%ymm0,%ymm0 - .byte 196,98,125,24,29,5,48,0,0 // vbroadcastss 0x3005(%rip),%ymm11 # 5550 <_sk_callback_avx+0x23e> + .byte 196,98,125,24,29,253,47,0,0 // vbroadcastss 0x2ffd(%rip),%ymm11 # 54c0 <_sk_callback_avx+0x236> .byte 196,65,44,89,219 // vmulps %ymm11,%ymm10,%ymm11 .byte 196,193,124,92,195 // vsubps %ymm11,%ymm0,%ymm0 - .byte 196,98,125,24,29,246,47,0,0 // vbroadcastss 0x2ff6(%rip),%ymm11 # 5554 <_sk_callback_avx+0x242> + .byte 196,98,125,24,29,238,47,0,0 // vbroadcastss 0x2fee(%rip),%ymm11 # 54c4 <_sk_callback_avx+0x23a> .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 - .byte 196,98,125,24,29,236,47,0,0 // vbroadcastss 0x2fec(%rip),%ymm11 # 5558 <_sk_callback_avx+0x246> + .byte 196,98,125,24,29,228,47,0,0 // vbroadcastss 0x2fe4(%rip),%ymm11 # 54c8 <_sk_callback_avx+0x23e> .byte 196,65,36,94,210 // vdivps %ymm10,%ymm11,%ymm10 .byte 196,193,124,88,194 // vaddps %ymm10,%ymm0,%ymm0 - .byte 196,98,125,24,21,221,47,0,0 // vbroadcastss 0x2fdd(%rip),%ymm10 # 555c <_sk_callback_avx+0x24a> + .byte 196,98,125,24,21,213,47,0,0 // vbroadcastss 0x2fd5(%rip),%ymm10 # 54cc <_sk_callback_avx+0x242> .byte 196,193,124,89,194 // vmulps %ymm10,%ymm0,%ymm0 .byte 197,253,91,192 // vcvtps2dq %ymm0,%ymm0 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -14201,7 +14141,7 @@ _sk_parametric_r_avx: .byte 196,195,125,74,193,128 // vblendvps %ymm8,%ymm9,%ymm0,%ymm0 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,124,95,192 // vmaxps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,180,47,0,0 // vbroadcastss 0x2fb4(%rip),%ymm8 # 5560 <_sk_callback_avx+0x24e> + .byte 196,98,125,24,5,172,47,0,0 // vbroadcastss 0x2fac(%rip),%ymm8 # 54d0 <_sk_callback_avx+0x246> .byte 196,193,124,93,192 // vminps %ymm8,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -14223,36 +14163,36 @@ _sk_parametric_g_avx: .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 .byte 196,98,125,24,16 // vbroadcastss (%rax),%ymm10 .byte 197,124,91,217 // vcvtdq2ps %ymm1,%ymm11 - .byte 196,98,125,24,37,101,47,0,0 // vbroadcastss 0x2f65(%rip),%ymm12 # 5564 <_sk_callback_avx+0x252> + .byte 196,98,125,24,37,93,47,0,0 // vbroadcastss 0x2f5d(%rip),%ymm12 # 54d4 <_sk_callback_avx+0x24a> .byte 196,65,36,89,220 // vmulps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,91,47,0,0 // vbroadcastss 0x2f5b(%rip),%ymm12 # 5568 <_sk_callback_avx+0x256> + .byte 196,98,125,24,37,83,47,0,0 // vbroadcastss 0x2f53(%rip),%ymm12 # 54d8 <_sk_callback_avx+0x24e> .byte 196,193,116,84,204 // vandps %ymm12,%ymm1,%ymm1 - .byte 196,98,125,24,37,81,47,0,0 // vbroadcastss 0x2f51(%rip),%ymm12 # 556c <_sk_callback_avx+0x25a> + .byte 196,98,125,24,37,73,47,0,0 // vbroadcastss 0x2f49(%rip),%ymm12 # 54dc <_sk_callback_avx+0x252> .byte 196,193,116,86,204 // vorps %ymm12,%ymm1,%ymm1 - .byte 196,98,125,24,37,71,47,0,0 // vbroadcastss 0x2f47(%rip),%ymm12 # 5570 <_sk_callback_avx+0x25e> + .byte 196,98,125,24,37,63,47,0,0 // vbroadcastss 0x2f3f(%rip),%ymm12 # 54e0 <_sk_callback_avx+0x256> .byte 196,65,36,88,220 // vaddps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,61,47,0,0 // vbroadcastss 0x2f3d(%rip),%ymm12 # 5574 <_sk_callback_avx+0x262> + .byte 196,98,125,24,37,53,47,0,0 // vbroadcastss 0x2f35(%rip),%ymm12 # 54e4 <_sk_callback_avx+0x25a> .byte 196,65,116,89,228 // vmulps %ymm12,%ymm1,%ymm12 .byte 196,65,36,92,220 // vsubps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,46,47,0,0 // vbroadcastss 0x2f2e(%rip),%ymm12 # 5578 <_sk_callback_avx+0x266> + .byte 196,98,125,24,37,38,47,0,0 // vbroadcastss 0x2f26(%rip),%ymm12 # 54e8 <_sk_callback_avx+0x25e> .byte 196,193,116,88,204 // vaddps %ymm12,%ymm1,%ymm1 - .byte 196,98,125,24,37,36,47,0,0 // vbroadcastss 0x2f24(%rip),%ymm12 # 557c <_sk_callback_avx+0x26a> + .byte 196,98,125,24,37,28,47,0,0 // vbroadcastss 0x2f1c(%rip),%ymm12 # 54ec <_sk_callback_avx+0x262> .byte 197,156,94,201 // vdivps %ymm1,%ymm12,%ymm1 .byte 197,164,92,201 // vsubps %ymm1,%ymm11,%ymm1 .byte 197,172,89,201 // vmulps %ymm1,%ymm10,%ymm1 .byte 196,99,125,8,209,1 // vroundps $0x1,%ymm1,%ymm10 .byte 196,65,116,92,210 // vsubps %ymm10,%ymm1,%ymm10 - .byte 196,98,125,24,29,8,47,0,0 // vbroadcastss 0x2f08(%rip),%ymm11 # 5580 <_sk_callback_avx+0x26e> + .byte 196,98,125,24,29,0,47,0,0 // vbroadcastss 0x2f00(%rip),%ymm11 # 54f0 <_sk_callback_avx+0x266> .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,254,46,0,0 // vbroadcastss 0x2efe(%rip),%ymm11 # 5584 <_sk_callback_avx+0x272> + .byte 196,98,125,24,29,246,46,0,0 // vbroadcastss 0x2ef6(%rip),%ymm11 # 54f4 <_sk_callback_avx+0x26a> .byte 196,65,44,89,219 // vmulps %ymm11,%ymm10,%ymm11 .byte 196,193,116,92,203 // vsubps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,29,239,46,0,0 // vbroadcastss 0x2eef(%rip),%ymm11 # 5588 <_sk_callback_avx+0x276> + .byte 196,98,125,24,29,231,46,0,0 // vbroadcastss 0x2ee7(%rip),%ymm11 # 54f8 <_sk_callback_avx+0x26e> .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 - .byte 196,98,125,24,29,229,46,0,0 // vbroadcastss 0x2ee5(%rip),%ymm11 # 558c <_sk_callback_avx+0x27a> + .byte 196,98,125,24,29,221,46,0,0 // vbroadcastss 0x2edd(%rip),%ymm11 # 54fc <_sk_callback_avx+0x272> .byte 196,65,36,94,210 // vdivps %ymm10,%ymm11,%ymm10 .byte 196,193,116,88,202 // vaddps %ymm10,%ymm1,%ymm1 - .byte 196,98,125,24,21,214,46,0,0 // vbroadcastss 0x2ed6(%rip),%ymm10 # 5590 <_sk_callback_avx+0x27e> + .byte 196,98,125,24,21,206,46,0,0 // vbroadcastss 0x2ece(%rip),%ymm10 # 5500 <_sk_callback_avx+0x276> .byte 196,193,116,89,202 // vmulps %ymm10,%ymm1,%ymm1 .byte 197,253,91,201 // vcvtps2dq %ymm1,%ymm1 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -14260,7 +14200,7 @@ _sk_parametric_g_avx: .byte 196,195,117,74,201,128 // vblendvps %ymm8,%ymm9,%ymm1,%ymm1 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,116,95,200 // vmaxps %ymm8,%ymm1,%ymm1 - .byte 196,98,125,24,5,173,46,0,0 // vbroadcastss 0x2ead(%rip),%ymm8 # 5594 <_sk_callback_avx+0x282> + .byte 196,98,125,24,5,165,46,0,0 // vbroadcastss 0x2ea5(%rip),%ymm8 # 5504 <_sk_callback_avx+0x27a> .byte 196,193,116,93,200 // vminps %ymm8,%ymm1,%ymm1 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -14282,36 +14222,36 @@ _sk_parametric_b_avx: .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 .byte 196,98,125,24,16 // vbroadcastss (%rax),%ymm10 .byte 197,124,91,218 // vcvtdq2ps %ymm2,%ymm11 - .byte 196,98,125,24,37,94,46,0,0 // vbroadcastss 0x2e5e(%rip),%ymm12 # 5598 <_sk_callback_avx+0x286> + .byte 196,98,125,24,37,86,46,0,0 // vbroadcastss 0x2e56(%rip),%ymm12 # 5508 <_sk_callback_avx+0x27e> .byte 196,65,36,89,220 // vmulps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,84,46,0,0 // vbroadcastss 0x2e54(%rip),%ymm12 # 559c <_sk_callback_avx+0x28a> + .byte 196,98,125,24,37,76,46,0,0 // vbroadcastss 0x2e4c(%rip),%ymm12 # 550c <_sk_callback_avx+0x282> .byte 196,193,108,84,212 // vandps %ymm12,%ymm2,%ymm2 - .byte 196,98,125,24,37,74,46,0,0 // vbroadcastss 0x2e4a(%rip),%ymm12 # 55a0 <_sk_callback_avx+0x28e> + .byte 196,98,125,24,37,66,46,0,0 // vbroadcastss 0x2e42(%rip),%ymm12 # 5510 <_sk_callback_avx+0x286> .byte 196,193,108,86,212 // vorps %ymm12,%ymm2,%ymm2 - .byte 196,98,125,24,37,64,46,0,0 // vbroadcastss 0x2e40(%rip),%ymm12 # 55a4 <_sk_callback_avx+0x292> + .byte 196,98,125,24,37,56,46,0,0 // vbroadcastss 0x2e38(%rip),%ymm12 # 5514 <_sk_callback_avx+0x28a> .byte 196,65,36,88,220 // vaddps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,54,46,0,0 // vbroadcastss 0x2e36(%rip),%ymm12 # 55a8 <_sk_callback_avx+0x296> + .byte 196,98,125,24,37,46,46,0,0 // vbroadcastss 0x2e2e(%rip),%ymm12 # 5518 <_sk_callback_avx+0x28e> .byte 196,65,108,89,228 // vmulps %ymm12,%ymm2,%ymm12 .byte 196,65,36,92,220 // vsubps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,39,46,0,0 // vbroadcastss 0x2e27(%rip),%ymm12 # 55ac <_sk_callback_avx+0x29a> + .byte 196,98,125,24,37,31,46,0,0 // vbroadcastss 0x2e1f(%rip),%ymm12 # 551c <_sk_callback_avx+0x292> .byte 196,193,108,88,212 // vaddps %ymm12,%ymm2,%ymm2 - .byte 196,98,125,24,37,29,46,0,0 // vbroadcastss 0x2e1d(%rip),%ymm12 # 55b0 <_sk_callback_avx+0x29e> + .byte 196,98,125,24,37,21,46,0,0 // vbroadcastss 0x2e15(%rip),%ymm12 # 5520 <_sk_callback_avx+0x296> .byte 197,156,94,210 // vdivps %ymm2,%ymm12,%ymm2 .byte 197,164,92,210 // vsubps %ymm2,%ymm11,%ymm2 .byte 197,172,89,210 // vmulps %ymm2,%ymm10,%ymm2 .byte 196,99,125,8,210,1 // vroundps $0x1,%ymm2,%ymm10 .byte 196,65,108,92,210 // vsubps %ymm10,%ymm2,%ymm10 - .byte 196,98,125,24,29,1,46,0,0 // vbroadcastss 0x2e01(%rip),%ymm11 # 55b4 <_sk_callback_avx+0x2a2> + .byte 196,98,125,24,29,249,45,0,0 // vbroadcastss 0x2df9(%rip),%ymm11 # 5524 <_sk_callback_avx+0x29a> .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 - .byte 196,98,125,24,29,247,45,0,0 // vbroadcastss 0x2df7(%rip),%ymm11 # 55b8 <_sk_callback_avx+0x2a6> + .byte 196,98,125,24,29,239,45,0,0 // vbroadcastss 0x2def(%rip),%ymm11 # 5528 <_sk_callback_avx+0x29e> .byte 196,65,44,89,219 // vmulps %ymm11,%ymm10,%ymm11 .byte 196,193,108,92,211 // vsubps %ymm11,%ymm2,%ymm2 - .byte 196,98,125,24,29,232,45,0,0 // vbroadcastss 0x2de8(%rip),%ymm11 # 55bc <_sk_callback_avx+0x2aa> + .byte 196,98,125,24,29,224,45,0,0 // vbroadcastss 0x2de0(%rip),%ymm11 # 552c <_sk_callback_avx+0x2a2> .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 - .byte 196,98,125,24,29,222,45,0,0 // vbroadcastss 0x2dde(%rip),%ymm11 # 55c0 <_sk_callback_avx+0x2ae> + .byte 196,98,125,24,29,214,45,0,0 // vbroadcastss 0x2dd6(%rip),%ymm11 # 5530 <_sk_callback_avx+0x2a6> .byte 196,65,36,94,210 // vdivps %ymm10,%ymm11,%ymm10 .byte 196,193,108,88,210 // vaddps %ymm10,%ymm2,%ymm2 - .byte 196,98,125,24,21,207,45,0,0 // vbroadcastss 0x2dcf(%rip),%ymm10 # 55c4 <_sk_callback_avx+0x2b2> + .byte 196,98,125,24,21,199,45,0,0 // vbroadcastss 0x2dc7(%rip),%ymm10 # 5534 <_sk_callback_avx+0x2aa> .byte 196,193,108,89,210 // vmulps %ymm10,%ymm2,%ymm2 .byte 197,253,91,210 // vcvtps2dq %ymm2,%ymm2 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -14319,7 +14259,7 @@ _sk_parametric_b_avx: .byte 196,195,109,74,209,128 // vblendvps %ymm8,%ymm9,%ymm2,%ymm2 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,108,95,208 // vmaxps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,166,45,0,0 // vbroadcastss 0x2da6(%rip),%ymm8 # 55c8 <_sk_callback_avx+0x2b6> + .byte 196,98,125,24,5,158,45,0,0 // vbroadcastss 0x2d9e(%rip),%ymm8 # 5538 <_sk_callback_avx+0x2ae> .byte 196,193,108,93,208 // vminps %ymm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -14341,36 +14281,36 @@ _sk_parametric_a_avx: .byte 196,193,100,88,219 // vaddps %ymm11,%ymm3,%ymm3 .byte 196,98,125,24,16 // vbroadcastss (%rax),%ymm10 .byte 197,124,91,219 // vcvtdq2ps %ymm3,%ymm11 - .byte 196,98,125,24,37,87,45,0,0 // vbroadcastss 0x2d57(%rip),%ymm12 # 55cc <_sk_callback_avx+0x2ba> + .byte 196,98,125,24,37,79,45,0,0 // vbroadcastss 0x2d4f(%rip),%ymm12 # 553c <_sk_callback_avx+0x2b2> .byte 196,65,36,89,220 // vmulps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,77,45,0,0 // vbroadcastss 0x2d4d(%rip),%ymm12 # 55d0 <_sk_callback_avx+0x2be> + .byte 196,98,125,24,37,69,45,0,0 // vbroadcastss 0x2d45(%rip),%ymm12 # 5540 <_sk_callback_avx+0x2b6> .byte 196,193,100,84,220 // vandps %ymm12,%ymm3,%ymm3 - .byte 196,98,125,24,37,67,45,0,0 // vbroadcastss 0x2d43(%rip),%ymm12 # 55d4 <_sk_callback_avx+0x2c2> + .byte 196,98,125,24,37,59,45,0,0 // vbroadcastss 0x2d3b(%rip),%ymm12 # 5544 <_sk_callback_avx+0x2ba> .byte 196,193,100,86,220 // vorps %ymm12,%ymm3,%ymm3 - .byte 196,98,125,24,37,57,45,0,0 // vbroadcastss 0x2d39(%rip),%ymm12 # 55d8 <_sk_callback_avx+0x2c6> + .byte 196,98,125,24,37,49,45,0,0 // vbroadcastss 0x2d31(%rip),%ymm12 # 5548 <_sk_callback_avx+0x2be> .byte 196,65,36,88,220 // vaddps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,47,45,0,0 // vbroadcastss 0x2d2f(%rip),%ymm12 # 55dc <_sk_callback_avx+0x2ca> + .byte 196,98,125,24,37,39,45,0,0 // vbroadcastss 0x2d27(%rip),%ymm12 # 554c <_sk_callback_avx+0x2c2> .byte 196,65,100,89,228 // vmulps %ymm12,%ymm3,%ymm12 .byte 196,65,36,92,220 // vsubps %ymm12,%ymm11,%ymm11 - .byte 196,98,125,24,37,32,45,0,0 // vbroadcastss 0x2d20(%rip),%ymm12 # 55e0 <_sk_callback_avx+0x2ce> + .byte 196,98,125,24,37,24,45,0,0 // vbroadcastss 0x2d18(%rip),%ymm12 # 5550 <_sk_callback_avx+0x2c6> .byte 196,193,100,88,220 // vaddps %ymm12,%ymm3,%ymm3 - .byte 196,98,125,24,37,22,45,0,0 // vbroadcastss 0x2d16(%rip),%ymm12 # 55e4 <_sk_callback_avx+0x2d2> + .byte 196,98,125,24,37,14,45,0,0 // vbroadcastss 0x2d0e(%rip),%ymm12 # 5554 <_sk_callback_avx+0x2ca> .byte 197,156,94,219 // vdivps %ymm3,%ymm12,%ymm3 .byte 197,164,92,219 // vsubps %ymm3,%ymm11,%ymm3 .byte 197,172,89,219 // vmulps %ymm3,%ymm10,%ymm3 .byte 196,99,125,8,211,1 // vroundps $0x1,%ymm3,%ymm10 .byte 196,65,100,92,210 // vsubps %ymm10,%ymm3,%ymm10 - .byte 196,98,125,24,29,250,44,0,0 // vbroadcastss 0x2cfa(%rip),%ymm11 # 55e8 <_sk_callback_avx+0x2d6> + .byte 196,98,125,24,29,242,44,0,0 // vbroadcastss 0x2cf2(%rip),%ymm11 # 5558 <_sk_callback_avx+0x2ce> .byte 196,193,100,88,219 // vaddps %ymm11,%ymm3,%ymm3 - .byte 196,98,125,24,29,240,44,0,0 // vbroadcastss 0x2cf0(%rip),%ymm11 # 55ec <_sk_callback_avx+0x2da> + .byte 196,98,125,24,29,232,44,0,0 // vbroadcastss 0x2ce8(%rip),%ymm11 # 555c <_sk_callback_avx+0x2d2> .byte 196,65,44,89,219 // vmulps %ymm11,%ymm10,%ymm11 .byte 196,193,100,92,219 // vsubps %ymm11,%ymm3,%ymm3 - .byte 196,98,125,24,29,225,44,0,0 // vbroadcastss 0x2ce1(%rip),%ymm11 # 55f0 <_sk_callback_avx+0x2de> + .byte 196,98,125,24,29,217,44,0,0 // vbroadcastss 0x2cd9(%rip),%ymm11 # 5560 <_sk_callback_avx+0x2d6> .byte 196,65,36,92,210 // vsubps %ymm10,%ymm11,%ymm10 - .byte 196,98,125,24,29,215,44,0,0 // vbroadcastss 0x2cd7(%rip),%ymm11 # 55f4 <_sk_callback_avx+0x2e2> + .byte 196,98,125,24,29,207,44,0,0 // vbroadcastss 0x2ccf(%rip),%ymm11 # 5564 <_sk_callback_avx+0x2da> .byte 196,65,36,94,210 // vdivps %ymm10,%ymm11,%ymm10 .byte 196,193,100,88,218 // vaddps %ymm10,%ymm3,%ymm3 - .byte 196,98,125,24,21,200,44,0,0 // vbroadcastss 0x2cc8(%rip),%ymm10 # 55f8 <_sk_callback_avx+0x2e6> + .byte 196,98,125,24,21,192,44,0,0 // vbroadcastss 0x2cc0(%rip),%ymm10 # 5568 <_sk_callback_avx+0x2de> .byte 196,193,100,89,218 // vmulps %ymm10,%ymm3,%ymm3 .byte 197,253,91,219 // vcvtps2dq %ymm3,%ymm3 .byte 196,98,125,24,80,20 // vbroadcastss 0x14(%rax),%ymm10 @@ -14378,7 +14318,7 @@ _sk_parametric_a_avx: .byte 196,195,101,74,217,128 // vblendvps %ymm8,%ymm9,%ymm3,%ymm3 .byte 196,65,60,87,192 // vxorps %ymm8,%ymm8,%ymm8 .byte 196,193,100,95,216 // vmaxps %ymm8,%ymm3,%ymm3 - .byte 196,98,125,24,5,159,44,0,0 // vbroadcastss 0x2c9f(%rip),%ymm8 # 55fc <_sk_callback_avx+0x2ea> + .byte 196,98,125,24,5,151,44,0,0 // vbroadcastss 0x2c97(%rip),%ymm8 # 556c <_sk_callback_avx+0x2e2> .byte 196,193,100,93,216 // vminps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -14387,31 +14327,31 @@ HIDDEN _sk_lab_to_xyz_avx .globl _sk_lab_to_xyz_avx FUNCTION(_sk_lab_to_xyz_avx) _sk_lab_to_xyz_avx: - .byte 196,98,125,24,5,145,44,0,0 // vbroadcastss 0x2c91(%rip),%ymm8 # 5600 <_sk_callback_avx+0x2ee> + .byte 196,98,125,24,5,137,44,0,0 // vbroadcastss 0x2c89(%rip),%ymm8 # 5570 <_sk_callback_avx+0x2e6> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,135,44,0,0 // vbroadcastss 0x2c87(%rip),%ymm8 # 5604 <_sk_callback_avx+0x2f2> + .byte 196,98,125,24,5,127,44,0,0 // vbroadcastss 0x2c7f(%rip),%ymm8 # 5574 <_sk_callback_avx+0x2ea> .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 - .byte 196,98,125,24,13,125,44,0,0 // vbroadcastss 0x2c7d(%rip),%ymm9 # 5608 <_sk_callback_avx+0x2f6> + .byte 196,98,125,24,13,117,44,0,0 // vbroadcastss 0x2c75(%rip),%ymm9 # 5578 <_sk_callback_avx+0x2ee> .byte 196,193,116,88,201 // vaddps %ymm9,%ymm1,%ymm1 .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 196,193,108,88,209 // vaddps %ymm9,%ymm2,%ymm2 - .byte 196,98,125,24,5,105,44,0,0 // vbroadcastss 0x2c69(%rip),%ymm8 # 560c <_sk_callback_avx+0x2fa> + .byte 196,98,125,24,5,97,44,0,0 // vbroadcastss 0x2c61(%rip),%ymm8 # 557c <_sk_callback_avx+0x2f2> .byte 196,193,124,88,192 // vaddps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,95,44,0,0 // vbroadcastss 0x2c5f(%rip),%ymm8 # 5610 <_sk_callback_avx+0x2fe> + .byte 196,98,125,24,5,87,44,0,0 // vbroadcastss 0x2c57(%rip),%ymm8 # 5580 <_sk_callback_avx+0x2f6> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 - .byte 196,98,125,24,5,85,44,0,0 // vbroadcastss 0x2c55(%rip),%ymm8 # 5614 <_sk_callback_avx+0x302> + .byte 196,98,125,24,5,77,44,0,0 // vbroadcastss 0x2c4d(%rip),%ymm8 # 5584 <_sk_callback_avx+0x2fa> .byte 196,193,116,89,200 // vmulps %ymm8,%ymm1,%ymm1 .byte 197,252,88,201 // vaddps %ymm1,%ymm0,%ymm1 - .byte 196,98,125,24,5,71,44,0,0 // vbroadcastss 0x2c47(%rip),%ymm8 # 5618 <_sk_callback_avx+0x306> + .byte 196,98,125,24,5,63,44,0,0 // vbroadcastss 0x2c3f(%rip),%ymm8 # 5588 <_sk_callback_avx+0x2fe> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 197,252,92,210 // vsubps %ymm2,%ymm0,%ymm2 .byte 197,116,89,193 // vmulps %ymm1,%ymm1,%ymm8 .byte 196,65,116,89,192 // vmulps %ymm8,%ymm1,%ymm8 - .byte 196,98,125,24,13,48,44,0,0 // vbroadcastss 0x2c30(%rip),%ymm9 # 561c <_sk_callback_avx+0x30a> + .byte 196,98,125,24,13,40,44,0,0 // vbroadcastss 0x2c28(%rip),%ymm9 # 558c <_sk_callback_avx+0x302> .byte 196,65,52,194,208,1 // vcmpltps %ymm8,%ymm9,%ymm10 - .byte 196,98,125,24,29,37,44,0,0 // vbroadcastss 0x2c25(%rip),%ymm11 # 5620 <_sk_callback_avx+0x30e> + .byte 196,98,125,24,29,29,44,0,0 // vbroadcastss 0x2c1d(%rip),%ymm11 # 5590 <_sk_callback_avx+0x306> .byte 196,193,116,88,203 // vaddps %ymm11,%ymm1,%ymm1 - .byte 196,98,125,24,37,27,44,0,0 // vbroadcastss 0x2c1b(%rip),%ymm12 # 5624 <_sk_callback_avx+0x312> + .byte 196,98,125,24,37,19,44,0,0 // vbroadcastss 0x2c13(%rip),%ymm12 # 5594 <_sk_callback_avx+0x30a> .byte 196,193,116,89,204 // vmulps %ymm12,%ymm1,%ymm1 .byte 196,67,117,74,192,160 // vblendvps %ymm10,%ymm8,%ymm1,%ymm8 .byte 197,252,89,200 // vmulps %ymm0,%ymm0,%ymm1 @@ -14426,9 +14366,9 @@ _sk_lab_to_xyz_avx: .byte 196,193,108,88,211 // vaddps %ymm11,%ymm2,%ymm2 .byte 196,193,108,89,212 // vmulps %ymm12,%ymm2,%ymm2 .byte 196,227,109,74,208,144 // vblendvps %ymm9,%ymm0,%ymm2,%ymm2 - .byte 196,226,125,24,5,209,43,0,0 // vbroadcastss 0x2bd1(%rip),%ymm0 # 5628 <_sk_callback_avx+0x316> + .byte 196,226,125,24,5,201,43,0,0 // vbroadcastss 0x2bc9(%rip),%ymm0 # 5598 <_sk_callback_avx+0x30e> .byte 197,188,89,192 // vmulps %ymm0,%ymm8,%ymm0 - .byte 196,98,125,24,5,200,43,0,0 // vbroadcastss 0x2bc8(%rip),%ymm8 # 562c <_sk_callback_avx+0x31a> + .byte 196,98,125,24,5,192,43,0,0 // vbroadcastss 0x2bc0(%rip),%ymm8 # 559c <_sk_callback_avx+0x312> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -14442,14 +14382,14 @@ _sk_load_a8_avx: .byte 72,139,0 // mov (%rax),%rax .byte 72,1,248 // add %rdi,%rax .byte 77,133,192 // test %r8,%r8 - .byte 117,62 // jne 2abb <_sk_load_a8_avx+0x4e> + .byte 117,62 // jne 2a33 <_sk_load_a8_avx+0x4e> .byte 197,250,126,0 // vmovq (%rax),%xmm0 .byte 196,226,121,49,200 // vpmovzxbd %xmm0,%xmm1 .byte 196,227,121,4,192,229 // vpermilps $0xe5,%xmm0,%xmm0 .byte 196,226,121,49,192 // vpmovzxbd %xmm0,%xmm0 .byte 196,227,117,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm1,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,140,43,0,0 // vbroadcastss 0x2b8c(%rip),%ymm1 # 5630 <_sk_callback_avx+0x31e> + .byte 196,226,125,24,13,132,43,0,0 // vbroadcastss 0x2b84(%rip),%ymm1 # 55a0 <_sk_callback_avx+0x316> .byte 197,252,89,217 // vmulps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -14466,9 +14406,9 @@ _sk_load_a8_avx: .byte 77,9,217 // or %r11,%r9 .byte 72,131,193,8 // add $0x8,%rcx .byte 73,255,202 // dec %r10 - .byte 117,234 // jne 2ac3 <_sk_load_a8_avx+0x56> + .byte 117,234 // jne 2a3b <_sk_load_a8_avx+0x56> .byte 196,193,249,110,193 // vmovq %r9,%xmm0 - .byte 235,161 // jmp 2a81 <_sk_load_a8_avx+0x14> + .byte 235,161 // jmp 29f9 <_sk_load_a8_avx+0x14> HIDDEN _sk_gather_a8_avx .globl _sk_gather_a8_avx @@ -14518,7 +14458,7 @@ _sk_gather_a8_avx: .byte 196,226,121,49,201 // vpmovzxbd %xmm1,%xmm1 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,129,42,0,0 // vbroadcastss 0x2a81(%rip),%ymm1 # 5634 <_sk_callback_avx+0x322> + .byte 196,226,125,24,13,121,42,0,0 // vbroadcastss 0x2a79(%rip),%ymm1 # 55a4 <_sk_callback_avx+0x31a> .byte 197,252,89,217 // vmulps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 197,252,87,192 // vxorps %ymm0,%ymm0,%ymm0 @@ -14536,14 +14476,14 @@ FUNCTION(_sk_store_a8_avx) _sk_store_a8_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,92,42,0,0 // vbroadcastss 0x2a5c(%rip),%ymm8 # 5638 <_sk_callback_avx+0x326> + .byte 196,98,125,24,5,84,42,0,0 // vbroadcastss 0x2a54(%rip),%ymm8 # 55a8 <_sk_callback_avx+0x31e> .byte 196,65,100,89,192 // vmulps %ymm8,%ymm3,%ymm8 .byte 196,65,125,91,192 // vcvtps2dq %ymm8,%ymm8 .byte 196,67,125,25,193,1 // vextractf128 $0x1,%ymm8,%xmm9 .byte 196,66,57,43,193 // vpackusdw %xmm9,%xmm8,%xmm8 .byte 196,65,57,103,192 // vpackuswb %xmm8,%xmm8,%xmm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,10 // jne 2c05 <_sk_store_a8_avx+0x37> + .byte 117,10 // jne 2b7d <_sk_store_a8_avx+0x37> .byte 196,65,123,17,4,58 // vmovsd %xmm8,(%r10,%rdi,1) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -14551,10 +14491,10 @@ _sk_store_a8_avx: .byte 65,128,224,7 // and $0x7,%r8b .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 119,236 // ja 2c01 <_sk_store_a8_avx+0x33> + .byte 119,236 // ja 2b79 <_sk_store_a8_avx+0x33> .byte 196,66,121,48,192 // vpmovzxbw %xmm8,%xmm8 .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,67,0,0,0 // lea 0x43(%rip),%r9 # 2c68 <_sk_store_a8_avx+0x9a> + .byte 76,141,13,67,0,0,0 // lea 0x43(%rip),%r9 # 2be0 <_sk_store_a8_avx+0x9a> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -14565,7 +14505,7 @@ _sk_store_a8_avx: .byte 196,67,121,20,68,58,2,4 // vpextrb $0x4,%xmm8,0x2(%r10,%rdi,1) .byte 196,67,121,20,68,58,1,2 // vpextrb $0x2,%xmm8,0x1(%r10,%rdi,1) .byte 196,67,121,20,4,58,0 // vpextrb $0x0,%xmm8,(%r10,%rdi,1) - .byte 235,154 // jmp 2c01 <_sk_store_a8_avx+0x33> + .byte 235,154 // jmp 2b79 <_sk_store_a8_avx+0x33> .byte 144 // nop .byte 246,255 // idiv %bh .byte 255 // (bad) @@ -14599,17 +14539,17 @@ _sk_load_g8_avx: .byte 72,139,0 // mov (%rax),%rax .byte 72,1,248 // add %rdi,%rax .byte 77,133,192 // test %r8,%r8 - .byte 117,67 // jne 2cd7 <_sk_load_g8_avx+0x53> + .byte 117,67 // jne 2c4f <_sk_load_g8_avx+0x53> .byte 197,250,126,0 // vmovq (%rax),%xmm0 .byte 196,226,121,49,200 // vpmovzxbd %xmm0,%xmm1 .byte 196,227,121,4,192,229 // vpermilps $0xe5,%xmm0,%xmm0 .byte 196,226,121,49,192 // vpmovzxbd %xmm0,%xmm0 .byte 196,227,117,24,192,1 // vinsertf128 $0x1,%xmm0,%ymm1,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,129,41,0,0 // vbroadcastss 0x2981(%rip),%ymm1 # 563c <_sk_callback_avx+0x32a> + .byte 196,226,125,24,13,121,41,0,0 // vbroadcastss 0x2979(%rip),%ymm1 # 55ac <_sk_callback_avx+0x322> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,118,41,0,0 // vbroadcastss 0x2976(%rip),%ymm3 # 5640 <_sk_callback_avx+0x32e> + .byte 196,226,125,24,29,110,41,0,0 // vbroadcastss 0x296e(%rip),%ymm3 # 55b0 <_sk_callback_avx+0x326> .byte 76,137,193 // mov %r8,%rcx .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 @@ -14623,9 +14563,9 @@ _sk_load_g8_avx: .byte 77,9,217 // or %r11,%r9 .byte 72,131,193,8 // add $0x8,%rcx .byte 73,255,202 // dec %r10 - .byte 117,234 // jne 2cdf <_sk_load_g8_avx+0x5b> + .byte 117,234 // jne 2c57 <_sk_load_g8_avx+0x5b> .byte 196,193,249,110,193 // vmovq %r9,%xmm0 - .byte 235,156 // jmp 2c98 <_sk_load_g8_avx+0x14> + .byte 235,156 // jmp 2c10 <_sk_load_g8_avx+0x14> HIDDEN _sk_gather_g8_avx .globl _sk_gather_g8_avx @@ -14675,10 +14615,10 @@ _sk_gather_g8_avx: .byte 196,226,121,49,201 // vpmovzxbd %xmm1,%xmm1 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,117,40,0,0 // vbroadcastss 0x2875(%rip),%ymm1 # 5644 <_sk_callback_avx+0x332> + .byte 196,226,125,24,13,109,40,0,0 // vbroadcastss 0x286d(%rip),%ymm1 # 55b4 <_sk_callback_avx+0x32a> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,106,40,0,0 // vbroadcastss 0x286a(%rip),%ymm3 # 5648 <_sk_callback_avx+0x336> + .byte 196,226,125,24,29,98,40,0,0 // vbroadcastss 0x2862(%rip),%ymm3 # 55b8 <_sk_callback_avx+0x32e> .byte 197,252,40,200 // vmovaps %ymm0,%ymm1 .byte 197,252,40,208 // vmovaps %ymm0,%ymm2 .byte 91 // pop %rbx @@ -14694,9 +14634,9 @@ _sk_gather_i8_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 73,137,192 // mov %rax,%r8 .byte 77,133,192 // test %r8,%r8 - .byte 116,5 // je 2dfe <_sk_gather_i8_avx+0xf> + .byte 116,5 // je 2d76 <_sk_gather_i8_avx+0xf> .byte 76,137,192 // mov %r8,%rax - .byte 235,2 // jmp 2e00 <_sk_gather_i8_avx+0x11> + .byte 235,2 // jmp 2d78 <_sk_gather_i8_avx+0x11> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,87 // push %r15 .byte 65,86 // push %r14 @@ -14758,10 +14698,10 @@ _sk_gather_i8_avx: .byte 196,163,121,34,4,163,2 // vpinsrd $0x2,(%rbx,%r12,4),%xmm0,%xmm0 .byte 196,163,121,34,28,19,3 // vpinsrd $0x3,(%rbx,%r10,1),%xmm0,%xmm3 .byte 196,227,61,24,195,1 // vinsertf128 $0x1,%xmm3,%ymm8,%ymm0 - .byte 197,124,40,21,214,40,0,0 // vmovaps 0x28d6(%rip),%ymm10 # 5800 <_sk_callback_avx+0x4ee> + .byte 197,124,40,21,190,40,0,0 // vmovaps 0x28be(%rip),%ymm10 # 5760 <_sk_callback_avx+0x4d6> .byte 196,193,124,84,194 // vandps %ymm10,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,16,39,0,0 // vbroadcastss 0x2710(%rip),%ymm9 # 564c <_sk_callback_avx+0x33a> + .byte 196,98,125,24,13,8,39,0,0 // vbroadcastss 0x2708(%rip),%ymm9 # 55bc <_sk_callback_avx+0x332> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 196,193,113,114,208,8 // vpsrld $0x8,%xmm8,%xmm1 .byte 197,233,114,211,8 // vpsrld $0x8,%xmm3,%xmm2 @@ -14795,38 +14735,38 @@ _sk_load_565_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,128,0,0,0 // jne 3034 <_sk_load_565_avx+0x8e> + .byte 15,133,128,0,0,0 // jne 2fac <_sk_load_565_avx+0x8e> .byte 196,193,122,111,4,122 // vmovdqu (%r10,%rdi,2),%xmm0 .byte 197,241,239,201 // vpxor %xmm1,%xmm1,%xmm1 .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,209,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm2 - .byte 196,226,125,24,5,122,38,0,0 // vbroadcastss 0x267a(%rip),%ymm0 # 5650 <_sk_callback_avx+0x33e> + .byte 196,226,125,24,5,114,38,0,0 // vbroadcastss 0x2672(%rip),%ymm0 # 55c0 <_sk_callback_avx+0x336> .byte 197,236,84,192 // vandps %ymm0,%ymm2,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,109,38,0,0 // vbroadcastss 0x266d(%rip),%ymm1 # 5654 <_sk_callback_avx+0x342> + .byte 196,226,125,24,13,101,38,0,0 // vbroadcastss 0x2665(%rip),%ymm1 # 55c4 <_sk_callback_avx+0x33a> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,100,38,0,0 // vbroadcastss 0x2664(%rip),%ymm1 # 5658 <_sk_callback_avx+0x346> + .byte 196,226,125,24,13,92,38,0,0 // vbroadcastss 0x265c(%rip),%ymm1 # 55c8 <_sk_callback_avx+0x33e> .byte 197,236,84,201 // vandps %ymm1,%ymm2,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,29,87,38,0,0 // vbroadcastss 0x2657(%rip),%ymm3 # 565c <_sk_callback_avx+0x34a> + .byte 196,226,125,24,29,79,38,0,0 // vbroadcastss 0x264f(%rip),%ymm3 # 55cc <_sk_callback_avx+0x342> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 - .byte 196,226,125,24,29,78,38,0,0 // vbroadcastss 0x264e(%rip),%ymm3 # 5660 <_sk_callback_avx+0x34e> + .byte 196,226,125,24,29,70,38,0,0 // vbroadcastss 0x2646(%rip),%ymm3 # 55d0 <_sk_callback_avx+0x346> .byte 197,236,84,211 // vandps %ymm3,%ymm2,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,226,125,24,29,65,38,0,0 // vbroadcastss 0x2641(%rip),%ymm3 # 5664 <_sk_callback_avx+0x352> + .byte 196,226,125,24,29,57,38,0,0 // vbroadcastss 0x2639(%rip),%ymm3 # 55d4 <_sk_callback_avx+0x34a> .byte 197,236,89,211 // vmulps %ymm3,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,54,38,0,0 // vbroadcastss 0x2636(%rip),%ymm3 # 5668 <_sk_callback_avx+0x356> + .byte 196,226,125,24,29,46,38,0,0 // vbroadcastss 0x262e(%rip),%ymm3 # 55d8 <_sk_callback_avx+0x34e> .byte 255,224 // jmpq *%rax .byte 65,137,200 // mov %ecx,%r8d .byte 65,128,224,7 // and $0x7,%r8b .byte 197,249,239,192 // vpxor %xmm0,%xmm0,%xmm0 .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 15,135,110,255,255,255 // ja 2fba <_sk_load_565_avx+0x14> + .byte 15,135,110,255,255,255 // ja 2f32 <_sk_load_565_avx+0x14> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,73,0,0,0 // lea 0x49(%rip),%r9 # 30a0 <_sk_load_565_avx+0xfa> + .byte 76,141,13,73,0,0,0 // lea 0x49(%rip),%r9 # 3018 <_sk_load_565_avx+0xfa> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -14838,7 +14778,7 @@ _sk_load_565_avx: .byte 196,193,121,196,68,122,4,2 // vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm0,%xmm0 .byte 196,193,121,196,68,122,2,1 // vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm0,%xmm0 .byte 196,193,121,196,4,122,0 // vpinsrw $0x0,(%r10,%rdi,2),%xmm0,%xmm0 - .byte 233,26,255,255,255 // jmpq 2fba <_sk_load_565_avx+0x14> + .byte 233,26,255,255,255 // jmpq 2f32 <_sk_load_565_avx+0x14> .byte 244 // hlt .byte 255 // (bad) .byte 255 // (bad) @@ -14916,23 +14856,23 @@ _sk_gather_565_avx: .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,209,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm2 - .byte 196,226,125,24,5,214,36,0,0 // vbroadcastss 0x24d6(%rip),%ymm0 # 566c <_sk_callback_avx+0x35a> + .byte 196,226,125,24,5,206,36,0,0 // vbroadcastss 0x24ce(%rip),%ymm0 # 55dc <_sk_callback_avx+0x352> .byte 197,236,84,192 // vandps %ymm0,%ymm2,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,201,36,0,0 // vbroadcastss 0x24c9(%rip),%ymm1 # 5670 <_sk_callback_avx+0x35e> + .byte 196,226,125,24,13,193,36,0,0 // vbroadcastss 0x24c1(%rip),%ymm1 # 55e0 <_sk_callback_avx+0x356> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,192,36,0,0 // vbroadcastss 0x24c0(%rip),%ymm1 # 5674 <_sk_callback_avx+0x362> + .byte 196,226,125,24,13,184,36,0,0 // vbroadcastss 0x24b8(%rip),%ymm1 # 55e4 <_sk_callback_avx+0x35a> .byte 197,236,84,201 // vandps %ymm1,%ymm2,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,29,179,36,0,0 // vbroadcastss 0x24b3(%rip),%ymm3 # 5678 <_sk_callback_avx+0x366> + .byte 196,226,125,24,29,171,36,0,0 // vbroadcastss 0x24ab(%rip),%ymm3 # 55e8 <_sk_callback_avx+0x35e> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 - .byte 196,226,125,24,29,170,36,0,0 // vbroadcastss 0x24aa(%rip),%ymm3 # 567c <_sk_callback_avx+0x36a> + .byte 196,226,125,24,29,162,36,0,0 // vbroadcastss 0x24a2(%rip),%ymm3 # 55ec <_sk_callback_avx+0x362> .byte 197,236,84,211 // vandps %ymm3,%ymm2,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,226,125,24,29,157,36,0,0 // vbroadcastss 0x249d(%rip),%ymm3 # 5680 <_sk_callback_avx+0x36e> + .byte 196,226,125,24,29,149,36,0,0 // vbroadcastss 0x2495(%rip),%ymm3 # 55f0 <_sk_callback_avx+0x366> .byte 197,236,89,211 // vmulps %ymm3,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,146,36,0,0 // vbroadcastss 0x2492(%rip),%ymm3 # 5684 <_sk_callback_avx+0x372> + .byte 196,226,125,24,29,138,36,0,0 // vbroadcastss 0x248a(%rip),%ymm3 # 55f4 <_sk_callback_avx+0x36a> .byte 91 // pop %rbx .byte 65,92 // pop %r12 .byte 65,94 // pop %r14 @@ -14946,14 +14886,14 @@ FUNCTION(_sk_store_565_avx) _sk_store_565_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,126,36,0,0 // vbroadcastss 0x247e(%rip),%ymm8 # 5688 <_sk_callback_avx+0x376> + .byte 196,98,125,24,5,118,36,0,0 // vbroadcastss 0x2476(%rip),%ymm8 # 55f8 <_sk_callback_avx+0x36e> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,193,41,114,241,11 // vpslld $0xb,%xmm9,%xmm10 .byte 196,67,125,25,201,1 // vextractf128 $0x1,%ymm9,%xmm9 .byte 196,193,49,114,241,11 // vpslld $0xb,%xmm9,%xmm9 .byte 196,67,45,24,201,1 // vinsertf128 $0x1,%xmm9,%ymm10,%ymm9 - .byte 196,98,125,24,21,87,36,0,0 // vbroadcastss 0x2457(%rip),%ymm10 # 568c <_sk_callback_avx+0x37a> + .byte 196,98,125,24,21,79,36,0,0 // vbroadcastss 0x244f(%rip),%ymm10 # 55fc <_sk_callback_avx+0x372> .byte 196,65,116,89,210 // vmulps %ymm10,%ymm1,%ymm10 .byte 196,65,125,91,210 // vcvtps2dq %ymm10,%ymm10 .byte 196,193,33,114,242,5 // vpslld $0x5,%xmm10,%xmm11 @@ -14967,7 +14907,7 @@ _sk_store_565_avx: .byte 196,67,125,25,193,1 // vextractf128 $0x1,%ymm8,%xmm9 .byte 196,66,57,43,193 // vpackusdw %xmm9,%xmm8,%xmm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,10 // jne 3285 <_sk_store_565_avx+0x89> + .byte 117,10 // jne 31fd <_sk_store_565_avx+0x89> .byte 196,65,122,127,4,122 // vmovdqu %xmm8,(%r10,%rdi,2) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -14975,9 +14915,9 @@ _sk_store_565_avx: .byte 65,128,224,7 // and $0x7,%r8b .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 119,236 // ja 3281 <_sk_store_565_avx+0x85> + .byte 119,236 // ja 31f9 <_sk_store_565_avx+0x85> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,68,0,0,0 // lea 0x44(%rip),%r9 # 32e4 <_sk_store_565_avx+0xe8> + .byte 76,141,13,68,0,0,0 // lea 0x44(%rip),%r9 # 325c <_sk_store_565_avx+0xe8> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -14988,7 +14928,7 @@ _sk_store_565_avx: .byte 196,67,121,21,68,122,4,2 // vpextrw $0x2,%xmm8,0x4(%r10,%rdi,2) .byte 196,67,121,21,68,122,2,1 // vpextrw $0x1,%xmm8,0x2(%r10,%rdi,2) .byte 196,67,121,21,4,122,0 // vpextrw $0x0,%xmm8,(%r10,%rdi,2) - .byte 235,159 // jmp 3281 <_sk_store_565_avx+0x85> + .byte 235,159 // jmp 31f9 <_sk_store_565_avx+0x85> .byte 102,144 // xchg %ax,%ax .byte 245 // cmc .byte 255 // (bad) @@ -15021,31 +14961,31 @@ _sk_load_4444_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,152,0,0,0 // jne 33a6 <_sk_load_4444_avx+0xa6> + .byte 15,133,152,0,0,0 // jne 331e <_sk_load_4444_avx+0xa6> .byte 196,193,122,111,4,122 // vmovdqu (%r10,%rdi,2),%xmm0 .byte 197,241,239,201 // vpxor %xmm1,%xmm1,%xmm1 .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,217,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm3 - .byte 196,226,125,24,5,96,35,0,0 // vbroadcastss 0x2360(%rip),%ymm0 # 5690 <_sk_callback_avx+0x37e> + .byte 196,226,125,24,5,88,35,0,0 // vbroadcastss 0x2358(%rip),%ymm0 # 5600 <_sk_callback_avx+0x376> .byte 197,228,84,192 // vandps %ymm0,%ymm3,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,83,35,0,0 // vbroadcastss 0x2353(%rip),%ymm1 # 5694 <_sk_callback_avx+0x382> + .byte 196,226,125,24,13,75,35,0,0 // vbroadcastss 0x234b(%rip),%ymm1 # 5604 <_sk_callback_avx+0x37a> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,74,35,0,0 // vbroadcastss 0x234a(%rip),%ymm1 # 5698 <_sk_callback_avx+0x386> + .byte 196,226,125,24,13,66,35,0,0 // vbroadcastss 0x2342(%rip),%ymm1 # 5608 <_sk_callback_avx+0x37e> .byte 197,228,84,201 // vandps %ymm1,%ymm3,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,21,61,35,0,0 // vbroadcastss 0x233d(%rip),%ymm2 # 569c <_sk_callback_avx+0x38a> + .byte 196,226,125,24,21,53,35,0,0 // vbroadcastss 0x2335(%rip),%ymm2 # 560c <_sk_callback_avx+0x382> .byte 197,244,89,202 // vmulps %ymm2,%ymm1,%ymm1 - .byte 196,226,125,24,21,52,35,0,0 // vbroadcastss 0x2334(%rip),%ymm2 # 56a0 <_sk_callback_avx+0x38e> + .byte 196,226,125,24,21,44,35,0,0 // vbroadcastss 0x232c(%rip),%ymm2 # 5610 <_sk_callback_avx+0x386> .byte 197,228,84,210 // vandps %ymm2,%ymm3,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,98,125,24,5,39,35,0,0 // vbroadcastss 0x2327(%rip),%ymm8 # 56a4 <_sk_callback_avx+0x392> + .byte 196,98,125,24,5,31,35,0,0 // vbroadcastss 0x231f(%rip),%ymm8 # 5614 <_sk_callback_avx+0x38a> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,29,35,0,0 // vbroadcastss 0x231d(%rip),%ymm8 # 56a8 <_sk_callback_avx+0x396> + .byte 196,98,125,24,5,21,35,0,0 // vbroadcastss 0x2315(%rip),%ymm8 # 5618 <_sk_callback_avx+0x38e> .byte 196,193,100,84,216 // vandps %ymm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,15,35,0,0 // vbroadcastss 0x230f(%rip),%ymm8 # 56ac <_sk_callback_avx+0x39a> + .byte 196,98,125,24,5,7,35,0,0 // vbroadcastss 0x2307(%rip),%ymm8 # 561c <_sk_callback_avx+0x392> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -15054,9 +14994,9 @@ _sk_load_4444_avx: .byte 197,249,239,192 // vpxor %xmm0,%xmm0,%xmm0 .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 15,135,86,255,255,255 // ja 3314 <_sk_load_4444_avx+0x14> + .byte 15,135,86,255,255,255 // ja 328c <_sk_load_4444_avx+0x14> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,75,0,0,0 // lea 0x4b(%rip),%r9 # 3414 <_sk_load_4444_avx+0x114> + .byte 76,141,13,75,0,0,0 // lea 0x4b(%rip),%r9 # 338c <_sk_load_4444_avx+0x114> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -15068,7 +15008,7 @@ _sk_load_4444_avx: .byte 196,193,121,196,68,122,4,2 // vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm0,%xmm0 .byte 196,193,121,196,68,122,2,1 // vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm0,%xmm0 .byte 196,193,121,196,4,122,0 // vpinsrw $0x0,(%r10,%rdi,2),%xmm0,%xmm0 - .byte 233,2,255,255,255 // jmpq 3314 <_sk_load_4444_avx+0x14> + .byte 233,2,255,255,255 // jmpq 328c <_sk_load_4444_avx+0x14> .byte 102,144 // xchg %ax,%ax .byte 242,255 // repnz (bad) .byte 255 // (bad) @@ -15147,25 +15087,25 @@ _sk_gather_4444_avx: .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,217,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm3 - .byte 196,226,125,24,5,166,33,0,0 // vbroadcastss 0x21a6(%rip),%ymm0 # 56b0 <_sk_callback_avx+0x39e> + .byte 196,226,125,24,5,158,33,0,0 // vbroadcastss 0x219e(%rip),%ymm0 # 5620 <_sk_callback_avx+0x396> .byte 197,228,84,192 // vandps %ymm0,%ymm3,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,226,125,24,13,153,33,0,0 // vbroadcastss 0x2199(%rip),%ymm1 # 56b4 <_sk_callback_avx+0x3a2> + .byte 196,226,125,24,13,145,33,0,0 // vbroadcastss 0x2191(%rip),%ymm1 # 5624 <_sk_callback_avx+0x39a> .byte 197,252,89,193 // vmulps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,144,33,0,0 // vbroadcastss 0x2190(%rip),%ymm1 # 56b8 <_sk_callback_avx+0x3a6> + .byte 196,226,125,24,13,136,33,0,0 // vbroadcastss 0x2188(%rip),%ymm1 # 5628 <_sk_callback_avx+0x39e> .byte 197,228,84,201 // vandps %ymm1,%ymm3,%ymm1 .byte 197,252,91,201 // vcvtdq2ps %ymm1,%ymm1 - .byte 196,226,125,24,21,131,33,0,0 // vbroadcastss 0x2183(%rip),%ymm2 # 56bc <_sk_callback_avx+0x3aa> + .byte 196,226,125,24,21,123,33,0,0 // vbroadcastss 0x217b(%rip),%ymm2 # 562c <_sk_callback_avx+0x3a2> .byte 197,244,89,202 // vmulps %ymm2,%ymm1,%ymm1 - .byte 196,226,125,24,21,122,33,0,0 // vbroadcastss 0x217a(%rip),%ymm2 # 56c0 <_sk_callback_avx+0x3ae> + .byte 196,226,125,24,21,114,33,0,0 // vbroadcastss 0x2172(%rip),%ymm2 # 5630 <_sk_callback_avx+0x3a6> .byte 197,228,84,210 // vandps %ymm2,%ymm3,%ymm2 .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 - .byte 196,98,125,24,5,109,33,0,0 // vbroadcastss 0x216d(%rip),%ymm8 # 56c4 <_sk_callback_avx+0x3b2> + .byte 196,98,125,24,5,101,33,0,0 // vbroadcastss 0x2165(%rip),%ymm8 # 5634 <_sk_callback_avx+0x3aa> .byte 196,193,108,89,208 // vmulps %ymm8,%ymm2,%ymm2 - .byte 196,98,125,24,5,99,33,0,0 // vbroadcastss 0x2163(%rip),%ymm8 # 56c8 <_sk_callback_avx+0x3b6> + .byte 196,98,125,24,5,91,33,0,0 // vbroadcastss 0x215b(%rip),%ymm8 # 5638 <_sk_callback_avx+0x3ae> .byte 196,193,100,84,216 // vandps %ymm8,%ymm3,%ymm3 .byte 197,252,91,219 // vcvtdq2ps %ymm3,%ymm3 - .byte 196,98,125,24,5,85,33,0,0 // vbroadcastss 0x2155(%rip),%ymm8 # 56cc <_sk_callback_avx+0x3ba> + .byte 196,98,125,24,5,77,33,0,0 // vbroadcastss 0x214d(%rip),%ymm8 # 563c <_sk_callback_avx+0x3b2> .byte 196,193,100,89,216 // vmulps %ymm8,%ymm3,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 91 // pop %rbx @@ -15181,7 +15121,7 @@ FUNCTION(_sk_store_4444_avx) _sk_store_4444_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,58,33,0,0 // vbroadcastss 0x213a(%rip),%ymm8 # 56d0 <_sk_callback_avx+0x3be> + .byte 196,98,125,24,5,50,33,0,0 // vbroadcastss 0x2132(%rip),%ymm8 # 5640 <_sk_callback_avx+0x3b6> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,193,41,114,241,12 // vpslld $0xc,%xmm9,%xmm10 @@ -15208,7 +15148,7 @@ _sk_store_4444_avx: .byte 196,67,125,25,193,1 // vextractf128 $0x1,%ymm8,%xmm9 .byte 196,66,57,43,193 // vpackusdw %xmm9,%xmm8,%xmm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,10 // jne 362f <_sk_store_4444_avx+0xa7> + .byte 117,10 // jne 35a7 <_sk_store_4444_avx+0xa7> .byte 196,65,122,127,4,122 // vmovdqu %xmm8,(%r10,%rdi,2) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -15216,9 +15156,9 @@ _sk_store_4444_avx: .byte 65,128,224,7 // and $0x7,%r8b .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 119,236 // ja 362b <_sk_store_4444_avx+0xa3> + .byte 119,236 // ja 35a3 <_sk_store_4444_avx+0xa3> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,66,0,0,0 // lea 0x42(%rip),%r9 # 368c <_sk_store_4444_avx+0x104> + .byte 76,141,13,66,0,0,0 // lea 0x42(%rip),%r9 # 3604 <_sk_store_4444_avx+0x104> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -15229,7 +15169,7 @@ _sk_store_4444_avx: .byte 196,67,121,21,68,122,4,2 // vpextrw $0x2,%xmm8,0x4(%r10,%rdi,2) .byte 196,67,121,21,68,122,2,1 // vpextrw $0x1,%xmm8,0x2(%r10,%rdi,2) .byte 196,67,121,21,4,122,0 // vpextrw $0x0,%xmm8,(%r10,%rdi,2) - .byte 235,159 // jmp 362b <_sk_store_4444_avx+0xa3> + .byte 235,159 // jmp 35a3 <_sk_store_4444_avx+0xa3> .byte 247,255 // idiv %edi .byte 255 // (bad) .byte 255 // (bad) @@ -15260,12 +15200,12 @@ _sk_load_8888_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,135,0,0,0 // jne 373d <_sk_load_8888_avx+0x95> + .byte 15,133,135,0,0,0 // jne 36b5 <_sk_load_8888_avx+0x95> .byte 196,65,124,16,12,186 // vmovups (%r10,%rdi,4),%ymm9 - .byte 197,124,40,21,92,33,0,0 // vmovaps 0x215c(%rip),%ymm10 # 5820 <_sk_callback_avx+0x50e> + .byte 197,124,40,21,68,33,0,0 // vmovaps 0x2144(%rip),%ymm10 # 5780 <_sk_callback_avx+0x4f6> .byte 196,193,52,84,194 // vandps %ymm10,%ymm9,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,5,254,31,0,0 // vbroadcastss 0x1ffe(%rip),%ymm8 # 56d4 <_sk_callback_avx+0x3c2> + .byte 196,98,125,24,5,246,31,0,0 // vbroadcastss 0x1ff6(%rip),%ymm8 # 5644 <_sk_callback_avx+0x3ba> .byte 196,193,124,89,192 // vmulps %ymm8,%ymm0,%ymm0 .byte 196,193,113,114,209,8 // vpsrld $0x8,%xmm9,%xmm1 .byte 196,99,125,25,203,1 // vextractf128 $0x1,%ymm9,%xmm3 @@ -15292,9 +15232,9 @@ _sk_load_8888_avx: .byte 196,65,52,87,201 // vxorps %ymm9,%ymm9,%ymm9 .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 15,135,102,255,255,255 // ja 36bc <_sk_load_8888_avx+0x14> + .byte 15,135,102,255,255,255 // ja 3634 <_sk_load_8888_avx+0x14> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,139,0,0,0 // lea 0x8b(%rip),%r9 # 37ec <_sk_load_8888_avx+0x144> + .byte 76,141,13,139,0,0,0 // lea 0x8b(%rip),%r9 # 3764 <_sk_load_8888_avx+0x144> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -15317,7 +15257,7 @@ _sk_load_8888_avx: .byte 196,99,53,12,200,15 // vblendps $0xf,%ymm0,%ymm9,%ymm9 .byte 196,195,49,34,4,186,0 // vpinsrd $0x0,(%r10,%rdi,4),%xmm9,%xmm0 .byte 196,99,53,12,200,15 // vblendps $0xf,%ymm0,%ymm9,%ymm9 - .byte 233,210,254,255,255 // jmpq 36bc <_sk_load_8888_avx+0x14> + .byte 233,210,254,255,255 // jmpq 3634 <_sk_load_8888_avx+0x14> .byte 102,144 // xchg %ax,%ax .byte 236 // in (%dx),%al .byte 255 // (bad) @@ -15335,7 +15275,7 @@ _sk_load_8888_avx: .byte 255 // (bad) .byte 255 // (bad) .byte 255 // (bad) - .byte 126,255 // jle 3805 <_sk_load_8888_avx+0x15d> + .byte 126,255 // jle 377d <_sk_load_8888_avx+0x15d> .byte 255 // (bad) .byte 255 // .byte 0xff @@ -15380,10 +15320,10 @@ _sk_gather_8888_avx: .byte 196,131,121,34,4,152,2 // vpinsrd $0x2,(%r8,%r11,4),%xmm0,%xmm0 .byte 196,131,121,34,28,144,3 // vpinsrd $0x3,(%r8,%r10,4),%xmm0,%xmm3 .byte 196,227,61,24,195,1 // vinsertf128 $0x1,%xmm3,%ymm8,%ymm0 - .byte 197,124,40,21,134,31,0,0 // vmovaps 0x1f86(%rip),%ymm10 # 5840 <_sk_callback_avx+0x52e> + .byte 197,124,40,21,110,31,0,0 // vmovaps 0x1f6e(%rip),%ymm10 # 57a0 <_sk_callback_avx+0x516> .byte 196,193,124,84,194 // vandps %ymm10,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,13,12,30,0,0 // vbroadcastss 0x1e0c(%rip),%ymm9 # 56d8 <_sk_callback_avx+0x3c6> + .byte 196,98,125,24,13,4,30,0,0 // vbroadcastss 0x1e04(%rip),%ymm9 # 5648 <_sk_callback_avx+0x3be> .byte 196,193,124,89,193 // vmulps %ymm9,%ymm0,%ymm0 .byte 196,193,113,114,208,8 // vpsrld $0x8,%xmm8,%xmm1 .byte 197,233,114,211,8 // vpsrld $0x8,%xmm3,%xmm2 @@ -15415,7 +15355,7 @@ FUNCTION(_sk_store_8888_avx) _sk_store_8888_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 - .byte 196,98,125,24,5,154,29,0,0 // vbroadcastss 0x1d9a(%rip),%ymm8 # 56dc <_sk_callback_avx+0x3ca> + .byte 196,98,125,24,5,146,29,0,0 // vbroadcastss 0x1d92(%rip),%ymm8 # 564c <_sk_callback_avx+0x3c2> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,65,116,89,208 // vmulps %ymm8,%ymm1,%ymm10 @@ -15440,7 +15380,7 @@ _sk_store_8888_avx: .byte 196,65,45,86,192 // vorpd %ymm8,%ymm10,%ymm8 .byte 196,65,53,86,192 // vorpd %ymm8,%ymm9,%ymm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,10 // jne 39d0 <_sk_store_8888_avx+0x9c> + .byte 117,10 // jne 3948 <_sk_store_8888_avx+0x9c> .byte 196,65,124,17,4,186 // vmovups %ymm8,(%r10,%rdi,4) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -15448,9 +15388,9 @@ _sk_store_8888_avx: .byte 65,128,224,7 // and $0x7,%r8b .byte 65,254,200 // dec %r8b .byte 65,128,248,6 // cmp $0x6,%r8b - .byte 119,236 // ja 39cc <_sk_store_8888_avx+0x98> + .byte 119,236 // ja 3944 <_sk_store_8888_avx+0x98> .byte 69,15,182,192 // movzbl %r8b,%r8d - .byte 76,141,13,85,0,0,0 // lea 0x55(%rip),%r9 # 3a40 <_sk_store_8888_avx+0x10c> + .byte 76,141,13,85,0,0,0 // lea 0x55(%rip),%r9 # 39b8 <_sk_store_8888_avx+0x10c> .byte 75,99,4,129 // movslq (%r9,%r8,4),%rax .byte 76,1,200 // add %r9,%rax .byte 255,224 // jmpq *%rax @@ -15464,7 +15404,7 @@ _sk_store_8888_avx: .byte 196,67,121,22,68,186,8,2 // vpextrd $0x2,%xmm8,0x8(%r10,%rdi,4) .byte 196,67,121,22,68,186,4,1 // vpextrd $0x1,%xmm8,0x4(%r10,%rdi,4) .byte 196,65,121,126,4,186 // vmovd %xmm8,(%r10,%rdi,4) - .byte 235,143 // jmp 39cc <_sk_store_8888_avx+0x98> + .byte 235,143 // jmp 3944 <_sk_store_8888_avx+0x98> .byte 15,31,0 // nopl (%rax) .byte 245 // cmc .byte 255 // (bad) @@ -15502,7 +15442,7 @@ _sk_load_f16_avx: .byte 197,252,17,116,36,192 // vmovups %ymm6,-0x40(%rsp) .byte 197,252,17,108,36,160 // vmovups %ymm5,-0x60(%rsp) .byte 197,254,127,100,36,128 // vmovdqu %ymm4,-0x80(%rsp) - .byte 15,133,141,2,0,0 // jne 3d13 <_sk_load_f16_avx+0x2b7> + .byte 15,133,141,2,0,0 // jne 3c8b <_sk_load_f16_avx+0x2b7> .byte 197,121,16,4,248 // vmovupd (%rax,%rdi,8),%xmm8 .byte 197,249,16,84,248,16 // vmovupd 0x10(%rax,%rdi,8),%xmm2 .byte 197,249,16,76,248,32 // vmovupd 0x20(%rax,%rdi,8),%xmm1 @@ -15520,13 +15460,13 @@ _sk_load_f16_avx: .byte 197,249,105,201 // vpunpckhwd %xmm1,%xmm0,%xmm1 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 - .byte 196,98,125,24,37,1,28,0,0 // vbroadcastss 0x1c01(%rip),%ymm12 # 56e0 <_sk_callback_avx+0x3ce> + .byte 196,98,125,24,37,249,27,0,0 // vbroadcastss 0x1bf9(%rip),%ymm12 # 5650 <_sk_callback_avx+0x3c6> .byte 196,193,124,84,204 // vandps %ymm12,%ymm0,%ymm1 .byte 197,252,87,193 // vxorps %ymm1,%ymm0,%ymm0 .byte 196,195,125,25,198,1 // vextractf128 $0x1,%ymm0,%xmm14 - .byte 196,98,121,24,29,237,27,0,0 // vbroadcastss 0x1bed(%rip),%xmm11 # 56e4 <_sk_callback_avx+0x3d2> + .byte 196,98,121,24,29,229,27,0,0 // vbroadcastss 0x1be5(%rip),%xmm11 # 5654 <_sk_callback_avx+0x3ca> .byte 196,193,8,87,219 // vxorps %xmm11,%xmm14,%xmm3 - .byte 196,98,121,24,45,227,27,0,0 // vbroadcastss 0x1be3(%rip),%xmm13 # 56e8 <_sk_callback_avx+0x3d6> + .byte 196,98,121,24,45,219,27,0,0 // vbroadcastss 0x1bdb(%rip),%xmm13 # 5658 <_sk_callback_avx+0x3ce> .byte 197,145,102,219 // vpcmpgtd %xmm3,%xmm13,%xmm3 .byte 196,65,120,87,211 // vxorps %xmm11,%xmm0,%xmm10 .byte 196,65,17,102,210 // vpcmpgtd %xmm10,%xmm13,%xmm10 @@ -15540,7 +15480,7 @@ _sk_load_f16_avx: .byte 196,227,125,24,195,1 // vinsertf128 $0x1,%xmm3,%ymm0,%ymm0 .byte 197,252,86,193 // vorps %ymm1,%ymm0,%ymm0 .byte 196,227,125,25,193,1 // vextractf128 $0x1,%ymm0,%xmm1 - .byte 196,226,121,24,29,153,27,0,0 // vbroadcastss 0x1b99(%rip),%xmm3 # 56ec <_sk_callback_avx+0x3da> + .byte 196,226,121,24,29,145,27,0,0 // vbroadcastss 0x1b91(%rip),%xmm3 # 565c <_sk_callback_avx+0x3d2> .byte 197,241,254,203 // vpaddd %xmm3,%xmm1,%xmm1 .byte 197,249,254,195 // vpaddd %xmm3,%xmm0,%xmm0 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 @@ -15633,29 +15573,29 @@ _sk_load_f16_avx: .byte 197,123,16,4,248 // vmovsd (%rax,%rdi,8),%xmm8 .byte 196,65,49,239,201 // vpxor %xmm9,%xmm9,%xmm9 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,79 // je 3d72 <_sk_load_f16_avx+0x316> + .byte 116,79 // je 3cea <_sk_load_f16_avx+0x316> .byte 197,57,22,68,248,8 // vmovhpd 0x8(%rax,%rdi,8),%xmm8,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,67 // jb 3d72 <_sk_load_f16_avx+0x316> + .byte 114,67 // jb 3cea <_sk_load_f16_avx+0x316> .byte 197,251,16,84,248,16 // vmovsd 0x10(%rax,%rdi,8),%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 116,68 // je 3d7f <_sk_load_f16_avx+0x323> + .byte 116,68 // je 3cf7 <_sk_load_f16_avx+0x323> .byte 197,233,22,84,248,24 // vmovhpd 0x18(%rax,%rdi,8),%xmm2,%xmm2 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,56 // jb 3d7f <_sk_load_f16_avx+0x323> + .byte 114,56 // jb 3cf7 <_sk_load_f16_avx+0x323> .byte 197,251,16,76,248,32 // vmovsd 0x20(%rax,%rdi,8),%xmm1 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 15,132,70,253,255,255 // je 3a9d <_sk_load_f16_avx+0x41> + .byte 15,132,70,253,255,255 // je 3a15 <_sk_load_f16_avx+0x41> .byte 197,241,22,76,248,40 // vmovhpd 0x28(%rax,%rdi,8),%xmm1,%xmm1 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 15,130,54,253,255,255 // jb 3a9d <_sk_load_f16_avx+0x41> + .byte 15,130,54,253,255,255 // jb 3a15 <_sk_load_f16_avx+0x41> .byte 197,122,126,76,248,48 // vmovq 0x30(%rax,%rdi,8),%xmm9 - .byte 233,43,253,255,255 // jmpq 3a9d <_sk_load_f16_avx+0x41> + .byte 233,43,253,255,255 // jmpq 3a15 <_sk_load_f16_avx+0x41> .byte 197,241,87,201 // vxorpd %xmm1,%xmm1,%xmm1 .byte 197,233,87,210 // vxorpd %xmm2,%xmm2,%xmm2 - .byte 233,30,253,255,255 // jmpq 3a9d <_sk_load_f16_avx+0x41> + .byte 233,30,253,255,255 // jmpq 3a15 <_sk_load_f16_avx+0x41> .byte 197,241,87,201 // vxorpd %xmm1,%xmm1,%xmm1 - .byte 233,21,253,255,255 // jmpq 3a9d <_sk_load_f16_avx+0x41> + .byte 233,21,253,255,255 // jmpq 3a15 <_sk_load_f16_avx+0x41> HIDDEN _sk_gather_f16_avx .globl _sk_gather_f16_avx @@ -15719,13 +15659,13 @@ _sk_gather_f16_avx: .byte 197,249,105,210 // vpunpckhwd %xmm2,%xmm0,%xmm2 .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,194,1 // vinsertf128 $0x1,%xmm2,%ymm0,%ymm0 - .byte 196,98,125,24,37,93,24,0,0 // vbroadcastss 0x185d(%rip),%ymm12 # 56f0 <_sk_callback_avx+0x3de> + .byte 196,98,125,24,37,85,24,0,0 // vbroadcastss 0x1855(%rip),%ymm12 # 5660 <_sk_callback_avx+0x3d6> .byte 196,193,124,84,212 // vandps %ymm12,%ymm0,%ymm2 .byte 197,252,87,194 // vxorps %ymm2,%ymm0,%ymm0 .byte 196,195,125,25,198,1 // vextractf128 $0x1,%ymm0,%xmm14 - .byte 196,98,121,24,29,73,24,0,0 // vbroadcastss 0x1849(%rip),%xmm11 # 56f4 <_sk_callback_avx+0x3e2> + .byte 196,98,121,24,29,65,24,0,0 // vbroadcastss 0x1841(%rip),%xmm11 # 5664 <_sk_callback_avx+0x3da> .byte 196,193,8,87,219 // vxorps %xmm11,%xmm14,%xmm3 - .byte 196,98,121,24,45,63,24,0,0 // vbroadcastss 0x183f(%rip),%xmm13 # 56f8 <_sk_callback_avx+0x3e6> + .byte 196,98,121,24,45,55,24,0,0 // vbroadcastss 0x1837(%rip),%xmm13 # 5668 <_sk_callback_avx+0x3de> .byte 197,145,102,219 // vpcmpgtd %xmm3,%xmm13,%xmm3 .byte 196,65,120,87,211 // vxorps %xmm11,%xmm0,%xmm10 .byte 196,65,17,102,210 // vpcmpgtd %xmm10,%xmm13,%xmm10 @@ -15739,7 +15679,7 @@ _sk_gather_f16_avx: .byte 196,227,125,24,195,1 // vinsertf128 $0x1,%xmm3,%ymm0,%ymm0 .byte 197,252,86,194 // vorps %ymm2,%ymm0,%ymm0 .byte 196,227,125,25,194,1 // vextractf128 $0x1,%ymm0,%xmm2 - .byte 196,226,121,24,29,245,23,0,0 // vbroadcastss 0x17f5(%rip),%xmm3 # 56fc <_sk_callback_avx+0x3ea> + .byte 196,226,121,24,29,237,23,0,0 // vbroadcastss 0x17ed(%rip),%xmm3 # 566c <_sk_callback_avx+0x3e2> .byte 197,233,254,211 // vpaddd %xmm3,%xmm2,%xmm2 .byte 197,249,254,195 // vpaddd %xmm3,%xmm0,%xmm0 .byte 196,227,125,24,194,1 // vinsertf128 $0x1,%xmm2,%ymm0,%ymm0 @@ -15843,12 +15783,12 @@ _sk_store_f16_avx: .byte 197,252,17,52,36 // vmovups %ymm6,(%rsp) .byte 197,252,17,108,36,224 // vmovups %ymm5,-0x20(%rsp) .byte 197,252,17,100,36,192 // vmovups %ymm4,-0x40(%rsp) - .byte 196,98,125,24,13,14,22,0,0 // vbroadcastss 0x160e(%rip),%ymm9 # 5700 <_sk_callback_avx+0x3ee> + .byte 196,98,125,24,13,6,22,0,0 // vbroadcastss 0x1606(%rip),%ymm9 # 5670 <_sk_callback_avx+0x3e6> .byte 196,65,124,84,209 // vandps %ymm9,%ymm0,%ymm10 .byte 197,252,17,68,36,128 // vmovups %ymm0,-0x80(%rsp) .byte 196,65,124,87,218 // vxorps %ymm10,%ymm0,%ymm11 .byte 196,67,125,25,220,1 // vextractf128 $0x1,%ymm11,%xmm12 - .byte 196,98,121,24,5,243,21,0,0 // vbroadcastss 0x15f3(%rip),%xmm8 # 5704 <_sk_callback_avx+0x3f2> + .byte 196,98,121,24,5,235,21,0,0 // vbroadcastss 0x15eb(%rip),%xmm8 # 5674 <_sk_callback_avx+0x3ea> .byte 196,65,57,102,236 // vpcmpgtd %xmm12,%xmm8,%xmm13 .byte 196,65,57,102,243 // vpcmpgtd %xmm11,%xmm8,%xmm14 .byte 196,67,13,24,237,1 // vinsertf128 $0x1,%xmm13,%ymm14,%ymm13 @@ -15858,7 +15798,7 @@ _sk_store_f16_avx: .byte 196,67,13,24,242,1 // vinsertf128 $0x1,%xmm10,%ymm14,%ymm14 .byte 196,193,33,114,211,13 // vpsrld $0xd,%xmm11,%xmm11 .byte 196,193,25,114,212,13 // vpsrld $0xd,%xmm12,%xmm12 - .byte 196,98,125,24,21,186,21,0,0 // vbroadcastss 0x15ba(%rip),%ymm10 # 5708 <_sk_callback_avx+0x3f6> + .byte 196,98,125,24,21,178,21,0,0 // vbroadcastss 0x15b2(%rip),%ymm10 # 5678 <_sk_callback_avx+0x3ee> .byte 196,65,12,86,242 // vorps %ymm10,%ymm14,%ymm14 .byte 196,67,125,25,247,1 // vextractf128 $0x1,%ymm14,%xmm15 .byte 196,65,1,254,228 // vpaddd %xmm12,%xmm15,%xmm12 @@ -15940,7 +15880,7 @@ _sk_store_f16_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 72,133,201 // test %rcx,%rcx - .byte 117,66 // jne 432c <_sk_store_f16_avx+0x25e> + .byte 117,66 // jne 42a4 <_sk_store_f16_avx+0x25e> .byte 197,120,17,28,248 // vmovups %xmm11,(%rax,%rdi,8) .byte 197,120,17,84,248,16 // vmovups %xmm10,0x10(%rax,%rdi,8) .byte 197,120,17,76,248,32 // vmovups %xmm9,0x20(%rax,%rdi,8) @@ -15956,22 +15896,22 @@ _sk_store_f16_avx: .byte 255,224 // jmpq *%rax .byte 197,121,214,28,248 // vmovq %xmm11,(%rax,%rdi,8) .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,202 // je 4301 <_sk_store_f16_avx+0x233> + .byte 116,202 // je 4279 <_sk_store_f16_avx+0x233> .byte 197,121,23,92,248,8 // vmovhpd %xmm11,0x8(%rax,%rdi,8) .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,190 // jb 4301 <_sk_store_f16_avx+0x233> + .byte 114,190 // jb 4279 <_sk_store_f16_avx+0x233> .byte 197,121,214,84,248,16 // vmovq %xmm10,0x10(%rax,%rdi,8) - .byte 116,182 // je 4301 <_sk_store_f16_avx+0x233> + .byte 116,182 // je 4279 <_sk_store_f16_avx+0x233> .byte 197,121,23,84,248,24 // vmovhpd %xmm10,0x18(%rax,%rdi,8) .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,170 // jb 4301 <_sk_store_f16_avx+0x233> + .byte 114,170 // jb 4279 <_sk_store_f16_avx+0x233> .byte 197,121,214,76,248,32 // vmovq %xmm9,0x20(%rax,%rdi,8) - .byte 116,162 // je 4301 <_sk_store_f16_avx+0x233> + .byte 116,162 // je 4279 <_sk_store_f16_avx+0x233> .byte 197,121,23,76,248,40 // vmovhpd %xmm9,0x28(%rax,%rdi,8) .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,150 // jb 4301 <_sk_store_f16_avx+0x233> + .byte 114,150 // jb 4279 <_sk_store_f16_avx+0x233> .byte 197,121,214,68,248,48 // vmovq %xmm8,0x30(%rax,%rdi,8) - .byte 235,142 // jmp 4301 <_sk_store_f16_avx+0x233> + .byte 235,142 // jmp 4279 <_sk_store_f16_avx+0x233> HIDDEN _sk_load_u16_be_avx .globl _sk_load_u16_be_avx @@ -15981,7 +15921,7 @@ _sk_load_u16_be_avx: .byte 76,139,0 // mov (%rax),%r8 .byte 72,141,4,189,0,0,0,0 // lea 0x0(,%rdi,4),%rax .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,253,0,0,0 // jne 4486 <_sk_load_u16_be_avx+0x113> + .byte 15,133,253,0,0,0 // jne 43fe <_sk_load_u16_be_avx+0x113> .byte 196,65,121,16,4,64 // vmovupd (%r8,%rax,2),%xmm8 .byte 196,193,121,16,84,64,16 // vmovupd 0x10(%r8,%rax,2),%xmm2 .byte 196,193,121,16,92,64,32 // vmovupd 0x20(%r8,%rax,2),%xmm3 @@ -16003,7 +15943,7 @@ _sk_load_u16_be_avx: .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,29,18,19,0,0 // vbroadcastss 0x1312(%rip),%ymm11 # 570c <_sk_callback_avx+0x3fa> + .byte 196,98,125,24,29,10,19,0,0 // vbroadcastss 0x130a(%rip),%ymm11 # 567c <_sk_callback_avx+0x3f2> .byte 196,193,124,89,195 // vmulps %ymm11,%ymm0,%ymm0 .byte 197,177,109,202 // vpunpckhqdq %xmm2,%xmm9,%xmm1 .byte 197,233,113,241,8 // vpsllw $0x8,%xmm1,%xmm2 @@ -16037,29 +15977,29 @@ _sk_load_u16_be_avx: .byte 196,65,123,16,4,64 // vmovsd (%r8,%rax,2),%xmm8 .byte 196,65,49,239,201 // vpxor %xmm9,%xmm9,%xmm9 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,85 // je 44ec <_sk_load_u16_be_avx+0x179> + .byte 116,85 // je 4464 <_sk_load_u16_be_avx+0x179> .byte 196,65,57,22,68,64,8 // vmovhpd 0x8(%r8,%rax,2),%xmm8,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,72 // jb 44ec <_sk_load_u16_be_avx+0x179> + .byte 114,72 // jb 4464 <_sk_load_u16_be_avx+0x179> .byte 196,193,123,16,84,64,16 // vmovsd 0x10(%r8,%rax,2),%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 116,72 // je 44f9 <_sk_load_u16_be_avx+0x186> + .byte 116,72 // je 4471 <_sk_load_u16_be_avx+0x186> .byte 196,193,105,22,84,64,24 // vmovhpd 0x18(%r8,%rax,2),%xmm2,%xmm2 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,59 // jb 44f9 <_sk_load_u16_be_avx+0x186> + .byte 114,59 // jb 4471 <_sk_load_u16_be_avx+0x186> .byte 196,193,123,16,92,64,32 // vmovsd 0x20(%r8,%rax,2),%xmm3 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 15,132,213,254,255,255 // je 43a4 <_sk_load_u16_be_avx+0x31> + .byte 15,132,213,254,255,255 // je 431c <_sk_load_u16_be_avx+0x31> .byte 196,193,97,22,92,64,40 // vmovhpd 0x28(%r8,%rax,2),%xmm3,%xmm3 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 15,130,196,254,255,255 // jb 43a4 <_sk_load_u16_be_avx+0x31> + .byte 15,130,196,254,255,255 // jb 431c <_sk_load_u16_be_avx+0x31> .byte 196,65,122,126,76,64,48 // vmovq 0x30(%r8,%rax,2),%xmm9 - .byte 233,184,254,255,255 // jmpq 43a4 <_sk_load_u16_be_avx+0x31> + .byte 233,184,254,255,255 // jmpq 431c <_sk_load_u16_be_avx+0x31> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 .byte 197,233,87,210 // vxorpd %xmm2,%xmm2,%xmm2 - .byte 233,171,254,255,255 // jmpq 43a4 <_sk_load_u16_be_avx+0x31> + .byte 233,171,254,255,255 // jmpq 431c <_sk_load_u16_be_avx+0x31> .byte 197,225,87,219 // vxorpd %xmm3,%xmm3,%xmm3 - .byte 233,162,254,255,255 // jmpq 43a4 <_sk_load_u16_be_avx+0x31> + .byte 233,162,254,255,255 // jmpq 431c <_sk_load_u16_be_avx+0x31> HIDDEN _sk_load_rgb_u16_be_avx .globl _sk_load_rgb_u16_be_avx @@ -16069,7 +16009,7 @@ _sk_load_rgb_u16_be_avx: .byte 76,139,0 // mov (%rax),%r8 .byte 72,141,4,127 // lea (%rdi,%rdi,2),%rax .byte 72,133,201 // test %rcx,%rcx - .byte 15,133,243,0,0,0 // jne 4607 <_sk_load_rgb_u16_be_avx+0x105> + .byte 15,133,243,0,0,0 // jne 457f <_sk_load_rgb_u16_be_avx+0x105> .byte 196,193,122,111,4,64 // vmovdqu (%r8,%rax,2),%xmm0 .byte 196,193,122,111,84,64,12 // vmovdqu 0xc(%r8,%rax,2),%xmm2 .byte 196,193,122,111,76,64,24 // vmovdqu 0x18(%r8,%rax,2),%xmm1 @@ -16096,7 +16036,7 @@ _sk_load_rgb_u16_be_avx: .byte 196,226,121,51,192 // vpmovzxwd %xmm0,%xmm0 .byte 196,227,125,24,193,1 // vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 .byte 197,252,91,192 // vcvtdq2ps %ymm0,%ymm0 - .byte 196,98,125,24,29,114,17,0,0 // vbroadcastss 0x1172(%rip),%ymm11 # 5710 <_sk_callback_avx+0x3fe> + .byte 196,98,125,24,29,106,17,0,0 // vbroadcastss 0x116a(%rip),%ymm11 # 5680 <_sk_callback_avx+0x3f6> .byte 196,193,124,89,195 // vmulps %ymm11,%ymm0,%ymm0 .byte 197,185,109,202 // vpunpckhqdq %xmm2,%xmm8,%xmm1 .byte 197,233,113,241,8 // vpsllw $0x8,%xmm1,%xmm2 @@ -16117,41 +16057,41 @@ _sk_load_rgb_u16_be_avx: .byte 197,252,91,210 // vcvtdq2ps %ymm2,%ymm2 .byte 196,193,108,89,211 // vmulps %ymm11,%ymm2,%ymm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,29,15,17,0,0 // vbroadcastss 0x110f(%rip),%ymm3 # 5714 <_sk_callback_avx+0x402> + .byte 196,226,125,24,29,7,17,0,0 // vbroadcastss 0x1107(%rip),%ymm3 # 5684 <_sk_callback_avx+0x3fa> .byte 255,224 // jmpq *%rax .byte 196,193,121,110,4,64 // vmovd (%r8,%rax,2),%xmm0 .byte 196,193,121,196,68,64,4,2 // vpinsrw $0x2,0x4(%r8,%rax,2),%xmm0,%xmm0 .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 117,5 // jne 4620 <_sk_load_rgb_u16_be_avx+0x11e> - .byte 233,40,255,255,255 // jmpq 4548 <_sk_load_rgb_u16_be_avx+0x46> + .byte 117,5 // jne 4598 <_sk_load_rgb_u16_be_avx+0x11e> + .byte 233,40,255,255,255 // jmpq 44c0 <_sk_load_rgb_u16_be_avx+0x46> .byte 196,193,121,110,76,64,6 // vmovd 0x6(%r8,%rax,2),%xmm1 .byte 196,65,113,196,68,64,10,2 // vpinsrw $0x2,0xa(%r8,%rax,2),%xmm1,%xmm8 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,26 // jb 464f <_sk_load_rgb_u16_be_avx+0x14d> + .byte 114,26 // jb 45c7 <_sk_load_rgb_u16_be_avx+0x14d> .byte 196,193,121,110,76,64,12 // vmovd 0xc(%r8,%rax,2),%xmm1 .byte 196,193,113,196,84,64,16,2 // vpinsrw $0x2,0x10(%r8,%rax,2),%xmm1,%xmm2 .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 117,10 // jne 4654 <_sk_load_rgb_u16_be_avx+0x152> - .byte 233,249,254,255,255 // jmpq 4548 <_sk_load_rgb_u16_be_avx+0x46> - .byte 233,244,254,255,255 // jmpq 4548 <_sk_load_rgb_u16_be_avx+0x46> + .byte 117,10 // jne 45cc <_sk_load_rgb_u16_be_avx+0x152> + .byte 233,249,254,255,255 // jmpq 44c0 <_sk_load_rgb_u16_be_avx+0x46> + .byte 233,244,254,255,255 // jmpq 44c0 <_sk_load_rgb_u16_be_avx+0x46> .byte 196,193,121,110,76,64,18 // vmovd 0x12(%r8,%rax,2),%xmm1 .byte 196,65,113,196,76,64,22,2 // vpinsrw $0x2,0x16(%r8,%rax,2),%xmm1,%xmm9 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,26 // jb 4683 <_sk_load_rgb_u16_be_avx+0x181> + .byte 114,26 // jb 45fb <_sk_load_rgb_u16_be_avx+0x181> .byte 196,193,121,110,76,64,24 // vmovd 0x18(%r8,%rax,2),%xmm1 .byte 196,193,113,196,76,64,28,2 // vpinsrw $0x2,0x1c(%r8,%rax,2),%xmm1,%xmm1 .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 117,10 // jne 4688 <_sk_load_rgb_u16_be_avx+0x186> - .byte 233,197,254,255,255 // jmpq 4548 <_sk_load_rgb_u16_be_avx+0x46> - .byte 233,192,254,255,255 // jmpq 4548 <_sk_load_rgb_u16_be_avx+0x46> + .byte 117,10 // jne 4600 <_sk_load_rgb_u16_be_avx+0x186> + .byte 233,197,254,255,255 // jmpq 44c0 <_sk_load_rgb_u16_be_avx+0x46> + .byte 233,192,254,255,255 // jmpq 44c0 <_sk_load_rgb_u16_be_avx+0x46> .byte 196,193,121,110,92,64,30 // vmovd 0x1e(%r8,%rax,2),%xmm3 .byte 196,65,97,196,92,64,34,2 // vpinsrw $0x2,0x22(%r8,%rax,2),%xmm3,%xmm11 .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,20 // jb 46b1 <_sk_load_rgb_u16_be_avx+0x1af> + .byte 114,20 // jb 4629 <_sk_load_rgb_u16_be_avx+0x1af> .byte 196,193,121,110,92,64,36 // vmovd 0x24(%r8,%rax,2),%xmm3 .byte 196,193,97,196,92,64,40,2 // vpinsrw $0x2,0x28(%r8,%rax,2),%xmm3,%xmm3 - .byte 233,151,254,255,255 // jmpq 4548 <_sk_load_rgb_u16_be_avx+0x46> - .byte 233,146,254,255,255 // jmpq 4548 <_sk_load_rgb_u16_be_avx+0x46> + .byte 233,151,254,255,255 // jmpq 44c0 <_sk_load_rgb_u16_be_avx+0x46> + .byte 233,146,254,255,255 // jmpq 44c0 <_sk_load_rgb_u16_be_avx+0x46> HIDDEN _sk_store_u16_be_avx .globl _sk_store_u16_be_avx @@ -16160,7 +16100,7 @@ _sk_store_u16_be_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,0 // mov (%rax),%r8 .byte 72,141,4,189,0,0,0,0 // lea 0x0(,%rdi,4),%rax - .byte 196,98,125,24,5,76,16,0,0 // vbroadcastss 0x104c(%rip),%ymm8 # 5718 <_sk_callback_avx+0x406> + .byte 196,98,125,24,5,68,16,0,0 // vbroadcastss 0x1044(%rip),%ymm8 # 5688 <_sk_callback_avx+0x3fe> .byte 196,65,124,89,200 // vmulps %ymm8,%ymm0,%ymm9 .byte 196,65,125,91,201 // vcvtps2dq %ymm9,%ymm9 .byte 196,67,125,25,202,1 // vextractf128 $0x1,%ymm9,%xmm10 @@ -16198,7 +16138,7 @@ _sk_store_u16_be_avx: .byte 196,65,17,98,200 // vpunpckldq %xmm8,%xmm13,%xmm9 .byte 196,65,17,106,192 // vpunpckhdq %xmm8,%xmm13,%xmm8 .byte 72,133,201 // test %rcx,%rcx - .byte 117,31 // jne 47b0 <_sk_store_u16_be_avx+0xfa> + .byte 117,31 // jne 4728 <_sk_store_u16_be_avx+0xfa> .byte 196,65,120,17,28,64 // vmovups %xmm11,(%r8,%rax,2) .byte 196,65,120,17,84,64,16 // vmovups %xmm10,0x10(%r8,%rax,2) .byte 196,65,120,17,76,64,32 // vmovups %xmm9,0x20(%r8,%rax,2) @@ -16207,22 +16147,22 @@ _sk_store_u16_be_avx: .byte 255,224 // jmpq *%rax .byte 196,65,121,214,28,64 // vmovq %xmm11,(%r8,%rax,2) .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,240 // je 47ac <_sk_store_u16_be_avx+0xf6> + .byte 116,240 // je 4724 <_sk_store_u16_be_avx+0xf6> .byte 196,65,121,23,92,64,8 // vmovhpd %xmm11,0x8(%r8,%rax,2) .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,227 // jb 47ac <_sk_store_u16_be_avx+0xf6> + .byte 114,227 // jb 4724 <_sk_store_u16_be_avx+0xf6> .byte 196,65,121,214,84,64,16 // vmovq %xmm10,0x10(%r8,%rax,2) - .byte 116,218 // je 47ac <_sk_store_u16_be_avx+0xf6> + .byte 116,218 // je 4724 <_sk_store_u16_be_avx+0xf6> .byte 196,65,121,23,84,64,24 // vmovhpd %xmm10,0x18(%r8,%rax,2) .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,205 // jb 47ac <_sk_store_u16_be_avx+0xf6> + .byte 114,205 // jb 4724 <_sk_store_u16_be_avx+0xf6> .byte 196,65,121,214,76,64,32 // vmovq %xmm9,0x20(%r8,%rax,2) - .byte 116,196 // je 47ac <_sk_store_u16_be_avx+0xf6> + .byte 116,196 // je 4724 <_sk_store_u16_be_avx+0xf6> .byte 196,65,121,23,76,64,40 // vmovhpd %xmm9,0x28(%r8,%rax,2) .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,183 // jb 47ac <_sk_store_u16_be_avx+0xf6> + .byte 114,183 // jb 4724 <_sk_store_u16_be_avx+0xf6> .byte 196,65,121,214,68,64,48 // vmovq %xmm8,0x30(%r8,%rax,2) - .byte 235,174 // jmp 47ac <_sk_store_u16_be_avx+0xf6> + .byte 235,174 // jmp 4724 <_sk_store_u16_be_avx+0xf6> HIDDEN _sk_load_f32_avx .globl _sk_load_f32_avx @@ -16230,10 +16170,10 @@ FUNCTION(_sk_load_f32_avx) _sk_load_f32_avx: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 119,110 // ja 4874 <_sk_load_f32_avx+0x76> + .byte 119,110 // ja 47ec <_sk_load_f32_avx+0x76> .byte 76,139,0 // mov (%rax),%r8 .byte 76,141,12,189,0,0,0,0 // lea 0x0(,%rdi,4),%r9 - .byte 76,141,21,132,0,0,0 // lea 0x84(%rip),%r10 # 489c <_sk_load_f32_avx+0x9e> + .byte 76,141,21,132,0,0,0 // lea 0x84(%rip),%r10 # 4814 <_sk_load_f32_avx+0x9e> .byte 73,99,4,138 // movslq (%r10,%rcx,4),%rax .byte 76,1,208 // add %r10,%rax .byte 255,224 // jmpq *%rax @@ -16292,7 +16232,7 @@ _sk_store_f32_avx: .byte 196,65,37,20,196 // vunpcklpd %ymm12,%ymm11,%ymm8 .byte 196,65,37,21,220 // vunpckhpd %ymm12,%ymm11,%ymm11 .byte 72,133,201 // test %rcx,%rcx - .byte 117,55 // jne 4929 <_sk_store_f32_avx+0x6d> + .byte 117,55 // jne 48a1 <_sk_store_f32_avx+0x6d> .byte 196,67,45,24,225,1 // vinsertf128 $0x1,%xmm9,%ymm10,%ymm12 .byte 196,67,61,24,235,1 // vinsertf128 $0x1,%xmm11,%ymm8,%ymm13 .byte 196,67,45,6,201,49 // vperm2f128 $0x31,%ymm9,%ymm10,%ymm9 @@ -16305,22 +16245,22 @@ _sk_store_f32_avx: .byte 255,224 // jmpq *%rax .byte 196,65,121,17,20,128 // vmovupd %xmm10,(%r8,%rax,4) .byte 72,131,249,1 // cmp $0x1,%rcx - .byte 116,240 // je 4925 <_sk_store_f32_avx+0x69> + .byte 116,240 // je 489d <_sk_store_f32_avx+0x69> .byte 196,65,121,17,76,128,16 // vmovupd %xmm9,0x10(%r8,%rax,4) .byte 72,131,249,3 // cmp $0x3,%rcx - .byte 114,227 // jb 4925 <_sk_store_f32_avx+0x69> + .byte 114,227 // jb 489d <_sk_store_f32_avx+0x69> .byte 196,65,121,17,68,128,32 // vmovupd %xmm8,0x20(%r8,%rax,4) - .byte 116,218 // je 4925 <_sk_store_f32_avx+0x69> + .byte 116,218 // je 489d <_sk_store_f32_avx+0x69> .byte 196,65,121,17,92,128,48 // vmovupd %xmm11,0x30(%r8,%rax,4) .byte 72,131,249,5 // cmp $0x5,%rcx - .byte 114,205 // jb 4925 <_sk_store_f32_avx+0x69> + .byte 114,205 // jb 489d <_sk_store_f32_avx+0x69> .byte 196,67,125,25,84,128,64,1 // vextractf128 $0x1,%ymm10,0x40(%r8,%rax,4) - .byte 116,195 // je 4925 <_sk_store_f32_avx+0x69> + .byte 116,195 // je 489d <_sk_store_f32_avx+0x69> .byte 196,67,125,25,76,128,80,1 // vextractf128 $0x1,%ymm9,0x50(%r8,%rax,4) .byte 72,131,249,7 // cmp $0x7,%rcx - .byte 114,181 // jb 4925 <_sk_store_f32_avx+0x69> + .byte 114,181 // jb 489d <_sk_store_f32_avx+0x69> .byte 196,67,125,25,68,128,96,1 // vextractf128 $0x1,%ymm8,0x60(%r8,%rax,4) - .byte 235,171 // jmp 4925 <_sk_store_f32_avx+0x69> + .byte 235,171 // jmp 489d <_sk_store_f32_avx+0x69> HIDDEN _sk_clamp_x_avx .globl _sk_clamp_x_avx @@ -16456,12 +16396,12 @@ HIDDEN _sk_luminance_to_alpha_avx .globl _sk_luminance_to_alpha_avx FUNCTION(_sk_luminance_to_alpha_avx) _sk_luminance_to_alpha_avx: - .byte 196,226,125,24,29,215,11,0,0 // vbroadcastss 0xbd7(%rip),%ymm3 # 571c <_sk_callback_avx+0x40a> + .byte 196,226,125,24,29,207,11,0,0 // vbroadcastss 0xbcf(%rip),%ymm3 # 568c <_sk_callback_avx+0x402> .byte 197,252,89,195 // vmulps %ymm3,%ymm0,%ymm0 - .byte 196,226,125,24,29,206,11,0,0 // vbroadcastss 0xbce(%rip),%ymm3 # 5720 <_sk_callback_avx+0x40e> + .byte 196,226,125,24,29,198,11,0,0 // vbroadcastss 0xbc6(%rip),%ymm3 # 5690 <_sk_callback_avx+0x406> .byte 197,244,89,203 // vmulps %ymm3,%ymm1,%ymm1 .byte 197,252,88,193 // vaddps %ymm1,%ymm0,%ymm0 - .byte 196,226,125,24,13,193,11,0,0 // vbroadcastss 0xbc1(%rip),%ymm1 # 5724 <_sk_callback_avx+0x412> + .byte 196,226,125,24,13,185,11,0,0 // vbroadcastss 0xbb9(%rip),%ymm1 # 5694 <_sk_callback_avx+0x40a> .byte 197,236,89,201 // vmulps %ymm1,%ymm2,%ymm1 .byte 197,252,88,217 // vaddps %ymm1,%ymm0,%ymm3 .byte 72,173 // lods %ds:(%rsi),%rax @@ -16639,7 +16579,7 @@ _sk_linear_gradient_avx: .byte 196,226,125,24,88,28 // vbroadcastss 0x1c(%rax),%ymm3 .byte 76,139,0 // mov (%rax),%r8 .byte 77,133,192 // test %r8,%r8 - .byte 15,132,146,0,0,0 // je 4eb9 <_sk_linear_gradient_avx+0xb8> + .byte 15,132,146,0,0,0 // je 4e31 <_sk_linear_gradient_avx+0xb8> .byte 72,139,64,8 // mov 0x8(%rax),%rax .byte 72,131,192,32 // add $0x20,%rax .byte 196,65,28,87,228 // vxorps %ymm12,%ymm12,%ymm12 @@ -16666,8 +16606,8 @@ _sk_linear_gradient_avx: .byte 196,227,13,74,219,208 // vblendvps %ymm13,%ymm3,%ymm14,%ymm3 .byte 72,131,192,36 // add $0x24,%rax .byte 73,255,200 // dec %r8 - .byte 117,140 // jne 4e43 <_sk_linear_gradient_avx+0x42> - .byte 235,20 // jmp 4ecd <_sk_linear_gradient_avx+0xcc> + .byte 117,140 // jne 4dbb <_sk_linear_gradient_avx+0x42> + .byte 235,20 // jmp 4e45 <_sk_linear_gradient_avx+0xcc> .byte 196,65,36,87,219 // vxorps %ymm11,%ymm11,%ymm11 .byte 196,65,44,87,210 // vxorps %ymm10,%ymm10,%ymm10 .byte 196,65,52,87,201 // vxorps %ymm9,%ymm9,%ymm9 @@ -16714,7 +16654,7 @@ HIDDEN _sk_save_xy_avx FUNCTION(_sk_save_xy_avx) _sk_save_xy_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,205,7,0,0 // vbroadcastss 0x7cd(%rip),%ymm8 # 5728 <_sk_callback_avx+0x416> + .byte 196,98,125,24,5,197,7,0,0 // vbroadcastss 0x7c5(%rip),%ymm8 # 5698 <_sk_callback_avx+0x40e> .byte 196,65,124,88,200 // vaddps %ymm8,%ymm0,%ymm9 .byte 196,67,125,8,209,1 // vroundps $0x1,%ymm9,%ymm10 .byte 196,65,52,92,202 // vsubps %ymm10,%ymm9,%ymm9 @@ -16751,9 +16691,9 @@ HIDDEN _sk_bilinear_nx_avx FUNCTION(_sk_bilinear_nx_avx) _sk_bilinear_nx_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,89,7,0,0 // vbroadcastss 0x759(%rip),%ymm0 # 572c <_sk_callback_avx+0x41a> + .byte 196,226,125,24,5,81,7,0,0 // vbroadcastss 0x751(%rip),%ymm0 # 569c <_sk_callback_avx+0x412> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,80,7,0,0 // vbroadcastss 0x750(%rip),%ymm8 # 5730 <_sk_callback_avx+0x41e> + .byte 196,98,125,24,5,72,7,0,0 // vbroadcastss 0x748(%rip),%ymm8 # 56a0 <_sk_callback_avx+0x416> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -16764,7 +16704,7 @@ HIDDEN _sk_bilinear_px_avx FUNCTION(_sk_bilinear_px_avx) _sk_bilinear_px_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,56,7,0,0 // vbroadcastss 0x738(%rip),%ymm0 # 5734 <_sk_callback_avx+0x422> + .byte 196,226,125,24,5,48,7,0,0 // vbroadcastss 0x730(%rip),%ymm0 # 56a4 <_sk_callback_avx+0x41a> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 .byte 197,124,16,64,64 // vmovups 0x40(%rax),%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -16776,9 +16716,9 @@ HIDDEN _sk_bilinear_ny_avx FUNCTION(_sk_bilinear_ny_avx) _sk_bilinear_ny_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,28,7,0,0 // vbroadcastss 0x71c(%rip),%ymm1 # 5738 <_sk_callback_avx+0x426> + .byte 196,226,125,24,13,20,7,0,0 // vbroadcastss 0x714(%rip),%ymm1 # 56a8 <_sk_callback_avx+0x41e> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,18,7,0,0 // vbroadcastss 0x712(%rip),%ymm8 # 573c <_sk_callback_avx+0x42a> + .byte 196,98,125,24,5,10,7,0,0 // vbroadcastss 0x70a(%rip),%ymm8 # 56ac <_sk_callback_avx+0x422> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -16789,7 +16729,7 @@ HIDDEN _sk_bilinear_py_avx FUNCTION(_sk_bilinear_py_avx) _sk_bilinear_py_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,250,6,0,0 // vbroadcastss 0x6fa(%rip),%ymm1 # 5740 <_sk_callback_avx+0x42e> + .byte 196,226,125,24,13,242,6,0,0 // vbroadcastss 0x6f2(%rip),%ymm1 # 56b0 <_sk_callback_avx+0x426> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 .byte 197,124,16,64,96 // vmovups 0x60(%rax),%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -16801,14 +16741,14 @@ HIDDEN _sk_bicubic_n3x_avx FUNCTION(_sk_bicubic_n3x_avx) _sk_bicubic_n3x_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,221,6,0,0 // vbroadcastss 0x6dd(%rip),%ymm0 # 5744 <_sk_callback_avx+0x432> + .byte 196,226,125,24,5,213,6,0,0 // vbroadcastss 0x6d5(%rip),%ymm0 # 56b4 <_sk_callback_avx+0x42a> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,212,6,0,0 // vbroadcastss 0x6d4(%rip),%ymm8 # 5748 <_sk_callback_avx+0x436> + .byte 196,98,125,24,5,204,6,0,0 // vbroadcastss 0x6cc(%rip),%ymm8 # 56b8 <_sk_callback_avx+0x42e> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,197,6,0,0 // vbroadcastss 0x6c5(%rip),%ymm10 # 574c <_sk_callback_avx+0x43a> + .byte 196,98,125,24,21,189,6,0,0 // vbroadcastss 0x6bd(%rip),%ymm10 # 56bc <_sk_callback_avx+0x432> .byte 196,65,60,89,194 // vmulps %ymm10,%ymm8,%ymm8 - .byte 196,98,125,24,21,187,6,0,0 // vbroadcastss 0x6bb(%rip),%ymm10 # 5750 <_sk_callback_avx+0x43e> + .byte 196,98,125,24,21,179,6,0,0 // vbroadcastss 0x6b3(%rip),%ymm10 # 56c0 <_sk_callback_avx+0x436> .byte 196,65,60,88,194 // vaddps %ymm10,%ymm8,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -16820,19 +16760,19 @@ HIDDEN _sk_bicubic_n1x_avx FUNCTION(_sk_bicubic_n1x_avx) _sk_bicubic_n1x_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,158,6,0,0 // vbroadcastss 0x69e(%rip),%ymm0 # 5754 <_sk_callback_avx+0x442> + .byte 196,226,125,24,5,150,6,0,0 // vbroadcastss 0x696(%rip),%ymm0 # 56c4 <_sk_callback_avx+0x43a> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 - .byte 196,98,125,24,5,149,6,0,0 // vbroadcastss 0x695(%rip),%ymm8 # 5758 <_sk_callback_avx+0x446> + .byte 196,98,125,24,5,141,6,0,0 // vbroadcastss 0x68d(%rip),%ymm8 # 56c8 <_sk_callback_avx+0x43e> .byte 197,60,92,64,64 // vsubps 0x40(%rax),%ymm8,%ymm8 - .byte 196,98,125,24,13,139,6,0,0 // vbroadcastss 0x68b(%rip),%ymm9 # 575c <_sk_callback_avx+0x44a> + .byte 196,98,125,24,13,131,6,0,0 // vbroadcastss 0x683(%rip),%ymm9 # 56cc <_sk_callback_avx+0x442> .byte 196,65,60,89,201 // vmulps %ymm9,%ymm8,%ymm9 - .byte 196,98,125,24,21,129,6,0,0 // vbroadcastss 0x681(%rip),%ymm10 # 5760 <_sk_callback_avx+0x44e> + .byte 196,98,125,24,21,121,6,0,0 // vbroadcastss 0x679(%rip),%ymm10 # 56d0 <_sk_callback_avx+0x446> .byte 196,65,52,88,202 // vaddps %ymm10,%ymm9,%ymm9 .byte 196,65,60,89,201 // vmulps %ymm9,%ymm8,%ymm9 - .byte 196,98,125,24,21,114,6,0,0 // vbroadcastss 0x672(%rip),%ymm10 # 5764 <_sk_callback_avx+0x452> + .byte 196,98,125,24,21,106,6,0,0 // vbroadcastss 0x66a(%rip),%ymm10 # 56d4 <_sk_callback_avx+0x44a> .byte 196,65,52,88,202 // vaddps %ymm10,%ymm9,%ymm9 .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 - .byte 196,98,125,24,13,99,6,0,0 // vbroadcastss 0x663(%rip),%ymm9 # 5768 <_sk_callback_avx+0x456> + .byte 196,98,125,24,13,91,6,0,0 // vbroadcastss 0x65b(%rip),%ymm9 # 56d8 <_sk_callback_avx+0x44e> .byte 196,65,60,88,193 // vaddps %ymm9,%ymm8,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -16843,17 +16783,17 @@ HIDDEN _sk_bicubic_p1x_avx FUNCTION(_sk_bicubic_p1x_avx) _sk_bicubic_p1x_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,75,6,0,0 // vbroadcastss 0x64b(%rip),%ymm8 # 576c <_sk_callback_avx+0x45a> + .byte 196,98,125,24,5,67,6,0,0 // vbroadcastss 0x643(%rip),%ymm8 # 56dc <_sk_callback_avx+0x452> .byte 197,188,88,0 // vaddps (%rax),%ymm8,%ymm0 .byte 197,124,16,72,64 // vmovups 0x40(%rax),%ymm9 - .byte 196,98,125,24,21,61,6,0,0 // vbroadcastss 0x63d(%rip),%ymm10 # 5770 <_sk_callback_avx+0x45e> + .byte 196,98,125,24,21,53,6,0,0 // vbroadcastss 0x635(%rip),%ymm10 # 56e0 <_sk_callback_avx+0x456> .byte 196,65,52,89,210 // vmulps %ymm10,%ymm9,%ymm10 - .byte 196,98,125,24,29,51,6,0,0 // vbroadcastss 0x633(%rip),%ymm11 # 5774 <_sk_callback_avx+0x462> + .byte 196,98,125,24,29,43,6,0,0 // vbroadcastss 0x62b(%rip),%ymm11 # 56e4 <_sk_callback_avx+0x45a> .byte 196,65,44,88,211 // vaddps %ymm11,%ymm10,%ymm10 .byte 196,65,52,89,210 // vmulps %ymm10,%ymm9,%ymm10 .byte 196,65,44,88,192 // vaddps %ymm8,%ymm10,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 - .byte 196,98,125,24,13,26,6,0,0 // vbroadcastss 0x61a(%rip),%ymm9 # 5778 <_sk_callback_avx+0x466> + .byte 196,98,125,24,13,18,6,0,0 // vbroadcastss 0x612(%rip),%ymm9 # 56e8 <_sk_callback_avx+0x45e> .byte 196,65,60,88,193 // vaddps %ymm9,%ymm8,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -16864,13 +16804,13 @@ HIDDEN _sk_bicubic_p3x_avx FUNCTION(_sk_bicubic_p3x_avx) _sk_bicubic_p3x_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,5,2,6,0,0 // vbroadcastss 0x602(%rip),%ymm0 # 577c <_sk_callback_avx+0x46a> + .byte 196,226,125,24,5,250,5,0,0 // vbroadcastss 0x5fa(%rip),%ymm0 # 56ec <_sk_callback_avx+0x462> .byte 197,252,88,0 // vaddps (%rax),%ymm0,%ymm0 .byte 197,124,16,64,64 // vmovups 0x40(%rax),%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,239,5,0,0 // vbroadcastss 0x5ef(%rip),%ymm10 # 5780 <_sk_callback_avx+0x46e> + .byte 196,98,125,24,21,231,5,0,0 // vbroadcastss 0x5e7(%rip),%ymm10 # 56f0 <_sk_callback_avx+0x466> .byte 196,65,60,89,194 // vmulps %ymm10,%ymm8,%ymm8 - .byte 196,98,125,24,21,229,5,0,0 // vbroadcastss 0x5e5(%rip),%ymm10 # 5784 <_sk_callback_avx+0x472> + .byte 196,98,125,24,21,221,5,0,0 // vbroadcastss 0x5dd(%rip),%ymm10 # 56f4 <_sk_callback_avx+0x46a> .byte 196,65,60,88,194 // vaddps %ymm10,%ymm8,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 .byte 197,124,17,128,128,0,0,0 // vmovups %ymm8,0x80(%rax) @@ -16882,14 +16822,14 @@ HIDDEN _sk_bicubic_n3y_avx FUNCTION(_sk_bicubic_n3y_avx) _sk_bicubic_n3y_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,200,5,0,0 // vbroadcastss 0x5c8(%rip),%ymm1 # 5788 <_sk_callback_avx+0x476> + .byte 196,226,125,24,13,192,5,0,0 // vbroadcastss 0x5c0(%rip),%ymm1 # 56f8 <_sk_callback_avx+0x46e> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,190,5,0,0 // vbroadcastss 0x5be(%rip),%ymm8 # 578c <_sk_callback_avx+0x47a> + .byte 196,98,125,24,5,182,5,0,0 // vbroadcastss 0x5b6(%rip),%ymm8 # 56fc <_sk_callback_avx+0x472> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,175,5,0,0 // vbroadcastss 0x5af(%rip),%ymm10 # 5790 <_sk_callback_avx+0x47e> + .byte 196,98,125,24,21,167,5,0,0 // vbroadcastss 0x5a7(%rip),%ymm10 # 5700 <_sk_callback_avx+0x476> .byte 196,65,60,89,194 // vmulps %ymm10,%ymm8,%ymm8 - .byte 196,98,125,24,21,165,5,0,0 // vbroadcastss 0x5a5(%rip),%ymm10 # 5794 <_sk_callback_avx+0x482> + .byte 196,98,125,24,21,157,5,0,0 // vbroadcastss 0x59d(%rip),%ymm10 # 5704 <_sk_callback_avx+0x47a> .byte 196,65,60,88,194 // vaddps %ymm10,%ymm8,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -16901,19 +16841,19 @@ HIDDEN _sk_bicubic_n1y_avx FUNCTION(_sk_bicubic_n1y_avx) _sk_bicubic_n1y_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,136,5,0,0 // vbroadcastss 0x588(%rip),%ymm1 # 5798 <_sk_callback_avx+0x486> + .byte 196,226,125,24,13,128,5,0,0 // vbroadcastss 0x580(%rip),%ymm1 # 5708 <_sk_callback_avx+0x47e> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 - .byte 196,98,125,24,5,126,5,0,0 // vbroadcastss 0x57e(%rip),%ymm8 # 579c <_sk_callback_avx+0x48a> + .byte 196,98,125,24,5,118,5,0,0 // vbroadcastss 0x576(%rip),%ymm8 # 570c <_sk_callback_avx+0x482> .byte 197,60,92,64,96 // vsubps 0x60(%rax),%ymm8,%ymm8 - .byte 196,98,125,24,13,116,5,0,0 // vbroadcastss 0x574(%rip),%ymm9 # 57a0 <_sk_callback_avx+0x48e> + .byte 196,98,125,24,13,108,5,0,0 // vbroadcastss 0x56c(%rip),%ymm9 # 5710 <_sk_callback_avx+0x486> .byte 196,65,60,89,201 // vmulps %ymm9,%ymm8,%ymm9 - .byte 196,98,125,24,21,106,5,0,0 // vbroadcastss 0x56a(%rip),%ymm10 # 57a4 <_sk_callback_avx+0x492> + .byte 196,98,125,24,21,98,5,0,0 // vbroadcastss 0x562(%rip),%ymm10 # 5714 <_sk_callback_avx+0x48a> .byte 196,65,52,88,202 // vaddps %ymm10,%ymm9,%ymm9 .byte 196,65,60,89,201 // vmulps %ymm9,%ymm8,%ymm9 - .byte 196,98,125,24,21,91,5,0,0 // vbroadcastss 0x55b(%rip),%ymm10 # 57a8 <_sk_callback_avx+0x496> + .byte 196,98,125,24,21,83,5,0,0 // vbroadcastss 0x553(%rip),%ymm10 # 5718 <_sk_callback_avx+0x48e> .byte 196,65,52,88,202 // vaddps %ymm10,%ymm9,%ymm9 .byte 196,65,60,89,193 // vmulps %ymm9,%ymm8,%ymm8 - .byte 196,98,125,24,13,76,5,0,0 // vbroadcastss 0x54c(%rip),%ymm9 # 57ac <_sk_callback_avx+0x49a> + .byte 196,98,125,24,13,68,5,0,0 // vbroadcastss 0x544(%rip),%ymm9 # 571c <_sk_callback_avx+0x492> .byte 196,65,60,88,193 // vaddps %ymm9,%ymm8,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -16924,17 +16864,17 @@ HIDDEN _sk_bicubic_p1y_avx FUNCTION(_sk_bicubic_p1y_avx) _sk_bicubic_p1y_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,98,125,24,5,52,5,0,0 // vbroadcastss 0x534(%rip),%ymm8 # 57b0 <_sk_callback_avx+0x49e> + .byte 196,98,125,24,5,44,5,0,0 // vbroadcastss 0x52c(%rip),%ymm8 # 5720 <_sk_callback_avx+0x496> .byte 197,188,88,72,32 // vaddps 0x20(%rax),%ymm8,%ymm1 .byte 197,124,16,72,96 // vmovups 0x60(%rax),%ymm9 - .byte 196,98,125,24,21,37,5,0,0 // vbroadcastss 0x525(%rip),%ymm10 # 57b4 <_sk_callback_avx+0x4a2> + .byte 196,98,125,24,21,29,5,0,0 // vbroadcastss 0x51d(%rip),%ymm10 # 5724 <_sk_callback_avx+0x49a> .byte 196,65,52,89,210 // vmulps %ymm10,%ymm9,%ymm10 - .byte 196,98,125,24,29,27,5,0,0 // vbroadcastss 0x51b(%rip),%ymm11 # 57b8 <_sk_callback_avx+0x4a6> + .byte 196,98,125,24,29,19,5,0,0 // vbroadcastss 0x513(%rip),%ymm11 # 5728 <_sk_callback_avx+0x49e> .byte 196,65,44,88,211 // vaddps %ymm11,%ymm10,%ymm10 .byte 196,65,52,89,210 // vmulps %ymm10,%ymm9,%ymm10 .byte 196,65,44,88,192 // vaddps %ymm8,%ymm10,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 - .byte 196,98,125,24,13,2,5,0,0 // vbroadcastss 0x502(%rip),%ymm9 # 57bc <_sk_callback_avx+0x4aa> + .byte 196,98,125,24,13,250,4,0,0 // vbroadcastss 0x4fa(%rip),%ymm9 # 572c <_sk_callback_avx+0x4a2> .byte 196,65,60,88,193 // vaddps %ymm9,%ymm8,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -16945,13 +16885,13 @@ HIDDEN _sk_bicubic_p3y_avx FUNCTION(_sk_bicubic_p3y_avx) _sk_bicubic_p3y_avx: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 196,226,125,24,13,234,4,0,0 // vbroadcastss 0x4ea(%rip),%ymm1 # 57c0 <_sk_callback_avx+0x4ae> + .byte 196,226,125,24,13,226,4,0,0 // vbroadcastss 0x4e2(%rip),%ymm1 # 5730 <_sk_callback_avx+0x4a6> .byte 197,244,88,72,32 // vaddps 0x20(%rax),%ymm1,%ymm1 .byte 197,124,16,64,96 // vmovups 0x60(%rax),%ymm8 .byte 196,65,60,89,200 // vmulps %ymm8,%ymm8,%ymm9 - .byte 196,98,125,24,21,214,4,0,0 // vbroadcastss 0x4d6(%rip),%ymm10 # 57c4 <_sk_callback_avx+0x4b2> + .byte 196,98,125,24,21,206,4,0,0 // vbroadcastss 0x4ce(%rip),%ymm10 # 5734 <_sk_callback_avx+0x4aa> .byte 196,65,60,89,194 // vmulps %ymm10,%ymm8,%ymm8 - .byte 196,98,125,24,21,204,4,0,0 // vbroadcastss 0x4cc(%rip),%ymm10 # 57c8 <_sk_callback_avx+0x4b6> + .byte 196,98,125,24,21,196,4,0,0 // vbroadcastss 0x4c4(%rip),%ymm10 # 5738 <_sk_callback_avx+0x4ae> .byte 196,65,60,88,194 // vaddps %ymm10,%ymm8,%ymm8 .byte 196,65,52,89,192 // vmulps %ymm8,%ymm9,%ymm8 .byte 197,124,17,128,160,0,0,0 // vmovups %ymm8,0xa0(%rax) @@ -17092,21 +17032,17 @@ BALIGN4 .byte 0,128,64,171,170,42 // add %al,0x2aaaab40(%rax) .byte 62,0,0 // add %al,%ds:(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 0,0 // add %al,(%rax) - .byte 128,63,171 // cmpb $0xab,(%rdi) + .byte 171 // stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) .byte 62,0,0 // add %al,%ds:(%rax) - .byte 128,191,0,0,192,64,171 // cmpb $0xab,0x40c00000(%rdi) - .byte 170 // stos %al,%es:(%rdi) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) + .byte 192,64,0,0 // rolb $0x0,0x0(%rax) + .byte 128,64,171,170 // addb $0xaa,-0x55(%rax) .byte 170 // stos %al,%es:(%rdi) .byte 190,129,128,128,59 // mov $0x3b808081,%esi .byte 129,128,128,59,0,248,0,0,8,33 // addl $0x21080000,-0x7ffc480(%rax) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 550d <.literal4+0xd5> + .byte 224,7 // loopne 547d <.literal4+0xcd> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -17120,10 +17056,10 @@ BALIGN4 .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) .byte 0,52,255 // add %dh,(%rdi,%rdi,8) .byte 255 // (bad) - .byte 127,0 // jg 5538 <.literal4+0x100> + .byte 127,0 // jg 54a8 <.literal4+0xf8> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 55b1 <.literal4+0x179> + .byte 119,115 // ja 5521 <.literal4+0x171> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -17137,10 +17073,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 556c <.literal4+0x134> + .byte 127,0 // jg 54dc <.literal4+0x12c> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 55e5 <.literal4+0x1ad> + .byte 119,115 // ja 5555 <.literal4+0x1a5> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -17154,10 +17090,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 55a0 <.literal4+0x168> + .byte 127,0 // jg 5510 <.literal4+0x160> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 5619 <.literal4+0x1e1> + .byte 119,115 // ja 5589 <.literal4+0x1d9> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -17171,10 +17107,10 @@ BALIGN4 .byte 0,128,63,0,0,0 // add %al,0x3f(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 55d4 <.literal4+0x19c> + .byte 127,0 // jg 5544 <.literal4+0x194> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 564d <.literal4+0x215> + .byte 119,115 // ja 55bd <.literal4+0x20d> .byte 248 // clc .byte 194,117,191 // retq $0xbf75 .byte 191,63,249,68,180 // mov $0xb444f93f,%edi @@ -17187,7 +17123,7 @@ BALIGN4 .byte 0,75,0 // add %cl,0x0(%rbx) .byte 0,128,63,0,0,200 // add %al,-0x37ffffc1(%rax) .byte 66,0,0 // rex.X add %al,(%rax) - .byte 127,67 // jg 564b <.literal4+0x213> + .byte 127,67 // jg 55bb <.literal4+0x20b> .byte 0,0 // add %al,(%rax) .byte 0,195 // add %al,%bl .byte 0,0 // add %al,(%rax) @@ -17199,10 +17135,10 @@ BALIGN4 .byte 190,80,128,3,62 // mov $0x3e038050,%esi .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 566b <.literal4+0x233> + .byte 118,63 // jbe 55db <.literal4+0x22b> .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) - .byte 127,67 // jg 567f <.literal4+0x247> + .byte 127,67 // jg 55ef <.literal4+0x23f> .byte 129,128,128,59,0,0,128,63,129,128 // addl $0x80813f80,0x3b80(%rax) .byte 128,59,0 // cmpb $0x0,(%rbx) .byte 0,128,63,129,128,128 // add %al,-0x7f7f7ec1(%rax) @@ -17211,7 +17147,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 5661 <.literal4+0x229> + .byte 224,7 // loopne 55d1 <.literal4+0x221> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -17223,7 +17159,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 567d <.literal4+0x245> + .byte 224,7 // loopne 55ed <.literal4+0x23d> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -17234,7 +17170,7 @@ BALIGN4 .byte 0,0 // add %al,(%rax) .byte 248 // clc .byte 65,0,0 // add %al,(%r8) - .byte 124,66 // jl 56d2 <.literal4+0x29a> + .byte 124,66 // jl 5642 <.literal4+0x292> .byte 0,240 // add %dh,%al .byte 0,0 // add %al,(%rax) .byte 137,136,136,55,0,15 // mov %ecx,0xf003788(%rax) @@ -17252,9 +17188,9 @@ BALIGN4 .byte 137,136,136,59,15,0 // mov %ecx,0xf3b88(%rax) .byte 0,0 // add %al,(%rax) .byte 137,136,136,61,0,0 // mov %ecx,0x3d88(%rax) - .byte 112,65 // jo 5715 <.literal4+0x2dd> + .byte 112,65 // jo 5685 <.literal4+0x2d5> .byte 129,128,128,59,129,128,128,59,0,0 // addl $0x3b80,-0x7f7ec480(%rax) - .byte 127,67 // jg 5723 <.literal4+0x2eb> + .byte 127,67 // jg 5693 <.literal4+0x2e3> .byte 0,128,0,0,0,0 // add %al,0x0(%rax) .byte 0,128,0,4,0,128 // add %al,-0x7ffffc00(%rax) .byte 0,0 // add %al,(%rax) @@ -17270,7 +17206,7 @@ BALIGN4 .byte 0,128,55,0,0,128 // add %al,-0x7fffffc9(%rax) .byte 63 // (bad) .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 5763 <.literal4+0x32b> + .byte 127,71 // jg 56d3 <.literal4+0x323> .byte 208 // (bad) .byte 179,89 // mov $0x59,%bl .byte 62,89 // ds pop %rcx @@ -17486,7 +17422,7 @@ _sk_seed_shader_sse41: .byte 102,15,110,199 // movd %edi,%xmm0 .byte 102,15,112,192,0 // pshufd $0x0,%xmm0,%xmm0 .byte 15,91,200 // cvtdq2ps %xmm0,%xmm1 - .byte 15,40,21,148,57,0,0 // movaps 0x3994(%rip),%xmm2 # 3a10 <_sk_callback_sse41+0xe3> + .byte 15,40,21,212,56,0,0 // movaps 0x38d4(%rip),%xmm2 # 3950 <_sk_callback_sse41+0xe2> .byte 15,88,202 // addps %xmm2,%xmm1 .byte 15,16,2 // movups (%rdx),%xmm0 .byte 15,88,193 // addps %xmm1,%xmm0 @@ -17495,7 +17431,7 @@ _sk_seed_shader_sse41: .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 15,88,202 // addps %xmm2,%xmm1 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,21,131,57,0,0 // movaps 0x3983(%rip),%xmm2 # 3a20 <_sk_callback_sse41+0xf3> + .byte 15,40,21,195,56,0,0 // movaps 0x38c3(%rip),%xmm2 # 3960 <_sk_callback_sse41+0xf2> .byte 15,87,219 // xorps %xmm3,%xmm3 .byte 15,87,228 // xorps %xmm4,%xmm4 .byte 15,87,237 // xorps %xmm5,%xmm5 @@ -17535,7 +17471,7 @@ HIDDEN _sk_srcatop_sse41 FUNCTION(_sk_srcatop_sse41) _sk_srcatop_sse41: .byte 15,89,199 // mulps %xmm7,%xmm0 - .byte 68,15,40,5,62,57,0,0 // movaps 0x393e(%rip),%xmm8 # 3a30 <_sk_callback_sse41+0x103> + .byte 68,15,40,5,126,56,0,0 // movaps 0x387e(%rip),%xmm8 # 3970 <_sk_callback_sse41+0x102> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,89,204 // mulps %xmm4,%xmm9 @@ -17560,7 +17496,7 @@ FUNCTION(_sk_dstatop_sse41) _sk_dstatop_sse41: .byte 68,15,40,195 // movaps %xmm3,%xmm8 .byte 68,15,89,196 // mulps %xmm4,%xmm8 - .byte 68,15,40,13,1,57,0,0 // movaps 0x3901(%rip),%xmm9 # 3a40 <_sk_callback_sse41+0x113> + .byte 68,15,40,13,65,56,0,0 // movaps 0x3841(%rip),%xmm9 # 3980 <_sk_callback_sse41+0x112> .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 65,15,88,192 // addps %xmm8,%xmm0 @@ -17607,7 +17543,7 @@ HIDDEN _sk_srcout_sse41 .globl _sk_srcout_sse41 FUNCTION(_sk_srcout_sse41) _sk_srcout_sse41: - .byte 68,15,40,5,165,56,0,0 // movaps 0x38a5(%rip),%xmm8 # 3a50 <_sk_callback_sse41+0x123> + .byte 68,15,40,5,229,55,0,0 // movaps 0x37e5(%rip),%xmm8 # 3990 <_sk_callback_sse41+0x122> .byte 68,15,92,199 // subps %xmm7,%xmm8 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 @@ -17620,7 +17556,7 @@ HIDDEN _sk_dstout_sse41 .globl _sk_dstout_sse41 FUNCTION(_sk_dstout_sse41) _sk_dstout_sse41: - .byte 68,15,40,5,149,56,0,0 // movaps 0x3895(%rip),%xmm8 # 3a60 <_sk_callback_sse41+0x133> + .byte 68,15,40,5,213,55,0,0 // movaps 0x37d5(%rip),%xmm8 # 39a0 <_sk_callback_sse41+0x132> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 15,89,196 // mulps %xmm4,%xmm0 @@ -17637,7 +17573,7 @@ HIDDEN _sk_srcover_sse41 .globl _sk_srcover_sse41 FUNCTION(_sk_srcover_sse41) _sk_srcover_sse41: - .byte 68,15,40,5,120,56,0,0 // movaps 0x3878(%rip),%xmm8 # 3a70 <_sk_callback_sse41+0x143> + .byte 68,15,40,5,184,55,0,0 // movaps 0x37b8(%rip),%xmm8 # 39b0 <_sk_callback_sse41+0x142> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,89,204 // mulps %xmm4,%xmm9 @@ -17657,7 +17593,7 @@ HIDDEN _sk_dstover_sse41 .globl _sk_dstover_sse41 FUNCTION(_sk_dstover_sse41) _sk_dstover_sse41: - .byte 68,15,40,5,76,56,0,0 // movaps 0x384c(%rip),%xmm8 # 3a80 <_sk_callback_sse41+0x153> + .byte 68,15,40,5,140,55,0,0 // movaps 0x378c(%rip),%xmm8 # 39c0 <_sk_callback_sse41+0x152> .byte 68,15,92,199 // subps %xmm7,%xmm8 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -17685,7 +17621,7 @@ HIDDEN _sk_multiply_sse41 .globl _sk_multiply_sse41 FUNCTION(_sk_multiply_sse41) _sk_multiply_sse41: - .byte 68,15,40,5,32,56,0,0 // movaps 0x3820(%rip),%xmm8 # 3a90 <_sk_callback_sse41+0x163> + .byte 68,15,40,5,96,55,0,0 // movaps 0x3760(%rip),%xmm8 # 39d0 <_sk_callback_sse41+0x162> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 69,15,40,209 // movaps %xmm9,%xmm10 @@ -17761,7 +17697,7 @@ HIDDEN _sk_xor__sse41 FUNCTION(_sk_xor__sse41) _sk_xor__sse41: .byte 68,15,40,195 // movaps %xmm3,%xmm8 - .byte 15,40,29,81,55,0,0 // movaps 0x3751(%rip),%xmm3 # 3aa0 <_sk_callback_sse41+0x173> + .byte 15,40,29,145,54,0,0 // movaps 0x3691(%rip),%xmm3 # 39e0 <_sk_callback_sse41+0x172> .byte 68,15,40,203 // movaps %xmm3,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 65,15,89,193 // mulps %xmm9,%xmm0 @@ -17809,7 +17745,7 @@ _sk_darken_sse41: .byte 68,15,89,206 // mulps %xmm6,%xmm9 .byte 65,15,95,209 // maxps %xmm9,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,188,54,0,0 // movaps 0x36bc(%rip),%xmm2 # 3ab0 <_sk_callback_sse41+0x183> + .byte 15,40,21,252,53,0,0 // movaps 0x35fc(%rip),%xmm2 # 39f0 <_sk_callback_sse41+0x182> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -17843,7 +17779,7 @@ _sk_lighten_sse41: .byte 68,15,89,206 // mulps %xmm6,%xmm9 .byte 65,15,93,209 // minps %xmm9,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,97,54,0,0 // movaps 0x3661(%rip),%xmm2 # 3ac0 <_sk_callback_sse41+0x193> + .byte 15,40,21,161,53,0,0 // movaps 0x35a1(%rip),%xmm2 # 3a00 <_sk_callback_sse41+0x192> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -17880,7 +17816,7 @@ _sk_difference_sse41: .byte 65,15,93,209 // minps %xmm9,%xmm2 .byte 15,88,210 // addps %xmm2,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,251,53,0,0 // movaps 0x35fb(%rip),%xmm2 # 3ad0 <_sk_callback_sse41+0x1a3> + .byte 15,40,21,59,53,0,0 // movaps 0x353b(%rip),%xmm2 # 3a10 <_sk_callback_sse41+0x1a2> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -17907,7 +17843,7 @@ _sk_exclusion_sse41: .byte 15,89,214 // mulps %xmm6,%xmm2 .byte 15,88,210 // addps %xmm2,%xmm2 .byte 68,15,92,202 // subps %xmm2,%xmm9 - .byte 15,40,13,188,53,0,0 // movaps 0x35bc(%rip),%xmm1 # 3ae0 <_sk_callback_sse41+0x1b3> + .byte 15,40,13,252,52,0,0 // movaps 0x34fc(%rip),%xmm1 # 3a20 <_sk_callback_sse41+0x1b2> .byte 15,92,203 // subps %xmm3,%xmm1 .byte 15,89,207 // mulps %xmm7,%xmm1 .byte 15,88,217 // addps %xmm1,%xmm3 @@ -17921,7 +17857,7 @@ HIDDEN _sk_colorburn_sse41 FUNCTION(_sk_colorburn_sse41) _sk_colorburn_sse41: .byte 68,15,40,192 // movaps %xmm0,%xmm8 - .byte 68,15,40,21,171,53,0,0 // movaps 0x35ab(%rip),%xmm10 # 3af0 <_sk_callback_sse41+0x1c3> + .byte 68,15,40,21,235,52,0,0 // movaps 0x34eb(%rip),%xmm10 # 3a30 <_sk_callback_sse41+0x1c2> .byte 69,15,40,218 // movaps %xmm10,%xmm11 .byte 68,15,92,223 // subps %xmm7,%xmm11 .byte 69,15,40,203 // movaps %xmm11,%xmm9 @@ -18003,7 +17939,7 @@ HIDDEN _sk_colordodge_sse41 FUNCTION(_sk_colordodge_sse41) _sk_colordodge_sse41: .byte 68,15,40,192 // movaps %xmm0,%xmm8 - .byte 68,15,40,21,137,52,0,0 // movaps 0x3489(%rip),%xmm10 # 3b00 <_sk_callback_sse41+0x1d3> + .byte 68,15,40,21,201,51,0,0 // movaps 0x33c9(%rip),%xmm10 # 3a40 <_sk_callback_sse41+0x1d2> .byte 69,15,40,218 // movaps %xmm10,%xmm11 .byte 68,15,92,223 // subps %xmm7,%xmm11 .byte 69,15,40,227 // movaps %xmm11,%xmm12 @@ -18085,7 +18021,7 @@ _sk_hardlight_sse41: .byte 15,40,244 // movaps %xmm4,%xmm6 .byte 15,40,227 // movaps %xmm3,%xmm4 .byte 68,15,40,200 // movaps %xmm0,%xmm9 - .byte 68,15,40,21,98,51,0,0 // movaps 0x3362(%rip),%xmm10 # 3b10 <_sk_callback_sse41+0x1e3> + .byte 68,15,40,21,162,50,0,0 // movaps 0x32a2(%rip),%xmm10 # 3a50 <_sk_callback_sse41+0x1e2> .byte 65,15,40,234 // movaps %xmm10,%xmm5 .byte 15,92,239 // subps %xmm7,%xmm5 .byte 15,40,197 // movaps %xmm5,%xmm0 @@ -18168,7 +18104,7 @@ FUNCTION(_sk_overlay_sse41) _sk_overlay_sse41: .byte 68,15,40,201 // movaps %xmm1,%xmm9 .byte 68,15,40,240 // movaps %xmm0,%xmm14 - .byte 68,15,40,21,71,50,0,0 // movaps 0x3247(%rip),%xmm10 # 3b20 <_sk_callback_sse41+0x1f3> + .byte 68,15,40,21,135,49,0,0 // movaps 0x3187(%rip),%xmm10 # 3a60 <_sk_callback_sse41+0x1f2> .byte 69,15,40,218 // movaps %xmm10,%xmm11 .byte 68,15,92,223 // subps %xmm7,%xmm11 .byte 65,15,40,195 // movaps %xmm11,%xmm0 @@ -18253,7 +18189,7 @@ _sk_softlight_sse41: .byte 15,40,198 // movaps %xmm6,%xmm0 .byte 15,94,199 // divps %xmm7,%xmm0 .byte 65,15,84,193 // andps %xmm9,%xmm0 - .byte 15,40,13,30,49,0,0 // movaps 0x311e(%rip),%xmm1 # 3b30 <_sk_callback_sse41+0x203> + .byte 15,40,13,94,48,0,0 // movaps 0x305e(%rip),%xmm1 # 3a70 <_sk_callback_sse41+0x202> .byte 68,15,40,209 // movaps %xmm1,%xmm10 .byte 68,15,92,208 // subps %xmm0,%xmm10 .byte 68,15,40,240 // movaps %xmm0,%xmm14 @@ -18266,10 +18202,10 @@ _sk_softlight_sse41: .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 15,89,210 // mulps %xmm2,%xmm2 .byte 15,88,208 // addps %xmm0,%xmm2 - .byte 68,15,40,45,252,48,0,0 // movaps 0x30fc(%rip),%xmm13 # 3b40 <_sk_callback_sse41+0x213> + .byte 68,15,40,45,60,48,0,0 // movaps 0x303c(%rip),%xmm13 # 3a80 <_sk_callback_sse41+0x212> .byte 69,15,88,245 // addps %xmm13,%xmm14 .byte 68,15,89,242 // mulps %xmm2,%xmm14 - .byte 68,15,40,37,252,48,0,0 // movaps 0x30fc(%rip),%xmm12 # 3b50 <_sk_callback_sse41+0x223> + .byte 68,15,40,37,60,48,0,0 // movaps 0x303c(%rip),%xmm12 # 3a90 <_sk_callback_sse41+0x222> .byte 69,15,89,252 // mulps %xmm12,%xmm15 .byte 69,15,88,254 // addps %xmm14,%xmm15 .byte 15,40,198 // movaps %xmm6,%xmm0 @@ -18417,7 +18353,7 @@ HIDDEN _sk_clamp_1_sse41 .globl _sk_clamp_1_sse41 FUNCTION(_sk_clamp_1_sse41) _sk_clamp_1_sse41: - .byte 68,15,40,5,14,47,0,0 // movaps 0x2f0e(%rip),%xmm8 # 3b60 <_sk_callback_sse41+0x233> + .byte 68,15,40,5,78,46,0,0 // movaps 0x2e4e(%rip),%xmm8 # 3aa0 <_sk_callback_sse41+0x232> .byte 65,15,93,192 // minps %xmm8,%xmm0 .byte 65,15,93,200 // minps %xmm8,%xmm1 .byte 65,15,93,208 // minps %xmm8,%xmm2 @@ -18429,7 +18365,7 @@ HIDDEN _sk_clamp_a_sse41 .globl _sk_clamp_a_sse41 FUNCTION(_sk_clamp_a_sse41) _sk_clamp_a_sse41: - .byte 15,93,29,3,47,0,0 // minps 0x2f03(%rip),%xmm3 # 3b70 <_sk_callback_sse41+0x243> + .byte 15,93,29,67,46,0,0 // minps 0x2e43(%rip),%xmm3 # 3ab0 <_sk_callback_sse41+0x242> .byte 15,93,195 // minps %xmm3,%xmm0 .byte 15,93,203 // minps %xmm3,%xmm1 .byte 15,93,211 // minps %xmm3,%xmm2 @@ -18516,7 +18452,7 @@ HIDDEN _sk_unpremul_sse41 FUNCTION(_sk_unpremul_sse41) _sk_unpremul_sse41: .byte 69,15,87,192 // xorps %xmm8,%xmm8 - .byte 68,15,40,13,110,46,0,0 // movaps 0x2e6e(%rip),%xmm9 # 3b80 <_sk_callback_sse41+0x253> + .byte 68,15,40,13,174,45,0,0 // movaps 0x2dae(%rip),%xmm9 # 3ac0 <_sk_callback_sse41+0x252> .byte 68,15,94,203 // divps %xmm3,%xmm9 .byte 68,15,194,195,4 // cmpneqps %xmm3,%xmm8 .byte 69,15,84,193 // andps %xmm9,%xmm8 @@ -18530,20 +18466,20 @@ HIDDEN _sk_from_srgb_sse41 .globl _sk_from_srgb_sse41 FUNCTION(_sk_from_srgb_sse41) _sk_from_srgb_sse41: - .byte 68,15,40,29,89,46,0,0 // movaps 0x2e59(%rip),%xmm11 # 3b90 <_sk_callback_sse41+0x263> + .byte 68,15,40,29,153,45,0,0 // movaps 0x2d99(%rip),%xmm11 # 3ad0 <_sk_callback_sse41+0x262> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 .byte 68,15,40,208 // movaps %xmm0,%xmm10 .byte 69,15,89,210 // mulps %xmm10,%xmm10 - .byte 68,15,40,37,81,46,0,0 // movaps 0x2e51(%rip),%xmm12 # 3ba0 <_sk_callback_sse41+0x273> + .byte 68,15,40,37,145,45,0,0 // movaps 0x2d91(%rip),%xmm12 # 3ae0 <_sk_callback_sse41+0x272> .byte 68,15,40,192 // movaps %xmm0,%xmm8 .byte 69,15,89,196 // mulps %xmm12,%xmm8 - .byte 68,15,40,45,81,46,0,0 // movaps 0x2e51(%rip),%xmm13 # 3bb0 <_sk_callback_sse41+0x283> + .byte 68,15,40,45,145,45,0,0 // movaps 0x2d91(%rip),%xmm13 # 3af0 <_sk_callback_sse41+0x282> .byte 69,15,88,197 // addps %xmm13,%xmm8 .byte 69,15,89,194 // mulps %xmm10,%xmm8 - .byte 68,15,40,53,81,46,0,0 // movaps 0x2e51(%rip),%xmm14 # 3bc0 <_sk_callback_sse41+0x293> + .byte 68,15,40,53,145,45,0,0 // movaps 0x2d91(%rip),%xmm14 # 3b00 <_sk_callback_sse41+0x292> .byte 69,15,88,198 // addps %xmm14,%xmm8 - .byte 68,15,40,61,85,46,0,0 // movaps 0x2e55(%rip),%xmm15 # 3bd0 <_sk_callback_sse41+0x2a3> + .byte 68,15,40,61,149,45,0,0 // movaps 0x2d95(%rip),%xmm15 # 3b10 <_sk_callback_sse41+0x2a2> .byte 65,15,194,199,1 // cmpltps %xmm15,%xmm0 .byte 102,69,15,56,20,193 // blendvps %xmm0,%xmm9,%xmm8 .byte 68,15,40,209 // movaps %xmm1,%xmm10 @@ -18588,20 +18524,20 @@ _sk_to_srgb_sse41: .byte 68,15,82,192 // rsqrtps %xmm0,%xmm8 .byte 69,15,83,200 // rcpps %xmm8,%xmm9 .byte 69,15,82,208 // rsqrtps %xmm8,%xmm10 - .byte 68,15,40,29,197,45,0,0 // movaps 0x2dc5(%rip),%xmm11 # 3be0 <_sk_callback_sse41+0x2b3> + .byte 68,15,40,29,5,45,0,0 // movaps 0x2d05(%rip),%xmm11 # 3b20 <_sk_callback_sse41+0x2b2> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 65,15,89,203 // mulps %xmm11,%xmm1 - .byte 68,15,40,37,198,45,0,0 // movaps 0x2dc6(%rip),%xmm12 # 3bf0 <_sk_callback_sse41+0x2c3> + .byte 68,15,40,37,6,45,0,0 // movaps 0x2d06(%rip),%xmm12 # 3b30 <_sk_callback_sse41+0x2c2> .byte 69,15,89,204 // mulps %xmm12,%xmm9 - .byte 68,15,40,45,202,45,0,0 // movaps 0x2dca(%rip),%xmm13 # 3c00 <_sk_callback_sse41+0x2d3> + .byte 68,15,40,45,10,45,0,0 // movaps 0x2d0a(%rip),%xmm13 # 3b40 <_sk_callback_sse41+0x2d2> .byte 69,15,88,205 // addps %xmm13,%xmm9 - .byte 68,15,40,53,206,45,0,0 // movaps 0x2dce(%rip),%xmm14 # 3c10 <_sk_callback_sse41+0x2e3> + .byte 68,15,40,53,14,45,0,0 // movaps 0x2d0e(%rip),%xmm14 # 3b50 <_sk_callback_sse41+0x2e2> .byte 69,15,89,214 // mulps %xmm14,%xmm10 .byte 69,15,88,209 // addps %xmm9,%xmm10 - .byte 68,15,40,5,206,45,0,0 // movaps 0x2dce(%rip),%xmm8 # 3c20 <_sk_callback_sse41+0x2f3> + .byte 68,15,40,5,14,45,0,0 // movaps 0x2d0e(%rip),%xmm8 # 3b60 <_sk_callback_sse41+0x2f2> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,93,202 // minps %xmm10,%xmm9 - .byte 68,15,40,61,206,45,0,0 // movaps 0x2dce(%rip),%xmm15 # 3c30 <_sk_callback_sse41+0x303> + .byte 68,15,40,61,14,45,0,0 // movaps 0x2d0e(%rip),%xmm15 # 3b70 <_sk_callback_sse41+0x302> .byte 65,15,194,199,1 // cmpltps %xmm15,%xmm0 .byte 102,68,15,56,20,201 // blendvps %xmm0,%xmm1,%xmm9 .byte 15,82,194 // rsqrtps %xmm2,%xmm0 @@ -18655,7 +18591,7 @@ _sk_rgb_to_hsl_sse41: .byte 68,15,93,226 // minps %xmm2,%xmm12 .byte 65,15,40,203 // movaps %xmm11,%xmm1 .byte 65,15,92,204 // subps %xmm12,%xmm1 - .byte 68,15,40,53,31,45,0,0 // movaps 0x2d1f(%rip),%xmm14 # 3c40 <_sk_callback_sse41+0x313> + .byte 68,15,40,53,95,44,0,0 // movaps 0x2c5f(%rip),%xmm14 # 3b80 <_sk_callback_sse41+0x312> .byte 68,15,94,241 // divps %xmm1,%xmm14 .byte 69,15,40,211 // movaps %xmm11,%xmm10 .byte 69,15,194,208,0 // cmpeqps %xmm8,%xmm10 @@ -18664,27 +18600,27 @@ _sk_rgb_to_hsl_sse41: .byte 65,15,89,198 // mulps %xmm14,%xmm0 .byte 69,15,40,249 // movaps %xmm9,%xmm15 .byte 68,15,194,250,1 // cmpltps %xmm2,%xmm15 - .byte 68,15,84,61,6,45,0,0 // andps 0x2d06(%rip),%xmm15 # 3c50 <_sk_callback_sse41+0x323> + .byte 68,15,84,61,70,44,0,0 // andps 0x2c46(%rip),%xmm15 # 3b90 <_sk_callback_sse41+0x322> .byte 68,15,88,248 // addps %xmm0,%xmm15 .byte 65,15,40,195 // movaps %xmm11,%xmm0 .byte 65,15,194,193,0 // cmpeqps %xmm9,%xmm0 .byte 65,15,92,208 // subps %xmm8,%xmm2 .byte 65,15,89,214 // mulps %xmm14,%xmm2 - .byte 68,15,40,45,249,44,0,0 // movaps 0x2cf9(%rip),%xmm13 # 3c60 <_sk_callback_sse41+0x333> + .byte 68,15,40,45,57,44,0,0 // movaps 0x2c39(%rip),%xmm13 # 3ba0 <_sk_callback_sse41+0x332> .byte 65,15,88,213 // addps %xmm13,%xmm2 .byte 69,15,92,193 // subps %xmm9,%xmm8 .byte 69,15,89,198 // mulps %xmm14,%xmm8 - .byte 68,15,88,5,245,44,0,0 // addps 0x2cf5(%rip),%xmm8 # 3c70 <_sk_callback_sse41+0x343> + .byte 68,15,88,5,53,44,0,0 // addps 0x2c35(%rip),%xmm8 # 3bb0 <_sk_callback_sse41+0x342> .byte 102,68,15,56,20,194 // blendvps %xmm0,%xmm2,%xmm8 .byte 65,15,40,194 // movaps %xmm10,%xmm0 .byte 102,69,15,56,20,199 // blendvps %xmm0,%xmm15,%xmm8 - .byte 68,15,89,5,237,44,0,0 // mulps 0x2ced(%rip),%xmm8 # 3c80 <_sk_callback_sse41+0x353> + .byte 68,15,89,5,45,44,0,0 // mulps 0x2c2d(%rip),%xmm8 # 3bc0 <_sk_callback_sse41+0x352> .byte 69,15,40,203 // movaps %xmm11,%xmm9 .byte 69,15,194,204,4 // cmpneqps %xmm12,%xmm9 .byte 69,15,84,193 // andps %xmm9,%xmm8 .byte 69,15,92,235 // subps %xmm11,%xmm13 .byte 69,15,88,220 // addps %xmm12,%xmm11 - .byte 15,40,5,225,44,0,0 // movaps 0x2ce1(%rip),%xmm0 # 3c90 <_sk_callback_sse41+0x363> + .byte 15,40,5,33,44,0,0 // movaps 0x2c21(%rip),%xmm0 # 3bd0 <_sk_callback_sse41+0x362> .byte 65,15,40,211 // movaps %xmm11,%xmm2 .byte 15,89,208 // mulps %xmm0,%xmm2 .byte 15,194,194,1 // cmpltps %xmm2,%xmm0 @@ -18700,163 +18636,126 @@ HIDDEN _sk_hsl_to_rgb_sse41 .globl _sk_hsl_to_rgb_sse41 FUNCTION(_sk_hsl_to_rgb_sse41) _sk_hsl_to_rgb_sse41: - .byte 72,131,236,24 // sub $0x18,%rsp - .byte 15,41,60,36 // movaps %xmm7,(%rsp) - .byte 15,41,116,36,240 // movaps %xmm6,-0x10(%rsp) - .byte 15,41,108,36,224 // movaps %xmm5,-0x20(%rsp) - .byte 15,41,100,36,208 // movaps %xmm4,-0x30(%rsp) - .byte 15,41,92,36,192 // movaps %xmm3,-0x40(%rsp) - .byte 68,15,40,216 // movaps %xmm0,%xmm11 + .byte 80 // push %rax + .byte 15,41,124,36,240 // movaps %xmm7,-0x10(%rsp) + .byte 15,41,116,36,224 // movaps %xmm6,-0x20(%rsp) + .byte 15,41,108,36,208 // movaps %xmm5,-0x30(%rsp) + .byte 15,41,100,36,192 // movaps %xmm4,-0x40(%rsp) + .byte 15,41,92,36,176 // movaps %xmm3,-0x50(%rsp) + .byte 15,40,233 // movaps %xmm1,%xmm5 + .byte 68,15,40,208 // movaps %xmm0,%xmm10 .byte 184,0,0,0,63 // mov $0x3f000000,%eax - .byte 102,15,110,216 // movd %eax,%xmm3 - .byte 15,198,219,0 // shufps $0x0,%xmm3,%xmm3 - .byte 15,41,92,36,128 // movaps %xmm3,-0x80(%rsp) - .byte 15,40,194 // movaps %xmm2,%xmm0 - .byte 15,194,195,1 // cmpltps %xmm3,%xmm0 - .byte 15,40,45,140,44,0,0 // movaps 0x2c8c(%rip),%xmm5 # 3ca0 <_sk_callback_sse41+0x373> - .byte 15,40,249 // movaps %xmm1,%xmm7 - .byte 15,40,225 // movaps %xmm1,%xmm4 - .byte 15,40,217 // movaps %xmm1,%xmm3 - .byte 15,88,221 // addps %xmm5,%xmm3 - .byte 15,40,245 // movaps %xmm5,%xmm6 - .byte 15,89,218 // mulps %xmm2,%xmm3 - .byte 15,88,250 // addps %xmm2,%xmm7 - .byte 15,89,226 // mulps %xmm2,%xmm4 - .byte 15,40,234 // movaps %xmm2,%xmm5 - .byte 15,92,252 // subps %xmm4,%xmm7 - .byte 102,15,56,20,251 // blendvps %xmm0,%xmm3,%xmm7 - .byte 68,15,40,37,113,44,0,0 // movaps 0x2c71(%rip),%xmm12 # 3cb0 <_sk_callback_sse41+0x383> - .byte 69,15,88,227 // addps %xmm11,%xmm12 - .byte 184,0,0,0,0 // mov $0x0,%eax - .byte 185,0,0,128,63 // mov $0x3f800000,%ecx - .byte 102,68,15,110,201 // movd %ecx,%xmm9 - .byte 69,15,198,201,0 // shufps $0x0,%xmm9,%xmm9 - .byte 65,15,40,193 // movaps %xmm9,%xmm0 - .byte 65,15,194,196,1 // cmpltps %xmm12,%xmm0 - .byte 65,15,40,212 // movaps %xmm12,%xmm2 - .byte 15,88,21,85,44,0,0 // addps 0x2c55(%rip),%xmm2 # 3cc0 <_sk_callback_sse41+0x393> - .byte 69,15,40,196 // movaps %xmm12,%xmm8 - .byte 65,15,40,220 // movaps %xmm12,%xmm3 - .byte 102,68,15,56,20,226 // blendvps %xmm0,%xmm2,%xmm12 - .byte 102,15,110,192 // movd %eax,%xmm0 - .byte 15,198,192,0 // shufps $0x0,%xmm0,%xmm0 - .byte 15,41,68,36,160 // movaps %xmm0,-0x60(%rsp) - .byte 68,15,194,192,1 // cmpltps %xmm0,%xmm8 - .byte 15,88,222 // addps %xmm6,%xmm3 - .byte 65,15,40,192 // movaps %xmm8,%xmm0 - .byte 102,68,15,56,20,227 // blendvps %xmm0,%xmm3,%xmm12 - .byte 15,40,213 // movaps %xmm5,%xmm2 - .byte 15,41,84,36,176 // movaps %xmm2,-0x50(%rsp) - .byte 68,15,40,194 // movaps %xmm2,%xmm8 - .byte 69,15,88,192 // addps %xmm8,%xmm8 - .byte 68,15,92,199 // subps %xmm7,%xmm8 + .byte 102,15,110,200 // movd %eax,%xmm1 .byte 184,171,170,42,62 // mov $0x3e2aaaab,%eax - .byte 15,40,247 // movaps %xmm7,%xmm6 - .byte 65,15,92,240 // subps %xmm8,%xmm6 - .byte 15,89,53,17,44,0,0 // mulps 0x2c11(%rip),%xmm6 # 3cd0 <_sk_callback_sse41+0x3a3> .byte 185,171,170,42,63 // mov $0x3f2aaaab,%ecx - .byte 102,15,110,193 // movd %ecx,%xmm0 - .byte 15,198,192,0 // shufps $0x0,%xmm0,%xmm0 - .byte 15,41,68,36,144 // movaps %xmm0,-0x70(%rsp) - .byte 15,40,37,8,44,0,0 // movaps 0x2c08(%rip),%xmm4 # 3ce0 <_sk_callback_sse41+0x3b3> + .byte 102,68,15,110,241 // movd %ecx,%xmm14 + .byte 15,198,201,0 // shufps $0x0,%xmm1,%xmm1 + .byte 15,40,218 // movaps %xmm2,%xmm3 + .byte 15,40,195 // movaps %xmm3,%xmm0 + .byte 15,194,193,1 // cmpltps %xmm1,%xmm0 + .byte 15,41,76,36,160 // movaps %xmm1,-0x60(%rsp) + .byte 15,41,108,36,128 // movaps %xmm5,-0x80(%rsp) + .byte 68,15,40,253 // movaps %xmm5,%xmm15 + .byte 15,89,235 // mulps %xmm3,%xmm5 + .byte 68,15,92,253 // subps %xmm5,%xmm15 + .byte 102,68,15,56,20,253 // blendvps %xmm0,%xmm5,%xmm15 + .byte 68,15,88,251 // addps %xmm3,%xmm15 + .byte 68,15,40,195 // movaps %xmm3,%xmm8 + .byte 15,41,92,36,144 // movaps %xmm3,-0x70(%rsp) + .byte 69,15,88,192 // addps %xmm8,%xmm8 + .byte 69,15,92,199 // subps %xmm15,%xmm8 + .byte 15,40,5,142,43,0,0 // movaps 0x2b8e(%rip),%xmm0 # 3be0 <_sk_callback_sse41+0x372> + .byte 65,15,88,194 // addps %xmm10,%xmm0 + .byte 102,15,58,8,208,1 // roundps $0x1,%xmm0,%xmm2 + .byte 15,92,194 // subps %xmm2,%xmm0 + .byte 65,15,40,255 // movaps %xmm15,%xmm7 + .byte 65,15,92,248 // subps %xmm8,%xmm7 + .byte 15,40,53,130,43,0,0 // movaps 0x2b82(%rip),%xmm6 # 3bf0 <_sk_callback_sse41+0x382> + .byte 68,15,40,232 // movaps %xmm0,%xmm13 + .byte 68,15,89,238 // mulps %xmm6,%xmm13 + .byte 69,15,198,246,0 // shufps $0x0,%xmm14,%xmm14 + .byte 68,15,40,216 // movaps %xmm0,%xmm11 + .byte 68,15,40,224 // movaps %xmm0,%xmm12 + .byte 65,15,194,198,1 // cmpltps %xmm14,%xmm0 + .byte 15,40,37,113,43,0,0 // movaps 0x2b71(%rip),%xmm4 # 3c00 <_sk_callback_sse41+0x392> .byte 15,40,236 // movaps %xmm4,%xmm5 - .byte 65,15,92,236 // subps %xmm12,%xmm5 - .byte 69,15,40,236 // movaps %xmm12,%xmm13 - .byte 69,15,40,252 // movaps %xmm12,%xmm15 - .byte 69,15,40,244 // movaps %xmm12,%xmm14 - .byte 68,15,194,224,1 // cmpltps %xmm0,%xmm12 - .byte 15,89,238 // mulps %xmm6,%xmm5 + .byte 65,15,92,237 // subps %xmm13,%xmm5 + .byte 15,89,239 // mulps %xmm7,%xmm5 .byte 65,15,88,232 // addps %xmm8,%xmm5 - .byte 69,15,40,208 // movaps %xmm8,%xmm10 + .byte 69,15,40,200 // movaps %xmm8,%xmm9 + .byte 102,68,15,56,20,205 // blendvps %xmm0,%xmm5,%xmm9 + .byte 68,15,194,225,1 // cmpltps %xmm1,%xmm12 .byte 65,15,40,196 // movaps %xmm12,%xmm0 - .byte 102,68,15,56,20,213 // blendvps %xmm0,%xmm5,%xmm10 - .byte 68,15,194,116,36,128,1 // cmpltps -0x80(%rsp),%xmm14 - .byte 65,15,40,198 // movaps %xmm14,%xmm0 - .byte 102,68,15,56,20,215 // blendvps %xmm0,%xmm7,%xmm10 + .byte 102,69,15,56,20,207 // blendvps %xmm0,%xmm15,%xmm9 .byte 102,15,110,232 // movd %eax,%xmm5 .byte 15,198,237,0 // shufps $0x0,%xmm5,%xmm5 - .byte 68,15,194,237,1 // cmpltps %xmm5,%xmm13 - .byte 68,15,89,254 // mulps %xmm6,%xmm15 - .byte 69,15,88,248 // addps %xmm8,%xmm15 - .byte 65,15,40,197 // movaps %xmm13,%xmm0 - .byte 102,69,15,56,20,215 // blendvps %xmm0,%xmm15,%xmm10 - .byte 69,15,87,228 // xorps %xmm12,%xmm12 - .byte 68,15,194,225,0 // cmpeqps %xmm1,%xmm12 - .byte 65,15,40,196 // movaps %xmm12,%xmm0 - .byte 102,68,15,56,20,210 // blendvps %xmm0,%xmm2,%xmm10 - .byte 65,15,40,193 // movaps %xmm9,%xmm0 - .byte 65,15,194,195,1 // cmpltps %xmm11,%xmm0 - .byte 65,15,40,203 // movaps %xmm11,%xmm1 - .byte 15,88,13,100,43,0,0 // addps 0x2b64(%rip),%xmm1 # 3cc0 <_sk_callback_sse41+0x393> - .byte 69,15,40,235 // movaps %xmm11,%xmm13 - .byte 102,68,15,56,20,233 // blendvps %xmm0,%xmm1,%xmm13 + .byte 68,15,194,221,1 // cmpltps %xmm5,%xmm11 + .byte 68,15,89,239 // mulps %xmm7,%xmm13 + .byte 69,15,88,232 // addps %xmm8,%xmm13 .byte 65,15,40,195 // movaps %xmm11,%xmm0 - .byte 15,194,68,36,160,1 // cmpltps -0x60(%rsp),%xmm0 - .byte 65,15,40,203 // movaps %xmm11,%xmm1 - .byte 15,88,13,37,43,0,0 // addps 0x2b25(%rip),%xmm1 # 3ca0 <_sk_callback_sse41+0x373> - .byte 102,68,15,56,20,233 // blendvps %xmm0,%xmm1,%xmm13 + .byte 102,69,15,56,20,205 // blendvps %xmm0,%xmm13,%xmm9 + .byte 69,15,87,219 // xorps %xmm11,%xmm11 + .byte 68,15,194,92,36,128,0 // cmpeqps -0x80(%rsp),%xmm11 + .byte 65,15,40,195 // movaps %xmm11,%xmm0 + .byte 102,68,15,56,20,203 // blendvps %xmm0,%xmm3,%xmm9 + .byte 102,65,15,58,8,202,1 // roundps $0x1,%xmm10,%xmm1 + .byte 65,15,40,194 // movaps %xmm10,%xmm0 + .byte 15,92,193 // subps %xmm1,%xmm0 + .byte 15,40,200 // movaps %xmm0,%xmm1 + .byte 15,89,206 // mulps %xmm6,%xmm1 .byte 15,40,220 // movaps %xmm4,%xmm3 - .byte 65,15,92,221 // subps %xmm13,%xmm3 - .byte 65,15,40,213 // movaps %xmm13,%xmm2 - .byte 69,15,40,245 // movaps %xmm13,%xmm14 - .byte 69,15,40,253 // movaps %xmm13,%xmm15 - .byte 68,15,194,108,36,144,1 // cmpltps -0x70(%rsp),%xmm13 - .byte 15,89,222 // mulps %xmm6,%xmm3 + .byte 15,92,217 // subps %xmm1,%xmm3 + .byte 68,15,40,224 // movaps %xmm0,%xmm12 + .byte 68,15,40,232 // movaps %xmm0,%xmm13 + .byte 65,15,194,198,1 // cmpltps %xmm14,%xmm0 + .byte 15,89,223 // mulps %xmm7,%xmm3 .byte 65,15,88,216 // addps %xmm8,%xmm3 - .byte 65,15,40,200 // movaps %xmm8,%xmm1 + .byte 65,15,40,208 // movaps %xmm8,%xmm2 + .byte 102,15,56,20,211 // blendvps %xmm0,%xmm3,%xmm2 + .byte 15,40,92,36,160 // movaps -0x60(%rsp),%xmm3 + .byte 68,15,194,235,1 // cmpltps %xmm3,%xmm13 .byte 65,15,40,197 // movaps %xmm13,%xmm0 - .byte 102,15,56,20,203 // blendvps %xmm0,%xmm3,%xmm1 - .byte 68,15,194,124,36,128,1 // cmpltps -0x80(%rsp),%xmm15 - .byte 65,15,40,199 // movaps %xmm15,%xmm0 - .byte 102,15,56,20,207 // blendvps %xmm0,%xmm7,%xmm1 - .byte 15,194,213,1 // cmpltps %xmm5,%xmm2 - .byte 68,15,89,246 // mulps %xmm6,%xmm14 - .byte 69,15,88,240 // addps %xmm8,%xmm14 - .byte 15,40,194 // movaps %xmm2,%xmm0 - .byte 102,65,15,56,20,206 // blendvps %xmm0,%xmm14,%xmm1 + .byte 102,65,15,56,20,215 // blendvps %xmm0,%xmm15,%xmm2 + .byte 68,15,194,229,1 // cmpltps %xmm5,%xmm12 + .byte 15,89,207 // mulps %xmm7,%xmm1 + .byte 65,15,88,200 // addps %xmm8,%xmm1 .byte 65,15,40,196 // movaps %xmm12,%xmm0 - .byte 68,15,40,116,36,176 // movaps -0x50(%rsp),%xmm14 - .byte 102,65,15,56,20,206 // blendvps %xmm0,%xmm14,%xmm1 - .byte 68,15,88,29,4,43,0,0 // addps 0x2b04(%rip),%xmm11 # 3cf0 <_sk_callback_sse41+0x3c3> - .byte 15,40,21,173,42,0,0 // movaps 0x2aad(%rip),%xmm2 # 3ca0 <_sk_callback_sse41+0x373> - .byte 65,15,88,211 // addps %xmm11,%xmm2 - .byte 69,15,194,203,1 // cmpltps %xmm11,%xmm9 - .byte 15,40,29,189,42,0,0 // movaps 0x2abd(%rip),%xmm3 # 3cc0 <_sk_callback_sse41+0x393> - .byte 65,15,88,219 // addps %xmm11,%xmm3 - .byte 69,15,40,235 // movaps %xmm11,%xmm13 - .byte 65,15,40,193 // movaps %xmm9,%xmm0 - .byte 102,68,15,56,20,219 // blendvps %xmm0,%xmm3,%xmm11 - .byte 68,15,194,108,36,160,1 // cmpltps -0x60(%rsp),%xmm13 - .byte 65,15,40,197 // movaps %xmm13,%xmm0 - .byte 102,68,15,56,20,218 // blendvps %xmm0,%xmm2,%xmm11 - .byte 65,15,92,227 // subps %xmm11,%xmm4 - .byte 69,15,40,203 // movaps %xmm11,%xmm9 - .byte 65,15,40,211 // movaps %xmm11,%xmm2 - .byte 69,15,40,235 // movaps %xmm11,%xmm13 - .byte 68,15,194,92,36,144,1 // cmpltps -0x70(%rsp),%xmm11 - .byte 15,89,214 // mulps %xmm6,%xmm2 - .byte 15,89,230 // mulps %xmm6,%xmm4 - .byte 65,15,88,208 // addps %xmm8,%xmm2 - .byte 65,15,88,224 // addps %xmm8,%xmm4 + .byte 102,15,56,20,209 // blendvps %xmm0,%xmm1,%xmm2 .byte 65,15,40,195 // movaps %xmm11,%xmm0 + .byte 15,40,76,36,144 // movaps -0x70(%rsp),%xmm1 + .byte 102,15,56,20,209 // blendvps %xmm0,%xmm1,%xmm2 + .byte 68,15,88,21,176,42,0,0 // addps 0x2ab0(%rip),%xmm10 # 3c10 <_sk_callback_sse41+0x3a2> + .byte 102,65,15,58,8,194,1 // roundps $0x1,%xmm10,%xmm0 + .byte 68,15,92,208 // subps %xmm0,%xmm10 + .byte 65,15,89,242 // mulps %xmm10,%xmm6 + .byte 69,15,40,226 // movaps %xmm10,%xmm12 + .byte 69,15,40,234 // movaps %xmm10,%xmm13 + .byte 69,15,194,214,1 // cmpltps %xmm14,%xmm10 + .byte 15,92,230 // subps %xmm6,%xmm4 + .byte 15,89,247 // mulps %xmm7,%xmm6 + .byte 15,89,231 // mulps %xmm7,%xmm4 + .byte 65,15,88,240 // addps %xmm8,%xmm6 + .byte 65,15,88,224 // addps %xmm8,%xmm4 + .byte 65,15,40,194 // movaps %xmm10,%xmm0 .byte 102,68,15,56,20,196 // blendvps %xmm0,%xmm4,%xmm8 - .byte 68,15,194,108,36,128,1 // cmpltps -0x80(%rsp),%xmm13 + .byte 68,15,194,235,1 // cmpltps %xmm3,%xmm13 .byte 65,15,40,197 // movaps %xmm13,%xmm0 - .byte 102,68,15,56,20,199 // blendvps %xmm0,%xmm7,%xmm8 - .byte 68,15,194,205,1 // cmpltps %xmm5,%xmm9 - .byte 65,15,40,193 // movaps %xmm9,%xmm0 - .byte 102,68,15,56,20,194 // blendvps %xmm0,%xmm2,%xmm8 + .byte 102,69,15,56,20,199 // blendvps %xmm0,%xmm15,%xmm8 + .byte 68,15,194,229,1 // cmpltps %xmm5,%xmm12 .byte 65,15,40,196 // movaps %xmm12,%xmm0 - .byte 102,69,15,56,20,198 // blendvps %xmm0,%xmm14,%xmm8 + .byte 102,68,15,56,20,198 // blendvps %xmm0,%xmm6,%xmm8 + .byte 65,15,40,195 // movaps %xmm11,%xmm0 + .byte 102,68,15,56,20,193 // blendvps %xmm0,%xmm1,%xmm8 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 65,15,40,194 // movaps %xmm10,%xmm0 + .byte 65,15,40,193 // movaps %xmm9,%xmm0 + .byte 15,40,202 // movaps %xmm2,%xmm1 .byte 65,15,40,208 // movaps %xmm8,%xmm2 - .byte 15,40,92,36,192 // movaps -0x40(%rsp),%xmm3 - .byte 15,40,100,36,208 // movaps -0x30(%rsp),%xmm4 - .byte 15,40,108,36,224 // movaps -0x20(%rsp),%xmm5 - .byte 15,40,116,36,240 // movaps -0x10(%rsp),%xmm6 - .byte 15,40,60,36 // movaps (%rsp),%xmm7 - .byte 72,131,196,24 // add $0x18,%rsp + .byte 15,40,92,36,176 // movaps -0x50(%rsp),%xmm3 + .byte 15,40,100,36,192 // movaps -0x40(%rsp),%xmm4 + .byte 15,40,108,36,208 // movaps -0x30(%rsp),%xmm5 + .byte 15,40,116,36,224 // movaps -0x20(%rsp),%xmm6 + .byte 15,40,124,36,240 // movaps -0x10(%rsp),%xmm7 + .byte 89 // pop %rcx .byte 255,224 // jmpq *%rax HIDDEN _sk_scale_1_float_sse41 @@ -18881,7 +18780,7 @@ _sk_scale_u8_sse41: .byte 72,139,0 // mov (%rax),%rax .byte 102,68,15,56,49,4,56 // pmovzxbd (%rax,%rdi,1),%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,33,42,0,0 // mulps 0x2a21(%rip),%xmm8 # 3d00 <_sk_callback_sse41+0x3d3> + .byte 68,15,89,5,0,42,0,0 // mulps 0x2a00(%rip),%xmm8 # 3c20 <_sk_callback_sse41+0x3b2> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 65,15,89,208 // mulps %xmm8,%xmm2 @@ -18919,7 +18818,7 @@ _sk_lerp_u8_sse41: .byte 72,139,0 // mov (%rax),%rax .byte 102,68,15,56,49,4,56 // pmovzxbd (%rax,%rdi,1),%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,205,41,0,0 // mulps 0x29cd(%rip),%xmm8 # 3d10 <_sk_callback_sse41+0x3e3> + .byte 68,15,89,5,172,41,0,0 // mulps 0x29ac(%rip),%xmm8 # 3c30 <_sk_callback_sse41+0x3c2> .byte 15,92,196 // subps %xmm4,%xmm0 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -18942,17 +18841,17 @@ _sk_lerp_565_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 102,68,15,56,51,4,120 // pmovzxwd (%rax,%rdi,2),%xmm8 - .byte 102,15,111,29,157,41,0,0 // movdqa 0x299d(%rip),%xmm3 # 3d20 <_sk_callback_sse41+0x3f3> + .byte 102,15,111,29,124,41,0,0 // movdqa 0x297c(%rip),%xmm3 # 3c40 <_sk_callback_sse41+0x3d2> .byte 102,65,15,219,216 // pand %xmm8,%xmm3 .byte 68,15,91,203 // cvtdq2ps %xmm3,%xmm9 - .byte 68,15,89,13,156,41,0,0 // mulps 0x299c(%rip),%xmm9 # 3d30 <_sk_callback_sse41+0x403> - .byte 102,15,111,29,164,41,0,0 // movdqa 0x29a4(%rip),%xmm3 # 3d40 <_sk_callback_sse41+0x413> + .byte 68,15,89,13,123,41,0,0 // mulps 0x297b(%rip),%xmm9 # 3c50 <_sk_callback_sse41+0x3e2> + .byte 102,15,111,29,131,41,0,0 // movdqa 0x2983(%rip),%xmm3 # 3c60 <_sk_callback_sse41+0x3f2> .byte 102,65,15,219,216 // pand %xmm8,%xmm3 .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,165,41,0,0 // mulps 0x29a5(%rip),%xmm3 # 3d50 <_sk_callback_sse41+0x423> - .byte 102,68,15,219,5,172,41,0,0 // pand 0x29ac(%rip),%xmm8 # 3d60 <_sk_callback_sse41+0x433> + .byte 15,89,29,132,41,0,0 // mulps 0x2984(%rip),%xmm3 # 3c70 <_sk_callback_sse41+0x402> + .byte 102,68,15,219,5,139,41,0,0 // pand 0x298b(%rip),%xmm8 # 3c80 <_sk_callback_sse41+0x412> .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,176,41,0,0 // mulps 0x29b0(%rip),%xmm8 # 3d70 <_sk_callback_sse41+0x443> + .byte 68,15,89,5,143,41,0,0 // mulps 0x298f(%rip),%xmm8 # 3c90 <_sk_callback_sse41+0x422> .byte 15,92,196 // subps %xmm4,%xmm0 .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -18963,7 +18862,7 @@ _sk_lerp_565_sse41: .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 15,88,214 // addps %xmm6,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,154,41,0,0 // movaps 0x299a(%rip),%xmm3 # 3d80 <_sk_callback_sse41+0x453> + .byte 15,40,29,121,41,0,0 // movaps 0x2979(%rip),%xmm3 # 3ca0 <_sk_callback_sse41+0x432> .byte 255,224 // jmpq *%rax HIDDEN _sk_load_tables_sse41 @@ -18974,7 +18873,7 @@ _sk_load_tables_sse41: .byte 76,139,0 // mov (%rax),%r8 .byte 76,139,72,8 // mov 0x8(%rax),%r9 .byte 243,69,15,111,4,184 // movdqu (%r8,%rdi,4),%xmm8 - .byte 102,15,111,5,145,41,0,0 // movdqa 0x2991(%rip),%xmm0 # 3d90 <_sk_callback_sse41+0x463> + .byte 102,15,111,5,112,41,0,0 // movdqa 0x2970(%rip),%xmm0 # 3cb0 <_sk_callback_sse41+0x442> .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,73,15,58,22,192,1 // pextrq $0x1,%xmm0,%r8 .byte 102,72,15,126,193 // movq %xmm0,%rcx @@ -18989,7 +18888,7 @@ _sk_load_tables_sse41: .byte 102,15,58,33,193,48 // insertps $0x30,%xmm1,%xmm0 .byte 76,139,64,16 // mov 0x10(%rax),%r8 .byte 102,65,15,111,200 // movdqa %xmm8,%xmm1 - .byte 102,15,56,0,13,76,41,0,0 // pshufb 0x294c(%rip),%xmm1 # 3da0 <_sk_callback_sse41+0x473> + .byte 102,15,56,0,13,43,41,0,0 // pshufb 0x292b(%rip),%xmm1 # 3cc0 <_sk_callback_sse41+0x452> .byte 102,73,15,58,22,201,1 // pextrq $0x1,%xmm1,%r9 .byte 102,72,15,126,201 // movq %xmm1,%rcx .byte 68,15,182,209 // movzbl %cl,%r10d @@ -19004,7 +18903,7 @@ _sk_load_tables_sse41: .byte 102,15,58,33,202,48 // insertps $0x30,%xmm2,%xmm1 .byte 76,139,64,24 // mov 0x18(%rax),%r8 .byte 102,65,15,111,208 // movdqa %xmm8,%xmm2 - .byte 102,15,56,0,21,8,41,0,0 // pshufb 0x2908(%rip),%xmm2 # 3db0 <_sk_callback_sse41+0x483> + .byte 102,15,56,0,21,231,40,0,0 // pshufb 0x28e7(%rip),%xmm2 # 3cd0 <_sk_callback_sse41+0x462> .byte 102,72,15,58,22,209,1 // pextrq $0x1,%xmm2,%rcx .byte 102,72,15,126,208 // movq %xmm2,%rax .byte 68,15,182,200 // movzbl %al,%r9d @@ -19019,7 +18918,7 @@ _sk_load_tables_sse41: .byte 102,15,58,33,211,48 // insertps $0x30,%xmm3,%xmm2 .byte 102,65,15,114,208,24 // psrld $0x18,%xmm8 .byte 65,15,91,216 // cvtdq2ps %xmm8,%xmm3 - .byte 15,89,29,197,40,0,0 // mulps 0x28c5(%rip),%xmm3 # 3dc0 <_sk_callback_sse41+0x493> + .byte 15,89,29,164,40,0,0 // mulps 0x28a4(%rip),%xmm3 # 3ce0 <_sk_callback_sse41+0x472> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -19038,7 +18937,7 @@ _sk_load_tables_u16_be_sse41: .byte 102,65,15,111,201 // movdqa %xmm9,%xmm1 .byte 102,15,97,200 // punpcklwd %xmm0,%xmm1 .byte 102,68,15,105,200 // punpckhwd %xmm0,%xmm9 - .byte 102,68,15,111,5,152,40,0,0 // movdqa 0x2898(%rip),%xmm8 # 3dd0 <_sk_callback_sse41+0x4a3> + .byte 102,68,15,111,5,119,40,0,0 // movdqa 0x2877(%rip),%xmm8 # 3cf0 <_sk_callback_sse41+0x482> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,15,56,51,192 // pmovzxwd %xmm0,%xmm0 @@ -19055,7 +18954,7 @@ _sk_load_tables_u16_be_sse41: .byte 243,67,15,16,20,8 // movss (%r8,%r9,1),%xmm2 .byte 102,15,58,33,194,48 // insertps $0x30,%xmm2,%xmm0 .byte 76,139,64,16 // mov 0x10(%rax),%r8 - .byte 102,15,56,0,13,75,40,0,0 // pshufb 0x284b(%rip),%xmm1 # 3de0 <_sk_callback_sse41+0x4b3> + .byte 102,15,56,0,13,42,40,0,0 // pshufb 0x282a(%rip),%xmm1 # 3d00 <_sk_callback_sse41+0x492> .byte 102,15,56,51,201 // pmovzxwd %xmm1,%xmm1 .byte 102,73,15,58,22,201,1 // pextrq $0x1,%xmm1,%r9 .byte 102,72,15,126,201 // movq %xmm1,%rcx @@ -19091,7 +18990,7 @@ _sk_load_tables_u16_be_sse41: .byte 102,65,15,235,216 // por %xmm8,%xmm3 .byte 102,15,56,51,219 // pmovzxwd %xmm3,%xmm3 .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,153,39,0,0 // mulps 0x2799(%rip),%xmm3 # 3df0 <_sk_callback_sse41+0x4c3> + .byte 15,89,29,120,39,0,0 // mulps 0x2778(%rip),%xmm3 # 3d10 <_sk_callback_sse41+0x4a2> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -19113,7 +19012,7 @@ _sk_load_tables_rgb_u16_be_sse41: .byte 102,68,15,97,200 // punpcklwd %xmm0,%xmm9 .byte 102,15,111,202 // movdqa %xmm2,%xmm1 .byte 102,65,15,97,201 // punpcklwd %xmm9,%xmm1 - .byte 102,68,15,111,5,91,39,0,0 // movdqa 0x275b(%rip),%xmm8 # 3e00 <_sk_callback_sse41+0x4d3> + .byte 102,68,15,111,5,58,39,0,0 // movdqa 0x273a(%rip),%xmm8 # 3d20 <_sk_callback_sse41+0x4b2> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,15,56,51,192 // pmovzxwd %xmm0,%xmm0 @@ -19130,7 +19029,7 @@ _sk_load_tables_rgb_u16_be_sse41: .byte 243,67,15,16,28,8 // movss (%r8,%r9,1),%xmm3 .byte 102,15,58,33,195,48 // insertps $0x30,%xmm3,%xmm0 .byte 76,139,64,16 // mov 0x10(%rax),%r8 - .byte 102,15,56,0,13,14,39,0,0 // pshufb 0x270e(%rip),%xmm1 # 3e10 <_sk_callback_sse41+0x4e3> + .byte 102,15,56,0,13,237,38,0,0 // pshufb 0x26ed(%rip),%xmm1 # 3d30 <_sk_callback_sse41+0x4c2> .byte 102,15,56,51,201 // pmovzxwd %xmm1,%xmm1 .byte 102,73,15,58,22,201,1 // pextrq $0x1,%xmm1,%r9 .byte 102,72,15,126,201 // movq %xmm1,%rcx @@ -19161,7 +19060,7 @@ _sk_load_tables_rgb_u16_be_sse41: .byte 243,65,15,16,28,8 // movss (%r8,%rcx,1),%xmm3 .byte 102,15,58,33,211,48 // insertps $0x30,%xmm3,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,121,38,0,0 // movaps 0x2679(%rip),%xmm3 # 3e20 <_sk_callback_sse41+0x4f3> + .byte 15,40,29,88,38,0,0 // movaps 0x2658(%rip),%xmm3 # 3d40 <_sk_callback_sse41+0x4d2> .byte 255,224 // jmpq *%rax HIDDEN _sk_byte_tables_sse41 @@ -19171,7 +19070,7 @@ _sk_byte_tables_sse41: .byte 65,86 // push %r14 .byte 83 // push %rbx .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,122,38,0,0 // movaps 0x267a(%rip),%xmm8 # 3e30 <_sk_callback_sse41+0x503> + .byte 68,15,40,5,89,38,0,0 // movaps 0x2659(%rip),%xmm8 # 3d50 <_sk_callback_sse41+0x4e2> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,91,192 // cvtps2dq %xmm0,%xmm0 .byte 102,72,15,58,22,193,1 // pextrq $0x1,%xmm0,%rcx @@ -19190,7 +19089,7 @@ _sk_byte_tables_sse41: .byte 102,15,58,32,193,3 // pinsrb $0x3,%ecx,%xmm0 .byte 102,15,56,49,192 // pmovzxbd %xmm0,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,13,43,38,0,0 // movaps 0x262b(%rip),%xmm9 # 3e40 <_sk_callback_sse41+0x513> + .byte 68,15,40,13,10,38,0,0 // movaps 0x260a(%rip),%xmm9 # 3d60 <_sk_callback_sse41+0x4f2> .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,91,201 // cvtps2dq %xmm1,%xmm1 @@ -19281,7 +19180,7 @@ _sk_byte_tables_rgb_sse41: .byte 102,15,58,32,193,3 // pinsrb $0x3,%ecx,%xmm0 .byte 102,15,56,49,192 // pmovzxbd %xmm0,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,13,179,36,0,0 // movaps 0x24b3(%rip),%xmm9 # 3e50 <_sk_callback_sse41+0x523> + .byte 68,15,40,13,146,36,0,0 // movaps 0x2492(%rip),%xmm9 # 3d70 <_sk_callback_sse41+0x502> .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,91,201 // cvtps2dq %xmm1,%xmm1 @@ -19458,31 +19357,31 @@ _sk_parametric_r_sse41: .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,194 // cvtdq2ps %xmm10,%xmm8 - .byte 68,15,89,5,10,34,0,0 // mulps 0x220a(%rip),%xmm8 # 3e60 <_sk_callback_sse41+0x533> - .byte 68,15,84,21,18,34,0,0 // andps 0x2212(%rip),%xmm10 # 3e70 <_sk_callback_sse41+0x543> - .byte 68,15,86,21,26,34,0,0 // orps 0x221a(%rip),%xmm10 # 3e80 <_sk_callback_sse41+0x553> - .byte 68,15,88,5,34,34,0,0 // addps 0x2222(%rip),%xmm8 # 3e90 <_sk_callback_sse41+0x563> - .byte 68,15,40,37,42,34,0,0 // movaps 0x222a(%rip),%xmm12 # 3ea0 <_sk_callback_sse41+0x573> + .byte 68,15,89,5,233,33,0,0 // mulps 0x21e9(%rip),%xmm8 # 3d80 <_sk_callback_sse41+0x512> + .byte 68,15,84,21,241,33,0,0 // andps 0x21f1(%rip),%xmm10 # 3d90 <_sk_callback_sse41+0x522> + .byte 68,15,86,21,249,33,0,0 // orps 0x21f9(%rip),%xmm10 # 3da0 <_sk_callback_sse41+0x532> + .byte 68,15,88,5,1,34,0,0 // addps 0x2201(%rip),%xmm8 # 3db0 <_sk_callback_sse41+0x542> + .byte 68,15,40,37,9,34,0,0 // movaps 0x2209(%rip),%xmm12 # 3dc0 <_sk_callback_sse41+0x552> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,196 // subps %xmm12,%xmm8 - .byte 68,15,88,21,42,34,0,0 // addps 0x222a(%rip),%xmm10 # 3eb0 <_sk_callback_sse41+0x583> - .byte 68,15,40,37,50,34,0,0 // movaps 0x2232(%rip),%xmm12 # 3ec0 <_sk_callback_sse41+0x593> + .byte 68,15,88,21,9,34,0,0 // addps 0x2209(%rip),%xmm10 # 3dd0 <_sk_callback_sse41+0x562> + .byte 68,15,40,37,17,34,0,0 // movaps 0x2211(%rip),%xmm12 # 3de0 <_sk_callback_sse41+0x572> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,196 // subps %xmm12,%xmm8 .byte 69,15,89,195 // mulps %xmm11,%xmm8 .byte 102,69,15,58,8,208,1 // roundps $0x1,%xmm8,%xmm10 .byte 69,15,40,216 // movaps %xmm8,%xmm11 .byte 69,15,92,218 // subps %xmm10,%xmm11 - .byte 68,15,88,5,31,34,0,0 // addps 0x221f(%rip),%xmm8 # 3ed0 <_sk_callback_sse41+0x5a3> - .byte 68,15,40,21,39,34,0,0 // movaps 0x2227(%rip),%xmm10 # 3ee0 <_sk_callback_sse41+0x5b3> + .byte 68,15,88,5,254,33,0,0 // addps 0x21fe(%rip),%xmm8 # 3df0 <_sk_callback_sse41+0x582> + .byte 68,15,40,21,6,34,0,0 // movaps 0x2206(%rip),%xmm10 # 3e00 <_sk_callback_sse41+0x592> .byte 69,15,89,211 // mulps %xmm11,%xmm10 .byte 69,15,92,194 // subps %xmm10,%xmm8 - .byte 68,15,40,21,39,34,0,0 // movaps 0x2227(%rip),%xmm10 # 3ef0 <_sk_callback_sse41+0x5c3> + .byte 68,15,40,21,6,34,0,0 // movaps 0x2206(%rip),%xmm10 # 3e10 <_sk_callback_sse41+0x5a2> .byte 69,15,92,211 // subps %xmm11,%xmm10 - .byte 68,15,40,29,43,34,0,0 // movaps 0x222b(%rip),%xmm11 # 3f00 <_sk_callback_sse41+0x5d3> + .byte 68,15,40,29,10,34,0,0 // movaps 0x220a(%rip),%xmm11 # 3e20 <_sk_callback_sse41+0x5b2> .byte 69,15,94,218 // divps %xmm10,%xmm11 .byte 69,15,88,216 // addps %xmm8,%xmm11 - .byte 68,15,89,29,43,34,0,0 // mulps 0x222b(%rip),%xmm11 # 3f10 <_sk_callback_sse41+0x5e3> + .byte 68,15,89,29,10,34,0,0 // mulps 0x220a(%rip),%xmm11 # 3e30 <_sk_callback_sse41+0x5c2> .byte 102,69,15,91,211 // cvtps2dq %xmm11,%xmm10 .byte 243,68,15,16,64,20 // movss 0x14(%rax),%xmm8 .byte 69,15,198,192,0 // shufps $0x0,%xmm8,%xmm8 @@ -19490,7 +19389,7 @@ _sk_parametric_r_sse41: .byte 102,69,15,56,20,193 // blendvps %xmm0,%xmm9,%xmm8 .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 68,15,95,192 // maxps %xmm0,%xmm8 - .byte 68,15,93,5,18,34,0,0 // minps 0x2212(%rip),%xmm8 # 3f20 <_sk_callback_sse41+0x5f3> + .byte 68,15,93,5,241,33,0,0 // minps 0x21f1(%rip),%xmm8 # 3e40 <_sk_callback_sse41+0x5d2> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -19520,31 +19419,31 @@ _sk_parametric_g_sse41: .byte 68,15,88,217 // addps %xmm1,%xmm11 .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 .byte 69,15,91,227 // cvtdq2ps %xmm11,%xmm12 - .byte 68,15,89,37,179,33,0,0 // mulps 0x21b3(%rip),%xmm12 # 3f30 <_sk_callback_sse41+0x603> - .byte 68,15,84,29,187,33,0,0 // andps 0x21bb(%rip),%xmm11 # 3f40 <_sk_callback_sse41+0x613> - .byte 68,15,86,29,195,33,0,0 // orps 0x21c3(%rip),%xmm11 # 3f50 <_sk_callback_sse41+0x623> - .byte 68,15,88,37,203,33,0,0 // addps 0x21cb(%rip),%xmm12 # 3f60 <_sk_callback_sse41+0x633> - .byte 15,40,13,212,33,0,0 // movaps 0x21d4(%rip),%xmm1 # 3f70 <_sk_callback_sse41+0x643> + .byte 68,15,89,37,146,33,0,0 // mulps 0x2192(%rip),%xmm12 # 3e50 <_sk_callback_sse41+0x5e2> + .byte 68,15,84,29,154,33,0,0 // andps 0x219a(%rip),%xmm11 # 3e60 <_sk_callback_sse41+0x5f2> + .byte 68,15,86,29,162,33,0,0 // orps 0x21a2(%rip),%xmm11 # 3e70 <_sk_callback_sse41+0x602> + .byte 68,15,88,37,170,33,0,0 // addps 0x21aa(%rip),%xmm12 # 3e80 <_sk_callback_sse41+0x612> + .byte 15,40,13,179,33,0,0 // movaps 0x21b3(%rip),%xmm1 # 3e90 <_sk_callback_sse41+0x622> .byte 65,15,89,203 // mulps %xmm11,%xmm1 .byte 68,15,92,225 // subps %xmm1,%xmm12 - .byte 68,15,88,29,212,33,0,0 // addps 0x21d4(%rip),%xmm11 # 3f80 <_sk_callback_sse41+0x653> - .byte 15,40,13,221,33,0,0 // movaps 0x21dd(%rip),%xmm1 # 3f90 <_sk_callback_sse41+0x663> + .byte 68,15,88,29,179,33,0,0 // addps 0x21b3(%rip),%xmm11 # 3ea0 <_sk_callback_sse41+0x632> + .byte 15,40,13,188,33,0,0 // movaps 0x21bc(%rip),%xmm1 # 3eb0 <_sk_callback_sse41+0x642> .byte 65,15,94,203 // divps %xmm11,%xmm1 .byte 68,15,92,225 // subps %xmm1,%xmm12 .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 102,69,15,58,8,212,1 // roundps $0x1,%xmm12,%xmm10 .byte 69,15,40,220 // movaps %xmm12,%xmm11 .byte 69,15,92,218 // subps %xmm10,%xmm11 - .byte 68,15,88,37,202,33,0,0 // addps 0x21ca(%rip),%xmm12 # 3fa0 <_sk_callback_sse41+0x673> - .byte 15,40,13,211,33,0,0 // movaps 0x21d3(%rip),%xmm1 # 3fb0 <_sk_callback_sse41+0x683> + .byte 68,15,88,37,169,33,0,0 // addps 0x21a9(%rip),%xmm12 # 3ec0 <_sk_callback_sse41+0x652> + .byte 15,40,13,178,33,0,0 // movaps 0x21b2(%rip),%xmm1 # 3ed0 <_sk_callback_sse41+0x662> .byte 65,15,89,203 // mulps %xmm11,%xmm1 .byte 68,15,92,225 // subps %xmm1,%xmm12 - .byte 68,15,40,21,211,33,0,0 // movaps 0x21d3(%rip),%xmm10 # 3fc0 <_sk_callback_sse41+0x693> + .byte 68,15,40,21,178,33,0,0 // movaps 0x21b2(%rip),%xmm10 # 3ee0 <_sk_callback_sse41+0x672> .byte 69,15,92,211 // subps %xmm11,%xmm10 - .byte 15,40,13,216,33,0,0 // movaps 0x21d8(%rip),%xmm1 # 3fd0 <_sk_callback_sse41+0x6a3> + .byte 15,40,13,183,33,0,0 // movaps 0x21b7(%rip),%xmm1 # 3ef0 <_sk_callback_sse41+0x682> .byte 65,15,94,202 // divps %xmm10,%xmm1 .byte 65,15,88,204 // addps %xmm12,%xmm1 - .byte 15,89,13,217,33,0,0 // mulps 0x21d9(%rip),%xmm1 # 3fe0 <_sk_callback_sse41+0x6b3> + .byte 15,89,13,184,33,0,0 // mulps 0x21b8(%rip),%xmm1 # 3f00 <_sk_callback_sse41+0x692> .byte 102,68,15,91,209 // cvtps2dq %xmm1,%xmm10 .byte 243,15,16,72,20 // movss 0x14(%rax),%xmm1 .byte 15,198,201,0 // shufps $0x0,%xmm1,%xmm1 @@ -19552,7 +19451,7 @@ _sk_parametric_g_sse41: .byte 102,65,15,56,20,201 // blendvps %xmm0,%xmm9,%xmm1 .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 15,95,200 // maxps %xmm0,%xmm1 - .byte 15,93,13,196,33,0,0 // minps 0x21c4(%rip),%xmm1 # 3ff0 <_sk_callback_sse41+0x6c3> + .byte 15,93,13,163,33,0,0 // minps 0x21a3(%rip),%xmm1 # 3f10 <_sk_callback_sse41+0x6a2> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -19582,31 +19481,31 @@ _sk_parametric_b_sse41: .byte 68,15,88,218 // addps %xmm2,%xmm11 .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 .byte 69,15,91,227 // cvtdq2ps %xmm11,%xmm12 - .byte 68,15,89,37,101,33,0,0 // mulps 0x2165(%rip),%xmm12 # 4000 <_sk_callback_sse41+0x6d3> - .byte 68,15,84,29,109,33,0,0 // andps 0x216d(%rip),%xmm11 # 4010 <_sk_callback_sse41+0x6e3> - .byte 68,15,86,29,117,33,0,0 // orps 0x2175(%rip),%xmm11 # 4020 <_sk_callback_sse41+0x6f3> - .byte 68,15,88,37,125,33,0,0 // addps 0x217d(%rip),%xmm12 # 4030 <_sk_callback_sse41+0x703> - .byte 15,40,21,134,33,0,0 // movaps 0x2186(%rip),%xmm2 # 4040 <_sk_callback_sse41+0x713> + .byte 68,15,89,37,68,33,0,0 // mulps 0x2144(%rip),%xmm12 # 3f20 <_sk_callback_sse41+0x6b2> + .byte 68,15,84,29,76,33,0,0 // andps 0x214c(%rip),%xmm11 # 3f30 <_sk_callback_sse41+0x6c2> + .byte 68,15,86,29,84,33,0,0 // orps 0x2154(%rip),%xmm11 # 3f40 <_sk_callback_sse41+0x6d2> + .byte 68,15,88,37,92,33,0,0 // addps 0x215c(%rip),%xmm12 # 3f50 <_sk_callback_sse41+0x6e2> + .byte 15,40,21,101,33,0,0 // movaps 0x2165(%rip),%xmm2 # 3f60 <_sk_callback_sse41+0x6f2> .byte 65,15,89,211 // mulps %xmm11,%xmm2 .byte 68,15,92,226 // subps %xmm2,%xmm12 - .byte 68,15,88,29,134,33,0,0 // addps 0x2186(%rip),%xmm11 # 4050 <_sk_callback_sse41+0x723> - .byte 15,40,21,143,33,0,0 // movaps 0x218f(%rip),%xmm2 # 4060 <_sk_callback_sse41+0x733> + .byte 68,15,88,29,101,33,0,0 // addps 0x2165(%rip),%xmm11 # 3f70 <_sk_callback_sse41+0x702> + .byte 15,40,21,110,33,0,0 // movaps 0x216e(%rip),%xmm2 # 3f80 <_sk_callback_sse41+0x712> .byte 65,15,94,211 // divps %xmm11,%xmm2 .byte 68,15,92,226 // subps %xmm2,%xmm12 .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 102,69,15,58,8,212,1 // roundps $0x1,%xmm12,%xmm10 .byte 69,15,40,220 // movaps %xmm12,%xmm11 .byte 69,15,92,218 // subps %xmm10,%xmm11 - .byte 68,15,88,37,124,33,0,0 // addps 0x217c(%rip),%xmm12 # 4070 <_sk_callback_sse41+0x743> - .byte 15,40,21,133,33,0,0 // movaps 0x2185(%rip),%xmm2 # 4080 <_sk_callback_sse41+0x753> + .byte 68,15,88,37,91,33,0,0 // addps 0x215b(%rip),%xmm12 # 3f90 <_sk_callback_sse41+0x722> + .byte 15,40,21,100,33,0,0 // movaps 0x2164(%rip),%xmm2 # 3fa0 <_sk_callback_sse41+0x732> .byte 65,15,89,211 // mulps %xmm11,%xmm2 .byte 68,15,92,226 // subps %xmm2,%xmm12 - .byte 68,15,40,21,133,33,0,0 // movaps 0x2185(%rip),%xmm10 # 4090 <_sk_callback_sse41+0x763> + .byte 68,15,40,21,100,33,0,0 // movaps 0x2164(%rip),%xmm10 # 3fb0 <_sk_callback_sse41+0x742> .byte 69,15,92,211 // subps %xmm11,%xmm10 - .byte 15,40,21,138,33,0,0 // movaps 0x218a(%rip),%xmm2 # 40a0 <_sk_callback_sse41+0x773> + .byte 15,40,21,105,33,0,0 // movaps 0x2169(%rip),%xmm2 # 3fc0 <_sk_callback_sse41+0x752> .byte 65,15,94,210 // divps %xmm10,%xmm2 .byte 65,15,88,212 // addps %xmm12,%xmm2 - .byte 15,89,21,139,33,0,0 // mulps 0x218b(%rip),%xmm2 # 40b0 <_sk_callback_sse41+0x783> + .byte 15,89,21,106,33,0,0 // mulps 0x216a(%rip),%xmm2 # 3fd0 <_sk_callback_sse41+0x762> .byte 102,68,15,91,210 // cvtps2dq %xmm2,%xmm10 .byte 243,15,16,80,20 // movss 0x14(%rax),%xmm2 .byte 15,198,210,0 // shufps $0x0,%xmm2,%xmm2 @@ -19614,7 +19513,7 @@ _sk_parametric_b_sse41: .byte 102,65,15,56,20,209 // blendvps %xmm0,%xmm9,%xmm2 .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 15,95,208 // maxps %xmm0,%xmm2 - .byte 15,93,21,118,33,0,0 // minps 0x2176(%rip),%xmm2 # 40c0 <_sk_callback_sse41+0x793> + .byte 15,93,21,85,33,0,0 // minps 0x2155(%rip),%xmm2 # 3fe0 <_sk_callback_sse41+0x772> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -19644,31 +19543,31 @@ _sk_parametric_a_sse41: .byte 68,15,88,219 // addps %xmm3,%xmm11 .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 .byte 69,15,91,227 // cvtdq2ps %xmm11,%xmm12 - .byte 68,15,89,37,23,33,0,0 // mulps 0x2117(%rip),%xmm12 # 40d0 <_sk_callback_sse41+0x7a3> - .byte 68,15,84,29,31,33,0,0 // andps 0x211f(%rip),%xmm11 # 40e0 <_sk_callback_sse41+0x7b3> - .byte 68,15,86,29,39,33,0,0 // orps 0x2127(%rip),%xmm11 # 40f0 <_sk_callback_sse41+0x7c3> - .byte 68,15,88,37,47,33,0,0 // addps 0x212f(%rip),%xmm12 # 4100 <_sk_callback_sse41+0x7d3> - .byte 15,40,29,56,33,0,0 // movaps 0x2138(%rip),%xmm3 # 4110 <_sk_callback_sse41+0x7e3> + .byte 68,15,89,37,246,32,0,0 // mulps 0x20f6(%rip),%xmm12 # 3ff0 <_sk_callback_sse41+0x782> + .byte 68,15,84,29,254,32,0,0 // andps 0x20fe(%rip),%xmm11 # 4000 <_sk_callback_sse41+0x792> + .byte 68,15,86,29,6,33,0,0 // orps 0x2106(%rip),%xmm11 # 4010 <_sk_callback_sse41+0x7a2> + .byte 68,15,88,37,14,33,0,0 // addps 0x210e(%rip),%xmm12 # 4020 <_sk_callback_sse41+0x7b2> + .byte 15,40,29,23,33,0,0 // movaps 0x2117(%rip),%xmm3 # 4030 <_sk_callback_sse41+0x7c2> .byte 65,15,89,219 // mulps %xmm11,%xmm3 .byte 68,15,92,227 // subps %xmm3,%xmm12 - .byte 68,15,88,29,56,33,0,0 // addps 0x2138(%rip),%xmm11 # 4120 <_sk_callback_sse41+0x7f3> - .byte 15,40,29,65,33,0,0 // movaps 0x2141(%rip),%xmm3 # 4130 <_sk_callback_sse41+0x803> + .byte 68,15,88,29,23,33,0,0 // addps 0x2117(%rip),%xmm11 # 4040 <_sk_callback_sse41+0x7d2> + .byte 15,40,29,32,33,0,0 // movaps 0x2120(%rip),%xmm3 # 4050 <_sk_callback_sse41+0x7e2> .byte 65,15,94,219 // divps %xmm11,%xmm3 .byte 68,15,92,227 // subps %xmm3,%xmm12 .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 102,69,15,58,8,212,1 // roundps $0x1,%xmm12,%xmm10 .byte 69,15,40,220 // movaps %xmm12,%xmm11 .byte 69,15,92,218 // subps %xmm10,%xmm11 - .byte 68,15,88,37,46,33,0,0 // addps 0x212e(%rip),%xmm12 # 4140 <_sk_callback_sse41+0x813> - .byte 15,40,29,55,33,0,0 // movaps 0x2137(%rip),%xmm3 # 4150 <_sk_callback_sse41+0x823> + .byte 68,15,88,37,13,33,0,0 // addps 0x210d(%rip),%xmm12 # 4060 <_sk_callback_sse41+0x7f2> + .byte 15,40,29,22,33,0,0 // movaps 0x2116(%rip),%xmm3 # 4070 <_sk_callback_sse41+0x802> .byte 65,15,89,219 // mulps %xmm11,%xmm3 .byte 68,15,92,227 // subps %xmm3,%xmm12 - .byte 68,15,40,21,55,33,0,0 // movaps 0x2137(%rip),%xmm10 # 4160 <_sk_callback_sse41+0x833> + .byte 68,15,40,21,22,33,0,0 // movaps 0x2116(%rip),%xmm10 # 4080 <_sk_callback_sse41+0x812> .byte 69,15,92,211 // subps %xmm11,%xmm10 - .byte 15,40,29,60,33,0,0 // movaps 0x213c(%rip),%xmm3 # 4170 <_sk_callback_sse41+0x843> + .byte 15,40,29,27,33,0,0 // movaps 0x211b(%rip),%xmm3 # 4090 <_sk_callback_sse41+0x822> .byte 65,15,94,218 // divps %xmm10,%xmm3 .byte 65,15,88,220 // addps %xmm12,%xmm3 - .byte 15,89,29,61,33,0,0 // mulps 0x213d(%rip),%xmm3 # 4180 <_sk_callback_sse41+0x853> + .byte 15,89,29,28,33,0,0 // mulps 0x211c(%rip),%xmm3 # 40a0 <_sk_callback_sse41+0x832> .byte 102,68,15,91,211 // cvtps2dq %xmm3,%xmm10 .byte 243,15,16,88,20 // movss 0x14(%rax),%xmm3 .byte 15,198,219,0 // shufps $0x0,%xmm3,%xmm3 @@ -19676,7 +19575,7 @@ _sk_parametric_a_sse41: .byte 102,65,15,56,20,217 // blendvps %xmm0,%xmm9,%xmm3 .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 15,95,216 // maxps %xmm0,%xmm3 - .byte 15,93,29,40,33,0,0 // minps 0x2128(%rip),%xmm3 # 4190 <_sk_callback_sse41+0x863> + .byte 15,93,29,7,33,0,0 // minps 0x2107(%rip),%xmm3 # 40b0 <_sk_callback_sse41+0x842> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -19686,29 +19585,29 @@ HIDDEN _sk_lab_to_xyz_sse41 FUNCTION(_sk_lab_to_xyz_sse41) _sk_lab_to_xyz_sse41: .byte 68,15,40,192 // movaps %xmm0,%xmm8 - .byte 68,15,89,5,36,33,0,0 // mulps 0x2124(%rip),%xmm8 # 41a0 <_sk_callback_sse41+0x873> - .byte 68,15,40,13,44,33,0,0 // movaps 0x212c(%rip),%xmm9 # 41b0 <_sk_callback_sse41+0x883> + .byte 68,15,89,5,3,33,0,0 // mulps 0x2103(%rip),%xmm8 # 40c0 <_sk_callback_sse41+0x852> + .byte 68,15,40,13,11,33,0,0 // movaps 0x210b(%rip),%xmm9 # 40d0 <_sk_callback_sse41+0x862> .byte 65,15,89,201 // mulps %xmm9,%xmm1 - .byte 15,40,5,49,33,0,0 // movaps 0x2131(%rip),%xmm0 # 41c0 <_sk_callback_sse41+0x893> + .byte 15,40,5,16,33,0,0 // movaps 0x2110(%rip),%xmm0 # 40e0 <_sk_callback_sse41+0x872> .byte 15,88,200 // addps %xmm0,%xmm1 .byte 65,15,89,209 // mulps %xmm9,%xmm2 .byte 15,88,208 // addps %xmm0,%xmm2 - .byte 68,15,88,5,47,33,0,0 // addps 0x212f(%rip),%xmm8 # 41d0 <_sk_callback_sse41+0x8a3> - .byte 68,15,89,5,55,33,0,0 // mulps 0x2137(%rip),%xmm8 # 41e0 <_sk_callback_sse41+0x8b3> - .byte 15,89,13,64,33,0,0 // mulps 0x2140(%rip),%xmm1 # 41f0 <_sk_callback_sse41+0x8c3> + .byte 68,15,88,5,14,33,0,0 // addps 0x210e(%rip),%xmm8 # 40f0 <_sk_callback_sse41+0x882> + .byte 68,15,89,5,22,33,0,0 // mulps 0x2116(%rip),%xmm8 # 4100 <_sk_callback_sse41+0x892> + .byte 15,89,13,31,33,0,0 // mulps 0x211f(%rip),%xmm1 # 4110 <_sk_callback_sse41+0x8a2> .byte 65,15,88,200 // addps %xmm8,%xmm1 - .byte 15,89,21,69,33,0,0 // mulps 0x2145(%rip),%xmm2 # 4200 <_sk_callback_sse41+0x8d3> + .byte 15,89,21,36,33,0,0 // mulps 0x2124(%rip),%xmm2 # 4120 <_sk_callback_sse41+0x8b2> .byte 69,15,40,208 // movaps %xmm8,%xmm10 .byte 68,15,92,210 // subps %xmm2,%xmm10 .byte 68,15,40,217 // movaps %xmm1,%xmm11 .byte 69,15,89,219 // mulps %xmm11,%xmm11 .byte 68,15,89,217 // mulps %xmm1,%xmm11 - .byte 68,15,40,13,57,33,0,0 // movaps 0x2139(%rip),%xmm9 # 4210 <_sk_callback_sse41+0x8e3> + .byte 68,15,40,13,24,33,0,0 // movaps 0x2118(%rip),%xmm9 # 4130 <_sk_callback_sse41+0x8c2> .byte 65,15,40,193 // movaps %xmm9,%xmm0 .byte 65,15,194,195,1 // cmpltps %xmm11,%xmm0 - .byte 15,40,21,57,33,0,0 // movaps 0x2139(%rip),%xmm2 # 4220 <_sk_callback_sse41+0x8f3> + .byte 15,40,21,24,33,0,0 // movaps 0x2118(%rip),%xmm2 # 4140 <_sk_callback_sse41+0x8d2> .byte 15,88,202 // addps %xmm2,%xmm1 - .byte 68,15,40,37,62,33,0,0 // movaps 0x213e(%rip),%xmm12 # 4230 <_sk_callback_sse41+0x903> + .byte 68,15,40,37,29,33,0,0 // movaps 0x211d(%rip),%xmm12 # 4150 <_sk_callback_sse41+0x8e2> .byte 65,15,89,204 // mulps %xmm12,%xmm1 .byte 102,65,15,56,20,203 // blendvps %xmm0,%xmm11,%xmm1 .byte 69,15,40,216 // movaps %xmm8,%xmm11 @@ -19727,8 +19626,8 @@ _sk_lab_to_xyz_sse41: .byte 65,15,89,212 // mulps %xmm12,%xmm2 .byte 65,15,40,193 // movaps %xmm9,%xmm0 .byte 102,65,15,56,20,211 // blendvps %xmm0,%xmm11,%xmm2 - .byte 15,89,13,247,32,0,0 // mulps 0x20f7(%rip),%xmm1 # 4240 <_sk_callback_sse41+0x913> - .byte 15,89,21,0,33,0,0 // mulps 0x2100(%rip),%xmm2 # 4250 <_sk_callback_sse41+0x923> + .byte 15,89,13,214,32,0,0 // mulps 0x20d6(%rip),%xmm1 # 4160 <_sk_callback_sse41+0x8f2> + .byte 15,89,21,223,32,0,0 // mulps 0x20df(%rip),%xmm2 # 4170 <_sk_callback_sse41+0x902> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,40,193 // movaps %xmm1,%xmm0 .byte 65,15,40,200 // movaps %xmm8,%xmm1 @@ -19742,7 +19641,7 @@ _sk_load_a8_sse41: .byte 72,139,0 // mov (%rax),%rax .byte 102,15,56,49,4,56 // pmovzxbd (%rax,%rdi,1),%xmm0 .byte 15,91,216 // cvtdq2ps %xmm0,%xmm3 - .byte 15,89,29,240,32,0,0 // mulps 0x20f0(%rip),%xmm3 # 4260 <_sk_callback_sse41+0x933> + .byte 15,89,29,207,32,0,0 // mulps 0x20cf(%rip),%xmm3 # 4180 <_sk_callback_sse41+0x912> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 15,87,201 // xorps %xmm1,%xmm1 @@ -19775,7 +19674,7 @@ _sk_gather_a8_sse41: .byte 102,15,58,32,192,3 // pinsrb $0x3,%eax,%xmm0 .byte 102,15,56,49,192 // pmovzxbd %xmm0,%xmm0 .byte 15,91,216 // cvtdq2ps %xmm0,%xmm3 - .byte 15,89,29,132,32,0,0 // mulps 0x2084(%rip),%xmm3 # 4270 <_sk_callback_sse41+0x943> + .byte 15,89,29,99,32,0,0 // mulps 0x2063(%rip),%xmm3 # 4190 <_sk_callback_sse41+0x922> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 102,15,239,201 // pxor %xmm1,%xmm1 @@ -19788,7 +19687,7 @@ FUNCTION(_sk_store_a8_sse41) _sk_store_a8_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,120,32,0,0 // movaps 0x2078(%rip),%xmm8 # 4280 <_sk_callback_sse41+0x953> + .byte 68,15,40,5,87,32,0,0 // movaps 0x2057(%rip),%xmm8 # 41a0 <_sk_callback_sse41+0x932> .byte 68,15,89,195 // mulps %xmm3,%xmm8 .byte 102,69,15,91,192 // cvtps2dq %xmm8,%xmm8 .byte 102,69,15,56,43,192 // packusdw %xmm8,%xmm8 @@ -19805,9 +19704,9 @@ _sk_load_g8_sse41: .byte 72,139,0 // mov (%rax),%rax .byte 102,15,56,49,4,56 // pmovzxbd (%rax,%rdi,1),%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,85,32,0,0 // mulps 0x2055(%rip),%xmm0 # 4290 <_sk_callback_sse41+0x963> + .byte 15,89,5,52,32,0,0 // mulps 0x2034(%rip),%xmm0 # 41b0 <_sk_callback_sse41+0x942> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,92,32,0,0 // movaps 0x205c(%rip),%xmm3 # 42a0 <_sk_callback_sse41+0x973> + .byte 15,40,29,59,32,0,0 // movaps 0x203b(%rip),%xmm3 # 41c0 <_sk_callback_sse41+0x952> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 255,224 // jmpq *%rax @@ -19838,9 +19737,9 @@ _sk_gather_g8_sse41: .byte 102,15,58,32,192,3 // pinsrb $0x3,%eax,%xmm0 .byte 102,15,56,49,192 // pmovzxbd %xmm0,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,245,31,0,0 // mulps 0x1ff5(%rip),%xmm0 # 42b0 <_sk_callback_sse41+0x983> + .byte 15,89,5,212,31,0,0 // mulps 0x1fd4(%rip),%xmm0 # 41d0 <_sk_callback_sse41+0x962> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,252,31,0,0 // movaps 0x1ffc(%rip),%xmm3 # 42c0 <_sk_callback_sse41+0x993> + .byte 15,40,29,219,31,0,0 // movaps 0x1fdb(%rip),%xmm3 # 41e0 <_sk_callback_sse41+0x972> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 255,224 // jmpq *%rax @@ -19852,9 +19751,9 @@ _sk_gather_i8_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 73,137,192 // mov %rax,%r8 .byte 77,133,192 // test %r8,%r8 - .byte 116,5 // je 22db <_sk_gather_i8_sse41+0xf> + .byte 116,5 // je 221c <_sk_gather_i8_sse41+0xf> .byte 76,137,192 // mov %r8,%rax - .byte 235,2 // jmp 22dd <_sk_gather_i8_sse41+0x11> + .byte 235,2 // jmp 221e <_sk_gather_i8_sse41+0x11> .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 .byte 243,15,91,201 // cvttps2dq %xmm1,%xmm1 @@ -19885,17 +19784,17 @@ _sk_gather_i8_sse41: .byte 102,15,58,34,28,8,1 // pinsrd $0x1,(%rax,%rcx,1),%xmm3 .byte 102,66,15,58,34,28,144,2 // pinsrd $0x2,(%rax,%r10,4),%xmm3 .byte 102,66,15,58,34,28,8,3 // pinsrd $0x3,(%rax,%r9,1),%xmm3 - .byte 102,15,111,5,83,31,0,0 // movdqa 0x1f53(%rip),%xmm0 # 42d0 <_sk_callback_sse41+0x9a3> + .byte 102,15,111,5,50,31,0,0 // movdqa 0x1f32(%rip),%xmm0 # 41f0 <_sk_callback_sse41+0x982> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,84,31,0,0 // movaps 0x1f54(%rip),%xmm8 # 42e0 <_sk_callback_sse41+0x9b3> + .byte 68,15,40,5,51,31,0,0 // movaps 0x1f33(%rip),%xmm8 # 4200 <_sk_callback_sse41+0x992> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 - .byte 102,15,56,0,13,83,31,0,0 // pshufb 0x1f53(%rip),%xmm1 # 42f0 <_sk_callback_sse41+0x9c3> + .byte 102,15,56,0,13,50,31,0,0 // pshufb 0x1f32(%rip),%xmm1 # 4210 <_sk_callback_sse41+0x9a2> .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,111,211 // movdqa %xmm3,%xmm2 - .byte 102,15,56,0,21,79,31,0,0 // pshufb 0x1f4f(%rip),%xmm2 # 4300 <_sk_callback_sse41+0x9d3> + .byte 102,15,56,0,21,46,31,0,0 // pshufb 0x1f2e(%rip),%xmm2 # 4220 <_sk_callback_sse41+0x9b2> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 102,15,114,211,24 // psrld $0x18,%xmm3 @@ -19911,19 +19810,19 @@ _sk_load_565_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 102,15,56,51,20,120 // pmovzxwd (%rax,%rdi,2),%xmm2 - .byte 102,15,111,5,53,31,0,0 // movdqa 0x1f35(%rip),%xmm0 # 4310 <_sk_callback_sse41+0x9e3> + .byte 102,15,111,5,20,31,0,0 // movdqa 0x1f14(%rip),%xmm0 # 4230 <_sk_callback_sse41+0x9c2> .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,55,31,0,0 // mulps 0x1f37(%rip),%xmm0 # 4320 <_sk_callback_sse41+0x9f3> - .byte 102,15,111,13,63,31,0,0 // movdqa 0x1f3f(%rip),%xmm1 # 4330 <_sk_callback_sse41+0xa03> + .byte 15,89,5,22,31,0,0 // mulps 0x1f16(%rip),%xmm0 # 4240 <_sk_callback_sse41+0x9d2> + .byte 102,15,111,13,30,31,0,0 // movdqa 0x1f1e(%rip),%xmm1 # 4250 <_sk_callback_sse41+0x9e2> .byte 102,15,219,202 // pand %xmm2,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,65,31,0,0 // mulps 0x1f41(%rip),%xmm1 # 4340 <_sk_callback_sse41+0xa13> - .byte 102,15,219,21,73,31,0,0 // pand 0x1f49(%rip),%xmm2 # 4350 <_sk_callback_sse41+0xa23> + .byte 15,89,13,32,31,0,0 // mulps 0x1f20(%rip),%xmm1 # 4260 <_sk_callback_sse41+0x9f2> + .byte 102,15,219,21,40,31,0,0 // pand 0x1f28(%rip),%xmm2 # 4270 <_sk_callback_sse41+0xa02> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,79,31,0,0 // mulps 0x1f4f(%rip),%xmm2 # 4360 <_sk_callback_sse41+0xa33> + .byte 15,89,21,46,31,0,0 // mulps 0x1f2e(%rip),%xmm2 # 4280 <_sk_callback_sse41+0xa12> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,86,31,0,0 // movaps 0x1f56(%rip),%xmm3 # 4370 <_sk_callback_sse41+0xa43> + .byte 15,40,29,53,31,0,0 // movaps 0x1f35(%rip),%xmm3 # 4290 <_sk_callback_sse41+0xa22> .byte 255,224 // jmpq *%rax HIDDEN _sk_gather_565_sse41 @@ -19951,19 +19850,19 @@ _sk_gather_565_sse41: .byte 65,15,183,4,65 // movzwl (%r9,%rax,2),%eax .byte 102,15,196,192,3 // pinsrw $0x3,%eax,%xmm0 .byte 102,15,56,51,208 // pmovzxwd %xmm0,%xmm2 - .byte 102,15,111,5,251,30,0,0 // movdqa 0x1efb(%rip),%xmm0 # 4380 <_sk_callback_sse41+0xa53> + .byte 102,15,111,5,218,30,0,0 // movdqa 0x1eda(%rip),%xmm0 # 42a0 <_sk_callback_sse41+0xa32> .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,253,30,0,0 // mulps 0x1efd(%rip),%xmm0 # 4390 <_sk_callback_sse41+0xa63> - .byte 102,15,111,13,5,31,0,0 // movdqa 0x1f05(%rip),%xmm1 # 43a0 <_sk_callback_sse41+0xa73> + .byte 15,89,5,220,30,0,0 // mulps 0x1edc(%rip),%xmm0 # 42b0 <_sk_callback_sse41+0xa42> + .byte 102,15,111,13,228,30,0,0 // movdqa 0x1ee4(%rip),%xmm1 # 42c0 <_sk_callback_sse41+0xa52> .byte 102,15,219,202 // pand %xmm2,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,7,31,0,0 // mulps 0x1f07(%rip),%xmm1 # 43b0 <_sk_callback_sse41+0xa83> - .byte 102,15,219,21,15,31,0,0 // pand 0x1f0f(%rip),%xmm2 # 43c0 <_sk_callback_sse41+0xa93> + .byte 15,89,13,230,30,0,0 // mulps 0x1ee6(%rip),%xmm1 # 42d0 <_sk_callback_sse41+0xa62> + .byte 102,15,219,21,238,30,0,0 // pand 0x1eee(%rip),%xmm2 # 42e0 <_sk_callback_sse41+0xa72> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,21,31,0,0 // mulps 0x1f15(%rip),%xmm2 # 43d0 <_sk_callback_sse41+0xaa3> + .byte 15,89,21,244,30,0,0 // mulps 0x1ef4(%rip),%xmm2 # 42f0 <_sk_callback_sse41+0xa82> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,28,31,0,0 // movaps 0x1f1c(%rip),%xmm3 # 43e0 <_sk_callback_sse41+0xab3> + .byte 15,40,29,251,30,0,0 // movaps 0x1efb(%rip),%xmm3 # 4300 <_sk_callback_sse41+0xa92> .byte 255,224 // jmpq *%rax HIDDEN _sk_store_565_sse41 @@ -19972,12 +19871,12 @@ FUNCTION(_sk_store_565_sse41) _sk_store_565_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,29,31,0,0 // movaps 0x1f1d(%rip),%xmm8 # 43f0 <_sk_callback_sse41+0xac3> + .byte 68,15,40,5,252,30,0,0 // movaps 0x1efc(%rip),%xmm8 # 4310 <_sk_callback_sse41+0xaa2> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 .byte 102,65,15,114,241,11 // pslld $0xb,%xmm9 - .byte 68,15,40,21,18,31,0,0 // movaps 0x1f12(%rip),%xmm10 # 4400 <_sk_callback_sse41+0xad3> + .byte 68,15,40,21,241,30,0,0 // movaps 0x1ef1(%rip),%xmm10 # 4320 <_sk_callback_sse41+0xab2> .byte 68,15,89,209 // mulps %xmm1,%xmm10 .byte 102,69,15,91,210 // cvtps2dq %xmm10,%xmm10 .byte 102,65,15,114,242,5 // pslld $0x5,%xmm10 @@ -19997,21 +19896,21 @@ _sk_load_4444_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 102,15,56,51,28,120 // pmovzxwd (%rax,%rdi,2),%xmm3 - .byte 102,15,111,5,221,30,0,0 // movdqa 0x1edd(%rip),%xmm0 # 4410 <_sk_callback_sse41+0xae3> + .byte 102,15,111,5,188,30,0,0 // movdqa 0x1ebc(%rip),%xmm0 # 4330 <_sk_callback_sse41+0xac2> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,223,30,0,0 // mulps 0x1edf(%rip),%xmm0 # 4420 <_sk_callback_sse41+0xaf3> - .byte 102,15,111,13,231,30,0,0 // movdqa 0x1ee7(%rip),%xmm1 # 4430 <_sk_callback_sse41+0xb03> + .byte 15,89,5,190,30,0,0 // mulps 0x1ebe(%rip),%xmm0 # 4340 <_sk_callback_sse41+0xad2> + .byte 102,15,111,13,198,30,0,0 // movdqa 0x1ec6(%rip),%xmm1 # 4350 <_sk_callback_sse41+0xae2> .byte 102,15,219,203 // pand %xmm3,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,233,30,0,0 // mulps 0x1ee9(%rip),%xmm1 # 4440 <_sk_callback_sse41+0xb13> - .byte 102,15,111,21,241,30,0,0 // movdqa 0x1ef1(%rip),%xmm2 # 4450 <_sk_callback_sse41+0xb23> + .byte 15,89,13,200,30,0,0 // mulps 0x1ec8(%rip),%xmm1 # 4360 <_sk_callback_sse41+0xaf2> + .byte 102,15,111,21,208,30,0,0 // movdqa 0x1ed0(%rip),%xmm2 # 4370 <_sk_callback_sse41+0xb02> .byte 102,15,219,211 // pand %xmm3,%xmm2 .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,243,30,0,0 // mulps 0x1ef3(%rip),%xmm2 # 4460 <_sk_callback_sse41+0xb33> - .byte 102,15,219,29,251,30,0,0 // pand 0x1efb(%rip),%xmm3 # 4470 <_sk_callback_sse41+0xb43> + .byte 15,89,21,210,30,0,0 // mulps 0x1ed2(%rip),%xmm2 # 4380 <_sk_callback_sse41+0xb12> + .byte 102,15,219,29,218,30,0,0 // pand 0x1eda(%rip),%xmm3 # 4390 <_sk_callback_sse41+0xb22> .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,1,31,0,0 // mulps 0x1f01(%rip),%xmm3 # 4480 <_sk_callback_sse41+0xb53> + .byte 15,89,29,224,30,0,0 // mulps 0x1ee0(%rip),%xmm3 # 43a0 <_sk_callback_sse41+0xb32> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -20040,21 +19939,21 @@ _sk_gather_4444_sse41: .byte 65,15,183,4,65 // movzwl (%r9,%rax,2),%eax .byte 102,15,196,192,3 // pinsrw $0x3,%eax,%xmm0 .byte 102,15,56,51,216 // pmovzxwd %xmm0,%xmm3 - .byte 102,15,111,5,164,30,0,0 // movdqa 0x1ea4(%rip),%xmm0 # 4490 <_sk_callback_sse41+0xb63> + .byte 102,15,111,5,131,30,0,0 // movdqa 0x1e83(%rip),%xmm0 # 43b0 <_sk_callback_sse41+0xb42> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,166,30,0,0 // mulps 0x1ea6(%rip),%xmm0 # 44a0 <_sk_callback_sse41+0xb73> - .byte 102,15,111,13,174,30,0,0 // movdqa 0x1eae(%rip),%xmm1 # 44b0 <_sk_callback_sse41+0xb83> + .byte 15,89,5,133,30,0,0 // mulps 0x1e85(%rip),%xmm0 # 43c0 <_sk_callback_sse41+0xb52> + .byte 102,15,111,13,141,30,0,0 // movdqa 0x1e8d(%rip),%xmm1 # 43d0 <_sk_callback_sse41+0xb62> .byte 102,15,219,203 // pand %xmm3,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,176,30,0,0 // mulps 0x1eb0(%rip),%xmm1 # 44c0 <_sk_callback_sse41+0xb93> - .byte 102,15,111,21,184,30,0,0 // movdqa 0x1eb8(%rip),%xmm2 # 44d0 <_sk_callback_sse41+0xba3> + .byte 15,89,13,143,30,0,0 // mulps 0x1e8f(%rip),%xmm1 # 43e0 <_sk_callback_sse41+0xb72> + .byte 102,15,111,21,151,30,0,0 // movdqa 0x1e97(%rip),%xmm2 # 43f0 <_sk_callback_sse41+0xb82> .byte 102,15,219,211 // pand %xmm3,%xmm2 .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,186,30,0,0 // mulps 0x1eba(%rip),%xmm2 # 44e0 <_sk_callback_sse41+0xbb3> - .byte 102,15,219,29,194,30,0,0 // pand 0x1ec2(%rip),%xmm3 # 44f0 <_sk_callback_sse41+0xbc3> + .byte 15,89,21,153,30,0,0 // mulps 0x1e99(%rip),%xmm2 # 4400 <_sk_callback_sse41+0xb92> + .byte 102,15,219,29,161,30,0,0 // pand 0x1ea1(%rip),%xmm3 # 4410 <_sk_callback_sse41+0xba2> .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,200,30,0,0 // mulps 0x1ec8(%rip),%xmm3 # 4500 <_sk_callback_sse41+0xbd3> + .byte 15,89,29,167,30,0,0 // mulps 0x1ea7(%rip),%xmm3 # 4420 <_sk_callback_sse41+0xbb2> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -20064,7 +19963,7 @@ FUNCTION(_sk_store_4444_sse41) _sk_store_4444_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,199,30,0,0 // movaps 0x1ec7(%rip),%xmm8 # 4510 <_sk_callback_sse41+0xbe3> + .byte 68,15,40,5,166,30,0,0 // movaps 0x1ea6(%rip),%xmm8 # 4430 <_sk_callback_sse41+0xbc2> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 @@ -20094,17 +19993,17 @@ _sk_load_8888_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 15,16,28,184 // movups (%rax,%rdi,4),%xmm3 - .byte 15,40,5,102,30,0,0 // movaps 0x1e66(%rip),%xmm0 # 4520 <_sk_callback_sse41+0xbf3> + .byte 15,40,5,69,30,0,0 // movaps 0x1e45(%rip),%xmm0 # 4440 <_sk_callback_sse41+0xbd2> .byte 15,84,195 // andps %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,104,30,0,0 // movaps 0x1e68(%rip),%xmm8 # 4530 <_sk_callback_sse41+0xc03> + .byte 68,15,40,5,71,30,0,0 // movaps 0x1e47(%rip),%xmm8 # 4450 <_sk_callback_sse41+0xbe2> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,40,203 // movaps %xmm3,%xmm1 - .byte 102,15,56,0,13,104,30,0,0 // pshufb 0x1e68(%rip),%xmm1 # 4540 <_sk_callback_sse41+0xc13> + .byte 102,15,56,0,13,71,30,0,0 // pshufb 0x1e47(%rip),%xmm1 # 4460 <_sk_callback_sse41+0xbf2> .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 15,40,211 // movaps %xmm3,%xmm2 - .byte 102,15,56,0,21,101,30,0,0 // pshufb 0x1e65(%rip),%xmm2 # 4550 <_sk_callback_sse41+0xc23> + .byte 102,15,56,0,21,68,30,0,0 // pshufb 0x1e44(%rip),%xmm2 # 4470 <_sk_callback_sse41+0xc02> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 102,15,114,211,24 // psrld $0x18,%xmm3 @@ -20135,17 +20034,17 @@ _sk_gather_8888_sse41: .byte 102,65,15,58,34,28,129,1 // pinsrd $0x1,(%r9,%rax,4),%xmm3 .byte 102,67,15,58,34,28,145,2 // pinsrd $0x2,(%r9,%r10,4),%xmm3 .byte 102,65,15,58,34,28,137,3 // pinsrd $0x3,(%r9,%rcx,4),%xmm3 - .byte 102,15,111,5,254,29,0,0 // movdqa 0x1dfe(%rip),%xmm0 # 4560 <_sk_callback_sse41+0xc33> + .byte 102,15,111,5,221,29,0,0 // movdqa 0x1ddd(%rip),%xmm0 # 4480 <_sk_callback_sse41+0xc12> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,255,29,0,0 // movaps 0x1dff(%rip),%xmm8 # 4570 <_sk_callback_sse41+0xc43> + .byte 68,15,40,5,222,29,0,0 // movaps 0x1dde(%rip),%xmm8 # 4490 <_sk_callback_sse41+0xc22> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 - .byte 102,15,56,0,13,254,29,0,0 // pshufb 0x1dfe(%rip),%xmm1 # 4580 <_sk_callback_sse41+0xc53> + .byte 102,15,56,0,13,221,29,0,0 // pshufb 0x1ddd(%rip),%xmm1 # 44a0 <_sk_callback_sse41+0xc32> .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,111,211 // movdqa %xmm3,%xmm2 - .byte 102,15,56,0,21,250,29,0,0 // pshufb 0x1dfa(%rip),%xmm2 # 4590 <_sk_callback_sse41+0xc63> + .byte 102,15,56,0,21,217,29,0,0 // pshufb 0x1dd9(%rip),%xmm2 # 44b0 <_sk_callback_sse41+0xc42> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 102,15,114,211,24 // psrld $0x18,%xmm3 @@ -20160,7 +20059,7 @@ FUNCTION(_sk_store_8888_sse41) _sk_store_8888_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,230,29,0,0 // movaps 0x1de6(%rip),%xmm8 # 45a0 <_sk_callback_sse41+0xc73> + .byte 68,15,40,5,197,29,0,0 // movaps 0x1dc5(%rip),%xmm8 # 44c0 <_sk_callback_sse41+0xc52> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 @@ -20197,18 +20096,18 @@ _sk_load_f16_sse41: .byte 102,68,15,97,216 // punpcklwd %xmm0,%xmm11 .byte 102,68,15,105,200 // punpckhwd %xmm0,%xmm9 .byte 102,65,15,56,51,203 // pmovzxwd %xmm11,%xmm1 - .byte 102,68,15,111,5,95,29,0,0 // movdqa 0x1d5f(%rip),%xmm8 # 45b0 <_sk_callback_sse41+0xc83> + .byte 102,68,15,111,5,62,29,0,0 // movdqa 0x1d3e(%rip),%xmm8 # 44d0 <_sk_callback_sse41+0xc62> .byte 102,15,111,209 // movdqa %xmm1,%xmm2 .byte 102,65,15,219,208 // pand %xmm8,%xmm2 .byte 102,15,239,202 // pxor %xmm2,%xmm1 - .byte 102,15,111,29,90,29,0,0 // movdqa 0x1d5a(%rip),%xmm3 # 45c0 <_sk_callback_sse41+0xc93> + .byte 102,15,111,29,57,29,0,0 // movdqa 0x1d39(%rip),%xmm3 # 44e0 <_sk_callback_sse41+0xc72> .byte 102,15,114,242,16 // pslld $0x10,%xmm2 .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,15,56,63,195 // pmaxud %xmm3,%xmm0 .byte 102,15,118,193 // pcmpeqd %xmm1,%xmm0 .byte 102,15,114,241,13 // pslld $0xd,%xmm1 .byte 102,15,235,202 // por %xmm2,%xmm1 - .byte 102,68,15,111,21,70,29,0,0 // movdqa 0x1d46(%rip),%xmm10 # 45d0 <_sk_callback_sse41+0xca3> + .byte 102,68,15,111,21,37,29,0,0 // movdqa 0x1d25(%rip),%xmm10 # 44f0 <_sk_callback_sse41+0xc82> .byte 102,65,15,254,202 // paddd %xmm10,%xmm1 .byte 102,15,219,193 // pand %xmm1,%xmm0 .byte 102,65,15,115,219,8 // psrldq $0x8,%xmm11 @@ -20281,18 +20180,18 @@ _sk_gather_f16_sse41: .byte 102,68,15,97,218 // punpcklwd %xmm2,%xmm11 .byte 102,68,15,105,202 // punpckhwd %xmm2,%xmm9 .byte 102,65,15,56,51,203 // pmovzxwd %xmm11,%xmm1 - .byte 102,68,15,111,5,4,28,0,0 // movdqa 0x1c04(%rip),%xmm8 # 45e0 <_sk_callback_sse41+0xcb3> + .byte 102,68,15,111,5,227,27,0,0 // movdqa 0x1be3(%rip),%xmm8 # 4500 <_sk_callback_sse41+0xc92> .byte 102,15,111,209 // movdqa %xmm1,%xmm2 .byte 102,65,15,219,208 // pand %xmm8,%xmm2 .byte 102,15,239,202 // pxor %xmm2,%xmm1 - .byte 102,15,111,29,255,27,0,0 // movdqa 0x1bff(%rip),%xmm3 # 45f0 <_sk_callback_sse41+0xcc3> + .byte 102,15,111,29,222,27,0,0 // movdqa 0x1bde(%rip),%xmm3 # 4510 <_sk_callback_sse41+0xca2> .byte 102,15,114,242,16 // pslld $0x10,%xmm2 .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,15,56,63,195 // pmaxud %xmm3,%xmm0 .byte 102,15,118,193 // pcmpeqd %xmm1,%xmm0 .byte 102,15,114,241,13 // pslld $0xd,%xmm1 .byte 102,15,235,202 // por %xmm2,%xmm1 - .byte 102,68,15,111,21,235,27,0,0 // movdqa 0x1beb(%rip),%xmm10 # 4600 <_sk_callback_sse41+0xcd3> + .byte 102,68,15,111,21,202,27,0,0 // movdqa 0x1bca(%rip),%xmm10 # 4520 <_sk_callback_sse41+0xcb2> .byte 102,65,15,254,202 // paddd %xmm10,%xmm1 .byte 102,15,219,193 // pand %xmm1,%xmm0 .byte 102,65,15,115,219,8 // psrldq $0x8,%xmm11 @@ -20340,17 +20239,17 @@ FUNCTION(_sk_store_f16_sse41) _sk_store_f16_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 102,68,15,111,21,33,27,0,0 // movdqa 0x1b21(%rip),%xmm10 # 4610 <_sk_callback_sse41+0xce3> + .byte 102,68,15,111,21,0,27,0,0 // movdqa 0x1b00(%rip),%xmm10 # 4530 <_sk_callback_sse41+0xcc2> .byte 102,68,15,111,224 // movdqa %xmm0,%xmm12 .byte 102,68,15,111,232 // movdqa %xmm0,%xmm13 .byte 102,69,15,219,234 // pand %xmm10,%xmm13 .byte 102,69,15,239,229 // pxor %xmm13,%xmm12 - .byte 102,68,15,111,13,20,27,0,0 // movdqa 0x1b14(%rip),%xmm9 # 4620 <_sk_callback_sse41+0xcf3> + .byte 102,68,15,111,13,243,26,0,0 // movdqa 0x1af3(%rip),%xmm9 # 4540 <_sk_callback_sse41+0xcd2> .byte 102,65,15,114,213,16 // psrld $0x10,%xmm13 .byte 102,69,15,111,193 // movdqa %xmm9,%xmm8 .byte 102,69,15,102,196 // pcmpgtd %xmm12,%xmm8 .byte 102,65,15,114,212,13 // psrld $0xd,%xmm12 - .byte 102,68,15,111,29,5,27,0,0 // movdqa 0x1b05(%rip),%xmm11 # 4630 <_sk_callback_sse41+0xd03> + .byte 102,68,15,111,29,228,26,0,0 // movdqa 0x1ae4(%rip),%xmm11 # 4550 <_sk_callback_sse41+0xce2> .byte 102,69,15,235,235 // por %xmm11,%xmm13 .byte 102,69,15,254,236 // paddd %xmm12,%xmm13 .byte 102,69,15,223,197 // pandn %xmm13,%xmm8 @@ -20420,7 +20319,7 @@ _sk_load_u16_be_sse41: .byte 102,15,235,200 // por %xmm0,%xmm1 .byte 102,15,56,51,193 // pmovzxwd %xmm1,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,212,25,0,0 // movaps 0x19d4(%rip),%xmm8 # 4640 <_sk_callback_sse41+0xd13> + .byte 68,15,40,5,179,25,0,0 // movaps 0x19b3(%rip),%xmm8 # 4560 <_sk_callback_sse41+0xcf2> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 .byte 102,15,113,241,8 // psllw $0x8,%xmm1 @@ -20472,7 +20371,7 @@ _sk_load_rgb_u16_be_sse41: .byte 102,15,235,193 // por %xmm1,%xmm0 .byte 102,15,56,51,192 // pmovzxwd %xmm0,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,21,25,0,0 // movaps 0x1915(%rip),%xmm8 # 4650 <_sk_callback_sse41+0xd23> + .byte 68,15,40,5,244,24,0,0 // movaps 0x18f4(%rip),%xmm8 # 4570 <_sk_callback_sse41+0xd02> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 .byte 102,15,113,241,8 // psllw $0x8,%xmm1 @@ -20489,7 +20388,7 @@ _sk_load_rgb_u16_be_sse41: .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,220,24,0,0 // movaps 0x18dc(%rip),%xmm3 # 4660 <_sk_callback_sse41+0xd33> + .byte 15,40,29,187,24,0,0 // movaps 0x18bb(%rip),%xmm3 # 4580 <_sk_callback_sse41+0xd12> .byte 255,224 // jmpq *%rax HIDDEN _sk_store_u16_be_sse41 @@ -20498,7 +20397,7 @@ FUNCTION(_sk_store_u16_be_sse41) _sk_store_u16_be_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,13,221,24,0,0 // movaps 0x18dd(%rip),%xmm9 # 4670 <_sk_callback_sse41+0xd43> + .byte 68,15,40,13,188,24,0,0 // movaps 0x18bc(%rip),%xmm9 # 4590 <_sk_callback_sse41+0xd22> .byte 68,15,40,192 // movaps %xmm0,%xmm8 .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 102,69,15,91,192 // cvtps2dq %xmm8,%xmm8 @@ -20721,10 +20620,10 @@ HIDDEN _sk_luminance_to_alpha_sse41 FUNCTION(_sk_luminance_to_alpha_sse41) _sk_luminance_to_alpha_sse41: .byte 15,40,218 // movaps %xmm2,%xmm3 - .byte 15,89,5,251,21,0,0 // mulps 0x15fb(%rip),%xmm0 # 4680 <_sk_callback_sse41+0xd53> - .byte 15,89,13,4,22,0,0 // mulps 0x1604(%rip),%xmm1 # 4690 <_sk_callback_sse41+0xd63> + .byte 15,89,5,218,21,0,0 // mulps 0x15da(%rip),%xmm0 # 45a0 <_sk_callback_sse41+0xd32> + .byte 15,89,13,227,21,0,0 // mulps 0x15e3(%rip),%xmm1 # 45b0 <_sk_callback_sse41+0xd42> .byte 15,88,200 // addps %xmm0,%xmm1 - .byte 15,89,29,10,22,0,0 // mulps 0x160a(%rip),%xmm3 # 46a0 <_sk_callback_sse41+0xd73> + .byte 15,89,29,233,21,0,0 // mulps 0x15e9(%rip),%xmm3 # 45c0 <_sk_callback_sse41+0xd52> .byte 15,88,217 // addps %xmm1,%xmm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 @@ -20957,7 +20856,7 @@ _sk_linear_gradient_sse41: .byte 69,15,198,237,0 // shufps $0x0,%xmm13,%xmm13 .byte 72,139,8 // mov (%rax),%rcx .byte 72,133,201 // test %rcx,%rcx - .byte 15,132,254,0,0,0 // je 3538 <_sk_linear_gradient_sse41+0x138> + .byte 15,132,254,0,0,0 // je 3479 <_sk_linear_gradient_sse41+0x138> .byte 15,41,100,36,168 // movaps %xmm4,-0x58(%rsp) .byte 15,41,108,36,184 // movaps %xmm5,-0x48(%rsp) .byte 15,41,116,36,200 // movaps %xmm6,-0x38(%rsp) @@ -21007,12 +20906,12 @@ _sk_linear_gradient_sse41: .byte 15,40,196 // movaps %xmm4,%xmm0 .byte 72,131,192,36 // add $0x24,%rax .byte 72,255,201 // dec %rcx - .byte 15,133,65,255,255,255 // jne 3463 <_sk_linear_gradient_sse41+0x63> + .byte 15,133,65,255,255,255 // jne 33a4 <_sk_linear_gradient_sse41+0x63> .byte 15,40,124,36,216 // movaps -0x28(%rsp),%xmm7 .byte 15,40,116,36,200 // movaps -0x38(%rsp),%xmm6 .byte 15,40,108,36,184 // movaps -0x48(%rsp),%xmm5 .byte 15,40,100,36,168 // movaps -0x58(%rsp),%xmm4 - .byte 235,13 // jmp 3545 <_sk_linear_gradient_sse41+0x145> + .byte 235,13 // jmp 3486 <_sk_linear_gradient_sse41+0x145> .byte 15,87,201 // xorps %xmm1,%xmm1 .byte 15,87,210 // xorps %xmm2,%xmm2 .byte 15,87,219 // xorps %xmm3,%xmm3 @@ -21067,7 +20966,7 @@ HIDDEN _sk_save_xy_sse41 FUNCTION(_sk_save_xy_sse41) _sk_save_xy_sse41: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,204,16,0,0 // movaps 0x10cc(%rip),%xmm8 # 46b0 <_sk_callback_sse41+0xd83> + .byte 68,15,40,5,171,16,0,0 // movaps 0x10ab(%rip),%xmm8 # 45d0 <_sk_callback_sse41+0xd62> .byte 15,17,0 // movups %xmm0,(%rax) .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,88,200 // addps %xmm8,%xmm9 @@ -21111,8 +21010,8 @@ _sk_bilinear_nx_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,78,16,0,0 // addps 0x104e(%rip),%xmm0 # 46c0 <_sk_callback_sse41+0xd93> - .byte 68,15,40,13,86,16,0,0 // movaps 0x1056(%rip),%xmm9 # 46d0 <_sk_callback_sse41+0xda3> + .byte 15,88,5,45,16,0,0 // addps 0x102d(%rip),%xmm0 # 45e0 <_sk_callback_sse41+0xd72> + .byte 68,15,40,13,53,16,0,0 // movaps 0x1035(%rip),%xmm9 # 45f0 <_sk_callback_sse41+0xd82> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 68,15,17,136,128,0,0,0 // movups %xmm9,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -21125,7 +21024,7 @@ _sk_bilinear_px_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,69,16,0,0 // addps 0x1045(%rip),%xmm0 # 46e0 <_sk_callback_sse41+0xdb3> + .byte 15,88,5,36,16,0,0 // addps 0x1024(%rip),%xmm0 # 4600 <_sk_callback_sse41+0xd92> .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -21137,8 +21036,8 @@ _sk_bilinear_ny_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,55,16,0,0 // addps 0x1037(%rip),%xmm1 # 46f0 <_sk_callback_sse41+0xdc3> - .byte 68,15,40,13,63,16,0,0 // movaps 0x103f(%rip),%xmm9 # 4700 <_sk_callback_sse41+0xdd3> + .byte 15,88,13,22,16,0,0 // addps 0x1016(%rip),%xmm1 # 4610 <_sk_callback_sse41+0xda2> + .byte 68,15,40,13,30,16,0,0 // movaps 0x101e(%rip),%xmm9 # 4620 <_sk_callback_sse41+0xdb2> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 68,15,17,136,160,0,0,0 // movups %xmm9,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -21151,7 +21050,7 @@ _sk_bilinear_py_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,45,16,0,0 // addps 0x102d(%rip),%xmm1 # 4710 <_sk_callback_sse41+0xde3> + .byte 15,88,13,12,16,0,0 // addps 0x100c(%rip),%xmm1 # 4630 <_sk_callback_sse41+0xdc2> .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -21163,13 +21062,13 @@ _sk_bicubic_n3x_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,32,16,0,0 // addps 0x1020(%rip),%xmm0 # 4720 <_sk_callback_sse41+0xdf3> - .byte 68,15,40,13,40,16,0,0 // movaps 0x1028(%rip),%xmm9 # 4730 <_sk_callback_sse41+0xe03> + .byte 15,88,5,255,15,0,0 // addps 0xfff(%rip),%xmm0 # 4640 <_sk_callback_sse41+0xdd2> + .byte 68,15,40,13,7,16,0,0 // movaps 0x1007(%rip),%xmm9 # 4650 <_sk_callback_sse41+0xde2> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 69,15,40,193 // movaps %xmm9,%xmm8 .byte 69,15,89,192 // mulps %xmm8,%xmm8 - .byte 68,15,89,13,36,16,0,0 // mulps 0x1024(%rip),%xmm9 # 4740 <_sk_callback_sse41+0xe13> - .byte 68,15,88,13,44,16,0,0 // addps 0x102c(%rip),%xmm9 # 4750 <_sk_callback_sse41+0xe23> + .byte 68,15,89,13,3,16,0,0 // mulps 0x1003(%rip),%xmm9 # 4660 <_sk_callback_sse41+0xdf2> + .byte 68,15,88,13,11,16,0,0 // addps 0x100b(%rip),%xmm9 # 4670 <_sk_callback_sse41+0xe02> .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 68,15,17,136,128,0,0,0 // movups %xmm9,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -21182,16 +21081,16 @@ _sk_bicubic_n1x_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,27,16,0,0 // addps 0x101b(%rip),%xmm0 # 4760 <_sk_callback_sse41+0xe33> - .byte 68,15,40,13,35,16,0,0 // movaps 0x1023(%rip),%xmm9 # 4770 <_sk_callback_sse41+0xe43> + .byte 15,88,5,250,15,0,0 // addps 0xffa(%rip),%xmm0 # 4680 <_sk_callback_sse41+0xe12> + .byte 68,15,40,13,2,16,0,0 // movaps 0x1002(%rip),%xmm9 # 4690 <_sk_callback_sse41+0xe22> .byte 69,15,92,200 // subps %xmm8,%xmm9 - .byte 68,15,40,5,39,16,0,0 // movaps 0x1027(%rip),%xmm8 # 4780 <_sk_callback_sse41+0xe53> + .byte 68,15,40,5,6,16,0,0 // movaps 0x1006(%rip),%xmm8 # 46a0 <_sk_callback_sse41+0xe32> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,43,16,0,0 // addps 0x102b(%rip),%xmm8 # 4790 <_sk_callback_sse41+0xe63> + .byte 68,15,88,5,10,16,0,0 // addps 0x100a(%rip),%xmm8 # 46b0 <_sk_callback_sse41+0xe42> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,47,16,0,0 // addps 0x102f(%rip),%xmm8 # 47a0 <_sk_callback_sse41+0xe73> + .byte 68,15,88,5,14,16,0,0 // addps 0x100e(%rip),%xmm8 # 46c0 <_sk_callback_sse41+0xe52> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,51,16,0,0 // addps 0x1033(%rip),%xmm8 # 47b0 <_sk_callback_sse41+0xe83> + .byte 68,15,88,5,18,16,0,0 // addps 0x1012(%rip),%xmm8 # 46d0 <_sk_callback_sse41+0xe62> .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -21201,17 +21100,17 @@ HIDDEN _sk_bicubic_p1x_sse41 FUNCTION(_sk_bicubic_p1x_sse41) _sk_bicubic_p1x_sse41: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,45,16,0,0 // movaps 0x102d(%rip),%xmm8 # 47c0 <_sk_callback_sse41+0xe93> + .byte 68,15,40,5,12,16,0,0 // movaps 0x100c(%rip),%xmm8 # 46e0 <_sk_callback_sse41+0xe72> .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,72,64 // movups 0x40(%rax),%xmm9 .byte 65,15,88,192 // addps %xmm8,%xmm0 - .byte 68,15,40,21,41,16,0,0 // movaps 0x1029(%rip),%xmm10 # 47d0 <_sk_callback_sse41+0xea3> + .byte 68,15,40,21,8,16,0,0 // movaps 0x1008(%rip),%xmm10 # 46f0 <_sk_callback_sse41+0xe82> .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,45,16,0,0 // addps 0x102d(%rip),%xmm10 # 47e0 <_sk_callback_sse41+0xeb3> + .byte 68,15,88,21,12,16,0,0 // addps 0x100c(%rip),%xmm10 # 4700 <_sk_callback_sse41+0xe92> .byte 69,15,89,209 // mulps %xmm9,%xmm10 .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,41,16,0,0 // addps 0x1029(%rip),%xmm10 # 47f0 <_sk_callback_sse41+0xec3> + .byte 68,15,88,21,8,16,0,0 // addps 0x1008(%rip),%xmm10 # 4710 <_sk_callback_sse41+0xea2> .byte 68,15,17,144,128,0,0,0 // movups %xmm10,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -21223,11 +21122,11 @@ _sk_bicubic_p3x_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,28,16,0,0 // addps 0x101c(%rip),%xmm0 # 4800 <_sk_callback_sse41+0xed3> + .byte 15,88,5,251,15,0,0 // addps 0xffb(%rip),%xmm0 # 4720 <_sk_callback_sse41+0xeb2> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,89,201 // mulps %xmm9,%xmm9 - .byte 68,15,89,5,28,16,0,0 // mulps 0x101c(%rip),%xmm8 # 4810 <_sk_callback_sse41+0xee3> - .byte 68,15,88,5,36,16,0,0 // addps 0x1024(%rip),%xmm8 # 4820 <_sk_callback_sse41+0xef3> + .byte 68,15,89,5,251,15,0,0 // mulps 0xffb(%rip),%xmm8 # 4730 <_sk_callback_sse41+0xec2> + .byte 68,15,88,5,3,16,0,0 // addps 0x1003(%rip),%xmm8 # 4740 <_sk_callback_sse41+0xed2> .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -21240,13 +21139,13 @@ _sk_bicubic_n3y_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,18,16,0,0 // addps 0x1012(%rip),%xmm1 # 4830 <_sk_callback_sse41+0xf03> - .byte 68,15,40,13,26,16,0,0 // movaps 0x101a(%rip),%xmm9 # 4840 <_sk_callback_sse41+0xf13> + .byte 15,88,13,241,15,0,0 // addps 0xff1(%rip),%xmm1 # 4750 <_sk_callback_sse41+0xee2> + .byte 68,15,40,13,249,15,0,0 // movaps 0xff9(%rip),%xmm9 # 4760 <_sk_callback_sse41+0xef2> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 69,15,40,193 // movaps %xmm9,%xmm8 .byte 69,15,89,192 // mulps %xmm8,%xmm8 - .byte 68,15,89,13,22,16,0,0 // mulps 0x1016(%rip),%xmm9 # 4850 <_sk_callback_sse41+0xf23> - .byte 68,15,88,13,30,16,0,0 // addps 0x101e(%rip),%xmm9 # 4860 <_sk_callback_sse41+0xf33> + .byte 68,15,89,13,245,15,0,0 // mulps 0xff5(%rip),%xmm9 # 4770 <_sk_callback_sse41+0xf02> + .byte 68,15,88,13,253,15,0,0 // addps 0xffd(%rip),%xmm9 # 4780 <_sk_callback_sse41+0xf12> .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 68,15,17,136,160,0,0,0 // movups %xmm9,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -21259,16 +21158,16 @@ _sk_bicubic_n1y_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,12,16,0,0 // addps 0x100c(%rip),%xmm1 # 4870 <_sk_callback_sse41+0xf43> - .byte 68,15,40,13,20,16,0,0 // movaps 0x1014(%rip),%xmm9 # 4880 <_sk_callback_sse41+0xf53> + .byte 15,88,13,235,15,0,0 // addps 0xfeb(%rip),%xmm1 # 4790 <_sk_callback_sse41+0xf22> + .byte 68,15,40,13,243,15,0,0 // movaps 0xff3(%rip),%xmm9 # 47a0 <_sk_callback_sse41+0xf32> .byte 69,15,92,200 // subps %xmm8,%xmm9 - .byte 68,15,40,5,24,16,0,0 // movaps 0x1018(%rip),%xmm8 # 4890 <_sk_callback_sse41+0xf63> + .byte 68,15,40,5,247,15,0,0 // movaps 0xff7(%rip),%xmm8 # 47b0 <_sk_callback_sse41+0xf42> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,28,16,0,0 // addps 0x101c(%rip),%xmm8 # 48a0 <_sk_callback_sse41+0xf73> + .byte 68,15,88,5,251,15,0,0 // addps 0xffb(%rip),%xmm8 # 47c0 <_sk_callback_sse41+0xf52> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,32,16,0,0 // addps 0x1020(%rip),%xmm8 # 48b0 <_sk_callback_sse41+0xf83> + .byte 68,15,88,5,255,15,0,0 // addps 0xfff(%rip),%xmm8 # 47d0 <_sk_callback_sse41+0xf62> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,36,16,0,0 // addps 0x1024(%rip),%xmm8 # 48c0 <_sk_callback_sse41+0xf93> + .byte 68,15,88,5,3,16,0,0 // addps 0x1003(%rip),%xmm8 # 47e0 <_sk_callback_sse41+0xf72> .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -21278,17 +21177,17 @@ HIDDEN _sk_bicubic_p1y_sse41 FUNCTION(_sk_bicubic_p1y_sse41) _sk_bicubic_p1y_sse41: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,30,16,0,0 // movaps 0x101e(%rip),%xmm8 # 48d0 <_sk_callback_sse41+0xfa3> + .byte 68,15,40,5,253,15,0,0 // movaps 0xffd(%rip),%xmm8 # 47f0 <_sk_callback_sse41+0xf82> .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,72,96 // movups 0x60(%rax),%xmm9 .byte 65,15,88,200 // addps %xmm8,%xmm1 - .byte 68,15,40,21,25,16,0,0 // movaps 0x1019(%rip),%xmm10 # 48e0 <_sk_callback_sse41+0xfb3> + .byte 68,15,40,21,248,15,0,0 // movaps 0xff8(%rip),%xmm10 # 4800 <_sk_callback_sse41+0xf92> .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,29,16,0,0 // addps 0x101d(%rip),%xmm10 # 48f0 <_sk_callback_sse41+0xfc3> + .byte 68,15,88,21,252,15,0,0 // addps 0xffc(%rip),%xmm10 # 4810 <_sk_callback_sse41+0xfa2> .byte 69,15,89,209 // mulps %xmm9,%xmm10 .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,25,16,0,0 // addps 0x1019(%rip),%xmm10 # 4900 <_sk_callback_sse41+0xfd3> + .byte 68,15,88,21,248,15,0,0 // addps 0xff8(%rip),%xmm10 # 4820 <_sk_callback_sse41+0xfb2> .byte 68,15,17,144,160,0,0,0 // movups %xmm10,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -21300,11 +21199,11 @@ _sk_bicubic_p3y_sse41: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,11,16,0,0 // addps 0x100b(%rip),%xmm1 # 4910 <_sk_callback_sse41+0xfe3> + .byte 15,88,13,234,15,0,0 // addps 0xfea(%rip),%xmm1 # 4830 <_sk_callback_sse41+0xfc2> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,89,201 // mulps %xmm9,%xmm9 - .byte 68,15,89,5,11,16,0,0 // mulps 0x100b(%rip),%xmm8 # 4920 <_sk_callback_sse41+0xff3> - .byte 68,15,88,5,19,16,0,0 // addps 0x1013(%rip),%xmm8 # 4930 <_sk_callback_sse41+0x1003> + .byte 68,15,89,5,234,15,0,0 // mulps 0xfea(%rip),%xmm8 # 4840 <_sk_callback_sse41+0xfd2> + .byte 68,15,88,5,242,15,0,0 // addps 0xff2(%rip),%xmm8 # 4850 <_sk_callback_sse41+0xfe2> .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -21489,11 +21388,11 @@ BALIGN16 .byte 0,128,191,0,0,128 // add %al,-0x7fffff41(%rax) .byte 191,0,0,224,64 // mov $0x40e00000,%edi .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 3b98 <.literal16+0x188> + .byte 224,64 // loopne 3ad8 <.literal16+0x188> .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 3b9c <.literal16+0x18c> + .byte 224,64 // loopne 3adc <.literal16+0x18c> .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 3ba0 <.literal16+0x190> + .byte 224,64 // loopne 3ae0 <.literal16+0x190> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -21632,12 +21531,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 0,0 // add %al,(%rax) - .byte 128,63,0 // cmpb $0x0,(%rdi) - .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) - .byte 63 // (bad) - .byte 0,0 // add %al,(%rax) - .byte 128,63,171 // cmpb $0xab,(%rdi) + .byte 171 // stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) .byte 62,171 // ds stos %eax,%es:(%rdi) @@ -21650,25 +21544,14 @@ BALIGN16 .byte 170 // stos %al,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) .byte 62,0,0 // add %al,%ds:(%rax) - .byte 128,191,0,0,128,191,0 // cmpb $0x0,-0x40800000(%rdi) - .byte 0,128,191,0,0,128 // add %al,-0x7fffff41(%rax) - .byte 191,0,0,192,64 // mov $0x40c00000,%edi - .byte 0,0 // add %al,(%rax) .byte 192,64,0,0 // rolb $0x0,0x0(%rax) .byte 192,64,0,0 // rolb $0x0,0x0(%rax) - .byte 192,64,171,170 // rolb $0xaa,-0x55(%rax) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) + .byte 192,64,0,0 // rolb $0x0,0x0(%rax) + .byte 192,64,0,0 // rolb $0x0,0x0(%rax) + .byte 128,64,0,0 // addb $0x0,0x0(%rax) + .byte 128,64,0,0 // addb $0x0,0x0(%rax) + .byte 128,64,0,0 // addb $0x0,0x0(%rax) + .byte 128,64,171,170 // addb $0xaa,-0x55(%rax) .byte 170 // stos %al,%es:(%rdi) .byte 190,171,170,170,190 // mov $0xbeaaaaab,%esi .byte 171 // stos %eax,%es:(%rdi) @@ -21696,13 +21579,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 3d49 <.literal16+0x339> + .byte 224,7 // loopne 3c69 <.literal16+0x319> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 3d4d <.literal16+0x33d> + .byte 224,7 // loopne 3c6d <.literal16+0x31d> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 3d51 <.literal16+0x341> + .byte 224,7 // loopne 3c71 <.literal16+0x321> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 3d55 <.literal16+0x345> + .byte 224,7 // loopne 3c75 <.literal16+0x325> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -21742,10 +21625,10 @@ BALIGN16 .byte 0,1 // add %al,(%rcx) .byte 255 // (bad) .byte 255 // (bad) - .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a003da8 <_sk_callback_sse41+0xa00047b> + .byte 255,5,255,255,255,9 // incl 0x9ffffff(%rip) # a003cc8 <_sk_callback_sse41+0xa00045a> .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3003db0 <_sk_callback_sse41+0x3000483> + .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3003cd0 <_sk_callback_sse41+0x3000462> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -21800,11 +21683,11 @@ BALIGN16 .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 3e7b <.literal16+0x46b> + .byte 127,67 // jg 3d9b <.literal16+0x44b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 3e7f <.literal16+0x46f> + .byte 127,67 // jg 3d9f <.literal16+0x44f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 3e83 <.literal16+0x473> + .byte 127,67 // jg 3da3 <.literal16+0x453> .byte 129,128,128,59,129,128,128,59,129,128// addl $0x80813b80,-0x7f7ec480(%rax) .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,129,128,128,59 // addb $0x3b,-0x7f7f7ec5(%rax) @@ -21819,16 +21702,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 3e74 <.literal16+0x464> + .byte 127,0 // jg 3d94 <.literal16+0x444> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 3e78 <.literal16+0x468> + .byte 127,0 // jg 3d98 <.literal16+0x448> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 3e7c <.literal16+0x46c> + .byte 127,0 // jg 3d9c <.literal16+0x44c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 3e80 <.literal16+0x470> + .byte 127,0 // jg 3da0 <.literal16+0x450> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -21837,7 +21720,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 3f05 <.literal16+0x4f5> + .byte 119,115 // ja 3e25 <.literal16+0x4d5> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -21848,7 +21731,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 3e69 <.literal16+0x459> + .byte 117,191 // jne 3d89 <.literal16+0x439> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -21860,7 +21743,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a37eaa <_sk_callback_sse41+0xffffffffe9a3457d> + .byte 233,220,63,163,233 // jmpq ffffffffe9a37dca <_sk_callback_sse41+0xffffffffe9a3455c> .byte 220,63 // fdivrl (%rdi) .byte 81 // push %rcx .byte 140,242 // mov %?,%edx @@ -21915,16 +21798,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 3f44 <.literal16+0x534> + .byte 127,0 // jg 3e64 <.literal16+0x514> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 3f48 <.literal16+0x538> + .byte 127,0 // jg 3e68 <.literal16+0x518> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 3f4c <.literal16+0x53c> + .byte 127,0 // jg 3e6c <.literal16+0x51c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 3f50 <.literal16+0x540> + .byte 127,0 // jg 3e70 <.literal16+0x520> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -21933,7 +21816,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 3fd5 <.literal16+0x5c5> + .byte 119,115 // ja 3ef5 <.literal16+0x5a5> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -21944,7 +21827,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 3f39 <.literal16+0x529> + .byte 117,191 // jne 3e59 <.literal16+0x509> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -21956,7 +21839,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a37f7a <_sk_callback_sse41+0xffffffffe9a3464d> + .byte 233,220,63,163,233 // jmpq ffffffffe9a37e9a <_sk_callback_sse41+0xffffffffe9a3462c> .byte 220,63 // fdivrl (%rdi) .byte 81 // push %rcx .byte 140,242 // mov %?,%edx @@ -22011,16 +21894,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4014 <.literal16+0x604> + .byte 127,0 // jg 3f34 <.literal16+0x5e4> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4018 <.literal16+0x608> + .byte 127,0 // jg 3f38 <.literal16+0x5e8> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 401c <.literal16+0x60c> + .byte 127,0 // jg 3f3c <.literal16+0x5ec> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4020 <.literal16+0x610> + .byte 127,0 // jg 3f40 <.literal16+0x5f0> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -22029,7 +21912,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 40a5 <.literal16+0x695> + .byte 119,115 // ja 3fc5 <.literal16+0x675> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -22040,7 +21923,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 4009 <.literal16+0x5f9> + .byte 117,191 // jne 3f29 <.literal16+0x5d9> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -22052,7 +21935,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a3804a <_sk_callback_sse41+0xffffffffe9a3471d> + .byte 233,220,63,163,233 // jmpq ffffffffe9a37f6a <_sk_callback_sse41+0xffffffffe9a346fc> .byte 220,63 // fdivrl (%rdi) .byte 81 // push %rcx .byte 140,242 // mov %?,%edx @@ -22107,16 +21990,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 40e4 <.literal16+0x6d4> + .byte 127,0 // jg 4004 <.literal16+0x6b4> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 40e8 <.literal16+0x6d8> + .byte 127,0 // jg 4008 <.literal16+0x6b8> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 40ec <.literal16+0x6dc> + .byte 127,0 // jg 400c <.literal16+0x6bc> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 40f0 <.literal16+0x6e0> + .byte 127,0 // jg 4010 <.literal16+0x6c0> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -22125,7 +22008,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4175 <.literal16+0x765> + .byte 119,115 // ja 4095 <.literal16+0x745> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -22136,7 +22019,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 40d9 <.literal16+0x6c9> + .byte 117,191 // jne 3ff9 <.literal16+0x6a9> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -22148,7 +22031,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a3811a <_sk_callback_sse41+0xffffffffe9a347ed> + .byte 233,220,63,163,233 // jmpq ffffffffe9a3803a <_sk_callback_sse41+0xffffffffe9a347cc> .byte 220,63 // fdivrl (%rdi) .byte 81 // push %rcx .byte 140,242 // mov %?,%edx @@ -22199,13 +22082,13 @@ BALIGN16 .byte 200,66,0,0 // enterq $0x42,$0x0 .byte 200,66,0,0 // enterq $0x42,$0x0 .byte 200,66,0,0 // enterq $0x42,$0x0 - .byte 127,67 // jg 41f7 <.literal16+0x7e7> + .byte 127,67 // jg 4117 <.literal16+0x7c7> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 41fb <.literal16+0x7eb> + .byte 127,67 // jg 411b <.literal16+0x7cb> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 41ff <.literal16+0x7ef> + .byte 127,67 // jg 411f <.literal16+0x7cf> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4203 <.literal16+0x7f3> + .byte 127,67 // jg 4123 <.literal16+0x7d3> .byte 0,0 // add %al,(%rax) .byte 0,195 // add %al,%bl .byte 0,0 // add %al,(%rax) @@ -22252,16 +22135,16 @@ BALIGN16 .byte 128,3,62 // addb $0x3e,(%rbx) .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 4283 <.literal16+0x873> + .byte 118,63 // jbe 41a3 <.literal16+0x853> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 4287 <.literal16+0x877> + .byte 118,63 // jbe 41a7 <.literal16+0x857> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 428b <.literal16+0x87b> + .byte 118,63 // jbe 41ab <.literal16+0x85b> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 428f <.literal16+0x87f> + .byte 118,63 // jbe 41af <.literal16+0x85f> .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 246,64,83,63 // testb $0x3f,0x53(%rax) @@ -22273,11 +22156,11 @@ BALIGN16 .byte 128,59,0 // cmpb $0x0,(%rbx) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 42cb <.literal16+0x8bb> + .byte 127,67 // jg 41eb <.literal16+0x89b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 42cf <.literal16+0x8bf> + .byte 127,67 // jg 41ef <.literal16+0x89f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 42d3 <.literal16+0x8c3> + .byte 127,67 // jg 41f3 <.literal16+0x8a3> .byte 129,128,128,59,129,128,128,59,129,128// addl $0x80813b80,-0x7f7ec480(%rax) .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,0,0,128,63 // addb $0x3f,-0x7fffffc5(%rax) @@ -22306,7 +22189,7 @@ BALIGN16 .byte 5,255,255,255,9 // add $0x9ffffff,%eax .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3004300 <_sk_callback_sse41+0x30009d3> + .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3004220 <_sk_callback_sse41+0x30009b2> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -22335,13 +22218,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 4339 <.literal16+0x929> + .byte 224,7 // loopne 4259 <.literal16+0x909> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 433d <.literal16+0x92d> + .byte 224,7 // loopne 425d <.literal16+0x90d> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4341 <.literal16+0x931> + .byte 224,7 // loopne 4261 <.literal16+0x911> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4345 <.literal16+0x935> + .byte 224,7 // loopne 4265 <.literal16+0x915> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -22387,13 +22270,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 43a9 <.literal16+0x999> + .byte 224,7 // loopne 42c9 <.literal16+0x979> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 43ad <.literal16+0x99d> + .byte 224,7 // loopne 42cd <.literal16+0x97d> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 43b1 <.literal16+0x9a1> + .byte 224,7 // loopne 42d1 <.literal16+0x981> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 43b5 <.literal16+0x9a5> + .byte 224,7 // loopne 42d5 <.literal16+0x985> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -22431,13 +22314,13 @@ BALIGN16 .byte 65,0,0 // add %al,(%r8) .byte 248 // clc .byte 65,0,0 // add %al,(%r8) - .byte 124,66 // jl 4446 <.literal16+0xa36> + .byte 124,66 // jl 4366 <.literal16+0xa16> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 444a <.literal16+0xa3a> + .byte 124,66 // jl 436a <.literal16+0xa1a> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 444e <.literal16+0xa3e> + .byte 124,66 // jl 436e <.literal16+0xa1e> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 4452 <.literal16+0xa42> + .byte 124,66 // jl 4372 <.literal16+0xa22> .byte 0,240 // add %dh,%al .byte 0,0 // add %al,(%rax) .byte 0,240 // add %dh,%al @@ -22527,13 +22410,13 @@ BALIGN16 .byte 136,136,61,137,136,136 // mov %cl,-0x777776c3(%rax) .byte 61,137,136,136,61 // cmp $0x3d888889,%eax .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 4555 <.literal16+0xb45> + .byte 112,65 // jo 4475 <.literal16+0xb25> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 4559 <.literal16+0xb49> + .byte 112,65 // jo 4479 <.literal16+0xb29> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 455d <.literal16+0xb4d> + .byte 112,65 // jo 447d <.literal16+0xb2d> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 4561 <.literal16+0xb51> + .byte 112,65 // jo 4481 <.literal16+0xb31> .byte 255,0 // incl (%rax) .byte 0,0 // add %al,(%rax) .byte 255,0 // incl (%rax) @@ -22548,7 +22431,7 @@ BALIGN16 .byte 5,255,255,255,9 // add $0x9ffffff,%eax .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3004550 <_sk_callback_sse41+0x3000c23> + .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3004470 <_sk_callback_sse41+0x3000c02> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -22575,7 +22458,7 @@ BALIGN16 .byte 5,255,255,255,9 // add $0x9ffffff,%eax .byte 255 // (bad) .byte 255 // (bad) - .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 3004590 <_sk_callback_sse41+0x3000c63> + .byte 255,13,255,255,255,2 // decl 0x2ffffff(%rip) # 30044b0 <_sk_callback_sse41+0x3000c42> .byte 255 // (bad) .byte 255 // (bad) .byte 255,6 // incl (%rsi) @@ -22590,11 +22473,11 @@ BALIGN16 .byte 255,0 // incl (%rax) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 45eb <.literal16+0xbdb> + .byte 127,67 // jg 450b <.literal16+0xbbb> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 45ef <.literal16+0xbdf> + .byte 127,67 // jg 450f <.literal16+0xbbf> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 45f3 <.literal16+0xbe3> + .byte 127,67 // jg 4513 <.literal16+0xbc3> .byte 0,128,0,0,0,128 // add %al,-0x80000000(%rax) .byte 0,0 // add %al,(%rax) .byte 0,128,0,0,0,128 // add %al,-0x80000000(%rax) @@ -22670,13 +22553,13 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 255 // (bad) - .byte 127,71 // jg 46bb <.literal16+0xcab> + .byte 127,71 // jg 45db <.literal16+0xc8b> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 46bf <.literal16+0xcaf> + .byte 127,71 // jg 45df <.literal16+0xc8f> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 46c3 <.literal16+0xcb3> + .byte 127,71 // jg 45e3 <.literal16+0xc93> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 46c7 <.literal16+0xcb7> + .byte 127,71 // jg 45e7 <.literal16+0xc97> .byte 208 // (bad) .byte 179,89 // mov $0x59,%bl .byte 62,208 // ds (bad) @@ -22760,11 +22643,11 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,114 // cmpb $0x72,(%rdi) .byte 28,199 // sbb $0xc7,%al - .byte 62,114,28 // jb,pt 4762 <.literal16+0xd52> + .byte 62,114,28 // jb,pt 4682 <.literal16+0xd32> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4766 <.literal16+0xd56> + .byte 62,114,28 // jb,pt 4686 <.literal16+0xd36> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 476a <.literal16+0xd5a> + .byte 62,114,28 // jb,pt 468a <.literal16+0xd3a> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -22808,7 +22691,7 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d5f5 <_sk_callback_sse41+0x3d639cc8> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d515 <_sk_callback_sse41+0x3d639ca7> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -22834,7 +22717,7 @@ BALIGN16 .byte 0,192 // add %al,%al .byte 63 // (bad) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d635 <_sk_callback_sse41+0x3d639d08> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d555 <_sk_callback_sse41+0x3d639ce7> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al @@ -22843,13 +22726,13 @@ BALIGN16 .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al .byte 63 // (bad) - .byte 114,28 // jb 482e <.literal16+0xe1e> + .byte 114,28 // jb 474e <.literal16+0xdfe> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4832 <.literal16+0xe22> + .byte 62,114,28 // jb,pt 4752 <.literal16+0xe02> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4836 <.literal16+0xe26> + .byte 62,114,28 // jb,pt 4756 <.literal16+0xe06> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 483a <.literal16+0xe2a> + .byte 62,114,28 // jb,pt 475a <.literal16+0xe0a> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -22870,11 +22753,11 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,114 // cmpb $0x72,(%rdi) .byte 28,199 // sbb $0xc7,%al - .byte 62,114,28 // jb,pt 4872 <.literal16+0xe62> + .byte 62,114,28 // jb,pt 4792 <.literal16+0xe42> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4876 <.literal16+0xe66> + .byte 62,114,28 // jb,pt 4796 <.literal16+0xe46> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 487a <.literal16+0xe6a> + .byte 62,114,28 // jb,pt 479a <.literal16+0xe4a> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -22918,7 +22801,7 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d705 <_sk_callback_sse41+0x3d639dd8> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d625 <_sk_callback_sse41+0x3d639db7> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -22944,7 +22827,7 @@ BALIGN16 .byte 0,192 // add %al,%al .byte 63 // (bad) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d745 <_sk_callback_sse41+0x3d639e18> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d665 <_sk_callback_sse41+0x3d639df7> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al @@ -22953,13 +22836,13 @@ BALIGN16 .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al .byte 63 // (bad) - .byte 114,28 // jb 493e <.literal16+0xf2e> + .byte 114,28 // jb 485e <.literal16+0xf0e> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4942 <_sk_callback_sse41+0x1015> + .byte 62,114,28 // jb,pt 4862 <_sk_callback_sse41+0xff4> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4946 <_sk_callback_sse41+0x1019> + .byte 62,114,28 // jb,pt 4866 <_sk_callback_sse41+0xff8> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 494a <_sk_callback_sse41+0x101d> + .byte 62,114,28 // jb,pt 486a <_sk_callback_sse41+0xffc> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -23029,7 +22912,7 @@ _sk_seed_shader_sse2: .byte 102,15,110,199 // movd %edi,%xmm0 .byte 102,15,112,192,0 // pshufd $0x0,%xmm0,%xmm0 .byte 15,91,200 // cvtdq2ps %xmm0,%xmm1 - .byte 15,40,21,132,61,0,0 // movaps 0x3d84(%rip),%xmm2 # 3e00 <_sk_callback_sse2+0xd9> + .byte 15,40,21,20,61,0,0 // movaps 0x3d14(%rip),%xmm2 # 3d90 <_sk_callback_sse2+0xe3> .byte 15,88,202 // addps %xmm2,%xmm1 .byte 15,16,2 // movups (%rdx),%xmm0 .byte 15,88,193 // addps %xmm1,%xmm0 @@ -23038,7 +22921,7 @@ _sk_seed_shader_sse2: .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 .byte 15,88,202 // addps %xmm2,%xmm1 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,21,115,61,0,0 // movaps 0x3d73(%rip),%xmm2 # 3e10 <_sk_callback_sse2+0xe9> + .byte 15,40,21,3,61,0,0 // movaps 0x3d03(%rip),%xmm2 # 3da0 <_sk_callback_sse2+0xf3> .byte 15,87,219 // xorps %xmm3,%xmm3 .byte 15,87,228 // xorps %xmm4,%xmm4 .byte 15,87,237 // xorps %xmm5,%xmm5 @@ -23078,7 +22961,7 @@ HIDDEN _sk_srcatop_sse2 FUNCTION(_sk_srcatop_sse2) _sk_srcatop_sse2: .byte 15,89,199 // mulps %xmm7,%xmm0 - .byte 68,15,40,5,46,61,0,0 // movaps 0x3d2e(%rip),%xmm8 # 3e20 <_sk_callback_sse2+0xf9> + .byte 68,15,40,5,190,60,0,0 // movaps 0x3cbe(%rip),%xmm8 # 3db0 <_sk_callback_sse2+0x103> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,89,204 // mulps %xmm4,%xmm9 @@ -23103,7 +22986,7 @@ FUNCTION(_sk_dstatop_sse2) _sk_dstatop_sse2: .byte 68,15,40,195 // movaps %xmm3,%xmm8 .byte 68,15,89,196 // mulps %xmm4,%xmm8 - .byte 68,15,40,13,241,60,0,0 // movaps 0x3cf1(%rip),%xmm9 # 3e30 <_sk_callback_sse2+0x109> + .byte 68,15,40,13,129,60,0,0 // movaps 0x3c81(%rip),%xmm9 # 3dc0 <_sk_callback_sse2+0x113> .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 65,15,88,192 // addps %xmm8,%xmm0 @@ -23150,7 +23033,7 @@ HIDDEN _sk_srcout_sse2 .globl _sk_srcout_sse2 FUNCTION(_sk_srcout_sse2) _sk_srcout_sse2: - .byte 68,15,40,5,149,60,0,0 // movaps 0x3c95(%rip),%xmm8 # 3e40 <_sk_callback_sse2+0x119> + .byte 68,15,40,5,37,60,0,0 // movaps 0x3c25(%rip),%xmm8 # 3dd0 <_sk_callback_sse2+0x123> .byte 68,15,92,199 // subps %xmm7,%xmm8 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 @@ -23163,7 +23046,7 @@ HIDDEN _sk_dstout_sse2 .globl _sk_dstout_sse2 FUNCTION(_sk_dstout_sse2) _sk_dstout_sse2: - .byte 68,15,40,5,133,60,0,0 // movaps 0x3c85(%rip),%xmm8 # 3e50 <_sk_callback_sse2+0x129> + .byte 68,15,40,5,21,60,0,0 // movaps 0x3c15(%rip),%xmm8 # 3de0 <_sk_callback_sse2+0x133> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 15,89,196 // mulps %xmm4,%xmm0 @@ -23180,7 +23063,7 @@ HIDDEN _sk_srcover_sse2 .globl _sk_srcover_sse2 FUNCTION(_sk_srcover_sse2) _sk_srcover_sse2: - .byte 68,15,40,5,104,60,0,0 // movaps 0x3c68(%rip),%xmm8 # 3e60 <_sk_callback_sse2+0x139> + .byte 68,15,40,5,248,59,0,0 // movaps 0x3bf8(%rip),%xmm8 # 3df0 <_sk_callback_sse2+0x143> .byte 68,15,92,195 // subps %xmm3,%xmm8 .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,89,204 // mulps %xmm4,%xmm9 @@ -23200,7 +23083,7 @@ HIDDEN _sk_dstover_sse2 .globl _sk_dstover_sse2 FUNCTION(_sk_dstover_sse2) _sk_dstover_sse2: - .byte 68,15,40,5,60,60,0,0 // movaps 0x3c3c(%rip),%xmm8 # 3e70 <_sk_callback_sse2+0x149> + .byte 68,15,40,5,204,59,0,0 // movaps 0x3bcc(%rip),%xmm8 # 3e00 <_sk_callback_sse2+0x153> .byte 68,15,92,199 // subps %xmm7,%xmm8 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -23228,7 +23111,7 @@ HIDDEN _sk_multiply_sse2 .globl _sk_multiply_sse2 FUNCTION(_sk_multiply_sse2) _sk_multiply_sse2: - .byte 68,15,40,5,16,60,0,0 // movaps 0x3c10(%rip),%xmm8 # 3e80 <_sk_callback_sse2+0x159> + .byte 68,15,40,5,160,59,0,0 // movaps 0x3ba0(%rip),%xmm8 # 3e10 <_sk_callback_sse2+0x163> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 69,15,40,209 // movaps %xmm9,%xmm10 @@ -23304,7 +23187,7 @@ HIDDEN _sk_xor__sse2 FUNCTION(_sk_xor__sse2) _sk_xor__sse2: .byte 68,15,40,195 // movaps %xmm3,%xmm8 - .byte 15,40,29,65,59,0,0 // movaps 0x3b41(%rip),%xmm3 # 3e90 <_sk_callback_sse2+0x169> + .byte 15,40,29,209,58,0,0 // movaps 0x3ad1(%rip),%xmm3 # 3e20 <_sk_callback_sse2+0x173> .byte 68,15,40,203 // movaps %xmm3,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 65,15,89,193 // mulps %xmm9,%xmm0 @@ -23352,7 +23235,7 @@ _sk_darken_sse2: .byte 68,15,89,206 // mulps %xmm6,%xmm9 .byte 65,15,95,209 // maxps %xmm9,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,172,58,0,0 // movaps 0x3aac(%rip),%xmm2 # 3ea0 <_sk_callback_sse2+0x179> + .byte 15,40,21,60,58,0,0 // movaps 0x3a3c(%rip),%xmm2 # 3e30 <_sk_callback_sse2+0x183> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -23386,7 +23269,7 @@ _sk_lighten_sse2: .byte 68,15,89,206 // mulps %xmm6,%xmm9 .byte 65,15,93,209 // minps %xmm9,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,81,58,0,0 // movaps 0x3a51(%rip),%xmm2 # 3eb0 <_sk_callback_sse2+0x189> + .byte 15,40,21,225,57,0,0 // movaps 0x39e1(%rip),%xmm2 # 3e40 <_sk_callback_sse2+0x193> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -23423,7 +23306,7 @@ _sk_difference_sse2: .byte 65,15,93,209 // minps %xmm9,%xmm2 .byte 15,88,210 // addps %xmm2,%xmm2 .byte 68,15,92,194 // subps %xmm2,%xmm8 - .byte 15,40,21,235,57,0,0 // movaps 0x39eb(%rip),%xmm2 # 3ec0 <_sk_callback_sse2+0x199> + .byte 15,40,21,123,57,0,0 // movaps 0x397b(%rip),%xmm2 # 3e50 <_sk_callback_sse2+0x1a3> .byte 15,92,211 // subps %xmm3,%xmm2 .byte 15,89,215 // mulps %xmm7,%xmm2 .byte 15,88,218 // addps %xmm2,%xmm3 @@ -23450,7 +23333,7 @@ _sk_exclusion_sse2: .byte 15,89,214 // mulps %xmm6,%xmm2 .byte 15,88,210 // addps %xmm2,%xmm2 .byte 68,15,92,202 // subps %xmm2,%xmm9 - .byte 15,40,13,172,57,0,0 // movaps 0x39ac(%rip),%xmm1 # 3ed0 <_sk_callback_sse2+0x1a9> + .byte 15,40,13,60,57,0,0 // movaps 0x393c(%rip),%xmm1 # 3e60 <_sk_callback_sse2+0x1b3> .byte 15,92,203 // subps %xmm3,%xmm1 .byte 15,89,207 // mulps %xmm7,%xmm1 .byte 15,88,217 // addps %xmm1,%xmm3 @@ -23464,7 +23347,7 @@ HIDDEN _sk_colorburn_sse2 FUNCTION(_sk_colorburn_sse2) _sk_colorburn_sse2: .byte 68,15,40,192 // movaps %xmm0,%xmm8 - .byte 68,15,40,21,155,57,0,0 // movaps 0x399b(%rip),%xmm10 # 3ee0 <_sk_callback_sse2+0x1b9> + .byte 68,15,40,21,43,57,0,0 // movaps 0x392b(%rip),%xmm10 # 3e70 <_sk_callback_sse2+0x1c3> .byte 69,15,40,202 // movaps %xmm10,%xmm9 .byte 68,15,92,207 // subps %xmm7,%xmm9 .byte 69,15,40,217 // movaps %xmm9,%xmm11 @@ -23558,7 +23441,7 @@ HIDDEN _sk_colordodge_sse2 FUNCTION(_sk_colordodge_sse2) _sk_colordodge_sse2: .byte 68,15,40,200 // movaps %xmm0,%xmm9 - .byte 68,15,40,21,81,56,0,0 // movaps 0x3851(%rip),%xmm10 # 3ef0 <_sk_callback_sse2+0x1c9> + .byte 68,15,40,21,225,55,0,0 // movaps 0x37e1(%rip),%xmm10 # 3e80 <_sk_callback_sse2+0x1d3> .byte 69,15,40,218 // movaps %xmm10,%xmm11 .byte 68,15,92,223 // subps %xmm7,%xmm11 .byte 69,15,40,227 // movaps %xmm11,%xmm12 @@ -23652,7 +23535,7 @@ _sk_hardlight_sse2: .byte 15,41,116,36,232 // movaps %xmm6,-0x18(%rsp) .byte 15,40,245 // movaps %xmm5,%xmm6 .byte 15,40,236 // movaps %xmm4,%xmm5 - .byte 68,15,40,29,6,55,0,0 // movaps 0x3706(%rip),%xmm11 # 3f00 <_sk_callback_sse2+0x1d9> + .byte 68,15,40,29,150,54,0,0 // movaps 0x3696(%rip),%xmm11 # 3e90 <_sk_callback_sse2+0x1e3> .byte 69,15,40,211 // movaps %xmm11,%xmm10 .byte 68,15,92,215 // subps %xmm7,%xmm10 .byte 69,15,40,194 // movaps %xmm10,%xmm8 @@ -23740,7 +23623,7 @@ FUNCTION(_sk_overlay_sse2) _sk_overlay_sse2: .byte 68,15,40,193 // movaps %xmm1,%xmm8 .byte 68,15,40,232 // movaps %xmm0,%xmm13 - .byte 68,15,40,13,212,53,0,0 // movaps 0x35d4(%rip),%xmm9 # 3f10 <_sk_callback_sse2+0x1e9> + .byte 68,15,40,13,100,53,0,0 // movaps 0x3564(%rip),%xmm9 # 3ea0 <_sk_callback_sse2+0x1f3> .byte 69,15,40,209 // movaps %xmm9,%xmm10 .byte 68,15,92,215 // subps %xmm7,%xmm10 .byte 69,15,40,218 // movaps %xmm10,%xmm11 @@ -23831,7 +23714,7 @@ _sk_softlight_sse2: .byte 68,15,40,213 // movaps %xmm5,%xmm10 .byte 68,15,94,215 // divps %xmm7,%xmm10 .byte 69,15,84,212 // andps %xmm12,%xmm10 - .byte 68,15,40,13,145,52,0,0 // movaps 0x3491(%rip),%xmm9 # 3f20 <_sk_callback_sse2+0x1f9> + .byte 68,15,40,13,33,52,0,0 // movaps 0x3421(%rip),%xmm9 # 3eb0 <_sk_callback_sse2+0x203> .byte 69,15,40,249 // movaps %xmm9,%xmm15 .byte 69,15,92,250 // subps %xmm10,%xmm15 .byte 69,15,40,218 // movaps %xmm10,%xmm11 @@ -23844,10 +23727,10 @@ _sk_softlight_sse2: .byte 65,15,40,194 // movaps %xmm10,%xmm0 .byte 15,89,192 // mulps %xmm0,%xmm0 .byte 65,15,88,194 // addps %xmm10,%xmm0 - .byte 68,15,40,53,107,52,0,0 // movaps 0x346b(%rip),%xmm14 # 3f30 <_sk_callback_sse2+0x209> + .byte 68,15,40,53,251,51,0,0 // movaps 0x33fb(%rip),%xmm14 # 3ec0 <_sk_callback_sse2+0x213> .byte 69,15,88,222 // addps %xmm14,%xmm11 .byte 68,15,89,216 // mulps %xmm0,%xmm11 - .byte 68,15,40,21,107,52,0,0 // movaps 0x346b(%rip),%xmm10 # 3f40 <_sk_callback_sse2+0x219> + .byte 68,15,40,21,251,51,0,0 // movaps 0x33fb(%rip),%xmm10 # 3ed0 <_sk_callback_sse2+0x223> .byte 69,15,89,234 // mulps %xmm10,%xmm13 .byte 69,15,88,235 // addps %xmm11,%xmm13 .byte 15,88,228 // addps %xmm4,%xmm4 @@ -23999,7 +23882,7 @@ HIDDEN _sk_clamp_1_sse2 .globl _sk_clamp_1_sse2 FUNCTION(_sk_clamp_1_sse2) _sk_clamp_1_sse2: - .byte 68,15,40,5,122,50,0,0 // movaps 0x327a(%rip),%xmm8 # 3f50 <_sk_callback_sse2+0x229> + .byte 68,15,40,5,10,50,0,0 // movaps 0x320a(%rip),%xmm8 # 3ee0 <_sk_callback_sse2+0x233> .byte 65,15,93,192 // minps %xmm8,%xmm0 .byte 65,15,93,200 // minps %xmm8,%xmm1 .byte 65,15,93,208 // minps %xmm8,%xmm2 @@ -24011,7 +23894,7 @@ HIDDEN _sk_clamp_a_sse2 .globl _sk_clamp_a_sse2 FUNCTION(_sk_clamp_a_sse2) _sk_clamp_a_sse2: - .byte 15,93,29,111,50,0,0 // minps 0x326f(%rip),%xmm3 # 3f60 <_sk_callback_sse2+0x239> + .byte 15,93,29,255,49,0,0 // minps 0x31ff(%rip),%xmm3 # 3ef0 <_sk_callback_sse2+0x243> .byte 15,93,195 // minps %xmm3,%xmm0 .byte 15,93,203 // minps %xmm3,%xmm1 .byte 15,93,211 // minps %xmm3,%xmm2 @@ -24098,7 +23981,7 @@ HIDDEN _sk_unpremul_sse2 FUNCTION(_sk_unpremul_sse2) _sk_unpremul_sse2: .byte 69,15,87,192 // xorps %xmm8,%xmm8 - .byte 68,15,40,13,218,49,0,0 // movaps 0x31da(%rip),%xmm9 # 3f70 <_sk_callback_sse2+0x249> + .byte 68,15,40,13,106,49,0,0 // movaps 0x316a(%rip),%xmm9 # 3f00 <_sk_callback_sse2+0x253> .byte 68,15,94,203 // divps %xmm3,%xmm9 .byte 68,15,194,195,4 // cmpneqps %xmm3,%xmm8 .byte 69,15,84,193 // andps %xmm9,%xmm8 @@ -24112,20 +23995,20 @@ HIDDEN _sk_from_srgb_sse2 .globl _sk_from_srgb_sse2 FUNCTION(_sk_from_srgb_sse2) _sk_from_srgb_sse2: - .byte 68,15,40,5,197,49,0,0 // movaps 0x31c5(%rip),%xmm8 # 3f80 <_sk_callback_sse2+0x259> + .byte 68,15,40,5,85,49,0,0 // movaps 0x3155(%rip),%xmm8 # 3f10 <_sk_callback_sse2+0x263> .byte 68,15,40,232 // movaps %xmm0,%xmm13 .byte 69,15,89,232 // mulps %xmm8,%xmm13 .byte 68,15,40,216 // movaps %xmm0,%xmm11 .byte 69,15,89,219 // mulps %xmm11,%xmm11 - .byte 68,15,40,13,189,49,0,0 // movaps 0x31bd(%rip),%xmm9 # 3f90 <_sk_callback_sse2+0x269> + .byte 68,15,40,13,77,49,0,0 // movaps 0x314d(%rip),%xmm9 # 3f20 <_sk_callback_sse2+0x273> .byte 68,15,40,240 // movaps %xmm0,%xmm14 .byte 69,15,89,241 // mulps %xmm9,%xmm14 - .byte 68,15,40,21,189,49,0,0 // movaps 0x31bd(%rip),%xmm10 # 3fa0 <_sk_callback_sse2+0x279> + .byte 68,15,40,21,77,49,0,0 // movaps 0x314d(%rip),%xmm10 # 3f30 <_sk_callback_sse2+0x283> .byte 69,15,88,242 // addps %xmm10,%xmm14 .byte 69,15,89,243 // mulps %xmm11,%xmm14 - .byte 68,15,40,29,189,49,0,0 // movaps 0x31bd(%rip),%xmm11 # 3fb0 <_sk_callback_sse2+0x289> + .byte 68,15,40,29,77,49,0,0 // movaps 0x314d(%rip),%xmm11 # 3f40 <_sk_callback_sse2+0x293> .byte 69,15,88,243 // addps %xmm11,%xmm14 - .byte 68,15,40,37,193,49,0,0 // movaps 0x31c1(%rip),%xmm12 # 3fc0 <_sk_callback_sse2+0x299> + .byte 68,15,40,37,81,49,0,0 // movaps 0x3151(%rip),%xmm12 # 3f50 <_sk_callback_sse2+0x2a3> .byte 65,15,194,196,1 // cmpltps %xmm12,%xmm0 .byte 68,15,84,232 // andps %xmm0,%xmm13 .byte 65,15,85,198 // andnps %xmm14,%xmm0 @@ -24164,20 +24047,20 @@ _sk_to_srgb_sse2: .byte 68,15,82,192 // rsqrtps %xmm0,%xmm8 .byte 69,15,83,200 // rcpps %xmm8,%xmm9 .byte 69,15,82,232 // rsqrtps %xmm8,%xmm13 - .byte 68,15,40,5,70,49,0,0 // movaps 0x3146(%rip),%xmm8 # 3fd0 <_sk_callback_sse2+0x2a9> + .byte 68,15,40,5,214,48,0,0 // movaps 0x30d6(%rip),%xmm8 # 3f60 <_sk_callback_sse2+0x2b3> .byte 68,15,40,240 // movaps %xmm0,%xmm14 .byte 69,15,89,240 // mulps %xmm8,%xmm14 - .byte 68,15,40,21,70,49,0,0 // movaps 0x3146(%rip),%xmm10 # 3fe0 <_sk_callback_sse2+0x2b9> + .byte 68,15,40,21,214,48,0,0 // movaps 0x30d6(%rip),%xmm10 # 3f70 <_sk_callback_sse2+0x2c3> .byte 69,15,89,202 // mulps %xmm10,%xmm9 - .byte 68,15,40,29,74,49,0,0 // movaps 0x314a(%rip),%xmm11 # 3ff0 <_sk_callback_sse2+0x2c9> + .byte 68,15,40,29,218,48,0,0 // movaps 0x30da(%rip),%xmm11 # 3f80 <_sk_callback_sse2+0x2d3> .byte 69,15,88,203 // addps %xmm11,%xmm9 - .byte 68,15,40,37,78,49,0,0 // movaps 0x314e(%rip),%xmm12 # 4000 <_sk_callback_sse2+0x2d9> + .byte 68,15,40,37,222,48,0,0 // movaps 0x30de(%rip),%xmm12 # 3f90 <_sk_callback_sse2+0x2e3> .byte 69,15,89,236 // mulps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,40,13,78,49,0,0 // movaps 0x314e(%rip),%xmm9 # 4010 <_sk_callback_sse2+0x2e9> + .byte 68,15,40,13,222,48,0,0 // movaps 0x30de(%rip),%xmm9 # 3fa0 <_sk_callback_sse2+0x2f3> .byte 69,15,40,249 // movaps %xmm9,%xmm15 .byte 69,15,93,253 // minps %xmm13,%xmm15 - .byte 68,15,40,45,78,49,0,0 // movaps 0x314e(%rip),%xmm13 # 4020 <_sk_callback_sse2+0x2f9> + .byte 68,15,40,45,222,48,0,0 // movaps 0x30de(%rip),%xmm13 # 3fb0 <_sk_callback_sse2+0x303> .byte 65,15,194,197,1 // cmpltps %xmm13,%xmm0 .byte 68,15,84,240 // andps %xmm0,%xmm14 .byte 65,15,85,199 // andnps %xmm15,%xmm0 @@ -24227,7 +24110,7 @@ _sk_rgb_to_hsl_sse2: .byte 68,15,93,218 // minps %xmm2,%xmm11 .byte 65,15,40,202 // movaps %xmm10,%xmm1 .byte 65,15,92,203 // subps %xmm11,%xmm1 - .byte 68,15,40,45,167,48,0,0 // movaps 0x30a7(%rip),%xmm13 # 4030 <_sk_callback_sse2+0x309> + .byte 68,15,40,45,55,48,0,0 // movaps 0x3037(%rip),%xmm13 # 3fc0 <_sk_callback_sse2+0x313> .byte 68,15,94,233 // divps %xmm1,%xmm13 .byte 65,15,40,194 // movaps %xmm10,%xmm0 .byte 65,15,194,192,0 // cmpeqps %xmm8,%xmm0 @@ -24236,30 +24119,30 @@ _sk_rgb_to_hsl_sse2: .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,40,241 // movaps %xmm9,%xmm14 .byte 68,15,194,242,1 // cmpltps %xmm2,%xmm14 - .byte 68,15,84,53,141,48,0,0 // andps 0x308d(%rip),%xmm14 # 4040 <_sk_callback_sse2+0x319> + .byte 68,15,84,53,29,48,0,0 // andps 0x301d(%rip),%xmm14 # 3fd0 <_sk_callback_sse2+0x323> .byte 69,15,88,244 // addps %xmm12,%xmm14 .byte 69,15,40,250 // movaps %xmm10,%xmm15 .byte 69,15,194,249,0 // cmpeqps %xmm9,%xmm15 .byte 65,15,92,208 // subps %xmm8,%xmm2 .byte 65,15,89,213 // mulps %xmm13,%xmm2 - .byte 68,15,40,37,128,48,0,0 // movaps 0x3080(%rip),%xmm12 # 4050 <_sk_callback_sse2+0x329> + .byte 68,15,40,37,16,48,0,0 // movaps 0x3010(%rip),%xmm12 # 3fe0 <_sk_callback_sse2+0x333> .byte 65,15,88,212 // addps %xmm12,%xmm2 .byte 69,15,92,193 // subps %xmm9,%xmm8 .byte 69,15,89,197 // mulps %xmm13,%xmm8 - .byte 68,15,88,5,124,48,0,0 // addps 0x307c(%rip),%xmm8 # 4060 <_sk_callback_sse2+0x339> + .byte 68,15,88,5,12,48,0,0 // addps 0x300c(%rip),%xmm8 # 3ff0 <_sk_callback_sse2+0x343> .byte 65,15,84,215 // andps %xmm15,%xmm2 .byte 69,15,85,248 // andnps %xmm8,%xmm15 .byte 68,15,86,250 // orps %xmm2,%xmm15 .byte 68,15,84,240 // andps %xmm0,%xmm14 .byte 65,15,85,199 // andnps %xmm15,%xmm0 .byte 65,15,86,198 // orps %xmm14,%xmm0 - .byte 15,89,5,109,48,0,0 // mulps 0x306d(%rip),%xmm0 # 4070 <_sk_callback_sse2+0x349> + .byte 15,89,5,253,47,0,0 // mulps 0x2ffd(%rip),%xmm0 # 4000 <_sk_callback_sse2+0x353> .byte 69,15,40,194 // movaps %xmm10,%xmm8 .byte 69,15,194,195,4 // cmpneqps %xmm11,%xmm8 .byte 65,15,84,192 // andps %xmm8,%xmm0 .byte 69,15,92,226 // subps %xmm10,%xmm12 .byte 69,15,88,211 // addps %xmm11,%xmm10 - .byte 68,15,40,13,96,48,0,0 // movaps 0x3060(%rip),%xmm9 # 4080 <_sk_callback_sse2+0x359> + .byte 68,15,40,13,240,47,0,0 // movaps 0x2ff0(%rip),%xmm9 # 4010 <_sk_callback_sse2+0x363> .byte 65,15,40,210 // movaps %xmm10,%xmm2 .byte 65,15,89,209 // mulps %xmm9,%xmm2 .byte 68,15,194,202,1 // cmpltps %xmm2,%xmm9 @@ -24276,184 +24159,151 @@ HIDDEN _sk_hsl_to_rgb_sse2 .globl _sk_hsl_to_rgb_sse2 FUNCTION(_sk_hsl_to_rgb_sse2) _sk_hsl_to_rgb_sse2: - .byte 72,131,236,40 // sub $0x28,%rsp - .byte 15,41,124,36,16 // movaps %xmm7,0x10(%rsp) - .byte 15,41,52,36 // movaps %xmm6,(%rsp) - .byte 15,41,108,36,240 // movaps %xmm5,-0x10(%rsp) - .byte 15,41,100,36,224 // movaps %xmm4,-0x20(%rsp) - .byte 15,41,92,36,208 // movaps %xmm3,-0x30(%rsp) - .byte 68,15,40,226 // movaps %xmm2,%xmm12 - .byte 15,40,240 // movaps %xmm0,%xmm6 + .byte 15,41,124,36,232 // movaps %xmm7,-0x18(%rsp) + .byte 15,41,116,36,216 // movaps %xmm6,-0x28(%rsp) + .byte 15,41,108,36,200 // movaps %xmm5,-0x38(%rsp) + .byte 15,41,100,36,184 // movaps %xmm4,-0x48(%rsp) + .byte 15,41,92,36,168 // movaps %xmm3,-0x58(%rsp) + .byte 68,15,40,210 // movaps %xmm2,%xmm10 + .byte 15,40,224 // movaps %xmm0,%xmm4 .byte 184,0,0,0,63 // mov $0x3f000000,%eax - .byte 102,15,110,192 // movd %eax,%xmm0 - .byte 15,198,192,0 // shufps $0x0,%xmm0,%xmm0 - .byte 69,15,40,196 // movaps %xmm12,%xmm8 - .byte 68,15,194,192,1 // cmpltps %xmm0,%xmm8 - .byte 68,15,40,208 // movaps %xmm0,%xmm10 - .byte 68,15,41,84,36,176 // movaps %xmm10,-0x50(%rsp) - .byte 15,40,61,253,47,0,0 // movaps 0x2ffd(%rip),%xmm7 # 4090 <_sk_callback_sse2+0x369> - .byte 15,40,193 // movaps %xmm1,%xmm0 - .byte 15,40,225 // movaps %xmm1,%xmm4 - .byte 15,87,210 // xorps %xmm2,%xmm2 - .byte 15,194,209,0 // cmpeqps %xmm1,%xmm2 - .byte 15,41,84,36,160 // movaps %xmm2,-0x60(%rsp) - .byte 15,88,207 // addps %xmm7,%xmm1 - .byte 65,15,89,204 // mulps %xmm12,%xmm1 - .byte 65,15,88,196 // addps %xmm12,%xmm0 - .byte 65,15,89,228 // mulps %xmm12,%xmm4 - .byte 15,92,196 // subps %xmm4,%xmm0 - .byte 65,15,84,200 // andps %xmm8,%xmm1 - .byte 68,15,85,192 // andnps %xmm0,%xmm8 - .byte 68,15,86,193 // orps %xmm1,%xmm8 - .byte 15,40,13,214,47,0,0 // movaps 0x2fd6(%rip),%xmm1 # 40a0 <_sk_callback_sse2+0x379> - .byte 15,88,206 // addps %xmm6,%xmm1 - .byte 184,0,0,0,0 // mov $0x0,%eax - .byte 185,0,0,128,63 // mov $0x3f800000,%ecx - .byte 102,68,15,110,241 // movd %ecx,%xmm14 - .byte 69,15,198,246,0 // shufps $0x0,%xmm14,%xmm14 - .byte 65,15,40,198 // movaps %xmm14,%xmm0 - .byte 15,194,193,1 // cmpltps %xmm1,%xmm0 - .byte 68,15,40,61,191,47,0,0 // movaps 0x2fbf(%rip),%xmm15 # 40b0 <_sk_callback_sse2+0x389> - .byte 15,40,225 // movaps %xmm1,%xmm4 - .byte 65,15,88,231 // addps %xmm15,%xmm4 - .byte 15,84,224 // andps %xmm0,%xmm4 - .byte 15,85,193 // andnps %xmm1,%xmm0 - .byte 15,86,196 // orps %xmm4,%xmm0 - .byte 102,15,110,208 // movd %eax,%xmm2 - .byte 15,198,210,0 // shufps $0x0,%xmm2,%xmm2 - .byte 15,41,84,36,144 // movaps %xmm2,-0x70(%rsp) - .byte 15,40,225 // movaps %xmm1,%xmm4 - .byte 15,194,202,1 // cmpltps %xmm2,%xmm1 - .byte 15,88,231 // addps %xmm7,%xmm4 - .byte 15,84,225 // andps %xmm1,%xmm4 - .byte 15,85,200 // andnps %xmm0,%xmm1 - .byte 15,86,204 // orps %xmm4,%xmm1 - .byte 69,15,40,236 // movaps %xmm12,%xmm13 - .byte 69,15,88,237 // addps %xmm13,%xmm13 - .byte 69,15,92,232 // subps %xmm8,%xmm13 + .byte 102,68,15,110,248 // movd %eax,%xmm15 + .byte 69,15,198,255,0 // shufps $0x0,%xmm15,%xmm15 + .byte 69,15,40,202 // movaps %xmm10,%xmm9 + .byte 69,15,194,207,1 // cmpltps %xmm15,%xmm9 + .byte 15,40,209 // movaps %xmm1,%xmm2 + .byte 69,15,87,219 // xorps %xmm11,%xmm11 + .byte 68,15,194,217,0 // cmpeqps %xmm1,%xmm11 + .byte 65,15,89,202 // mulps %xmm10,%xmm1 + .byte 15,92,209 // subps %xmm1,%xmm2 + .byte 65,15,84,201 // andps %xmm9,%xmm1 + .byte 68,15,85,202 // andnps %xmm2,%xmm9 + .byte 68,15,86,201 // orps %xmm1,%xmm9 + .byte 69,15,88,202 // addps %xmm10,%xmm9 + .byte 69,15,40,226 // movaps %xmm10,%xmm12 + .byte 69,15,88,228 // addps %xmm12,%xmm12 + .byte 69,15,92,225 // subps %xmm9,%xmm12 + .byte 15,40,21,105,47,0,0 // movaps 0x2f69(%rip),%xmm2 # 4020 <_sk_callback_sse2+0x373> + .byte 15,88,212 // addps %xmm4,%xmm2 + .byte 243,15,91,202 // cvttps2dq %xmm2,%xmm1 + .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 + .byte 15,40,218 // movaps %xmm2,%xmm3 + .byte 15,194,217,1 // cmpltps %xmm1,%xmm3 + .byte 15,84,29,97,47,0,0 // andps 0x2f61(%rip),%xmm3 # 4030 <_sk_callback_sse2+0x383> + .byte 15,92,203 // subps %xmm3,%xmm1 + .byte 15,92,209 // subps %xmm1,%xmm2 .byte 184,171,170,42,62 // mov $0x3e2aaaab,%eax - .byte 69,15,40,200 // movaps %xmm8,%xmm9 - .byte 69,15,92,205 // subps %xmm13,%xmm9 - .byte 68,15,89,13,126,47,0,0 // mulps 0x2f7e(%rip),%xmm9 # 40c0 <_sk_callback_sse2+0x399> + .byte 65,15,40,249 // movaps %xmm9,%xmm7 + .byte 65,15,92,252 // subps %xmm12,%xmm7 + .byte 68,15,40,53,86,47,0,0 // movaps 0x2f56(%rip),%xmm14 # 4040 <_sk_callback_sse2+0x393> + .byte 68,15,40,194 // movaps %xmm2,%xmm8 + .byte 69,15,89,198 // mulps %xmm14,%xmm8 .byte 185,171,170,42,63 // mov $0x3f2aaaab,%ecx .byte 102,15,110,217 // movd %ecx,%xmm3 .byte 15,198,219,0 // shufps $0x0,%xmm3,%xmm3 - .byte 15,41,92,36,128 // movaps %xmm3,-0x80(%rsp) - .byte 15,40,45,117,47,0,0 // movaps 0x2f75(%rip),%xmm5 # 40d0 <_sk_callback_sse2+0x3a9> - .byte 15,40,229 // movaps %xmm5,%xmm4 - .byte 15,92,225 // subps %xmm1,%xmm4 - .byte 15,40,209 // movaps %xmm1,%xmm2 - .byte 68,15,40,217 // movaps %xmm1,%xmm11 - .byte 15,40,193 // movaps %xmm1,%xmm0 - .byte 15,194,203,1 // cmpltps %xmm3,%xmm1 - .byte 65,15,89,225 // mulps %xmm9,%xmm4 - .byte 65,15,88,229 // addps %xmm13,%xmm4 - .byte 15,84,225 // andps %xmm1,%xmm4 - .byte 65,15,85,205 // andnps %xmm13,%xmm1 - .byte 15,86,204 // orps %xmm4,%xmm1 - .byte 65,15,194,194,1 // cmpltps %xmm10,%xmm0 - .byte 65,15,40,224 // movaps %xmm8,%xmm4 - .byte 15,84,224 // andps %xmm0,%xmm4 - .byte 15,85,193 // andnps %xmm1,%xmm0 - .byte 15,86,196 // orps %xmm4,%xmm0 - .byte 102,68,15,110,208 // movd %eax,%xmm10 - .byte 69,15,198,210,0 // shufps $0x0,%xmm10,%xmm10 - .byte 65,15,194,210,1 // cmpltps %xmm10,%xmm2 - .byte 69,15,89,217 // mulps %xmm9,%xmm11 - .byte 69,15,88,221 // addps %xmm13,%xmm11 - .byte 68,15,84,218 // andps %xmm2,%xmm11 - .byte 15,85,208 // andnps %xmm0,%xmm2 - .byte 65,15,86,211 // orps %xmm11,%xmm2 - .byte 15,40,68,36,160 // movaps -0x60(%rsp),%xmm0 + .byte 15,41,92,36,136 // movaps %xmm3,-0x78(%rsp) + .byte 15,40,202 // movaps %xmm2,%xmm1 + .byte 15,40,194 // movaps %xmm2,%xmm0 + .byte 15,194,211,1 // cmpltps %xmm3,%xmm2 + .byte 15,40,53,59,47,0,0 // movaps 0x2f3b(%rip),%xmm6 # 4050 <_sk_callback_sse2+0x3a3> + .byte 15,40,238 // movaps %xmm6,%xmm5 + .byte 65,15,92,232 // subps %xmm8,%xmm5 + .byte 15,89,239 // mulps %xmm7,%xmm5 + .byte 65,15,88,236 // addps %xmm12,%xmm5 + .byte 15,84,234 // andps %xmm2,%xmm5 + .byte 65,15,85,212 // andnps %xmm12,%xmm2 + .byte 15,86,213 // orps %xmm5,%xmm2 + .byte 65,15,194,199,1 // cmpltps %xmm15,%xmm0 + .byte 68,15,41,124,36,152 // movaps %xmm15,-0x68(%rsp) + .byte 65,15,40,233 // movaps %xmm9,%xmm5 + .byte 15,84,232 // andps %xmm0,%xmm5 .byte 15,85,194 // andnps %xmm2,%xmm0 - .byte 15,41,68,36,192 // movaps %xmm0,-0x40(%rsp) - .byte 65,15,40,198 // movaps %xmm14,%xmm0 - .byte 15,194,198,1 // cmpltps %xmm6,%xmm0 - .byte 15,40,206 // movaps %xmm6,%xmm1 - .byte 65,15,88,207 // addps %xmm15,%xmm1 - .byte 15,84,200 // andps %xmm0,%xmm1 - .byte 15,85,198 // andnps %xmm6,%xmm0 - .byte 15,86,193 // orps %xmm1,%xmm0 - .byte 15,40,206 // movaps %xmm6,%xmm1 - .byte 15,194,76,36,144,1 // cmpltps -0x70(%rsp),%xmm1 - .byte 15,40,214 // movaps %xmm6,%xmm2 - .byte 15,88,215 // addps %xmm7,%xmm2 - .byte 15,84,209 // andps %xmm1,%xmm2 + .byte 15,86,197 // orps %xmm5,%xmm0 + .byte 102,15,110,232 // movd %eax,%xmm5 + .byte 15,198,237,0 // shufps $0x0,%xmm5,%xmm5 + .byte 15,194,205,1 // cmpltps %xmm5,%xmm1 + .byte 68,15,89,199 // mulps %xmm7,%xmm8 + .byte 69,15,88,196 // addps %xmm12,%xmm8 + .byte 68,15,84,193 // andps %xmm1,%xmm8 .byte 15,85,200 // andnps %xmm0,%xmm1 - .byte 15,86,202 // orps %xmm2,%xmm1 - .byte 15,40,197 // movaps %xmm5,%xmm0 + .byte 65,15,86,200 // orps %xmm8,%xmm1 + .byte 69,15,40,195 // movaps %xmm11,%xmm8 + .byte 68,15,85,193 // andnps %xmm1,%xmm8 + .byte 243,15,91,196 // cvttps2dq %xmm4,%xmm0 + .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 + .byte 15,40,204 // movaps %xmm4,%xmm1 + .byte 15,194,200,1 // cmpltps %xmm0,%xmm1 + .byte 15,84,13,175,46,0,0 // andps 0x2eaf(%rip),%xmm1 # 4030 <_sk_callback_sse2+0x383> .byte 15,92,193 // subps %xmm1,%xmm0 - .byte 15,40,217 // movaps %xmm1,%xmm3 - .byte 15,40,225 // movaps %xmm1,%xmm4 - .byte 15,40,209 // movaps %xmm1,%xmm2 - .byte 15,194,76,36,128,1 // cmpltps -0x80(%rsp),%xmm1 - .byte 65,15,89,193 // mulps %xmm9,%xmm0 - .byte 65,15,88,197 // addps %xmm13,%xmm0 - .byte 15,84,193 // andps %xmm1,%xmm0 - .byte 65,15,85,205 // andnps %xmm13,%xmm1 - .byte 15,86,200 // orps %xmm0,%xmm1 - .byte 68,15,40,92,36,176 // movaps -0x50(%rsp),%xmm11 - .byte 65,15,194,211,1 // cmpltps %xmm11,%xmm2 - .byte 65,15,40,192 // movaps %xmm8,%xmm0 - .byte 15,84,194 // andps %xmm2,%xmm0 - .byte 15,85,209 // andnps %xmm1,%xmm2 - .byte 15,86,208 // orps %xmm0,%xmm2 - .byte 65,15,194,218,1 // cmpltps %xmm10,%xmm3 - .byte 65,15,89,225 // mulps %xmm9,%xmm4 - .byte 65,15,88,229 // addps %xmm13,%xmm4 - .byte 15,84,227 // andps %xmm3,%xmm4 - .byte 15,85,218 // andnps %xmm2,%xmm3 - .byte 15,86,220 // orps %xmm4,%xmm3 - .byte 15,40,100,36,160 // movaps -0x60(%rsp),%xmm4 .byte 15,40,204 // movaps %xmm4,%xmm1 - .byte 15,85,203 // andnps %xmm3,%xmm1 - .byte 15,88,53,135,46,0,0 // addps 0x2e87(%rip),%xmm6 # 40e0 <_sk_callback_sse2+0x3b9> - .byte 15,88,254 // addps %xmm6,%xmm7 - .byte 68,15,194,246,1 // cmpltps %xmm6,%xmm14 - .byte 68,15,88,254 // addps %xmm6,%xmm15 - .byte 69,15,84,254 // andps %xmm14,%xmm15 - .byte 68,15,85,246 // andnps %xmm6,%xmm14 - .byte 15,194,116,36,144,1 // cmpltps -0x70(%rsp),%xmm6 - .byte 69,15,86,247 // orps %xmm15,%xmm14 - .byte 15,84,254 // andps %xmm6,%xmm7 - .byte 65,15,85,246 // andnps %xmm14,%xmm6 - .byte 15,86,247 // orps %xmm7,%xmm6 - .byte 15,40,254 // movaps %xmm6,%xmm7 - .byte 65,15,194,250,1 // cmpltps %xmm10,%xmm7 - .byte 15,40,198 // movaps %xmm6,%xmm0 - .byte 65,15,194,195,1 // cmpltps %xmm11,%xmm0 - .byte 15,92,238 // subps %xmm6,%xmm5 + .byte 15,92,200 // subps %xmm0,%xmm1 + .byte 15,40,193 // movaps %xmm1,%xmm0 + .byte 65,15,89,198 // mulps %xmm14,%xmm0 + .byte 68,15,40,239 // movaps %xmm7,%xmm13 + .byte 68,15,89,232 // mulps %xmm0,%xmm13 .byte 15,40,222 // movaps %xmm6,%xmm3 - .byte 15,194,116,36,128,1 // cmpltps -0x80(%rsp),%xmm6 - .byte 65,15,89,217 // mulps %xmm9,%xmm3 - .byte 65,15,89,233 // mulps %xmm9,%xmm5 - .byte 65,15,88,221 // addps %xmm13,%xmm3 - .byte 65,15,88,237 // addps %xmm13,%xmm5 - .byte 15,84,238 // andps %xmm6,%xmm5 - .byte 65,15,85,245 // andnps %xmm13,%xmm6 - .byte 15,86,245 // orps %xmm5,%xmm6 - .byte 68,15,84,192 // andps %xmm0,%xmm8 - .byte 15,85,198 // andnps %xmm6,%xmm0 - .byte 65,15,86,192 // orps %xmm8,%xmm0 - .byte 15,84,223 // andps %xmm7,%xmm3 - .byte 15,85,248 // andnps %xmm0,%xmm7 - .byte 15,86,251 // orps %xmm3,%xmm7 + .byte 15,92,216 // subps %xmm0,%xmm3 + .byte 15,89,223 // mulps %xmm7,%xmm3 + .byte 15,40,209 // movaps %xmm1,%xmm2 + .byte 15,40,193 // movaps %xmm1,%xmm0 + .byte 15,194,76,36,136,1 // cmpltps -0x78(%rsp),%xmm1 + .byte 65,15,88,220 // addps %xmm12,%xmm3 + .byte 15,84,217 // andps %xmm1,%xmm3 + .byte 65,15,85,204 // andnps %xmm12,%xmm1 + .byte 15,86,203 // orps %xmm3,%xmm1 + .byte 65,15,194,199,1 // cmpltps %xmm15,%xmm0 + .byte 65,15,40,217 // movaps %xmm9,%xmm3 + .byte 15,84,216 // andps %xmm0,%xmm3 + .byte 15,85,193 // andnps %xmm1,%xmm0 + .byte 15,86,195 // orps %xmm3,%xmm0 + .byte 15,194,213,1 // cmpltps %xmm5,%xmm2 + .byte 69,15,88,236 // addps %xmm12,%xmm13 + .byte 68,15,84,234 // andps %xmm2,%xmm13 + .byte 15,85,208 // andnps %xmm0,%xmm2 + .byte 65,15,86,213 // orps %xmm13,%xmm2 + .byte 65,15,40,203 // movaps %xmm11,%xmm1 + .byte 15,85,202 // andnps %xmm2,%xmm1 + .byte 15,88,37,113,46,0,0 // addps 0x2e71(%rip),%xmm4 # 4060 <_sk_callback_sse2+0x3b3> + .byte 243,15,91,196 // cvttps2dq %xmm4,%xmm0 + .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 + .byte 15,40,212 // movaps %xmm4,%xmm2 + .byte 15,194,208,1 // cmpltps %xmm0,%xmm2 + .byte 15,84,21,44,46,0,0 // andps 0x2e2c(%rip),%xmm2 # 4030 <_sk_callback_sse2+0x383> + .byte 15,92,194 // subps %xmm2,%xmm0 + .byte 15,92,224 // subps %xmm0,%xmm4 + .byte 68,15,40,252 // movaps %xmm4,%xmm15 + .byte 68,15,194,253,1 // cmpltps %xmm5,%xmm15 + .byte 68,15,89,244 // mulps %xmm4,%xmm14 + .byte 65,15,92,246 // subps %xmm14,%xmm6 + .byte 15,89,247 // mulps %xmm7,%xmm6 + .byte 65,15,89,254 // mulps %xmm14,%xmm7 .byte 15,40,196 // movaps %xmm4,%xmm0 - .byte 68,15,84,224 // andps %xmm0,%xmm12 - .byte 15,85,199 // andnps %xmm7,%xmm0 - .byte 15,40,84,36,192 // movaps -0x40(%rsp),%xmm2 - .byte 65,15,86,212 // orps %xmm12,%xmm2 - .byte 65,15,86,204 // orps %xmm12,%xmm1 - .byte 68,15,86,224 // orps %xmm0,%xmm12 + .byte 15,194,68,36,152,1 // cmpltps -0x68(%rsp),%xmm0 + .byte 15,194,100,36,136,1 // cmpltps -0x78(%rsp),%xmm4 + .byte 65,15,88,252 // addps %xmm12,%xmm7 + .byte 65,15,88,244 // addps %xmm12,%xmm6 + .byte 15,84,244 // andps %xmm4,%xmm6 + .byte 65,15,85,228 // andnps %xmm12,%xmm4 + .byte 15,86,230 // orps %xmm6,%xmm4 + .byte 68,15,84,200 // andps %xmm0,%xmm9 + .byte 15,85,196 // andnps %xmm4,%xmm0 + .byte 65,15,86,193 // orps %xmm9,%xmm0 + .byte 65,15,84,255 // andps %xmm15,%xmm7 + .byte 68,15,85,248 // andnps %xmm0,%xmm15 + .byte 68,15,86,255 // orps %xmm7,%xmm15 + .byte 69,15,84,211 // andps %xmm11,%xmm10 + .byte 69,15,85,223 // andnps %xmm15,%xmm11 + .byte 69,15,86,194 // orps %xmm10,%xmm8 + .byte 65,15,86,202 // orps %xmm10,%xmm1 + .byte 69,15,86,211 // orps %xmm11,%xmm10 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,194 // movaps %xmm2,%xmm0 - .byte 65,15,40,212 // movaps %xmm12,%xmm2 - .byte 15,40,92,36,208 // movaps -0x30(%rsp),%xmm3 - .byte 15,40,100,36,224 // movaps -0x20(%rsp),%xmm4 - .byte 15,40,108,36,240 // movaps -0x10(%rsp),%xmm5 - .byte 15,40,52,36 // movaps (%rsp),%xmm6 - .byte 15,40,124,36,16 // movaps 0x10(%rsp),%xmm7 - .byte 72,131,196,40 // add $0x28,%rsp + .byte 65,15,40,192 // movaps %xmm8,%xmm0 + .byte 65,15,40,210 // movaps %xmm10,%xmm2 + .byte 15,40,92,36,168 // movaps -0x58(%rsp),%xmm3 + .byte 15,40,100,36,184 // movaps -0x48(%rsp),%xmm4 + .byte 15,40,108,36,200 // movaps -0x38(%rsp),%xmm5 + .byte 15,40,116,36,216 // movaps -0x28(%rsp),%xmm6 + .byte 15,40,124,36,232 // movaps -0x18(%rsp),%xmm7 .byte 255,224 // jmpq *%rax HIDDEN _sk_scale_1_float_sse2 @@ -24481,7 +24331,7 @@ _sk_scale_u8_sse2: .byte 102,69,15,96,193 // punpcklbw %xmm9,%xmm8 .byte 102,69,15,97,193 // punpcklwd %xmm9,%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,157,45,0,0 // mulps 0x2d9d(%rip),%xmm8 # 40f0 <_sk_callback_sse2+0x3c9> + .byte 68,15,89,5,151,45,0,0 // mulps 0x2d97(%rip),%xmm8 # 4070 <_sk_callback_sse2+0x3c3> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 65,15,89,208 // mulps %xmm8,%xmm2 @@ -24522,7 +24372,7 @@ _sk_lerp_u8_sse2: .byte 102,69,15,96,193 // punpcklbw %xmm9,%xmm8 .byte 102,69,15,97,193 // punpcklwd %xmm9,%xmm8 .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,59,45,0,0 // mulps 0x2d3b(%rip),%xmm8 # 4100 <_sk_callback_sse2+0x3d9> + .byte 68,15,89,5,53,45,0,0 // mulps 0x2d35(%rip),%xmm8 # 4080 <_sk_callback_sse2+0x3d3> .byte 15,92,196 // subps %xmm4,%xmm0 .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -24547,17 +24397,17 @@ _sk_lerp_565_sse2: .byte 243,68,15,126,4,120 // movq (%rax,%rdi,2),%xmm8 .byte 102,15,239,219 // pxor %xmm3,%xmm3 .byte 102,68,15,97,195 // punpcklwd %xmm3,%xmm8 - .byte 102,15,111,29,3,45,0,0 // movdqa 0x2d03(%rip),%xmm3 # 4110 <_sk_callback_sse2+0x3e9> + .byte 102,15,111,29,253,44,0,0 // movdqa 0x2cfd(%rip),%xmm3 # 4090 <_sk_callback_sse2+0x3e3> .byte 102,65,15,219,216 // pand %xmm8,%xmm3 .byte 68,15,91,203 // cvtdq2ps %xmm3,%xmm9 - .byte 68,15,89,13,2,45,0,0 // mulps 0x2d02(%rip),%xmm9 # 4120 <_sk_callback_sse2+0x3f9> - .byte 102,15,111,29,10,45,0,0 // movdqa 0x2d0a(%rip),%xmm3 # 4130 <_sk_callback_sse2+0x409> + .byte 68,15,89,13,252,44,0,0 // mulps 0x2cfc(%rip),%xmm9 # 40a0 <_sk_callback_sse2+0x3f3> + .byte 102,15,111,29,4,45,0,0 // movdqa 0x2d04(%rip),%xmm3 # 40b0 <_sk_callback_sse2+0x403> .byte 102,65,15,219,216 // pand %xmm8,%xmm3 .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,11,45,0,0 // mulps 0x2d0b(%rip),%xmm3 # 4140 <_sk_callback_sse2+0x419> - .byte 102,68,15,219,5,18,45,0,0 // pand 0x2d12(%rip),%xmm8 # 4150 <_sk_callback_sse2+0x429> + .byte 15,89,29,5,45,0,0 // mulps 0x2d05(%rip),%xmm3 # 40c0 <_sk_callback_sse2+0x413> + .byte 102,68,15,219,5,12,45,0,0 // pand 0x2d0c(%rip),%xmm8 # 40d0 <_sk_callback_sse2+0x423> .byte 69,15,91,192 // cvtdq2ps %xmm8,%xmm8 - .byte 68,15,89,5,22,45,0,0 // mulps 0x2d16(%rip),%xmm8 # 4160 <_sk_callback_sse2+0x439> + .byte 68,15,89,5,16,45,0,0 // mulps 0x2d10(%rip),%xmm8 # 40e0 <_sk_callback_sse2+0x433> .byte 15,92,196 // subps %xmm4,%xmm0 .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 15,88,196 // addps %xmm4,%xmm0 @@ -24568,7 +24418,7 @@ _sk_lerp_565_sse2: .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 15,88,214 // addps %xmm6,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,0,45,0,0 // movaps 0x2d00(%rip),%xmm3 # 4170 <_sk_callback_sse2+0x449> + .byte 15,40,29,250,44,0,0 // movaps 0x2cfa(%rip),%xmm3 # 40f0 <_sk_callback_sse2+0x443> .byte 255,224 // jmpq *%rax HIDDEN _sk_load_tables_sse2 @@ -24579,7 +24429,7 @@ _sk_load_tables_sse2: .byte 76,139,0 // mov (%rax),%r8 .byte 76,139,72,8 // mov 0x8(%rax),%r9 .byte 243,69,15,111,12,184 // movdqu (%r8,%rdi,4),%xmm9 - .byte 102,68,15,111,5,246,44,0,0 // movdqa 0x2cf6(%rip),%xmm8 # 4180 <_sk_callback_sse2+0x459> + .byte 102,68,15,111,5,240,44,0,0 // movdqa 0x2cf0(%rip),%xmm8 # 4100 <_sk_callback_sse2+0x453> .byte 102,65,15,111,193 // movdqa %xmm9,%xmm0 .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,15,112,200,78 // pshufd $0x4e,%xmm0,%xmm1 @@ -24634,7 +24484,7 @@ _sk_load_tables_sse2: .byte 65,15,20,208 // unpcklps %xmm8,%xmm2 .byte 102,65,15,114,209,24 // psrld $0x18,%xmm9 .byte 65,15,91,217 // cvtdq2ps %xmm9,%xmm3 - .byte 15,89,29,3,44,0,0 // mulps 0x2c03(%rip),%xmm3 # 4190 <_sk_callback_sse2+0x469> + .byte 15,89,29,253,43,0,0 // mulps 0x2bfd(%rip),%xmm3 # 4110 <_sk_callback_sse2+0x463> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -24653,7 +24503,7 @@ _sk_load_tables_u16_be_sse2: .byte 102,65,15,111,201 // movdqa %xmm9,%xmm1 .byte 102,15,97,200 // punpcklwd %xmm0,%xmm1 .byte 102,68,15,105,200 // punpckhwd %xmm0,%xmm9 - .byte 102,68,15,111,21,214,43,0,0 // movdqa 0x2bd6(%rip),%xmm10 # 41a0 <_sk_callback_sse2+0x479> + .byte 102,68,15,111,21,208,43,0,0 // movdqa 0x2bd0(%rip),%xmm10 # 4120 <_sk_callback_sse2+0x473> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,194 // pand %xmm10,%xmm0 .byte 102,69,15,239,192 // pxor %xmm8,%xmm8 @@ -24714,7 +24564,7 @@ _sk_load_tables_u16_be_sse2: .byte 102,65,15,235,217 // por %xmm9,%xmm3 .byte 102,65,15,97,216 // punpcklwd %xmm8,%xmm3 .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,197,42,0,0 // mulps 0x2ac5(%rip),%xmm3 # 41b0 <_sk_callback_sse2+0x489> + .byte 15,89,29,191,42,0,0 // mulps 0x2abf(%rip),%xmm3 # 4130 <_sk_callback_sse2+0x483> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -24736,7 +24586,7 @@ _sk_load_tables_rgb_u16_be_sse2: .byte 102,68,15,97,208 // punpcklwd %xmm0,%xmm10 .byte 102,65,15,111,195 // movdqa %xmm11,%xmm0 .byte 102,65,15,97,194 // punpcklwd %xmm10,%xmm0 - .byte 102,68,15,111,5,133,42,0,0 // movdqa 0x2a85(%rip),%xmm8 # 41c0 <_sk_callback_sse2+0x499> + .byte 102,68,15,111,5,127,42,0,0 // movdqa 0x2a7f(%rip),%xmm8 # 4140 <_sk_callback_sse2+0x493> .byte 102,15,112,200,78 // pshufd $0x4e,%xmm0,%xmm1 .byte 102,65,15,219,192 // pand %xmm8,%xmm0 .byte 102,69,15,239,201 // pxor %xmm9,%xmm9 @@ -24791,7 +24641,7 @@ _sk_load_tables_rgb_u16_be_sse2: .byte 15,20,211 // unpcklps %xmm3,%xmm2 .byte 65,15,20,208 // unpcklps %xmm8,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,148,41,0,0 // movaps 0x2994(%rip),%xmm3 # 41d0 <_sk_callback_sse2+0x4a9> + .byte 15,40,29,142,41,0,0 // movaps 0x298e(%rip),%xmm3 # 4150 <_sk_callback_sse2+0x4a3> .byte 255,224 // jmpq *%rax HIDDEN _sk_byte_tables_sse2 @@ -24801,7 +24651,7 @@ _sk_byte_tables_sse2: .byte 65,86 // push %r14 .byte 83 // push %rbx .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,149,41,0,0 // movaps 0x2995(%rip),%xmm8 # 41e0 <_sk_callback_sse2+0x4b9> + .byte 68,15,40,5,143,41,0,0 // movaps 0x298f(%rip),%xmm8 # 4160 <_sk_callback_sse2+0x4b3> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,91,192 // cvtps2dq %xmm0,%xmm0 .byte 102,72,15,126,193 // movq %xmm0,%rcx @@ -24828,7 +24678,7 @@ _sk_byte_tables_sse2: .byte 102,65,15,96,193 // punpcklbw %xmm9,%xmm0 .byte 102,65,15,97,193 // punpcklwd %xmm9,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,21,50,41,0,0 // movaps 0x2932(%rip),%xmm10 # 41f0 <_sk_callback_sse2+0x4c9> + .byte 68,15,40,21,44,41,0,0 // movaps 0x292c(%rip),%xmm10 # 4170 <_sk_callback_sse2+0x4c3> .byte 65,15,89,194 // mulps %xmm10,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,91,201 // cvtps2dq %xmm1,%xmm1 @@ -24944,7 +24794,7 @@ _sk_byte_tables_rgb_sse2: .byte 102,65,15,96,193 // punpcklbw %xmm9,%xmm0 .byte 102,65,15,97,193 // punpcklwd %xmm9,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,21,133,39,0,0 // movaps 0x2785(%rip),%xmm10 # 4200 <_sk_callback_sse2+0x4d9> + .byte 68,15,40,21,127,39,0,0 // movaps 0x277f(%rip),%xmm10 # 4180 <_sk_callback_sse2+0x4d3> .byte 65,15,89,194 // mulps %xmm10,%xmm0 .byte 65,15,89,200 // mulps %xmm8,%xmm1 .byte 102,15,91,201 // cvtps2dq %xmm1,%xmm1 @@ -25141,15 +24991,15 @@ _sk_parametric_r_sse2: .byte 69,15,88,209 // addps %xmm9,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,202 // cvtdq2ps %xmm10,%xmm9 - .byte 68,15,89,13,196,36,0,0 // mulps 0x24c4(%rip),%xmm9 # 4210 <_sk_callback_sse2+0x4e9> - .byte 68,15,84,21,204,36,0,0 // andps 0x24cc(%rip),%xmm10 # 4220 <_sk_callback_sse2+0x4f9> - .byte 68,15,86,21,212,36,0,0 // orps 0x24d4(%rip),%xmm10 # 4230 <_sk_callback_sse2+0x509> - .byte 68,15,88,13,220,36,0,0 // addps 0x24dc(%rip),%xmm9 # 4240 <_sk_callback_sse2+0x519> - .byte 68,15,40,37,228,36,0,0 // movaps 0x24e4(%rip),%xmm12 # 4250 <_sk_callback_sse2+0x529> + .byte 68,15,89,13,190,36,0,0 // mulps 0x24be(%rip),%xmm9 # 4190 <_sk_callback_sse2+0x4e3> + .byte 68,15,84,21,198,36,0,0 // andps 0x24c6(%rip),%xmm10 # 41a0 <_sk_callback_sse2+0x4f3> + .byte 68,15,86,21,206,36,0,0 // orps 0x24ce(%rip),%xmm10 # 41b0 <_sk_callback_sse2+0x503> + .byte 68,15,88,13,214,36,0,0 // addps 0x24d6(%rip),%xmm9 # 41c0 <_sk_callback_sse2+0x513> + .byte 68,15,40,37,222,36,0,0 // movaps 0x24de(%rip),%xmm12 # 41d0 <_sk_callback_sse2+0x523> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,88,21,228,36,0,0 // addps 0x24e4(%rip),%xmm10 # 4260 <_sk_callback_sse2+0x539> - .byte 68,15,40,37,236,36,0,0 // movaps 0x24ec(%rip),%xmm12 # 4270 <_sk_callback_sse2+0x549> + .byte 68,15,88,21,222,36,0,0 // addps 0x24de(%rip),%xmm10 # 41e0 <_sk_callback_sse2+0x533> + .byte 68,15,40,37,230,36,0,0 // movaps 0x24e6(%rip),%xmm12 # 41f0 <_sk_callback_sse2+0x543> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 @@ -25157,22 +25007,22 @@ _sk_parametric_r_sse2: .byte 69,15,91,226 // cvtdq2ps %xmm10,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,194,236,1 // cmpltps %xmm12,%xmm13 - .byte 68,15,40,21,214,36,0,0 // movaps 0x24d6(%rip),%xmm10 # 4280 <_sk_callback_sse2+0x559> + .byte 68,15,40,21,208,36,0,0 // movaps 0x24d0(%rip),%xmm10 # 4200 <_sk_callback_sse2+0x553> .byte 69,15,84,234 // andps %xmm10,%xmm13 .byte 69,15,87,219 // xorps %xmm11,%xmm11 .byte 69,15,92,229 // subps %xmm13,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,92,236 // subps %xmm12,%xmm13 - .byte 68,15,88,13,202,36,0,0 // addps 0x24ca(%rip),%xmm9 # 4290 <_sk_callback_sse2+0x569> - .byte 68,15,40,37,210,36,0,0 // movaps 0x24d2(%rip),%xmm12 # 42a0 <_sk_callback_sse2+0x579> + .byte 68,15,88,13,196,36,0,0 // addps 0x24c4(%rip),%xmm9 # 4210 <_sk_callback_sse2+0x563> + .byte 68,15,40,37,204,36,0,0 // movaps 0x24cc(%rip),%xmm12 # 4220 <_sk_callback_sse2+0x573> .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,40,37,210,36,0,0 // movaps 0x24d2(%rip),%xmm12 # 42b0 <_sk_callback_sse2+0x589> + .byte 68,15,40,37,204,36,0,0 // movaps 0x24cc(%rip),%xmm12 # 4230 <_sk_callback_sse2+0x583> .byte 69,15,92,229 // subps %xmm13,%xmm12 - .byte 68,15,40,45,214,36,0,0 // movaps 0x24d6(%rip),%xmm13 # 42c0 <_sk_callback_sse2+0x599> + .byte 68,15,40,45,208,36,0,0 // movaps 0x24d0(%rip),%xmm13 # 4240 <_sk_callback_sse2+0x593> .byte 69,15,94,236 // divps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,89,45,214,36,0,0 // mulps 0x24d6(%rip),%xmm13 # 42d0 <_sk_callback_sse2+0x5a9> + .byte 68,15,89,45,208,36,0,0 // mulps 0x24d0(%rip),%xmm13 # 4250 <_sk_callback_sse2+0x5a3> .byte 102,69,15,91,205 // cvtps2dq %xmm13,%xmm9 .byte 243,68,15,16,96,20 // movss 0x14(%rax),%xmm12 .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 @@ -25208,15 +25058,15 @@ _sk_parametric_g_sse2: .byte 69,15,88,209 // addps %xmm9,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,202 // cvtdq2ps %xmm10,%xmm9 - .byte 68,15,89,13,86,36,0,0 // mulps 0x2456(%rip),%xmm9 # 42e0 <_sk_callback_sse2+0x5b9> - .byte 68,15,84,21,94,36,0,0 // andps 0x245e(%rip),%xmm10 # 42f0 <_sk_callback_sse2+0x5c9> - .byte 68,15,86,21,102,36,0,0 // orps 0x2466(%rip),%xmm10 # 4300 <_sk_callback_sse2+0x5d9> - .byte 68,15,88,13,110,36,0,0 // addps 0x246e(%rip),%xmm9 # 4310 <_sk_callback_sse2+0x5e9> - .byte 68,15,40,37,118,36,0,0 // movaps 0x2476(%rip),%xmm12 # 4320 <_sk_callback_sse2+0x5f9> + .byte 68,15,89,13,80,36,0,0 // mulps 0x2450(%rip),%xmm9 # 4260 <_sk_callback_sse2+0x5b3> + .byte 68,15,84,21,88,36,0,0 // andps 0x2458(%rip),%xmm10 # 4270 <_sk_callback_sse2+0x5c3> + .byte 68,15,86,21,96,36,0,0 // orps 0x2460(%rip),%xmm10 # 4280 <_sk_callback_sse2+0x5d3> + .byte 68,15,88,13,104,36,0,0 // addps 0x2468(%rip),%xmm9 # 4290 <_sk_callback_sse2+0x5e3> + .byte 68,15,40,37,112,36,0,0 // movaps 0x2470(%rip),%xmm12 # 42a0 <_sk_callback_sse2+0x5f3> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,88,21,118,36,0,0 // addps 0x2476(%rip),%xmm10 # 4330 <_sk_callback_sse2+0x609> - .byte 68,15,40,37,126,36,0,0 // movaps 0x247e(%rip),%xmm12 # 4340 <_sk_callback_sse2+0x619> + .byte 68,15,88,21,112,36,0,0 // addps 0x2470(%rip),%xmm10 # 42b0 <_sk_callback_sse2+0x603> + .byte 68,15,40,37,120,36,0,0 // movaps 0x2478(%rip),%xmm12 # 42c0 <_sk_callback_sse2+0x613> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 @@ -25224,22 +25074,22 @@ _sk_parametric_g_sse2: .byte 69,15,91,226 // cvtdq2ps %xmm10,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,194,236,1 // cmpltps %xmm12,%xmm13 - .byte 68,15,40,21,104,36,0,0 // movaps 0x2468(%rip),%xmm10 # 4350 <_sk_callback_sse2+0x629> + .byte 68,15,40,21,98,36,0,0 // movaps 0x2462(%rip),%xmm10 # 42d0 <_sk_callback_sse2+0x623> .byte 69,15,84,234 // andps %xmm10,%xmm13 .byte 69,15,87,219 // xorps %xmm11,%xmm11 .byte 69,15,92,229 // subps %xmm13,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,92,236 // subps %xmm12,%xmm13 - .byte 68,15,88,13,92,36,0,0 // addps 0x245c(%rip),%xmm9 # 4360 <_sk_callback_sse2+0x639> - .byte 68,15,40,37,100,36,0,0 // movaps 0x2464(%rip),%xmm12 # 4370 <_sk_callback_sse2+0x649> + .byte 68,15,88,13,86,36,0,0 // addps 0x2456(%rip),%xmm9 # 42e0 <_sk_callback_sse2+0x633> + .byte 68,15,40,37,94,36,0,0 // movaps 0x245e(%rip),%xmm12 # 42f0 <_sk_callback_sse2+0x643> .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,40,37,100,36,0,0 // movaps 0x2464(%rip),%xmm12 # 4380 <_sk_callback_sse2+0x659> + .byte 68,15,40,37,94,36,0,0 // movaps 0x245e(%rip),%xmm12 # 4300 <_sk_callback_sse2+0x653> .byte 69,15,92,229 // subps %xmm13,%xmm12 - .byte 68,15,40,45,104,36,0,0 // movaps 0x2468(%rip),%xmm13 # 4390 <_sk_callback_sse2+0x669> + .byte 68,15,40,45,98,36,0,0 // movaps 0x2462(%rip),%xmm13 # 4310 <_sk_callback_sse2+0x663> .byte 69,15,94,236 // divps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,89,45,104,36,0,0 // mulps 0x2468(%rip),%xmm13 # 43a0 <_sk_callback_sse2+0x679> + .byte 68,15,89,45,98,36,0,0 // mulps 0x2462(%rip),%xmm13 # 4320 <_sk_callback_sse2+0x673> .byte 102,69,15,91,205 // cvtps2dq %xmm13,%xmm9 .byte 243,68,15,16,96,20 // movss 0x14(%rax),%xmm12 .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 @@ -25275,15 +25125,15 @@ _sk_parametric_b_sse2: .byte 69,15,88,209 // addps %xmm9,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,202 // cvtdq2ps %xmm10,%xmm9 - .byte 68,15,89,13,232,35,0,0 // mulps 0x23e8(%rip),%xmm9 # 43b0 <_sk_callback_sse2+0x689> - .byte 68,15,84,21,240,35,0,0 // andps 0x23f0(%rip),%xmm10 # 43c0 <_sk_callback_sse2+0x699> - .byte 68,15,86,21,248,35,0,0 // orps 0x23f8(%rip),%xmm10 # 43d0 <_sk_callback_sse2+0x6a9> - .byte 68,15,88,13,0,36,0,0 // addps 0x2400(%rip),%xmm9 # 43e0 <_sk_callback_sse2+0x6b9> - .byte 68,15,40,37,8,36,0,0 // movaps 0x2408(%rip),%xmm12 # 43f0 <_sk_callback_sse2+0x6c9> + .byte 68,15,89,13,226,35,0,0 // mulps 0x23e2(%rip),%xmm9 # 4330 <_sk_callback_sse2+0x683> + .byte 68,15,84,21,234,35,0,0 // andps 0x23ea(%rip),%xmm10 # 4340 <_sk_callback_sse2+0x693> + .byte 68,15,86,21,242,35,0,0 // orps 0x23f2(%rip),%xmm10 # 4350 <_sk_callback_sse2+0x6a3> + .byte 68,15,88,13,250,35,0,0 // addps 0x23fa(%rip),%xmm9 # 4360 <_sk_callback_sse2+0x6b3> + .byte 68,15,40,37,2,36,0,0 // movaps 0x2402(%rip),%xmm12 # 4370 <_sk_callback_sse2+0x6c3> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,88,21,8,36,0,0 // addps 0x2408(%rip),%xmm10 # 4400 <_sk_callback_sse2+0x6d9> - .byte 68,15,40,37,16,36,0,0 // movaps 0x2410(%rip),%xmm12 # 4410 <_sk_callback_sse2+0x6e9> + .byte 68,15,88,21,2,36,0,0 // addps 0x2402(%rip),%xmm10 # 4380 <_sk_callback_sse2+0x6d3> + .byte 68,15,40,37,10,36,0,0 // movaps 0x240a(%rip),%xmm12 # 4390 <_sk_callback_sse2+0x6e3> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 @@ -25291,22 +25141,22 @@ _sk_parametric_b_sse2: .byte 69,15,91,226 // cvtdq2ps %xmm10,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,194,236,1 // cmpltps %xmm12,%xmm13 - .byte 68,15,40,21,250,35,0,0 // movaps 0x23fa(%rip),%xmm10 # 4420 <_sk_callback_sse2+0x6f9> + .byte 68,15,40,21,244,35,0,0 // movaps 0x23f4(%rip),%xmm10 # 43a0 <_sk_callback_sse2+0x6f3> .byte 69,15,84,234 // andps %xmm10,%xmm13 .byte 69,15,87,219 // xorps %xmm11,%xmm11 .byte 69,15,92,229 // subps %xmm13,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,92,236 // subps %xmm12,%xmm13 - .byte 68,15,88,13,238,35,0,0 // addps 0x23ee(%rip),%xmm9 # 4430 <_sk_callback_sse2+0x709> - .byte 68,15,40,37,246,35,0,0 // movaps 0x23f6(%rip),%xmm12 # 4440 <_sk_callback_sse2+0x719> + .byte 68,15,88,13,232,35,0,0 // addps 0x23e8(%rip),%xmm9 # 43b0 <_sk_callback_sse2+0x703> + .byte 68,15,40,37,240,35,0,0 // movaps 0x23f0(%rip),%xmm12 # 43c0 <_sk_callback_sse2+0x713> .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,40,37,246,35,0,0 // movaps 0x23f6(%rip),%xmm12 # 4450 <_sk_callback_sse2+0x729> + .byte 68,15,40,37,240,35,0,0 // movaps 0x23f0(%rip),%xmm12 # 43d0 <_sk_callback_sse2+0x723> .byte 69,15,92,229 // subps %xmm13,%xmm12 - .byte 68,15,40,45,250,35,0,0 // movaps 0x23fa(%rip),%xmm13 # 4460 <_sk_callback_sse2+0x739> + .byte 68,15,40,45,244,35,0,0 // movaps 0x23f4(%rip),%xmm13 # 43e0 <_sk_callback_sse2+0x733> .byte 69,15,94,236 // divps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,89,45,250,35,0,0 // mulps 0x23fa(%rip),%xmm13 # 4470 <_sk_callback_sse2+0x749> + .byte 68,15,89,45,244,35,0,0 // mulps 0x23f4(%rip),%xmm13 # 43f0 <_sk_callback_sse2+0x743> .byte 102,69,15,91,205 // cvtps2dq %xmm13,%xmm9 .byte 243,68,15,16,96,20 // movss 0x14(%rax),%xmm12 .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 @@ -25342,15 +25192,15 @@ _sk_parametric_a_sse2: .byte 69,15,88,209 // addps %xmm9,%xmm10 .byte 69,15,198,219,0 // shufps $0x0,%xmm11,%xmm11 .byte 69,15,91,202 // cvtdq2ps %xmm10,%xmm9 - .byte 68,15,89,13,122,35,0,0 // mulps 0x237a(%rip),%xmm9 # 4480 <_sk_callback_sse2+0x759> - .byte 68,15,84,21,130,35,0,0 // andps 0x2382(%rip),%xmm10 # 4490 <_sk_callback_sse2+0x769> - .byte 68,15,86,21,138,35,0,0 // orps 0x238a(%rip),%xmm10 # 44a0 <_sk_callback_sse2+0x779> - .byte 68,15,88,13,146,35,0,0 // addps 0x2392(%rip),%xmm9 # 44b0 <_sk_callback_sse2+0x789> - .byte 68,15,40,37,154,35,0,0 // movaps 0x239a(%rip),%xmm12 # 44c0 <_sk_callback_sse2+0x799> + .byte 68,15,89,13,116,35,0,0 // mulps 0x2374(%rip),%xmm9 # 4400 <_sk_callback_sse2+0x753> + .byte 68,15,84,21,124,35,0,0 // andps 0x237c(%rip),%xmm10 # 4410 <_sk_callback_sse2+0x763> + .byte 68,15,86,21,132,35,0,0 // orps 0x2384(%rip),%xmm10 # 4420 <_sk_callback_sse2+0x773> + .byte 68,15,88,13,140,35,0,0 // addps 0x238c(%rip),%xmm9 # 4430 <_sk_callback_sse2+0x783> + .byte 68,15,40,37,148,35,0,0 // movaps 0x2394(%rip),%xmm12 # 4440 <_sk_callback_sse2+0x793> .byte 69,15,89,226 // mulps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,88,21,154,35,0,0 // addps 0x239a(%rip),%xmm10 # 44d0 <_sk_callback_sse2+0x7a9> - .byte 68,15,40,37,162,35,0,0 // movaps 0x23a2(%rip),%xmm12 # 44e0 <_sk_callback_sse2+0x7b9> + .byte 68,15,88,21,148,35,0,0 // addps 0x2394(%rip),%xmm10 # 4450 <_sk_callback_sse2+0x7a3> + .byte 68,15,40,37,156,35,0,0 // movaps 0x239c(%rip),%xmm12 # 4460 <_sk_callback_sse2+0x7b3> .byte 69,15,94,226 // divps %xmm10,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 .byte 69,15,89,203 // mulps %xmm11,%xmm9 @@ -25358,22 +25208,22 @@ _sk_parametric_a_sse2: .byte 69,15,91,226 // cvtdq2ps %xmm10,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,194,236,1 // cmpltps %xmm12,%xmm13 - .byte 68,15,40,21,140,35,0,0 // movaps 0x238c(%rip),%xmm10 # 44f0 <_sk_callback_sse2+0x7c9> + .byte 68,15,40,21,134,35,0,0 // movaps 0x2386(%rip),%xmm10 # 4470 <_sk_callback_sse2+0x7c3> .byte 69,15,84,234 // andps %xmm10,%xmm13 .byte 69,15,87,219 // xorps %xmm11,%xmm11 .byte 69,15,92,229 // subps %xmm13,%xmm12 .byte 69,15,40,233 // movaps %xmm9,%xmm13 .byte 69,15,92,236 // subps %xmm12,%xmm13 - .byte 68,15,88,13,128,35,0,0 // addps 0x2380(%rip),%xmm9 # 4500 <_sk_callback_sse2+0x7d9> - .byte 68,15,40,37,136,35,0,0 // movaps 0x2388(%rip),%xmm12 # 4510 <_sk_callback_sse2+0x7e9> + .byte 68,15,88,13,122,35,0,0 // addps 0x237a(%rip),%xmm9 # 4480 <_sk_callback_sse2+0x7d3> + .byte 68,15,40,37,130,35,0,0 // movaps 0x2382(%rip),%xmm12 # 4490 <_sk_callback_sse2+0x7e3> .byte 69,15,89,229 // mulps %xmm13,%xmm12 .byte 69,15,92,204 // subps %xmm12,%xmm9 - .byte 68,15,40,37,136,35,0,0 // movaps 0x2388(%rip),%xmm12 # 4520 <_sk_callback_sse2+0x7f9> + .byte 68,15,40,37,130,35,0,0 // movaps 0x2382(%rip),%xmm12 # 44a0 <_sk_callback_sse2+0x7f3> .byte 69,15,92,229 // subps %xmm13,%xmm12 - .byte 68,15,40,45,140,35,0,0 // movaps 0x238c(%rip),%xmm13 # 4530 <_sk_callback_sse2+0x809> + .byte 68,15,40,45,134,35,0,0 // movaps 0x2386(%rip),%xmm13 # 44b0 <_sk_callback_sse2+0x803> .byte 69,15,94,236 // divps %xmm12,%xmm13 .byte 69,15,88,233 // addps %xmm9,%xmm13 - .byte 68,15,89,45,140,35,0,0 // mulps 0x238c(%rip),%xmm13 # 4540 <_sk_callback_sse2+0x819> + .byte 68,15,89,45,134,35,0,0 // mulps 0x2386(%rip),%xmm13 # 44c0 <_sk_callback_sse2+0x813> .byte 102,69,15,91,205 // cvtps2dq %xmm13,%xmm9 .byte 243,68,15,16,96,20 // movss 0x14(%rax),%xmm12 .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 @@ -25390,29 +25240,29 @@ HIDDEN _sk_lab_to_xyz_sse2 .globl _sk_lab_to_xyz_sse2 FUNCTION(_sk_lab_to_xyz_sse2) _sk_lab_to_xyz_sse2: - .byte 15,89,5,105,35,0,0 // mulps 0x2369(%rip),%xmm0 # 4550 <_sk_callback_sse2+0x829> - .byte 68,15,40,5,113,35,0,0 // movaps 0x2371(%rip),%xmm8 # 4560 <_sk_callback_sse2+0x839> + .byte 15,89,5,99,35,0,0 // mulps 0x2363(%rip),%xmm0 # 44d0 <_sk_callback_sse2+0x823> + .byte 68,15,40,5,107,35,0,0 // movaps 0x236b(%rip),%xmm8 # 44e0 <_sk_callback_sse2+0x833> .byte 65,15,89,200 // mulps %xmm8,%xmm1 - .byte 68,15,40,13,117,35,0,0 // movaps 0x2375(%rip),%xmm9 # 4570 <_sk_callback_sse2+0x849> + .byte 68,15,40,13,111,35,0,0 // movaps 0x236f(%rip),%xmm9 # 44f0 <_sk_callback_sse2+0x843> .byte 65,15,88,201 // addps %xmm9,%xmm1 .byte 65,15,89,208 // mulps %xmm8,%xmm2 .byte 65,15,88,209 // addps %xmm9,%xmm2 - .byte 15,88,5,114,35,0,0 // addps 0x2372(%rip),%xmm0 # 4580 <_sk_callback_sse2+0x859> - .byte 15,89,5,123,35,0,0 // mulps 0x237b(%rip),%xmm0 # 4590 <_sk_callback_sse2+0x869> - .byte 15,89,13,132,35,0,0 // mulps 0x2384(%rip),%xmm1 # 45a0 <_sk_callback_sse2+0x879> + .byte 15,88,5,108,35,0,0 // addps 0x236c(%rip),%xmm0 # 4500 <_sk_callback_sse2+0x853> + .byte 15,89,5,117,35,0,0 // mulps 0x2375(%rip),%xmm0 # 4510 <_sk_callback_sse2+0x863> + .byte 15,89,13,126,35,0,0 // mulps 0x237e(%rip),%xmm1 # 4520 <_sk_callback_sse2+0x873> .byte 15,88,200 // addps %xmm0,%xmm1 - .byte 15,89,21,138,35,0,0 // mulps 0x238a(%rip),%xmm2 # 45b0 <_sk_callback_sse2+0x889> + .byte 15,89,21,132,35,0,0 // mulps 0x2384(%rip),%xmm2 # 4530 <_sk_callback_sse2+0x883> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 68,15,92,202 // subps %xmm2,%xmm9 .byte 68,15,40,225 // movaps %xmm1,%xmm12 .byte 69,15,89,228 // mulps %xmm12,%xmm12 .byte 68,15,89,225 // mulps %xmm1,%xmm12 - .byte 15,40,21,127,35,0,0 // movaps 0x237f(%rip),%xmm2 # 45c0 <_sk_callback_sse2+0x899> + .byte 15,40,21,121,35,0,0 // movaps 0x2379(%rip),%xmm2 # 4540 <_sk_callback_sse2+0x893> .byte 68,15,40,194 // movaps %xmm2,%xmm8 .byte 69,15,194,196,1 // cmpltps %xmm12,%xmm8 - .byte 68,15,40,21,126,35,0,0 // movaps 0x237e(%rip),%xmm10 # 45d0 <_sk_callback_sse2+0x8a9> + .byte 68,15,40,21,120,35,0,0 // movaps 0x2378(%rip),%xmm10 # 4550 <_sk_callback_sse2+0x8a3> .byte 65,15,88,202 // addps %xmm10,%xmm1 - .byte 68,15,40,29,130,35,0,0 // movaps 0x2382(%rip),%xmm11 # 45e0 <_sk_callback_sse2+0x8b9> + .byte 68,15,40,29,124,35,0,0 // movaps 0x237c(%rip),%xmm11 # 4560 <_sk_callback_sse2+0x8b3> .byte 65,15,89,203 // mulps %xmm11,%xmm1 .byte 69,15,84,224 // andps %xmm8,%xmm12 .byte 68,15,85,193 // andnps %xmm1,%xmm8 @@ -25436,8 +25286,8 @@ _sk_lab_to_xyz_sse2: .byte 15,84,194 // andps %xmm2,%xmm0 .byte 65,15,85,209 // andnps %xmm9,%xmm2 .byte 15,86,208 // orps %xmm0,%xmm2 - .byte 68,15,89,5,50,35,0,0 // mulps 0x2332(%rip),%xmm8 # 45f0 <_sk_callback_sse2+0x8c9> - .byte 15,89,21,59,35,0,0 // mulps 0x233b(%rip),%xmm2 # 4600 <_sk_callback_sse2+0x8d9> + .byte 68,15,89,5,44,35,0,0 // mulps 0x232c(%rip),%xmm8 # 4570 <_sk_callback_sse2+0x8c3> + .byte 15,89,21,53,35,0,0 // mulps 0x2335(%rip),%xmm2 # 4580 <_sk_callback_sse2+0x8d3> .byte 72,173 // lods %ds:(%rsi),%rax .byte 65,15,40,192 // movaps %xmm8,%xmm0 .byte 255,224 // jmpq *%rax @@ -25453,7 +25303,7 @@ _sk_load_a8_sse2: .byte 102,15,96,193 // punpcklbw %xmm1,%xmm0 .byte 102,15,97,193 // punpcklwd %xmm1,%xmm0 .byte 15,91,216 // cvtdq2ps %xmm0,%xmm3 - .byte 15,89,29,35,35,0,0 // mulps 0x2323(%rip),%xmm3 # 4610 <_sk_callback_sse2+0x8e9> + .byte 15,89,29,29,35,0,0 // mulps 0x231d(%rip),%xmm3 # 4590 <_sk_callback_sse2+0x8e3> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 102,15,239,201 // pxor %xmm1,%xmm1 @@ -25498,7 +25348,7 @@ _sk_gather_a8_sse2: .byte 102,15,96,193 // punpcklbw %xmm1,%xmm0 .byte 102,15,97,193 // punpcklwd %xmm1,%xmm0 .byte 15,91,216 // cvtdq2ps %xmm0,%xmm3 - .byte 15,89,29,146,34,0,0 // mulps 0x2292(%rip),%xmm3 # 4620 <_sk_callback_sse2+0x8f9> + .byte 15,89,29,140,34,0,0 // mulps 0x228c(%rip),%xmm3 # 45a0 <_sk_callback_sse2+0x8f3> .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 .byte 102,15,239,201 // pxor %xmm1,%xmm1 @@ -25511,7 +25361,7 @@ FUNCTION(_sk_store_a8_sse2) _sk_store_a8_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,134,34,0,0 // movaps 0x2286(%rip),%xmm8 # 4630 <_sk_callback_sse2+0x909> + .byte 68,15,40,5,128,34,0,0 // movaps 0x2280(%rip),%xmm8 # 45b0 <_sk_callback_sse2+0x903> .byte 68,15,89,195 // mulps %xmm3,%xmm8 .byte 102,69,15,91,192 // cvtps2dq %xmm8,%xmm8 .byte 102,65,15,114,240,16 // pslld $0x10,%xmm8 @@ -25533,9 +25383,9 @@ _sk_load_g8_sse2: .byte 102,15,96,193 // punpcklbw %xmm1,%xmm0 .byte 102,15,97,193 // punpcklwd %xmm1,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,77,34,0,0 // mulps 0x224d(%rip),%xmm0 # 4640 <_sk_callback_sse2+0x919> + .byte 15,89,5,71,34,0,0 // mulps 0x2247(%rip),%xmm0 # 45c0 <_sk_callback_sse2+0x913> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,84,34,0,0 // movaps 0x2254(%rip),%xmm3 # 4650 <_sk_callback_sse2+0x929> + .byte 15,40,29,78,34,0,0 // movaps 0x224e(%rip),%xmm3 # 45d0 <_sk_callback_sse2+0x923> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 255,224 // jmpq *%rax @@ -25578,9 +25428,9 @@ _sk_gather_g8_sse2: .byte 102,15,96,193 // punpcklbw %xmm1,%xmm0 .byte 102,15,97,193 // punpcklwd %xmm1,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,201,33,0,0 // mulps 0x21c9(%rip),%xmm0 # 4660 <_sk_callback_sse2+0x939> + .byte 15,89,5,195,33,0,0 // mulps 0x21c3(%rip),%xmm0 # 45e0 <_sk_callback_sse2+0x933> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,208,33,0,0 // movaps 0x21d0(%rip),%xmm3 # 4670 <_sk_callback_sse2+0x949> + .byte 15,40,29,202,33,0,0 // movaps 0x21ca(%rip),%xmm3 # 45f0 <_sk_callback_sse2+0x943> .byte 15,40,200 // movaps %xmm0,%xmm1 .byte 15,40,208 // movaps %xmm0,%xmm2 .byte 255,224 // jmpq *%rax @@ -25592,9 +25442,9 @@ _sk_gather_i8_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 73,137,192 // mov %rax,%r8 .byte 77,133,192 // test %r8,%r8 - .byte 116,5 // je 24b7 <_sk_gather_i8_sse2+0xf> + .byte 116,5 // je 243d <_sk_gather_i8_sse2+0xf> .byte 76,137,192 // mov %r8,%rax - .byte 235,2 // jmp 24b9 <_sk_gather_i8_sse2+0x11> + .byte 235,2 // jmp 243f <_sk_gather_i8_sse2+0x11> .byte 72,173 // lods %ds:(%rsi),%rax .byte 76,139,16 // mov (%rax),%r10 .byte 243,15,91,201 // cvttps2dq %xmm1,%xmm1 @@ -25643,11 +25493,11 @@ _sk_gather_i8_sse2: .byte 102,67,15,110,12,136 // movd (%r8,%r9,4),%xmm1 .byte 102,68,15,98,201 // punpckldq %xmm1,%xmm9 .byte 102,68,15,98,200 // punpckldq %xmm0,%xmm9 - .byte 102,15,111,21,239,32,0,0 // movdqa 0x20ef(%rip),%xmm2 # 4680 <_sk_callback_sse2+0x959> + .byte 102,15,111,21,233,32,0,0 // movdqa 0x20e9(%rip),%xmm2 # 4600 <_sk_callback_sse2+0x953> .byte 102,65,15,111,193 // movdqa %xmm9,%xmm0 .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,235,32,0,0 // movaps 0x20eb(%rip),%xmm8 # 4690 <_sk_callback_sse2+0x969> + .byte 68,15,40,5,229,32,0,0 // movaps 0x20e5(%rip),%xmm8 # 4610 <_sk_callback_sse2+0x963> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,65,15,111,201 // movdqa %xmm9,%xmm1 .byte 102,15,114,209,8 // psrld $0x8,%xmm1 @@ -25674,19 +25524,19 @@ _sk_load_565_sse2: .byte 243,15,126,20,120 // movq (%rax,%rdi,2),%xmm2 .byte 102,15,239,192 // pxor %xmm0,%xmm0 .byte 102,15,97,208 // punpcklwd %xmm0,%xmm2 - .byte 102,15,111,5,161,32,0,0 // movdqa 0x20a1(%rip),%xmm0 # 46a0 <_sk_callback_sse2+0x979> + .byte 102,15,111,5,155,32,0,0 // movdqa 0x209b(%rip),%xmm0 # 4620 <_sk_callback_sse2+0x973> .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,163,32,0,0 // mulps 0x20a3(%rip),%xmm0 # 46b0 <_sk_callback_sse2+0x989> - .byte 102,15,111,13,171,32,0,0 // movdqa 0x20ab(%rip),%xmm1 # 46c0 <_sk_callback_sse2+0x999> + .byte 15,89,5,157,32,0,0 // mulps 0x209d(%rip),%xmm0 # 4630 <_sk_callback_sse2+0x983> + .byte 102,15,111,13,165,32,0,0 // movdqa 0x20a5(%rip),%xmm1 # 4640 <_sk_callback_sse2+0x993> .byte 102,15,219,202 // pand %xmm2,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,173,32,0,0 // mulps 0x20ad(%rip),%xmm1 # 46d0 <_sk_callback_sse2+0x9a9> - .byte 102,15,219,21,181,32,0,0 // pand 0x20b5(%rip),%xmm2 # 46e0 <_sk_callback_sse2+0x9b9> + .byte 15,89,13,167,32,0,0 // mulps 0x20a7(%rip),%xmm1 # 4650 <_sk_callback_sse2+0x9a3> + .byte 102,15,219,21,175,32,0,0 // pand 0x20af(%rip),%xmm2 # 4660 <_sk_callback_sse2+0x9b3> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,187,32,0,0 // mulps 0x20bb(%rip),%xmm2 # 46f0 <_sk_callback_sse2+0x9c9> + .byte 15,89,21,181,32,0,0 // mulps 0x20b5(%rip),%xmm2 # 4670 <_sk_callback_sse2+0x9c3> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,194,32,0,0 // movaps 0x20c2(%rip),%xmm3 # 4700 <_sk_callback_sse2+0x9d9> + .byte 15,40,29,188,32,0,0 // movaps 0x20bc(%rip),%xmm3 # 4680 <_sk_callback_sse2+0x9d3> .byte 255,224 // jmpq *%rax HIDDEN _sk_gather_565_sse2 @@ -25721,19 +25571,19 @@ _sk_gather_565_sse2: .byte 102,15,196,208,3 // pinsrw $0x3,%eax,%xmm2 .byte 102,15,239,192 // pxor %xmm0,%xmm0 .byte 102,15,97,208 // punpcklwd %xmm0,%xmm2 - .byte 102,15,111,5,75,32,0,0 // movdqa 0x204b(%rip),%xmm0 # 4710 <_sk_callback_sse2+0x9e9> + .byte 102,15,111,5,69,32,0,0 // movdqa 0x2045(%rip),%xmm0 # 4690 <_sk_callback_sse2+0x9e3> .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,77,32,0,0 // mulps 0x204d(%rip),%xmm0 # 4720 <_sk_callback_sse2+0x9f9> - .byte 102,15,111,13,85,32,0,0 // movdqa 0x2055(%rip),%xmm1 # 4730 <_sk_callback_sse2+0xa09> + .byte 15,89,5,71,32,0,0 // mulps 0x2047(%rip),%xmm0 # 46a0 <_sk_callback_sse2+0x9f3> + .byte 102,15,111,13,79,32,0,0 // movdqa 0x204f(%rip),%xmm1 # 46b0 <_sk_callback_sse2+0xa03> .byte 102,15,219,202 // pand %xmm2,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,87,32,0,0 // mulps 0x2057(%rip),%xmm1 # 4740 <_sk_callback_sse2+0xa19> - .byte 102,15,219,21,95,32,0,0 // pand 0x205f(%rip),%xmm2 # 4750 <_sk_callback_sse2+0xa29> + .byte 15,89,13,81,32,0,0 // mulps 0x2051(%rip),%xmm1 # 46c0 <_sk_callback_sse2+0xa13> + .byte 102,15,219,21,89,32,0,0 // pand 0x2059(%rip),%xmm2 # 46d0 <_sk_callback_sse2+0xa23> .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,101,32,0,0 // mulps 0x2065(%rip),%xmm2 # 4760 <_sk_callback_sse2+0xa39> + .byte 15,89,21,95,32,0,0 // mulps 0x205f(%rip),%xmm2 # 46e0 <_sk_callback_sse2+0xa33> .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,108,32,0,0 // movaps 0x206c(%rip),%xmm3 # 4770 <_sk_callback_sse2+0xa49> + .byte 15,40,29,102,32,0,0 // movaps 0x2066(%rip),%xmm3 # 46f0 <_sk_callback_sse2+0xa43> .byte 255,224 // jmpq *%rax HIDDEN _sk_store_565_sse2 @@ -25742,12 +25592,12 @@ FUNCTION(_sk_store_565_sse2) _sk_store_565_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,109,32,0,0 // movaps 0x206d(%rip),%xmm8 # 4780 <_sk_callback_sse2+0xa59> + .byte 68,15,40,5,103,32,0,0 // movaps 0x2067(%rip),%xmm8 # 4700 <_sk_callback_sse2+0xa53> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 .byte 102,65,15,114,241,11 // pslld $0xb,%xmm9 - .byte 68,15,40,21,98,32,0,0 // movaps 0x2062(%rip),%xmm10 # 4790 <_sk_callback_sse2+0xa69> + .byte 68,15,40,21,92,32,0,0 // movaps 0x205c(%rip),%xmm10 # 4710 <_sk_callback_sse2+0xa63> .byte 68,15,89,209 // mulps %xmm1,%xmm10 .byte 102,69,15,91,210 // cvtps2dq %xmm10,%xmm10 .byte 102,65,15,114,242,5 // pslld $0x5,%xmm10 @@ -25771,21 +25621,21 @@ _sk_load_4444_sse2: .byte 243,15,126,28,120 // movq (%rax,%rdi,2),%xmm3 .byte 102,15,239,192 // pxor %xmm0,%xmm0 .byte 102,15,97,216 // punpcklwd %xmm0,%xmm3 - .byte 102,15,111,5,27,32,0,0 // movdqa 0x201b(%rip),%xmm0 # 47a0 <_sk_callback_sse2+0xa79> + .byte 102,15,111,5,21,32,0,0 // movdqa 0x2015(%rip),%xmm0 # 4720 <_sk_callback_sse2+0xa73> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,29,32,0,0 // mulps 0x201d(%rip),%xmm0 # 47b0 <_sk_callback_sse2+0xa89> - .byte 102,15,111,13,37,32,0,0 // movdqa 0x2025(%rip),%xmm1 # 47c0 <_sk_callback_sse2+0xa99> + .byte 15,89,5,23,32,0,0 // mulps 0x2017(%rip),%xmm0 # 4730 <_sk_callback_sse2+0xa83> + .byte 102,15,111,13,31,32,0,0 // movdqa 0x201f(%rip),%xmm1 # 4740 <_sk_callback_sse2+0xa93> .byte 102,15,219,203 // pand %xmm3,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,39,32,0,0 // mulps 0x2027(%rip),%xmm1 # 47d0 <_sk_callback_sse2+0xaa9> - .byte 102,15,111,21,47,32,0,0 // movdqa 0x202f(%rip),%xmm2 # 47e0 <_sk_callback_sse2+0xab9> + .byte 15,89,13,33,32,0,0 // mulps 0x2021(%rip),%xmm1 # 4750 <_sk_callback_sse2+0xaa3> + .byte 102,15,111,21,41,32,0,0 // movdqa 0x2029(%rip),%xmm2 # 4760 <_sk_callback_sse2+0xab3> .byte 102,15,219,211 // pand %xmm3,%xmm2 .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,49,32,0,0 // mulps 0x2031(%rip),%xmm2 # 47f0 <_sk_callback_sse2+0xac9> - .byte 102,15,219,29,57,32,0,0 // pand 0x2039(%rip),%xmm3 # 4800 <_sk_callback_sse2+0xad9> + .byte 15,89,21,43,32,0,0 // mulps 0x202b(%rip),%xmm2 # 4770 <_sk_callback_sse2+0xac3> + .byte 102,15,219,29,51,32,0,0 // pand 0x2033(%rip),%xmm3 # 4780 <_sk_callback_sse2+0xad3> .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,63,32,0,0 // mulps 0x203f(%rip),%xmm3 # 4810 <_sk_callback_sse2+0xae9> + .byte 15,89,29,57,32,0,0 // mulps 0x2039(%rip),%xmm3 # 4790 <_sk_callback_sse2+0xae3> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -25821,21 +25671,21 @@ _sk_gather_4444_sse2: .byte 102,15,196,216,3 // pinsrw $0x3,%eax,%xmm3 .byte 102,15,239,192 // pxor %xmm0,%xmm0 .byte 102,15,97,216 // punpcklwd %xmm0,%xmm3 - .byte 102,15,111,5,198,31,0,0 // movdqa 0x1fc6(%rip),%xmm0 # 4820 <_sk_callback_sse2+0xaf9> + .byte 102,15,111,5,192,31,0,0 // movdqa 0x1fc0(%rip),%xmm0 # 47a0 <_sk_callback_sse2+0xaf3> .byte 102,15,219,195 // pand %xmm3,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 15,89,5,200,31,0,0 // mulps 0x1fc8(%rip),%xmm0 # 4830 <_sk_callback_sse2+0xb09> - .byte 102,15,111,13,208,31,0,0 // movdqa 0x1fd0(%rip),%xmm1 # 4840 <_sk_callback_sse2+0xb19> + .byte 15,89,5,194,31,0,0 // mulps 0x1fc2(%rip),%xmm0 # 47b0 <_sk_callback_sse2+0xb03> + .byte 102,15,111,13,202,31,0,0 // movdqa 0x1fca(%rip),%xmm1 # 47c0 <_sk_callback_sse2+0xb13> .byte 102,15,219,203 // pand %xmm3,%xmm1 .byte 15,91,201 // cvtdq2ps %xmm1,%xmm1 - .byte 15,89,13,210,31,0,0 // mulps 0x1fd2(%rip),%xmm1 # 4850 <_sk_callback_sse2+0xb29> - .byte 102,15,111,21,218,31,0,0 // movdqa 0x1fda(%rip),%xmm2 # 4860 <_sk_callback_sse2+0xb39> + .byte 15,89,13,204,31,0,0 // mulps 0x1fcc(%rip),%xmm1 # 47d0 <_sk_callback_sse2+0xb23> + .byte 102,15,111,21,212,31,0,0 // movdqa 0x1fd4(%rip),%xmm2 # 47e0 <_sk_callback_sse2+0xb33> .byte 102,15,219,211 // pand %xmm3,%xmm2 .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 - .byte 15,89,21,220,31,0,0 // mulps 0x1fdc(%rip),%xmm2 # 4870 <_sk_callback_sse2+0xb49> - .byte 102,15,219,29,228,31,0,0 // pand 0x1fe4(%rip),%xmm3 # 4880 <_sk_callback_sse2+0xb59> + .byte 15,89,21,214,31,0,0 // mulps 0x1fd6(%rip),%xmm2 # 47f0 <_sk_callback_sse2+0xb43> + .byte 102,15,219,29,222,31,0,0 // pand 0x1fde(%rip),%xmm3 # 4800 <_sk_callback_sse2+0xb53> .byte 15,91,219 // cvtdq2ps %xmm3,%xmm3 - .byte 15,89,29,234,31,0,0 // mulps 0x1fea(%rip),%xmm3 # 4890 <_sk_callback_sse2+0xb69> + .byte 15,89,29,228,31,0,0 // mulps 0x1fe4(%rip),%xmm3 # 4810 <_sk_callback_sse2+0xb63> .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -25845,7 +25695,7 @@ FUNCTION(_sk_store_4444_sse2) _sk_store_4444_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,233,31,0,0 // movaps 0x1fe9(%rip),%xmm8 # 48a0 <_sk_callback_sse2+0xb79> + .byte 68,15,40,5,227,31,0,0 // movaps 0x1fe3(%rip),%xmm8 # 4820 <_sk_callback_sse2+0xb73> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 @@ -25877,11 +25727,11 @@ _sk_load_8888_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax .byte 68,15,16,12,184 // movups (%rax,%rdi,4),%xmm9 - .byte 15,40,21,124,31,0,0 // movaps 0x1f7c(%rip),%xmm2 # 48b0 <_sk_callback_sse2+0xb89> + .byte 15,40,21,118,31,0,0 // movaps 0x1f76(%rip),%xmm2 # 4830 <_sk_callback_sse2+0xb83> .byte 65,15,40,193 // movaps %xmm9,%xmm0 .byte 15,84,194 // andps %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,122,31,0,0 // movaps 0x1f7a(%rip),%xmm8 # 48c0 <_sk_callback_sse2+0xb99> + .byte 68,15,40,5,116,31,0,0 // movaps 0x1f74(%rip),%xmm8 # 4840 <_sk_callback_sse2+0xb93> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 65,15,40,201 // movaps %xmm9,%xmm1 .byte 102,15,114,209,8 // psrld $0x8,%xmm1 @@ -25930,11 +25780,11 @@ _sk_gather_8888_sse2: .byte 102,67,15,110,12,129 // movd (%r9,%r8,4),%xmm1 .byte 102,68,15,98,201 // punpckldq %xmm1,%xmm9 .byte 102,68,15,98,200 // punpckldq %xmm0,%xmm9 - .byte 102,15,111,21,203,30,0,0 // movdqa 0x1ecb(%rip),%xmm2 # 48d0 <_sk_callback_sse2+0xba9> + .byte 102,15,111,21,197,30,0,0 // movdqa 0x1ec5(%rip),%xmm2 # 4850 <_sk_callback_sse2+0xba3> .byte 102,65,15,111,193 // movdqa %xmm9,%xmm0 .byte 102,15,219,194 // pand %xmm2,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,5,199,30,0,0 // movaps 0x1ec7(%rip),%xmm8 # 48e0 <_sk_callback_sse2+0xbb9> + .byte 68,15,40,5,193,30,0,0 // movaps 0x1ec1(%rip),%xmm8 # 4860 <_sk_callback_sse2+0xbb3> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,65,15,111,201 // movdqa %xmm9,%xmm1 .byte 102,15,114,209,8 // psrld $0x8,%xmm1 @@ -25958,7 +25808,7 @@ FUNCTION(_sk_store_8888_sse2) _sk_store_8888_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,5,138,30,0,0 // movaps 0x1e8a(%rip),%xmm8 # 48f0 <_sk_callback_sse2+0xbc9> + .byte 68,15,40,5,132,30,0,0 // movaps 0x1e84(%rip),%xmm8 # 4870 <_sk_callback_sse2+0xbc3> .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 102,69,15,91,201 // cvtps2dq %xmm9,%xmm9 @@ -25997,7 +25847,7 @@ _sk_load_f16_sse2: .byte 102,69,15,239,210 // pxor %xmm10,%xmm10 .byte 102,65,15,111,206 // movdqa %xmm14,%xmm1 .byte 102,65,15,97,202 // punpcklwd %xmm10,%xmm1 - .byte 102,68,15,111,13,250,29,0,0 // movdqa 0x1dfa(%rip),%xmm9 # 4900 <_sk_callback_sse2+0xbd9> + .byte 102,68,15,111,13,244,29,0,0 // movdqa 0x1df4(%rip),%xmm9 # 4880 <_sk_callback_sse2+0xbd3> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,193 // pand %xmm9,%xmm0 .byte 102,15,239,200 // pxor %xmm0,%xmm1 @@ -26005,11 +25855,11 @@ _sk_load_f16_sse2: .byte 102,68,15,111,233 // movdqa %xmm1,%xmm13 .byte 102,65,15,114,245,13 // pslld $0xd,%xmm13 .byte 102,68,15,235,232 // por %xmm0,%xmm13 - .byte 102,68,15,111,29,223,29,0,0 // movdqa 0x1ddf(%rip),%xmm11 # 4910 <_sk_callback_sse2+0xbe9> + .byte 102,68,15,111,29,217,29,0,0 // movdqa 0x1dd9(%rip),%xmm11 # 4890 <_sk_callback_sse2+0xbe3> .byte 102,69,15,254,235 // paddd %xmm11,%xmm13 - .byte 102,68,15,111,37,225,29,0,0 // movdqa 0x1de1(%rip),%xmm12 # 4920 <_sk_callback_sse2+0xbf9> + .byte 102,68,15,111,37,219,29,0,0 // movdqa 0x1ddb(%rip),%xmm12 # 48a0 <_sk_callback_sse2+0xbf3> .byte 102,65,15,239,204 // pxor %xmm12,%xmm1 - .byte 102,15,111,29,228,29,0,0 // movdqa 0x1de4(%rip),%xmm3 # 4930 <_sk_callback_sse2+0xc09> + .byte 102,15,111,29,222,29,0,0 // movdqa 0x1dde(%rip),%xmm3 # 48b0 <_sk_callback_sse2+0xc03> .byte 102,15,111,195 // movdqa %xmm3,%xmm0 .byte 102,15,102,193 // pcmpgtd %xmm1,%xmm0 .byte 102,65,15,223,197 // pandn %xmm13,%xmm0 @@ -26095,7 +25945,7 @@ _sk_gather_f16_sse2: .byte 102,69,15,239,210 // pxor %xmm10,%xmm10 .byte 102,65,15,111,206 // movdqa %xmm14,%xmm1 .byte 102,65,15,97,202 // punpcklwd %xmm10,%xmm1 - .byte 102,68,15,111,13,114,28,0,0 // movdqa 0x1c72(%rip),%xmm9 # 4940 <_sk_callback_sse2+0xc19> + .byte 102,68,15,111,13,108,28,0,0 // movdqa 0x1c6c(%rip),%xmm9 # 48c0 <_sk_callback_sse2+0xc13> .byte 102,15,111,193 // movdqa %xmm1,%xmm0 .byte 102,65,15,219,193 // pand %xmm9,%xmm0 .byte 102,15,239,200 // pxor %xmm0,%xmm1 @@ -26103,11 +25953,11 @@ _sk_gather_f16_sse2: .byte 102,68,15,111,233 // movdqa %xmm1,%xmm13 .byte 102,65,15,114,245,13 // pslld $0xd,%xmm13 .byte 102,68,15,235,232 // por %xmm0,%xmm13 - .byte 102,68,15,111,29,87,28,0,0 // movdqa 0x1c57(%rip),%xmm11 # 4950 <_sk_callback_sse2+0xc29> + .byte 102,68,15,111,29,81,28,0,0 // movdqa 0x1c51(%rip),%xmm11 # 48d0 <_sk_callback_sse2+0xc23> .byte 102,69,15,254,235 // paddd %xmm11,%xmm13 - .byte 102,68,15,111,37,89,28,0,0 // movdqa 0x1c59(%rip),%xmm12 # 4960 <_sk_callback_sse2+0xc39> + .byte 102,68,15,111,37,83,28,0,0 // movdqa 0x1c53(%rip),%xmm12 # 48e0 <_sk_callback_sse2+0xc33> .byte 102,65,15,239,204 // pxor %xmm12,%xmm1 - .byte 102,15,111,29,92,28,0,0 // movdqa 0x1c5c(%rip),%xmm3 # 4970 <_sk_callback_sse2+0xc49> + .byte 102,15,111,29,86,28,0,0 // movdqa 0x1c56(%rip),%xmm3 # 48f0 <_sk_callback_sse2+0xc43> .byte 102,15,111,195 // movdqa %xmm3,%xmm0 .byte 102,15,102,193 // pcmpgtd %xmm1,%xmm0 .byte 102,65,15,223,197 // pandn %xmm13,%xmm0 @@ -26160,17 +26010,17 @@ FUNCTION(_sk_store_f16_sse2) _sk_store_f16_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 102,68,15,111,21,132,27,0,0 // movdqa 0x1b84(%rip),%xmm10 # 4980 <_sk_callback_sse2+0xc59> + .byte 102,68,15,111,21,126,27,0,0 // movdqa 0x1b7e(%rip),%xmm10 # 4900 <_sk_callback_sse2+0xc53> .byte 102,68,15,111,224 // movdqa %xmm0,%xmm12 .byte 102,68,15,111,232 // movdqa %xmm0,%xmm13 .byte 102,69,15,219,234 // pand %xmm10,%xmm13 .byte 102,69,15,239,229 // pxor %xmm13,%xmm12 - .byte 102,68,15,111,13,119,27,0,0 // movdqa 0x1b77(%rip),%xmm9 # 4990 <_sk_callback_sse2+0xc69> + .byte 102,68,15,111,13,113,27,0,0 // movdqa 0x1b71(%rip),%xmm9 # 4910 <_sk_callback_sse2+0xc63> .byte 102,65,15,114,213,16 // psrld $0x10,%xmm13 .byte 102,69,15,111,193 // movdqa %xmm9,%xmm8 .byte 102,69,15,102,196 // pcmpgtd %xmm12,%xmm8 .byte 102,65,15,114,212,13 // psrld $0xd,%xmm12 - .byte 102,68,15,111,29,104,27,0,0 // movdqa 0x1b68(%rip),%xmm11 # 49a0 <_sk_callback_sse2+0xc79> + .byte 102,68,15,111,29,98,27,0,0 // movdqa 0x1b62(%rip),%xmm11 # 4920 <_sk_callback_sse2+0xc73> .byte 102,69,15,235,235 // por %xmm11,%xmm13 .byte 102,69,15,254,236 // paddd %xmm12,%xmm13 .byte 102,65,15,114,245,16 // pslld $0x10,%xmm13 @@ -26249,7 +26099,7 @@ _sk_load_u16_be_sse2: .byte 102,69,15,239,201 // pxor %xmm9,%xmm9 .byte 102,65,15,97,201 // punpcklwd %xmm9,%xmm1 .byte 15,91,193 // cvtdq2ps %xmm1,%xmm0 - .byte 68,15,40,5,6,26,0,0 // movaps 0x1a06(%rip),%xmm8 # 49b0 <_sk_callback_sse2+0xc89> + .byte 68,15,40,5,0,26,0,0 // movaps 0x1a00(%rip),%xmm8 # 4930 <_sk_callback_sse2+0xc83> .byte 65,15,89,192 // mulps %xmm8,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 .byte 102,15,113,241,8 // psllw $0x8,%xmm1 @@ -26302,7 +26152,7 @@ _sk_load_rgb_u16_be_sse2: .byte 102,69,15,239,192 // pxor %xmm8,%xmm8 .byte 102,65,15,97,192 // punpcklwd %xmm8,%xmm0 .byte 15,91,192 // cvtdq2ps %xmm0,%xmm0 - .byte 68,15,40,13,66,25,0,0 // movaps 0x1942(%rip),%xmm9 # 49c0 <_sk_callback_sse2+0xc99> + .byte 68,15,40,13,60,25,0,0 // movaps 0x193c(%rip),%xmm9 # 4940 <_sk_callback_sse2+0xc93> .byte 65,15,89,193 // mulps %xmm9,%xmm0 .byte 102,15,111,203 // movdqa %xmm3,%xmm1 .byte 102,15,113,241,8 // psllw $0x8,%xmm1 @@ -26319,7 +26169,7 @@ _sk_load_rgb_u16_be_sse2: .byte 15,91,210 // cvtdq2ps %xmm2,%xmm2 .byte 65,15,89,209 // mulps %xmm9,%xmm2 .byte 72,173 // lods %ds:(%rsi),%rax - .byte 15,40,29,9,25,0,0 // movaps 0x1909(%rip),%xmm3 # 49d0 <_sk_callback_sse2+0xca9> + .byte 15,40,29,3,25,0,0 // movaps 0x1903(%rip),%xmm3 # 4950 <_sk_callback_sse2+0xca3> .byte 255,224 // jmpq *%rax HIDDEN _sk_store_u16_be_sse2 @@ -26328,7 +26178,7 @@ FUNCTION(_sk_store_u16_be_sse2) _sk_store_u16_be_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 72,139,0 // mov (%rax),%rax - .byte 68,15,40,13,10,25,0,0 // movaps 0x190a(%rip),%xmm9 # 49e0 <_sk_callback_sse2+0xcb9> + .byte 68,15,40,13,4,25,0,0 // movaps 0x1904(%rip),%xmm9 # 4960 <_sk_callback_sse2+0xcb3> .byte 68,15,40,192 // movaps %xmm0,%xmm8 .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 102,69,15,91,192 // cvtps2dq %xmm8,%xmm8 @@ -26478,7 +26328,7 @@ _sk_repeat_x_sse2: .byte 243,69,15,91,209 // cvttps2dq %xmm9,%xmm10 .byte 69,15,91,210 // cvtdq2ps %xmm10,%xmm10 .byte 69,15,194,202,1 // cmpltps %xmm10,%xmm9 - .byte 68,15,84,13,244,22,0,0 // andps 0x16f4(%rip),%xmm9 # 49f0 <_sk_callback_sse2+0xcc9> + .byte 68,15,84,13,238,22,0,0 // andps 0x16ee(%rip),%xmm9 # 4970 <_sk_callback_sse2+0xcc3> .byte 69,15,92,209 // subps %xmm9,%xmm10 .byte 69,15,89,208 // mulps %xmm8,%xmm10 .byte 65,15,92,194 // subps %xmm10,%xmm0 @@ -26500,7 +26350,7 @@ _sk_repeat_y_sse2: .byte 243,69,15,91,209 // cvttps2dq %xmm9,%xmm10 .byte 69,15,91,210 // cvtdq2ps %xmm10,%xmm10 .byte 69,15,194,202,1 // cmpltps %xmm10,%xmm9 - .byte 68,15,84,13,188,22,0,0 // andps 0x16bc(%rip),%xmm9 # 4a00 <_sk_callback_sse2+0xcd9> + .byte 68,15,84,13,182,22,0,0 // andps 0x16b6(%rip),%xmm9 # 4980 <_sk_callback_sse2+0xcd3> .byte 69,15,92,209 // subps %xmm9,%xmm10 .byte 69,15,89,208 // mulps %xmm8,%xmm10 .byte 65,15,92,202 // subps %xmm10,%xmm1 @@ -26526,7 +26376,7 @@ _sk_mirror_x_sse2: .byte 243,69,15,91,218 // cvttps2dq %xmm10,%xmm11 .byte 69,15,91,219 // cvtdq2ps %xmm11,%xmm11 .byte 69,15,194,211,1 // cmpltps %xmm11,%xmm10 - .byte 68,15,84,21,114,22,0,0 // andps 0x1672(%rip),%xmm10 # 4a10 <_sk_callback_sse2+0xce9> + .byte 68,15,84,21,108,22,0,0 // andps 0x166c(%rip),%xmm10 # 4990 <_sk_callback_sse2+0xce3> .byte 69,15,87,228 // xorps %xmm12,%xmm12 .byte 69,15,92,218 // subps %xmm10,%xmm11 .byte 69,15,89,216 // mulps %xmm8,%xmm11 @@ -26556,7 +26406,7 @@ _sk_mirror_y_sse2: .byte 243,69,15,91,218 // cvttps2dq %xmm10,%xmm11 .byte 69,15,91,219 // cvtdq2ps %xmm11,%xmm11 .byte 69,15,194,211,1 // cmpltps %xmm11,%xmm10 - .byte 68,15,84,21,24,22,0,0 // andps 0x1618(%rip),%xmm10 # 4a20 <_sk_callback_sse2+0xcf9> + .byte 68,15,84,21,18,22,0,0 // andps 0x1612(%rip),%xmm10 # 49a0 <_sk_callback_sse2+0xcf3> .byte 69,15,87,228 // xorps %xmm12,%xmm12 .byte 69,15,92,218 // subps %xmm10,%xmm11 .byte 69,15,89,216 // mulps %xmm8,%xmm11 @@ -26575,10 +26425,10 @@ HIDDEN _sk_luminance_to_alpha_sse2 FUNCTION(_sk_luminance_to_alpha_sse2) _sk_luminance_to_alpha_sse2: .byte 15,40,218 // movaps %xmm2,%xmm3 - .byte 15,89,5,240,21,0,0 // mulps 0x15f0(%rip),%xmm0 # 4a30 <_sk_callback_sse2+0xd09> - .byte 15,89,13,249,21,0,0 // mulps 0x15f9(%rip),%xmm1 # 4a40 <_sk_callback_sse2+0xd19> + .byte 15,89,5,234,21,0,0 // mulps 0x15ea(%rip),%xmm0 # 49b0 <_sk_callback_sse2+0xd03> + .byte 15,89,13,243,21,0,0 // mulps 0x15f3(%rip),%xmm1 # 49c0 <_sk_callback_sse2+0xd13> .byte 15,88,200 // addps %xmm0,%xmm1 - .byte 15,89,29,255,21,0,0 // mulps 0x15ff(%rip),%xmm3 # 4a50 <_sk_callback_sse2+0xd29> + .byte 15,89,29,249,21,0,0 // mulps 0x15f9(%rip),%xmm3 # 49d0 <_sk_callback_sse2+0xd23> .byte 15,88,217 // addps %xmm1,%xmm3 .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,87,192 // xorps %xmm0,%xmm0 @@ -26811,7 +26661,7 @@ _sk_linear_gradient_sse2: .byte 69,15,198,228,0 // shufps $0x0,%xmm12,%xmm12 .byte 72,139,8 // mov (%rax),%rcx .byte 72,133,201 // test %rcx,%rcx - .byte 15,132,15,1,0,0 // je 3904 <_sk_linear_gradient_sse2+0x149> + .byte 15,132,15,1,0,0 // je 388a <_sk_linear_gradient_sse2+0x149> .byte 72,139,64,8 // mov 0x8(%rax),%rax .byte 72,131,192,32 // add $0x20,%rax .byte 69,15,87,192 // xorps %xmm8,%xmm8 @@ -26872,8 +26722,8 @@ _sk_linear_gradient_sse2: .byte 69,15,86,231 // orps %xmm15,%xmm12 .byte 72,131,192,36 // add $0x24,%rax .byte 72,255,201 // dec %rcx - .byte 15,133,8,255,255,255 // jne 380a <_sk_linear_gradient_sse2+0x4f> - .byte 235,13 // jmp 3911 <_sk_linear_gradient_sse2+0x156> + .byte 15,133,8,255,255,255 // jne 3790 <_sk_linear_gradient_sse2+0x4f> + .byte 235,13 // jmp 3897 <_sk_linear_gradient_sse2+0x156> .byte 15,87,201 // xorps %xmm1,%xmm1 .byte 15,87,210 // xorps %xmm2,%xmm2 .byte 15,87,219 // xorps %xmm3,%xmm3 @@ -26928,7 +26778,7 @@ HIDDEN _sk_save_xy_sse2 FUNCTION(_sk_save_xy_sse2) _sk_save_xy_sse2: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,176,16,0,0 // movaps 0x10b0(%rip),%xmm8 # 4a60 <_sk_callback_sse2+0xd39> + .byte 68,15,40,5,170,16,0,0 // movaps 0x10aa(%rip),%xmm8 # 49e0 <_sk_callback_sse2+0xd33> .byte 15,17,0 // movups %xmm0,(%rax) .byte 68,15,40,200 // movaps %xmm0,%xmm9 .byte 69,15,88,200 // addps %xmm8,%xmm9 @@ -26936,7 +26786,7 @@ _sk_save_xy_sse2: .byte 69,15,91,210 // cvtdq2ps %xmm10,%xmm10 .byte 69,15,40,217 // movaps %xmm9,%xmm11 .byte 69,15,194,218,1 // cmpltps %xmm10,%xmm11 - .byte 68,15,40,37,155,16,0,0 // movaps 0x109b(%rip),%xmm12 # 4a70 <_sk_callback_sse2+0xd49> + .byte 68,15,40,37,149,16,0,0 // movaps 0x1095(%rip),%xmm12 # 49f0 <_sk_callback_sse2+0xd43> .byte 69,15,84,220 // andps %xmm12,%xmm11 .byte 69,15,92,211 // subps %xmm11,%xmm10 .byte 69,15,92,202 // subps %xmm10,%xmm9 @@ -26983,8 +26833,8 @@ _sk_bilinear_nx_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,20,16,0,0 // addps 0x1014(%rip),%xmm0 # 4a80 <_sk_callback_sse2+0xd59> - .byte 68,15,40,13,28,16,0,0 // movaps 0x101c(%rip),%xmm9 # 4a90 <_sk_callback_sse2+0xd69> + .byte 15,88,5,14,16,0,0 // addps 0x100e(%rip),%xmm0 # 4a00 <_sk_callback_sse2+0xd53> + .byte 68,15,40,13,22,16,0,0 // movaps 0x1016(%rip),%xmm9 # 4a10 <_sk_callback_sse2+0xd63> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 68,15,17,136,128,0,0,0 // movups %xmm9,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -26997,7 +26847,7 @@ _sk_bilinear_px_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,11,16,0,0 // addps 0x100b(%rip),%xmm0 # 4aa0 <_sk_callback_sse2+0xd79> + .byte 15,88,5,5,16,0,0 // addps 0x1005(%rip),%xmm0 # 4a20 <_sk_callback_sse2+0xd73> .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -27009,8 +26859,8 @@ _sk_bilinear_ny_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,253,15,0,0 // addps 0xffd(%rip),%xmm1 # 4ab0 <_sk_callback_sse2+0xd89> - .byte 68,15,40,13,5,16,0,0 // movaps 0x1005(%rip),%xmm9 # 4ac0 <_sk_callback_sse2+0xd99> + .byte 15,88,13,247,15,0,0 // addps 0xff7(%rip),%xmm1 # 4a30 <_sk_callback_sse2+0xd83> + .byte 68,15,40,13,255,15,0,0 // movaps 0xfff(%rip),%xmm9 # 4a40 <_sk_callback_sse2+0xd93> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 68,15,17,136,160,0,0,0 // movups %xmm9,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -27023,7 +26873,7 @@ _sk_bilinear_py_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,243,15,0,0 // addps 0xff3(%rip),%xmm1 # 4ad0 <_sk_callback_sse2+0xda9> + .byte 15,88,13,237,15,0,0 // addps 0xfed(%rip),%xmm1 # 4a50 <_sk_callback_sse2+0xda3> .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -27035,13 +26885,13 @@ _sk_bicubic_n3x_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,230,15,0,0 // addps 0xfe6(%rip),%xmm0 # 4ae0 <_sk_callback_sse2+0xdb9> - .byte 68,15,40,13,238,15,0,0 // movaps 0xfee(%rip),%xmm9 # 4af0 <_sk_callback_sse2+0xdc9> + .byte 15,88,5,224,15,0,0 // addps 0xfe0(%rip),%xmm0 # 4a60 <_sk_callback_sse2+0xdb3> + .byte 68,15,40,13,232,15,0,0 // movaps 0xfe8(%rip),%xmm9 # 4a70 <_sk_callback_sse2+0xdc3> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 69,15,40,193 // movaps %xmm9,%xmm8 .byte 69,15,89,192 // mulps %xmm8,%xmm8 - .byte 68,15,89,13,234,15,0,0 // mulps 0xfea(%rip),%xmm9 # 4b00 <_sk_callback_sse2+0xdd9> - .byte 68,15,88,13,242,15,0,0 // addps 0xff2(%rip),%xmm9 # 4b10 <_sk_callback_sse2+0xde9> + .byte 68,15,89,13,228,15,0,0 // mulps 0xfe4(%rip),%xmm9 # 4a80 <_sk_callback_sse2+0xdd3> + .byte 68,15,88,13,236,15,0,0 // addps 0xfec(%rip),%xmm9 # 4a90 <_sk_callback_sse2+0xde3> .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 68,15,17,136,128,0,0,0 // movups %xmm9,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -27054,16 +26904,16 @@ _sk_bicubic_n1x_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,225,15,0,0 // addps 0xfe1(%rip),%xmm0 # 4b20 <_sk_callback_sse2+0xdf9> - .byte 68,15,40,13,233,15,0,0 // movaps 0xfe9(%rip),%xmm9 # 4b30 <_sk_callback_sse2+0xe09> + .byte 15,88,5,219,15,0,0 // addps 0xfdb(%rip),%xmm0 # 4aa0 <_sk_callback_sse2+0xdf3> + .byte 68,15,40,13,227,15,0,0 // movaps 0xfe3(%rip),%xmm9 # 4ab0 <_sk_callback_sse2+0xe03> .byte 69,15,92,200 // subps %xmm8,%xmm9 - .byte 68,15,40,5,237,15,0,0 // movaps 0xfed(%rip),%xmm8 # 4b40 <_sk_callback_sse2+0xe19> + .byte 68,15,40,5,231,15,0,0 // movaps 0xfe7(%rip),%xmm8 # 4ac0 <_sk_callback_sse2+0xe13> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,241,15,0,0 // addps 0xff1(%rip),%xmm8 # 4b50 <_sk_callback_sse2+0xe29> + .byte 68,15,88,5,235,15,0,0 // addps 0xfeb(%rip),%xmm8 # 4ad0 <_sk_callback_sse2+0xe23> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,245,15,0,0 // addps 0xff5(%rip),%xmm8 # 4b60 <_sk_callback_sse2+0xe39> + .byte 68,15,88,5,239,15,0,0 // addps 0xfef(%rip),%xmm8 # 4ae0 <_sk_callback_sse2+0xe33> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,249,15,0,0 // addps 0xff9(%rip),%xmm8 # 4b70 <_sk_callback_sse2+0xe49> + .byte 68,15,88,5,243,15,0,0 // addps 0xff3(%rip),%xmm8 # 4af0 <_sk_callback_sse2+0xe43> .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -27073,17 +26923,17 @@ HIDDEN _sk_bicubic_p1x_sse2 FUNCTION(_sk_bicubic_p1x_sse2) _sk_bicubic_p1x_sse2: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,243,15,0,0 // movaps 0xff3(%rip),%xmm8 # 4b80 <_sk_callback_sse2+0xe59> + .byte 68,15,40,5,237,15,0,0 // movaps 0xfed(%rip),%xmm8 # 4b00 <_sk_callback_sse2+0xe53> .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,72,64 // movups 0x40(%rax),%xmm9 .byte 65,15,88,192 // addps %xmm8,%xmm0 - .byte 68,15,40,21,239,15,0,0 // movaps 0xfef(%rip),%xmm10 # 4b90 <_sk_callback_sse2+0xe69> + .byte 68,15,40,21,233,15,0,0 // movaps 0xfe9(%rip),%xmm10 # 4b10 <_sk_callback_sse2+0xe63> .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,243,15,0,0 // addps 0xff3(%rip),%xmm10 # 4ba0 <_sk_callback_sse2+0xe79> + .byte 68,15,88,21,237,15,0,0 // addps 0xfed(%rip),%xmm10 # 4b20 <_sk_callback_sse2+0xe73> .byte 69,15,89,209 // mulps %xmm9,%xmm10 .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,239,15,0,0 // addps 0xfef(%rip),%xmm10 # 4bb0 <_sk_callback_sse2+0xe89> + .byte 68,15,88,21,233,15,0,0 // addps 0xfe9(%rip),%xmm10 # 4b30 <_sk_callback_sse2+0xe83> .byte 68,15,17,144,128,0,0,0 // movups %xmm10,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -27095,11 +26945,11 @@ _sk_bicubic_p3x_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,0 // movups (%rax),%xmm0 .byte 68,15,16,64,64 // movups 0x40(%rax),%xmm8 - .byte 15,88,5,226,15,0,0 // addps 0xfe2(%rip),%xmm0 # 4bc0 <_sk_callback_sse2+0xe99> + .byte 15,88,5,220,15,0,0 // addps 0xfdc(%rip),%xmm0 # 4b40 <_sk_callback_sse2+0xe93> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,89,201 // mulps %xmm9,%xmm9 - .byte 68,15,89,5,226,15,0,0 // mulps 0xfe2(%rip),%xmm8 # 4bd0 <_sk_callback_sse2+0xea9> - .byte 68,15,88,5,234,15,0,0 // addps 0xfea(%rip),%xmm8 # 4be0 <_sk_callback_sse2+0xeb9> + .byte 68,15,89,5,220,15,0,0 // mulps 0xfdc(%rip),%xmm8 # 4b50 <_sk_callback_sse2+0xea3> + .byte 68,15,88,5,228,15,0,0 // addps 0xfe4(%rip),%xmm8 # 4b60 <_sk_callback_sse2+0xeb3> .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 68,15,17,128,128,0,0,0 // movups %xmm8,0x80(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -27112,13 +26962,13 @@ _sk_bicubic_n3y_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,216,15,0,0 // addps 0xfd8(%rip),%xmm1 # 4bf0 <_sk_callback_sse2+0xec9> - .byte 68,15,40,13,224,15,0,0 // movaps 0xfe0(%rip),%xmm9 # 4c00 <_sk_callback_sse2+0xed9> + .byte 15,88,13,210,15,0,0 // addps 0xfd2(%rip),%xmm1 # 4b70 <_sk_callback_sse2+0xec3> + .byte 68,15,40,13,218,15,0,0 // movaps 0xfda(%rip),%xmm9 # 4b80 <_sk_callback_sse2+0xed3> .byte 69,15,92,200 // subps %xmm8,%xmm9 .byte 69,15,40,193 // movaps %xmm9,%xmm8 .byte 69,15,89,192 // mulps %xmm8,%xmm8 - .byte 68,15,89,13,220,15,0,0 // mulps 0xfdc(%rip),%xmm9 # 4c10 <_sk_callback_sse2+0xee9> - .byte 68,15,88,13,228,15,0,0 // addps 0xfe4(%rip),%xmm9 # 4c20 <_sk_callback_sse2+0xef9> + .byte 68,15,89,13,214,15,0,0 // mulps 0xfd6(%rip),%xmm9 # 4b90 <_sk_callback_sse2+0xee3> + .byte 68,15,88,13,222,15,0,0 // addps 0xfde(%rip),%xmm9 # 4ba0 <_sk_callback_sse2+0xef3> .byte 69,15,89,200 // mulps %xmm8,%xmm9 .byte 68,15,17,136,160,0,0,0 // movups %xmm9,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -27131,16 +26981,16 @@ _sk_bicubic_n1y_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,210,15,0,0 // addps 0xfd2(%rip),%xmm1 # 4c30 <_sk_callback_sse2+0xf09> - .byte 68,15,40,13,218,15,0,0 // movaps 0xfda(%rip),%xmm9 # 4c40 <_sk_callback_sse2+0xf19> + .byte 15,88,13,204,15,0,0 // addps 0xfcc(%rip),%xmm1 # 4bb0 <_sk_callback_sse2+0xf03> + .byte 68,15,40,13,212,15,0,0 // movaps 0xfd4(%rip),%xmm9 # 4bc0 <_sk_callback_sse2+0xf13> .byte 69,15,92,200 // subps %xmm8,%xmm9 - .byte 68,15,40,5,222,15,0,0 // movaps 0xfde(%rip),%xmm8 # 4c50 <_sk_callback_sse2+0xf29> + .byte 68,15,40,5,216,15,0,0 // movaps 0xfd8(%rip),%xmm8 # 4bd0 <_sk_callback_sse2+0xf23> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,226,15,0,0 // addps 0xfe2(%rip),%xmm8 # 4c60 <_sk_callback_sse2+0xf39> + .byte 68,15,88,5,220,15,0,0 // addps 0xfdc(%rip),%xmm8 # 4be0 <_sk_callback_sse2+0xf33> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,230,15,0,0 // addps 0xfe6(%rip),%xmm8 # 4c70 <_sk_callback_sse2+0xf49> + .byte 68,15,88,5,224,15,0,0 // addps 0xfe0(%rip),%xmm8 # 4bf0 <_sk_callback_sse2+0xf43> .byte 69,15,89,193 // mulps %xmm9,%xmm8 - .byte 68,15,88,5,234,15,0,0 // addps 0xfea(%rip),%xmm8 # 4c80 <_sk_callback_sse2+0xf59> + .byte 68,15,88,5,228,15,0,0 // addps 0xfe4(%rip),%xmm8 # 4c00 <_sk_callback_sse2+0xf53> .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -27150,17 +27000,17 @@ HIDDEN _sk_bicubic_p1y_sse2 FUNCTION(_sk_bicubic_p1y_sse2) _sk_bicubic_p1y_sse2: .byte 72,173 // lods %ds:(%rsi),%rax - .byte 68,15,40,5,228,15,0,0 // movaps 0xfe4(%rip),%xmm8 # 4c90 <_sk_callback_sse2+0xf69> + .byte 68,15,40,5,222,15,0,0 // movaps 0xfde(%rip),%xmm8 # 4c10 <_sk_callback_sse2+0xf63> .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,72,96 // movups 0x60(%rax),%xmm9 .byte 65,15,88,200 // addps %xmm8,%xmm1 - .byte 68,15,40,21,223,15,0,0 // movaps 0xfdf(%rip),%xmm10 # 4ca0 <_sk_callback_sse2+0xf79> + .byte 68,15,40,21,217,15,0,0 // movaps 0xfd9(%rip),%xmm10 # 4c20 <_sk_callback_sse2+0xf73> .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,227,15,0,0 // addps 0xfe3(%rip),%xmm10 # 4cb0 <_sk_callback_sse2+0xf89> + .byte 68,15,88,21,221,15,0,0 // addps 0xfdd(%rip),%xmm10 # 4c30 <_sk_callback_sse2+0xf83> .byte 69,15,89,209 // mulps %xmm9,%xmm10 .byte 69,15,88,208 // addps %xmm8,%xmm10 .byte 69,15,89,209 // mulps %xmm9,%xmm10 - .byte 68,15,88,21,223,15,0,0 // addps 0xfdf(%rip),%xmm10 # 4cc0 <_sk_callback_sse2+0xf99> + .byte 68,15,88,21,217,15,0,0 // addps 0xfd9(%rip),%xmm10 # 4c40 <_sk_callback_sse2+0xf93> .byte 68,15,17,144,160,0,0,0 // movups %xmm10,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax .byte 255,224 // jmpq *%rax @@ -27172,11 +27022,11 @@ _sk_bicubic_p3y_sse2: .byte 72,173 // lods %ds:(%rsi),%rax .byte 15,16,72,32 // movups 0x20(%rax),%xmm1 .byte 68,15,16,64,96 // movups 0x60(%rax),%xmm8 - .byte 15,88,13,209,15,0,0 // addps 0xfd1(%rip),%xmm1 # 4cd0 <_sk_callback_sse2+0xfa9> + .byte 15,88,13,203,15,0,0 // addps 0xfcb(%rip),%xmm1 # 4c50 <_sk_callback_sse2+0xfa3> .byte 69,15,40,200 // movaps %xmm8,%xmm9 .byte 69,15,89,201 // mulps %xmm9,%xmm9 - .byte 68,15,89,5,209,15,0,0 // mulps 0xfd1(%rip),%xmm8 # 4ce0 <_sk_callback_sse2+0xfb9> - .byte 68,15,88,5,217,15,0,0 // addps 0xfd9(%rip),%xmm8 # 4cf0 <_sk_callback_sse2+0xfc9> + .byte 68,15,89,5,203,15,0,0 // mulps 0xfcb(%rip),%xmm8 # 4c60 <_sk_callback_sse2+0xfb3> + .byte 68,15,88,5,211,15,0,0 // addps 0xfd3(%rip),%xmm8 # 4c70 <_sk_callback_sse2+0xfc3> .byte 69,15,89,193 // mulps %xmm9,%xmm8 .byte 68,15,17,128,160,0,0,0 // movups %xmm8,0xa0(%rax) .byte 72,173 // lods %ds:(%rsi),%rax @@ -27361,11 +27211,11 @@ BALIGN16 .byte 0,128,191,0,0,128 // add %al,-0x7fffff41(%rax) .byte 191,0,0,224,64 // mov $0x40e00000,%edi .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 3f88 <.literal16+0x188> + .byte 224,64 // loopne 3f18 <.literal16+0x188> .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 3f8c <.literal16+0x18c> + .byte 224,64 // loopne 3f1c <.literal16+0x18c> .byte 0,0 // add %al,(%rax) - .byte 224,64 // loopne 3f90 <.literal16+0x190> + .byte 224,64 // loopne 3f20 <.literal16+0x190> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -27504,12 +27354,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 0,0 // add %al,(%rax) - .byte 128,63,0 // cmpb $0x0,(%rdi) - .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) - .byte 63 // (bad) - .byte 0,0 // add %al,(%rax) - .byte 128,63,171 // cmpb $0xab,(%rdi) + .byte 171 // stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) .byte 62,171 // ds stos %eax,%es:(%rdi) @@ -27522,25 +27367,20 @@ BALIGN16 .byte 170 // stos %al,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) .byte 62,0,0 // add %al,%ds:(%rax) - .byte 128,191,0,0,128,191,0 // cmpb $0x0,-0x40800000(%rdi) - .byte 0,128,191,0,0,128 // add %al,-0x7fffff41(%rax) - .byte 191,0,0,192,64 // mov $0x40c00000,%edi + .byte 128,63,0 // cmpb $0x0,(%rdi) + .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) + .byte 63 // (bad) .byte 0,0 // add %al,(%rax) + .byte 128,63,0 // cmpb $0x0,(%rdi) + .byte 0,192 // add %al,%al + .byte 64,0,0 // add %al,(%rax) .byte 192,64,0,0 // rolb $0x0,0x0(%rax) .byte 192,64,0,0 // rolb $0x0,0x0(%rax) - .byte 192,64,171,170 // rolb $0xaa,-0x55(%rax) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) - .byte 42,63 // sub (%rdi),%bh - .byte 171 // stos %eax,%es:(%rdi) - .byte 170 // stos %al,%es:(%rdi) + .byte 192,64,0,0 // rolb $0x0,0x0(%rax) + .byte 128,64,0,0 // addb $0x0,0x0(%rax) + .byte 128,64,0,0 // addb $0x0,0x0(%rax) + .byte 128,64,0,0 // addb $0x0,0x0(%rax) + .byte 128,64,171,170 // addb $0xaa,-0x55(%rax) .byte 170 // stos %al,%es:(%rdi) .byte 190,171,170,170,190 // mov $0xbeaaaaab,%esi .byte 171 // stos %eax,%es:(%rdi) @@ -27568,13 +27408,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 4139 <.literal16+0x339> + .byte 224,7 // loopne 40b9 <.literal16+0x329> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 413d <.literal16+0x33d> + .byte 224,7 // loopne 40bd <.literal16+0x32d> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4141 <.literal16+0x341> + .byte 224,7 // loopne 40c1 <.literal16+0x331> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4145 <.literal16+0x345> + .byte 224,7 // loopne 40c5 <.literal16+0x335> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -27643,11 +27483,11 @@ BALIGN16 .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 422b <.literal16+0x42b> + .byte 127,67 // jg 41ab <.literal16+0x41b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 422f <.literal16+0x42f> + .byte 127,67 // jg 41af <.literal16+0x41f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4233 <.literal16+0x433> + .byte 127,67 // jg 41b3 <.literal16+0x423> .byte 129,128,128,59,129,128,128,59,129,128// addl $0x80813b80,-0x7f7ec480(%rax) .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,129,128,128,59 // addb $0x3b,-0x7f7f7ec5(%rax) @@ -27662,16 +27502,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4224 <.literal16+0x424> + .byte 127,0 // jg 41a4 <.literal16+0x414> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4228 <.literal16+0x428> + .byte 127,0 // jg 41a8 <.literal16+0x418> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 422c <.literal16+0x42c> + .byte 127,0 // jg 41ac <.literal16+0x41c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4230 <.literal16+0x430> + .byte 127,0 // jg 41b0 <.literal16+0x420> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -27680,7 +27520,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 42b5 <.literal16+0x4b5> + .byte 119,115 // ja 4235 <.literal16+0x4a5> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -27691,7 +27531,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 4219 <.literal16+0x419> + .byte 117,191 // jne 4199 <.literal16+0x409> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -27703,7 +27543,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a3825a <_sk_callback_sse2+0xffffffffe9a34533> + .byte 233,220,63,163,233 // jmpq ffffffffe9a381da <_sk_callback_sse2+0xffffffffe9a3452d> .byte 220,63 // fdivrl (%rdi) .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) @@ -27757,16 +27597,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 42f4 <.literal16+0x4f4> + .byte 127,0 // jg 4274 <.literal16+0x4e4> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 42f8 <.literal16+0x4f8> + .byte 127,0 // jg 4278 <.literal16+0x4e8> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 42fc <.literal16+0x4fc> + .byte 127,0 // jg 427c <.literal16+0x4ec> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4300 <.literal16+0x500> + .byte 127,0 // jg 4280 <.literal16+0x4f0> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -27775,7 +27615,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4385 <.literal16+0x585> + .byte 119,115 // ja 4305 <.literal16+0x575> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -27786,7 +27626,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 42e9 <.literal16+0x4e9> + .byte 117,191 // jne 4269 <.literal16+0x4d9> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -27798,7 +27638,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a3832a <_sk_callback_sse2+0xffffffffe9a34603> + .byte 233,220,63,163,233 // jmpq ffffffffe9a382aa <_sk_callback_sse2+0xffffffffe9a345fd> .byte 220,63 // fdivrl (%rdi) .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) @@ -27852,16 +27692,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 43c4 <.literal16+0x5c4> + .byte 127,0 // jg 4344 <.literal16+0x5b4> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 43c8 <.literal16+0x5c8> + .byte 127,0 // jg 4348 <.literal16+0x5b8> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 43cc <.literal16+0x5cc> + .byte 127,0 // jg 434c <.literal16+0x5bc> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 43d0 <.literal16+0x5d0> + .byte 127,0 // jg 4350 <.literal16+0x5c0> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -27870,7 +27710,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4455 <.literal16+0x655> + .byte 119,115 // ja 43d5 <.literal16+0x645> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -27881,7 +27721,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 43b9 <.literal16+0x5b9> + .byte 117,191 // jne 4339 <.literal16+0x5a9> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -27893,7 +27733,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a383fa <_sk_callback_sse2+0xffffffffe9a346d3> + .byte 233,220,63,163,233 // jmpq ffffffffe9a3837a <_sk_callback_sse2+0xffffffffe9a346cd> .byte 220,63 // fdivrl (%rdi) .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) @@ -27947,16 +27787,16 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 52,255 // xor $0xff,%al .byte 255 // (bad) - .byte 127,0 // jg 4494 <.literal16+0x694> + .byte 127,0 // jg 4414 <.literal16+0x684> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 4498 <.literal16+0x698> + .byte 127,0 // jg 4418 <.literal16+0x688> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 449c <.literal16+0x69c> + .byte 127,0 // jg 441c <.literal16+0x68c> .byte 255 // (bad) .byte 255 // (bad) - .byte 127,0 // jg 44a0 <.literal16+0x6a0> + .byte 127,0 // jg 4420 <.literal16+0x690> .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -27965,7 +27805,7 @@ BALIGN16 .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) - .byte 119,115 // ja 4525 <.literal16+0x725> + .byte 119,115 // ja 44a5 <.literal16+0x715> .byte 248 // clc .byte 194,119,115 // retq $0x7377 .byte 248 // clc @@ -27976,7 +27816,7 @@ BALIGN16 .byte 194,117,191 // retq $0xbf75 .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) - .byte 117,191 // jne 4489 <.literal16+0x689> + .byte 117,191 // jne 4409 <.literal16+0x679> .byte 191,63,117,191,191 // mov $0xbfbf753f,%edi .byte 63 // (bad) .byte 249 // stc @@ -27988,7 +27828,7 @@ BALIGN16 .byte 249 // stc .byte 68,180,62 // rex.R mov $0x3e,%spl .byte 163,233,220,63,163,233,220,63,163 // movabs %eax,0xa33fdce9a33fdce9 - .byte 233,220,63,163,233 // jmpq ffffffffe9a384ca <_sk_callback_sse2+0xffffffffe9a347a3> + .byte 233,220,63,163,233 // jmpq ffffffffe9a3844a <_sk_callback_sse2+0xffffffffe9a3479d> .byte 220,63 // fdivrl (%rdi) .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) @@ -28038,13 +27878,13 @@ BALIGN16 .byte 200,66,0,0 // enterq $0x42,$0x0 .byte 200,66,0,0 // enterq $0x42,$0x0 .byte 200,66,0,0 // enterq $0x42,$0x0 - .byte 127,67 // jg 45a7 <.literal16+0x7a7> + .byte 127,67 // jg 4527 <.literal16+0x797> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 45ab <.literal16+0x7ab> + .byte 127,67 // jg 452b <.literal16+0x79b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 45af <.literal16+0x7af> + .byte 127,67 // jg 452f <.literal16+0x79f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 45b3 <.literal16+0x7b3> + .byte 127,67 // jg 4533 <.literal16+0x7a3> .byte 0,0 // add %al,(%rax) .byte 0,195 // add %al,%bl .byte 0,0 // add %al,(%rax) @@ -28091,16 +27931,16 @@ BALIGN16 .byte 128,3,62 // addb $0x3e,(%rbx) .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 4633 <.literal16+0x833> + .byte 118,63 // jbe 45b3 <.literal16+0x823> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 4637 <.literal16+0x837> + .byte 118,63 // jbe 45b7 <.literal16+0x827> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 463b <.literal16+0x83b> + .byte 118,63 // jbe 45bb <.literal16+0x82b> .byte 31 // (bad) .byte 215 // xlat %ds:(%rbx) - .byte 118,63 // jbe 463f <.literal16+0x83f> + .byte 118,63 // jbe 45bf <.literal16+0x82f> .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 246,64,83,63 // testb $0x3f,0x53(%rax) .byte 246,64,83,63 // testb $0x3f,0x53(%rax) @@ -28112,11 +27952,11 @@ BALIGN16 .byte 128,59,0 // cmpb $0x0,(%rbx) .byte 0,127,67 // add %bh,0x43(%rdi) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 467b <.literal16+0x87b> + .byte 127,67 // jg 45fb <.literal16+0x86b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 467f <.literal16+0x87f> + .byte 127,67 // jg 45ff <.literal16+0x86f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4683 <.literal16+0x883> + .byte 127,67 // jg 4603 <.literal16+0x873> .byte 129,128,128,59,129,128,128,59,129,128// addl $0x80813b80,-0x7f7ec480(%rax) .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,0,0,128,63 // addb $0x3f,-0x7fffffc5(%rax) @@ -28156,13 +27996,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 46c9 <.literal16+0x8c9> + .byte 224,7 // loopne 4649 <.literal16+0x8b9> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 46cd <.literal16+0x8cd> + .byte 224,7 // loopne 464d <.literal16+0x8bd> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 46d1 <.literal16+0x8d1> + .byte 224,7 // loopne 4651 <.literal16+0x8c1> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 46d5 <.literal16+0x8d5> + .byte 224,7 // loopne 4655 <.literal16+0x8c5> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -28208,13 +28048,13 @@ BALIGN16 .byte 132,55 // test %dh,(%rdi) .byte 8,33 // or %ah,(%rcx) .byte 132,55 // test %dh,(%rdi) - .byte 224,7 // loopne 4739 <.literal16+0x939> + .byte 224,7 // loopne 46b9 <.literal16+0x929> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 473d <.literal16+0x93d> + .byte 224,7 // loopne 46bd <.literal16+0x92d> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4741 <.literal16+0x941> + .byte 224,7 // loopne 46c1 <.literal16+0x931> .byte 0,0 // add %al,(%rax) - .byte 224,7 // loopne 4745 <.literal16+0x945> + .byte 224,7 // loopne 46c5 <.literal16+0x935> .byte 0,0 // add %al,(%rax) .byte 33,8 // and %ecx,(%rax) .byte 2,58 // add (%rdx),%bh @@ -28252,13 +28092,13 @@ BALIGN16 .byte 65,0,0 // add %al,(%r8) .byte 248 // clc .byte 65,0,0 // add %al,(%r8) - .byte 124,66 // jl 47d6 <.literal16+0x9d6> + .byte 124,66 // jl 4756 <.literal16+0x9c6> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 47da <.literal16+0x9da> + .byte 124,66 // jl 475a <.literal16+0x9ca> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 47de <.literal16+0x9de> + .byte 124,66 // jl 475e <.literal16+0x9ce> .byte 0,0 // add %al,(%rax) - .byte 124,66 // jl 47e2 <.literal16+0x9e2> + .byte 124,66 // jl 4762 <.literal16+0x9d2> .byte 0,240 // add %dh,%al .byte 0,0 // add %al,(%rax) .byte 0,240 // add %dh,%al @@ -28348,13 +28188,13 @@ BALIGN16 .byte 136,136,61,137,136,136 // mov %cl,-0x777776c3(%rax) .byte 61,137,136,136,61 // cmp $0x3d888889,%eax .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 48e5 <.literal16+0xae5> + .byte 112,65 // jo 4865 <.literal16+0xad5> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 48e9 <.literal16+0xae9> + .byte 112,65 // jo 4869 <.literal16+0xad9> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 48ed <.literal16+0xaed> + .byte 112,65 // jo 486d <.literal16+0xadd> .byte 0,0 // add %al,(%rax) - .byte 112,65 // jo 48f1 <.literal16+0xaf1> + .byte 112,65 // jo 4871 <.literal16+0xae1> .byte 255,0 // incl (%rax) .byte 0,0 // add %al,(%rax) .byte 255,0 // incl (%rax) @@ -28376,11 +28216,11 @@ BALIGN16 .byte 128,59,129 // cmpb $0x81,(%rbx) .byte 128,128,59,0,0,127,67 // addb $0x43,0x7f00003b(%rax) .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 493b <.literal16+0xb3b> + .byte 127,67 // jg 48bb <.literal16+0xb2b> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 493f <.literal16+0xb3f> + .byte 127,67 // jg 48bf <.literal16+0xb2f> .byte 0,0 // add %al,(%rax) - .byte 127,67 // jg 4943 <.literal16+0xb43> + .byte 127,67 // jg 48c3 <.literal16+0xb33> .byte 0,128,0,0,0,128 // add %al,-0x80000000(%rax) .byte 0,0 // add %al,(%rax) .byte 0,128,0,0,0,128 // add %al,-0x80000000(%rax) @@ -28456,13 +28296,13 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 255 // (bad) - .byte 127,71 // jg 4a2b <.literal16+0xc2b> + .byte 127,71 // jg 49ab <.literal16+0xc1b> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 4a2f <.literal16+0xc2f> + .byte 127,71 // jg 49af <.literal16+0xc1f> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 4a33 <.literal16+0xc33> + .byte 127,71 // jg 49b3 <.literal16+0xc23> .byte 0,255 // add %bh,%bh - .byte 127,71 // jg 4a37 <.literal16+0xc37> + .byte 127,71 // jg 49b7 <.literal16+0xc27> .byte 0,0 // add %al,(%rax) .byte 128,63,0 // cmpb $0x0,(%rdi) .byte 0,128,63,0,0,128 // add %al,-0x7fffffc1(%rax) @@ -28573,11 +28413,11 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,114 // cmpb $0x72,(%rdi) .byte 28,199 // sbb $0xc7,%al - .byte 62,114,28 // jb,pt 4b22 <.literal16+0xd22> + .byte 62,114,28 // jb,pt 4aa2 <.literal16+0xd12> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4b26 <.literal16+0xd26> + .byte 62,114,28 // jb,pt 4aa6 <.literal16+0xd16> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4b2a <.literal16+0xd2a> + .byte 62,114,28 // jb,pt 4aaa <.literal16+0xd1a> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -28621,7 +28461,7 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d9b5 <_sk_callback_sse2+0x3d639c8e> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d935 <_sk_callback_sse2+0x3d639c88> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -28647,7 +28487,7 @@ BALIGN16 .byte 0,192 // add %al,%al .byte 63 // (bad) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d9f5 <_sk_callback_sse2+0x3d639cce> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63d975 <_sk_callback_sse2+0x3d639cc8> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al @@ -28656,13 +28496,13 @@ BALIGN16 .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al .byte 63 // (bad) - .byte 114,28 // jb 4bee <.literal16+0xdee> + .byte 114,28 // jb 4b6e <.literal16+0xdde> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4bf2 <.literal16+0xdf2> + .byte 62,114,28 // jb,pt 4b72 <.literal16+0xde2> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4bf6 <.literal16+0xdf6> + .byte 62,114,28 // jb,pt 4b76 <.literal16+0xde6> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4bfa <.literal16+0xdfa> + .byte 62,114,28 // jb,pt 4b7a <.literal16+0xdea> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -28683,11 +28523,11 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 128,63,114 // cmpb $0x72,(%rdi) .byte 28,199 // sbb $0xc7,%al - .byte 62,114,28 // jb,pt 4c32 <.literal16+0xe32> + .byte 62,114,28 // jb,pt 4bb2 <.literal16+0xe22> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4c36 <.literal16+0xe36> + .byte 62,114,28 // jb,pt 4bb6 <.literal16+0xe26> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4c3a <.literal16+0xe3a> + .byte 62,114,28 // jb,pt 4bba <.literal16+0xe2a> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) @@ -28731,7 +28571,7 @@ BALIGN16 .byte 0,0 // add %al,(%rax) .byte 0,63 // add %bh,(%rdi) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63dac5 <_sk_callback_sse2+0x3d639d9e> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63da45 <_sk_callback_sse2+0x3d639d98> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 0,63 // add %bh,(%rdi) .byte 0,0 // add %al,(%rax) @@ -28757,7 +28597,7 @@ BALIGN16 .byte 0,192 // add %al,%al .byte 63 // (bad) .byte 57,142,99,61,57,142 // cmp %ecx,-0x71c6c29d(%rsi) - .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63db05 <_sk_callback_sse2+0x3d639dde> + .byte 99,61,57,142,99,61 // movslq 0x3d638e39(%rip),%edi # 3d63da85 <_sk_callback_sse2+0x3d639dd8> .byte 57,142,99,61,0,0 // cmp %ecx,0x3d63(%rsi) .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al @@ -28766,13 +28606,13 @@ BALIGN16 .byte 192,63,0 // sarb $0x0,(%rdi) .byte 0,192 // add %al,%al .byte 63 // (bad) - .byte 114,28 // jb 4cfe <.literal16+0xefe> + .byte 114,28 // jb 4c7e <.literal16+0xeee> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4d02 <_sk_callback_sse2+0xfdb> + .byte 62,114,28 // jb,pt 4c82 <_sk_callback_sse2+0xfd5> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4d06 <_sk_callback_sse2+0xfdf> + .byte 62,114,28 // jb,pt 4c86 <_sk_callback_sse2+0xfd9> .byte 199 // (bad) - .byte 62,114,28 // jb,pt 4d0a <_sk_callback_sse2+0xfe3> + .byte 62,114,28 // jb,pt 4c8a <_sk_callback_sse2+0xfdd> .byte 199 // (bad) .byte 62,171 // ds stos %eax,%es:(%rdi) .byte 170 // stos %al,%es:(%rdi) diff --git a/src/jumper/SkJumper_generated_win.S b/src/jumper/SkJumper_generated_win.S index 7e067eb89a..8465ca5031 100644 --- a/src/jumper/SkJumper_generated_win.S +++ b/src/jumper/SkJumper_generated_win.S @@ -106,14 +106,14 @@ _sk_seed_shader_hsw LABEL PROC DB 197,249,110,199 ; vmovd %edi,%xmm0 DB 196,226,125,88,192 ; vpbroadcastd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,186,60,0,0 ; vbroadcastss 0x3cba(%rip),%ymm1 # 3e14 <_sk_callback_hsw+0x119> + DB 196,226,125,24,13,58,60,0,0 ; vbroadcastss 0x3c3a(%rip),%ymm1 # 3d94 <_sk_callback_hsw+0x119> DB 197,252,88,193 ; vaddps %ymm1,%ymm0,%ymm0 DB 197,252,88,2 ; vaddps (%rdx),%ymm0,%ymm0 DB 196,226,125,24,16 ; vbroadcastss (%rax),%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 197,236,88,201 ; vaddps %ymm1,%ymm2,%ymm1 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,21,158,60,0,0 ; vbroadcastss 0x3c9e(%rip),%ymm2 # 3e18 <_sk_callback_hsw+0x11d> + DB 196,226,125,24,21,30,60,0,0 ; vbroadcastss 0x3c1e(%rip),%ymm2 # 3d98 <_sk_callback_hsw+0x11d> DB 197,228,87,219 ; vxorps %ymm3,%ymm3,%ymm3 DB 197,220,87,228 ; vxorps %ymm4,%ymm4,%ymm4 DB 197,212,87,237 ; vxorps %ymm5,%ymm5,%ymm5 @@ -143,7 +143,7 @@ _sk_clear_hsw LABEL PROC PUBLIC _sk_srcatop_hsw _sk_srcatop_hsw LABEL PROC DB 197,252,89,199 ; vmulps %ymm7,%ymm0,%ymm0 - DB 196,98,125,24,5,78,60,0,0 ; vbroadcastss 0x3c4e(%rip),%ymm8 # 3e1c <_sk_callback_hsw+0x121> + DB 196,98,125,24,5,206,59,0,0 ; vbroadcastss 0x3bce(%rip),%ymm8 # 3d9c <_sk_callback_hsw+0x121> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,226,61,184,196 ; vfmadd231ps %ymm4,%ymm8,%ymm0 DB 197,244,89,207 ; vmulps %ymm7,%ymm1,%ymm1 @@ -157,7 +157,7 @@ _sk_srcatop_hsw LABEL PROC PUBLIC _sk_dstatop_hsw _sk_dstatop_hsw LABEL PROC - DB 196,98,125,24,5,33,60,0,0 ; vbroadcastss 0x3c21(%rip),%ymm8 # 3e20 <_sk_callback_hsw+0x125> + DB 196,98,125,24,5,161,59,0,0 ; vbroadcastss 0x3ba1(%rip),%ymm8 # 3da0 <_sk_callback_hsw+0x125> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 196,226,101,184,196 ; vfmadd231ps %ymm4,%ymm3,%ymm0 @@ -190,7 +190,7 @@ _sk_dstin_hsw LABEL PROC PUBLIC _sk_srcout_hsw _sk_srcout_hsw LABEL PROC - DB 196,98,125,24,5,200,59,0,0 ; vbroadcastss 0x3bc8(%rip),%ymm8 # 3e24 <_sk_callback_hsw+0x129> + DB 196,98,125,24,5,72,59,0,0 ; vbroadcastss 0x3b48(%rip),%ymm8 # 3da4 <_sk_callback_hsw+0x129> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 @@ -201,7 +201,7 @@ _sk_srcout_hsw LABEL PROC PUBLIC _sk_dstout_hsw _sk_dstout_hsw LABEL PROC - DB 196,226,125,24,5,171,59,0,0 ; vbroadcastss 0x3bab(%rip),%ymm0 # 3e28 <_sk_callback_hsw+0x12d> + DB 196,226,125,24,5,43,59,0,0 ; vbroadcastss 0x3b2b(%rip),%ymm0 # 3da8 <_sk_callback_hsw+0x12d> DB 197,252,92,219 ; vsubps %ymm3,%ymm0,%ymm3 DB 197,228,89,196 ; vmulps %ymm4,%ymm3,%ymm0 DB 197,228,89,205 ; vmulps %ymm5,%ymm3,%ymm1 @@ -212,7 +212,7 @@ _sk_dstout_hsw LABEL PROC PUBLIC _sk_srcover_hsw _sk_srcover_hsw LABEL PROC - DB 196,98,125,24,5,142,59,0,0 ; vbroadcastss 0x3b8e(%rip),%ymm8 # 3e2c <_sk_callback_hsw+0x131> + DB 196,98,125,24,5,14,59,0,0 ; vbroadcastss 0x3b0e(%rip),%ymm8 # 3dac <_sk_callback_hsw+0x131> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,93,184,192 ; vfmadd231ps %ymm8,%ymm4,%ymm0 DB 196,194,85,184,200 ; vfmadd231ps %ymm8,%ymm5,%ymm1 @@ -223,7 +223,7 @@ _sk_srcover_hsw LABEL PROC PUBLIC _sk_dstover_hsw _sk_dstover_hsw LABEL PROC - DB 196,98,125,24,5,109,59,0,0 ; vbroadcastss 0x3b6d(%rip),%ymm8 # 3e30 <_sk_callback_hsw+0x135> + DB 196,98,125,24,5,237,58,0,0 ; vbroadcastss 0x3aed(%rip),%ymm8 # 3db0 <_sk_callback_hsw+0x135> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 196,226,61,168,196 ; vfmadd213ps %ymm4,%ymm8,%ymm0 DB 196,226,61,168,205 ; vfmadd213ps %ymm5,%ymm8,%ymm1 @@ -243,7 +243,7 @@ _sk_modulate_hsw LABEL PROC PUBLIC _sk_multiply_hsw _sk_multiply_hsw LABEL PROC - DB 196,98,125,24,5,56,59,0,0 ; vbroadcastss 0x3b38(%rip),%ymm8 # 3e34 <_sk_callback_hsw+0x139> + DB 196,98,125,24,5,184,58,0,0 ; vbroadcastss 0x3ab8(%rip),%ymm8 # 3db4 <_sk_callback_hsw+0x139> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,52,89,208 ; vmulps %ymm0,%ymm9,%ymm10 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -285,7 +285,7 @@ _sk_screen_hsw LABEL PROC PUBLIC _sk_xor__hsw _sk_xor__hsw LABEL PROC - DB 196,98,125,24,5,179,58,0,0 ; vbroadcastss 0x3ab3(%rip),%ymm8 # 3e38 <_sk_callback_hsw+0x13d> + DB 196,98,125,24,5,51,58,0,0 ; vbroadcastss 0x3a33(%rip),%ymm8 # 3db8 <_sk_callback_hsw+0x13d> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,180,89,192 ; vmulps %ymm0,%ymm9,%ymm0 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -317,7 +317,7 @@ _sk_darken_hsw LABEL PROC DB 197,100,89,206 ; vmulps %ymm6,%ymm3,%ymm9 DB 196,193,108,95,209 ; vmaxps %ymm9,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,59,58,0,0 ; vbroadcastss 0x3a3b(%rip),%ymm8 # 3e3c <_sk_callback_hsw+0x141> + DB 196,98,125,24,5,187,57,0,0 ; vbroadcastss 0x39bb(%rip),%ymm8 # 3dbc <_sk_callback_hsw+0x141> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,69,184,216 ; vfmadd231ps %ymm8,%ymm7,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -340,7 +340,7 @@ _sk_lighten_hsw LABEL PROC DB 197,100,89,206 ; vmulps %ymm6,%ymm3,%ymm9 DB 196,193,108,93,209 ; vminps %ymm9,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,234,57,0,0 ; vbroadcastss 0x39ea(%rip),%ymm8 # 3e40 <_sk_callback_hsw+0x145> + DB 196,98,125,24,5,106,57,0,0 ; vbroadcastss 0x396a(%rip),%ymm8 # 3dc0 <_sk_callback_hsw+0x145> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,69,184,216 ; vfmadd231ps %ymm8,%ymm7,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -366,7 +366,7 @@ _sk_difference_hsw LABEL PROC DB 196,193,108,93,209 ; vminps %ymm9,%ymm2,%ymm2 DB 197,236,88,210 ; vaddps %ymm2,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,141,57,0,0 ; vbroadcastss 0x398d(%rip),%ymm8 # 3e44 <_sk_callback_hsw+0x149> + DB 196,98,125,24,5,13,57,0,0 ; vbroadcastss 0x390d(%rip),%ymm8 # 3dc4 <_sk_callback_hsw+0x149> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,69,184,216 ; vfmadd231ps %ymm8,%ymm7,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -386,7 +386,7 @@ _sk_exclusion_hsw LABEL PROC DB 197,236,89,214 ; vmulps %ymm6,%ymm2,%ymm2 DB 197,236,88,210 ; vaddps %ymm2,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,75,57,0,0 ; vbroadcastss 0x394b(%rip),%ymm8 # 3e48 <_sk_callback_hsw+0x14d> + DB 196,98,125,24,5,203,56,0,0 ; vbroadcastss 0x38cb(%rip),%ymm8 # 3dc8 <_sk_callback_hsw+0x14d> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 196,194,69,184,216 ; vfmadd231ps %ymm8,%ymm7,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -394,7 +394,7 @@ _sk_exclusion_hsw LABEL PROC PUBLIC _sk_colorburn_hsw _sk_colorburn_hsw LABEL PROC - DB 196,98,125,24,5,57,57,0,0 ; vbroadcastss 0x3939(%rip),%ymm8 # 3e4c <_sk_callback_hsw+0x151> + DB 196,98,125,24,5,185,56,0,0 ; vbroadcastss 0x38b9(%rip),%ymm8 # 3dcc <_sk_callback_hsw+0x151> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,52,89,216 ; vmulps %ymm0,%ymm9,%ymm11 DB 196,65,44,87,210 ; vxorps %ymm10,%ymm10,%ymm10 @@ -450,7 +450,7 @@ _sk_colorburn_hsw LABEL PROC PUBLIC _sk_colordodge_hsw _sk_colordodge_hsw LABEL PROC DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 - DB 196,98,125,24,13,68,56,0,0 ; vbroadcastss 0x3844(%rip),%ymm9 # 3e50 <_sk_callback_hsw+0x155> + DB 196,98,125,24,13,196,55,0,0 ; vbroadcastss 0x37c4(%rip),%ymm9 # 3dd0 <_sk_callback_hsw+0x155> DB 197,52,92,215 ; vsubps %ymm7,%ymm9,%ymm10 DB 197,44,89,216 ; vmulps %ymm0,%ymm10,%ymm11 DB 197,52,92,203 ; vsubps %ymm3,%ymm9,%ymm9 @@ -501,7 +501,7 @@ _sk_colordodge_hsw LABEL PROC PUBLIC _sk_hardlight_hsw _sk_hardlight_hsw LABEL PROC - DB 196,98,125,24,5,101,55,0,0 ; vbroadcastss 0x3765(%rip),%ymm8 # 3e54 <_sk_callback_hsw+0x159> + DB 196,98,125,24,5,229,54,0,0 ; vbroadcastss 0x36e5(%rip),%ymm8 # 3dd4 <_sk_callback_hsw+0x159> DB 197,60,92,215 ; vsubps %ymm7,%ymm8,%ymm10 DB 197,44,89,216 ; vmulps %ymm0,%ymm10,%ymm11 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -550,7 +550,7 @@ _sk_hardlight_hsw LABEL PROC PUBLIC _sk_overlay_hsw _sk_overlay_hsw LABEL PROC - DB 196,98,125,24,5,157,54,0,0 ; vbroadcastss 0x369d(%rip),%ymm8 # 3e58 <_sk_callback_hsw+0x15d> + DB 196,98,125,24,5,29,54,0,0 ; vbroadcastss 0x361d(%rip),%ymm8 # 3dd8 <_sk_callback_hsw+0x15d> DB 197,60,92,215 ; vsubps %ymm7,%ymm8,%ymm10 DB 197,44,89,216 ; vmulps %ymm0,%ymm10,%ymm11 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -610,10 +610,10 @@ _sk_softlight_hsw LABEL PROC DB 196,65,20,88,197 ; vaddps %ymm13,%ymm13,%ymm8 DB 196,65,60,88,192 ; vaddps %ymm8,%ymm8,%ymm8 DB 196,66,61,168,192 ; vfmadd213ps %ymm8,%ymm8,%ymm8 - DB 196,98,125,24,29,164,53,0,0 ; vbroadcastss 0x35a4(%rip),%ymm11 # 3e60 <_sk_callback_hsw+0x165> + DB 196,98,125,24,29,36,53,0,0 ; vbroadcastss 0x3524(%rip),%ymm11 # 3de0 <_sk_callback_hsw+0x165> DB 196,65,20,88,227 ; vaddps %ymm11,%ymm13,%ymm12 DB 196,65,28,89,192 ; vmulps %ymm8,%ymm12,%ymm8 - DB 196,98,125,24,37,149,53,0,0 ; vbroadcastss 0x3595(%rip),%ymm12 # 3e64 <_sk_callback_hsw+0x169> + DB 196,98,125,24,37,21,53,0,0 ; vbroadcastss 0x3515(%rip),%ymm12 # 3de4 <_sk_callback_hsw+0x169> DB 196,66,21,184,196 ; vfmadd231ps %ymm12,%ymm13,%ymm8 DB 196,65,124,82,245 ; vrsqrtps %ymm13,%ymm14 DB 196,65,124,83,246 ; vrcpps %ymm14,%ymm14 @@ -623,7 +623,7 @@ _sk_softlight_hsw LABEL PROC DB 197,4,194,255,2 ; vcmpleps %ymm7,%ymm15,%ymm15 DB 196,67,13,74,240,240 ; vblendvps %ymm15,%ymm8,%ymm14,%ymm14 DB 197,116,88,249 ; vaddps %ymm1,%ymm1,%ymm15 - DB 196,98,125,24,5,88,53,0,0 ; vbroadcastss 0x3558(%rip),%ymm8 # 3e5c <_sk_callback_hsw+0x161> + DB 196,98,125,24,5,216,52,0,0 ; vbroadcastss 0x34d8(%rip),%ymm8 # 3ddc <_sk_callback_hsw+0x161> DB 196,65,60,92,237 ; vsubps %ymm13,%ymm8,%ymm13 DB 197,132,92,195 ; vsubps %ymm3,%ymm15,%ymm0 DB 196,98,125,168,235 ; vfmadd213ps %ymm3,%ymm0,%ymm13 @@ -713,7 +713,7 @@ _sk_clamp_0_hsw LABEL PROC PUBLIC _sk_clamp_1_hsw _sk_clamp_1_hsw LABEL PROC - DB 196,98,125,24,5,219,51,0,0 ; vbroadcastss 0x33db(%rip),%ymm8 # 3e68 <_sk_callback_hsw+0x16d> + DB 196,98,125,24,5,91,51,0,0 ; vbroadcastss 0x335b(%rip),%ymm8 # 3de8 <_sk_callback_hsw+0x16d> DB 196,193,124,93,192 ; vminps %ymm8,%ymm0,%ymm0 DB 196,193,116,93,200 ; vminps %ymm8,%ymm1,%ymm1 DB 196,193,108,93,208 ; vminps %ymm8,%ymm2,%ymm2 @@ -723,7 +723,7 @@ _sk_clamp_1_hsw LABEL PROC PUBLIC _sk_clamp_a_hsw _sk_clamp_a_hsw LABEL PROC - DB 196,98,125,24,5,190,51,0,0 ; vbroadcastss 0x33be(%rip),%ymm8 # 3e6c <_sk_callback_hsw+0x171> + DB 196,98,125,24,5,62,51,0,0 ; vbroadcastss 0x333e(%rip),%ymm8 # 3dec <_sk_callback_hsw+0x171> DB 196,193,100,93,216 ; vminps %ymm8,%ymm3,%ymm3 DB 197,252,93,195 ; vminps %ymm3,%ymm0,%ymm0 DB 197,244,93,203 ; vminps %ymm3,%ymm1,%ymm1 @@ -795,7 +795,7 @@ PUBLIC _sk_unpremul_hsw _sk_unpremul_hsw LABEL PROC DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,65,100,194,200,0 ; vcmpeqps %ymm8,%ymm3,%ymm9 - DB 196,98,125,24,21,6,51,0,0 ; vbroadcastss 0x3306(%rip),%ymm10 # 3e70 <_sk_callback_hsw+0x175> + DB 196,98,125,24,21,134,50,0,0 ; vbroadcastss 0x3286(%rip),%ymm10 # 3df0 <_sk_callback_hsw+0x175> DB 197,44,94,211 ; vdivps %ymm3,%ymm10,%ymm10 DB 196,67,45,74,192,144 ; vblendvps %ymm9,%ymm8,%ymm10,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 @@ -806,16 +806,16 @@ _sk_unpremul_hsw LABEL PROC PUBLIC _sk_from_srgb_hsw _sk_from_srgb_hsw LABEL PROC - DB 196,98,125,24,5,231,50,0,0 ; vbroadcastss 0x32e7(%rip),%ymm8 # 3e74 <_sk_callback_hsw+0x179> + DB 196,98,125,24,5,103,50,0,0 ; vbroadcastss 0x3267(%rip),%ymm8 # 3df4 <_sk_callback_hsw+0x179> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 197,124,89,208 ; vmulps %ymm0,%ymm0,%ymm10 - DB 196,98,125,24,29,217,50,0,0 ; vbroadcastss 0x32d9(%rip),%ymm11 # 3e78 <_sk_callback_hsw+0x17d> - DB 196,98,125,24,37,212,50,0,0 ; vbroadcastss 0x32d4(%rip),%ymm12 # 3e7c <_sk_callback_hsw+0x181> + DB 196,98,125,24,29,89,50,0,0 ; vbroadcastss 0x3259(%rip),%ymm11 # 3df8 <_sk_callback_hsw+0x17d> + DB 196,98,125,24,37,84,50,0,0 ; vbroadcastss 0x3254(%rip),%ymm12 # 3dfc <_sk_callback_hsw+0x181> DB 196,65,124,40,236 ; vmovaps %ymm12,%ymm13 DB 196,66,125,168,235 ; vfmadd213ps %ymm11,%ymm0,%ymm13 - DB 196,98,125,24,53,197,50,0,0 ; vbroadcastss 0x32c5(%rip),%ymm14 # 3e80 <_sk_callback_hsw+0x185> + DB 196,98,125,24,53,69,50,0,0 ; vbroadcastss 0x3245(%rip),%ymm14 # 3e00 <_sk_callback_hsw+0x185> DB 196,66,45,168,238 ; vfmadd213ps %ymm14,%ymm10,%ymm13 - DB 196,98,125,24,21,187,50,0,0 ; vbroadcastss 0x32bb(%rip),%ymm10 # 3e84 <_sk_callback_hsw+0x189> + DB 196,98,125,24,21,59,50,0,0 ; vbroadcastss 0x323b(%rip),%ymm10 # 3e04 <_sk_callback_hsw+0x189> DB 196,193,124,194,194,1 ; vcmpltps %ymm10,%ymm0,%ymm0 DB 196,195,21,74,193,0 ; vblendvps %ymm0,%ymm9,%ymm13,%ymm0 DB 196,65,116,89,200 ; vmulps %ymm8,%ymm1,%ymm9 @@ -839,16 +839,16 @@ _sk_to_srgb_hsw LABEL PROC DB 197,124,82,192 ; vrsqrtps %ymm0,%ymm8 DB 196,65,124,83,200 ; vrcpps %ymm8,%ymm9 DB 196,65,124,82,208 ; vrsqrtps %ymm8,%ymm10 - DB 196,98,125,24,5,85,50,0,0 ; vbroadcastss 0x3255(%rip),%ymm8 # 3e88 <_sk_callback_hsw+0x18d> + DB 196,98,125,24,5,213,49,0,0 ; vbroadcastss 0x31d5(%rip),%ymm8 # 3e08 <_sk_callback_hsw+0x18d> DB 196,65,124,89,216 ; vmulps %ymm8,%ymm0,%ymm11 - DB 196,98,125,24,37,75,50,0,0 ; vbroadcastss 0x324b(%rip),%ymm12 # 3e8c <_sk_callback_hsw+0x191> - DB 196,98,125,24,45,70,50,0,0 ; vbroadcastss 0x3246(%rip),%ymm13 # 3e90 <_sk_callback_hsw+0x195> + DB 196,98,125,24,37,203,49,0,0 ; vbroadcastss 0x31cb(%rip),%ymm12 # 3e0c <_sk_callback_hsw+0x191> + DB 196,98,125,24,45,198,49,0,0 ; vbroadcastss 0x31c6(%rip),%ymm13 # 3e10 <_sk_callback_hsw+0x195> DB 196,66,21,168,204 ; vfmadd213ps %ymm12,%ymm13,%ymm9 - DB 196,98,125,24,53,60,50,0,0 ; vbroadcastss 0x323c(%rip),%ymm14 # 3e94 <_sk_callback_hsw+0x199> + DB 196,98,125,24,53,188,49,0,0 ; vbroadcastss 0x31bc(%rip),%ymm14 # 3e14 <_sk_callback_hsw+0x199> DB 196,66,13,184,202 ; vfmadd231ps %ymm10,%ymm14,%ymm9 - DB 196,98,125,24,21,50,50,0,0 ; vbroadcastss 0x3232(%rip),%ymm10 # 3e98 <_sk_callback_hsw+0x19d> + DB 196,98,125,24,21,178,49,0,0 ; vbroadcastss 0x31b2(%rip),%ymm10 # 3e18 <_sk_callback_hsw+0x19d> DB 196,65,44,93,201 ; vminps %ymm9,%ymm10,%ymm9 - DB 196,98,125,24,61,40,50,0,0 ; vbroadcastss 0x3228(%rip),%ymm15 # 3e9c <_sk_callback_hsw+0x1a1> + DB 196,98,125,24,61,168,49,0,0 ; vbroadcastss 0x31a8(%rip),%ymm15 # 3e1c <_sk_callback_hsw+0x1a1> DB 196,193,124,194,199,1 ; vcmpltps %ymm15,%ymm0,%ymm0 DB 196,195,53,74,195,0 ; vblendvps %ymm0,%ymm11,%ymm9,%ymm0 DB 197,124,82,201 ; vrsqrtps %ymm1,%ymm9 @@ -879,26 +879,26 @@ _sk_rgb_to_hsl_hsw LABEL PROC DB 197,124,93,201 ; vminps %ymm1,%ymm0,%ymm9 DB 197,52,93,202 ; vminps %ymm2,%ymm9,%ymm9 DB 196,65,60,92,209 ; vsubps %ymm9,%ymm8,%ymm10 - DB 196,98,125,24,29,162,49,0,0 ; vbroadcastss 0x31a2(%rip),%ymm11 # 3ea0 <_sk_callback_hsw+0x1a5> + DB 196,98,125,24,29,34,49,0,0 ; vbroadcastss 0x3122(%rip),%ymm11 # 3e20 <_sk_callback_hsw+0x1a5> DB 196,65,36,94,218 ; vdivps %ymm10,%ymm11,%ymm11 DB 197,116,92,226 ; vsubps %ymm2,%ymm1,%ymm12 DB 197,116,194,234,1 ; vcmpltps %ymm2,%ymm1,%ymm13 - DB 196,98,125,24,53,143,49,0,0 ; vbroadcastss 0x318f(%rip),%ymm14 # 3ea4 <_sk_callback_hsw+0x1a9> + DB 196,98,125,24,53,15,49,0,0 ; vbroadcastss 0x310f(%rip),%ymm14 # 3e24 <_sk_callback_hsw+0x1a9> DB 196,65,4,87,255 ; vxorps %ymm15,%ymm15,%ymm15 DB 196,67,5,74,238,208 ; vblendvps %ymm13,%ymm14,%ymm15,%ymm13 DB 196,66,37,168,229 ; vfmadd213ps %ymm13,%ymm11,%ymm12 DB 197,236,92,208 ; vsubps %ymm0,%ymm2,%ymm2 DB 197,124,92,233 ; vsubps %ymm1,%ymm0,%ymm13 - DB 196,98,125,24,53,118,49,0,0 ; vbroadcastss 0x3176(%rip),%ymm14 # 3eac <_sk_callback_hsw+0x1b1> + DB 196,98,125,24,53,246,48,0,0 ; vbroadcastss 0x30f6(%rip),%ymm14 # 3e2c <_sk_callback_hsw+0x1b1> DB 196,66,37,168,238 ; vfmadd213ps %ymm14,%ymm11,%ymm13 - DB 196,98,125,24,53,100,49,0,0 ; vbroadcastss 0x3164(%rip),%ymm14 # 3ea8 <_sk_callback_hsw+0x1ad> + DB 196,98,125,24,53,228,48,0,0 ; vbroadcastss 0x30e4(%rip),%ymm14 # 3e28 <_sk_callback_hsw+0x1ad> DB 196,194,37,168,214 ; vfmadd213ps %ymm14,%ymm11,%ymm2 DB 197,188,194,201,0 ; vcmpeqps %ymm1,%ymm8,%ymm1 DB 196,227,21,74,202,16 ; vblendvps %ymm1,%ymm2,%ymm13,%ymm1 DB 197,188,194,192,0 ; vcmpeqps %ymm0,%ymm8,%ymm0 DB 196,195,117,74,196,0 ; vblendvps %ymm0,%ymm12,%ymm1,%ymm0 DB 196,193,60,88,201 ; vaddps %ymm9,%ymm8,%ymm1 - DB 196,98,125,24,29,71,49,0,0 ; vbroadcastss 0x3147(%rip),%ymm11 # 3eb4 <_sk_callback_hsw+0x1b9> + DB 196,98,125,24,29,199,48,0,0 ; vbroadcastss 0x30c7(%rip),%ymm11 # 3e34 <_sk_callback_hsw+0x1b9> DB 196,193,116,89,211 ; vmulps %ymm11,%ymm1,%ymm2 DB 197,36,194,218,1 ; vcmpltps %ymm2,%ymm11,%ymm11 DB 196,65,12,92,224 ; vsubps %ymm8,%ymm14,%ymm12 @@ -908,113 +908,93 @@ _sk_rgb_to_hsl_hsw LABEL PROC DB 197,172,94,201 ; vdivps %ymm1,%ymm10,%ymm1 DB 196,195,125,74,199,128 ; vblendvps %ymm8,%ymm15,%ymm0,%ymm0 DB 196,195,117,74,207,128 ; vblendvps %ymm8,%ymm15,%ymm1,%ymm1 - DB 196,98,125,24,5,10,49,0,0 ; vbroadcastss 0x310a(%rip),%ymm8 # 3eb0 <_sk_callback_hsw+0x1b5> + DB 196,98,125,24,5,138,48,0,0 ; vbroadcastss 0x308a(%rip),%ymm8 # 3e30 <_sk_callback_hsw+0x1b5> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax PUBLIC _sk_hsl_to_rgb_hsw _sk_hsl_to_rgb_hsw LABEL PROC - DB 72,129,236,248,0,0,0 ; sub $0xf8,%rsp - DB 197,252,17,188,36,192,0,0,0 ; vmovups %ymm7,0xc0(%rsp) - DB 197,252,17,180,36,160,0,0,0 ; vmovups %ymm6,0xa0(%rsp) - DB 197,252,17,172,36,128,0,0,0 ; vmovups %ymm5,0x80(%rsp) - DB 197,252,17,100,36,96 ; vmovups %ymm4,0x60(%rsp) - DB 197,252,17,92,36,64 ; vmovups %ymm3,0x40(%rsp) - DB 197,252,17,76,36,32 ; vmovups %ymm1,0x20(%rsp) + DB 72,129,236,184,0,0,0 ; sub $0xb8,%rsp + DB 197,252,17,188,36,128,0,0,0 ; vmovups %ymm7,0x80(%rsp) + DB 197,252,17,116,36,96 ; vmovups %ymm6,0x60(%rsp) + DB 197,252,17,108,36,64 ; vmovups %ymm5,0x40(%rsp) + DB 197,252,17,100,36,32 ; vmovups %ymm4,0x20(%rsp) + DB 197,252,17,28,36 ; vmovups %ymm3,(%rsp) + DB 197,252,40,217 ; vmovaps %ymm1,%ymm3 + DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 184,0,0,0,63 ; mov $0x3f000000,%eax - DB 197,249,110,216 ; vmovd %eax,%xmm3 - DB 196,98,125,88,195 ; vpbroadcastd %xmm3,%ymm8 - DB 196,193,108,194,232,1 ; vcmpltps %ymm8,%ymm2,%ymm5 - DB 196,98,125,24,21,184,48,0,0 ; vbroadcastss 0x30b8(%rip),%ymm10 # 3eb8 <_sk_callback_hsw+0x1bd> - DB 196,193,116,88,218 ; vaddps %ymm10,%ymm1,%ymm3 - DB 197,228,89,218 ; vmulps %ymm2,%ymm3,%ymm3 - DB 197,244,88,226 ; vaddps %ymm2,%ymm1,%ymm4 - DB 196,226,117,188,226 ; vfnmadd231ps %ymm2,%ymm1,%ymm4 - DB 196,99,93,74,203,80 ; vblendvps %ymm5,%ymm3,%ymm4,%ymm9 - DB 196,226,125,24,13,159,48,0,0 ; vbroadcastss 0x309f(%rip),%ymm1 # 3ec0 <_sk_callback_hsw+0x1c5> - DB 197,252,88,201 ; vaddps %ymm1,%ymm0,%ymm1 - DB 65,184,0,0,0,0 ; mov $0x0,%r8d - DB 184,0,0,128,63 ; mov $0x3f800000,%eax - DB 197,249,110,216 ; vmovd %eax,%xmm3 - DB 196,98,125,88,227 ; vpbroadcastd %xmm3,%ymm12 - DB 197,156,194,217,1 ; vcmpltps %ymm1,%ymm12,%ymm3 - DB 196,98,125,24,45,125,48,0,0 ; vbroadcastss 0x307d(%rip),%ymm13 # 3ec4 <_sk_callback_hsw+0x1c9> - DB 196,193,116,88,229 ; vaddps %ymm13,%ymm1,%ymm4 - DB 196,227,117,74,220,48 ; vblendvps %ymm3,%ymm4,%ymm1,%ymm3 - DB 196,193,121,110,224 ; vmovd %r8d,%xmm4 - DB 196,98,125,88,252 ; vpbroadcastd %xmm4,%ymm15 - DB 196,193,116,194,231,1 ; vcmpltps %ymm15,%ymm1,%ymm4 - DB 196,193,116,88,202 ; vaddps %ymm10,%ymm1,%ymm1 - DB 196,227,101,74,241,64 ; vblendvps %ymm4,%ymm1,%ymm3,%ymm6 - DB 196,98,125,24,29,70,48,0,0 ; vbroadcastss 0x3046(%rip),%ymm11 # 3ebc <_sk_callback_hsw+0x1c1> - DB 196,66,109,170,217 ; vfmsub213ps %ymm9,%ymm2,%ymm11 - DB 196,193,52,92,203 ; vsubps %ymm11,%ymm9,%ymm1 - DB 196,226,125,24,29,63,48,0,0 ; vbroadcastss 0x303f(%rip),%ymm3 # 3ec8 <_sk_callback_hsw+0x1cd> - DB 197,116,89,243 ; vmulps %ymm3,%ymm1,%ymm14 + DB 197,121,110,192 ; vmovd %eax,%xmm8 + DB 196,66,125,88,192 ; vpbroadcastd %xmm8,%ymm8 + DB 196,65,108,194,200,1 ; vcmpltps %ymm8,%ymm2,%ymm9 + DB 197,100,89,210 ; vmulps %ymm2,%ymm3,%ymm10 + DB 196,65,100,92,218 ; vsubps %ymm10,%ymm3,%ymm11 + DB 196,67,37,74,202,144 ; vblendvps %ymm9,%ymm10,%ymm11,%ymm9 + DB 197,52,88,202 ; vaddps %ymm2,%ymm9,%ymm9 + DB 196,98,125,24,21,42,48,0,0 ; vbroadcastss 0x302a(%rip),%ymm10 # 3e38 <_sk_callback_hsw+0x1bd> + DB 196,66,109,170,209 ; vfmsub213ps %ymm9,%ymm2,%ymm10 + DB 196,98,125,24,29,32,48,0,0 ; vbroadcastss 0x3020(%rip),%ymm11 # 3e3c <_sk_callback_hsw+0x1c1> + DB 196,65,116,88,219 ; vaddps %ymm11,%ymm1,%ymm11 + DB 196,67,125,8,227,1 ; vroundps $0x1,%ymm11,%ymm12 + DB 196,65,36,92,236 ; vsubps %ymm12,%ymm11,%ymm13 + DB 196,65,52,92,218 ; vsubps %ymm10,%ymm9,%ymm11 + DB 196,98,125,24,37,6,48,0,0 ; vbroadcastss 0x3006(%rip),%ymm12 # 3e40 <_sk_callback_hsw+0x1c5> + DB 196,65,20,89,244 ; vmulps %ymm12,%ymm13,%ymm14 + DB 196,65,124,40,251 ; vmovaps %ymm11,%ymm15 + DB 196,66,13,168,250 ; vfmadd213ps %ymm10,%ymm14,%ymm15 + DB 196,226,125,24,5,242,47,0,0 ; vbroadcastss 0x2ff2(%rip),%ymm0 # 3e44 <_sk_callback_hsw+0x1c9> + DB 196,65,124,92,246 ; vsubps %ymm14,%ymm0,%ymm14 + DB 196,66,37,168,242 ; vfmadd213ps %ymm10,%ymm11,%ymm14 DB 65,184,171,170,42,62 ; mov $0x3e2aaaab,%r8d DB 184,171,170,42,63 ; mov $0x3f2aaaab,%eax - DB 197,249,110,200 ; vmovd %eax,%xmm1 - DB 196,226,125,88,233 ; vpbroadcastd %xmm1,%ymm5 - DB 196,226,125,24,37,34,48,0,0 ; vbroadcastss 0x3022(%rip),%ymm4 # 3ecc <_sk_callback_hsw+0x1d1> - DB 197,220,92,206 ; vsubps %ymm6,%ymm4,%ymm1 - DB 196,194,13,168,203 ; vfmadd213ps %ymm11,%ymm14,%ymm1 - DB 197,204,194,253,1 ; vcmpltps %ymm5,%ymm6,%ymm7 - DB 196,227,37,74,201,112 ; vblendvps %ymm7,%ymm1,%ymm11,%ymm1 - DB 196,193,76,194,248,1 ; vcmpltps %ymm8,%ymm6,%ymm7 - DB 196,195,117,74,249,112 ; vblendvps %ymm7,%ymm9,%ymm1,%ymm7 - DB 196,193,121,110,200 ; vmovd %r8d,%xmm1 - DB 196,226,125,88,217 ; vpbroadcastd %xmm1,%ymm3 - DB 197,204,194,203,1 ; vcmpltps %ymm3,%ymm6,%ymm1 - DB 196,194,13,168,243 ; vfmadd213ps %ymm11,%ymm14,%ymm6 - DB 196,227,69,74,206,16 ; vblendvps %ymm1,%ymm6,%ymm7,%ymm1 - DB 197,252,17,12,36 ; vmovups %ymm1,(%rsp) - DB 197,156,194,200,1 ; vcmpltps %ymm0,%ymm12,%ymm1 - DB 196,193,124,88,253 ; vaddps %ymm13,%ymm0,%ymm7 - DB 196,227,125,74,207,16 ; vblendvps %ymm1,%ymm7,%ymm0,%ymm1 - DB 196,193,124,194,255,1 ; vcmpltps %ymm15,%ymm0,%ymm7 - DB 196,193,124,88,242 ; vaddps %ymm10,%ymm0,%ymm6 - DB 196,227,117,74,206,112 ; vblendvps %ymm7,%ymm6,%ymm1,%ymm1 - DB 197,220,92,241 ; vsubps %ymm1,%ymm4,%ymm6 - DB 196,194,13,168,243 ; vfmadd213ps %ymm11,%ymm14,%ymm6 - DB 197,244,194,253,1 ; vcmpltps %ymm5,%ymm1,%ymm7 - DB 196,227,37,74,246,112 ; vblendvps %ymm7,%ymm6,%ymm11,%ymm6 + DB 197,249,110,248 ; vmovd %eax,%xmm7 + DB 196,226,125,88,255 ; vpbroadcastd %xmm7,%ymm7 + DB 197,148,194,247,1 ; vcmpltps %ymm7,%ymm13,%ymm6 + DB 196,195,45,74,246,96 ; vblendvps %ymm6,%ymm14,%ymm10,%ymm6 + DB 196,65,20,194,240,1 ; vcmpltps %ymm8,%ymm13,%ymm14 + DB 196,195,77,74,241,224 ; vblendvps %ymm14,%ymm9,%ymm6,%ymm6 + DB 196,193,121,110,232 ; vmovd %r8d,%xmm5 + DB 196,226,125,88,237 ; vpbroadcastd %xmm5,%ymm5 + DB 197,20,194,237,1 ; vcmpltps %ymm5,%ymm13,%ymm13 + DB 196,195,77,74,247,208 ; vblendvps %ymm13,%ymm15,%ymm6,%ymm6 + DB 196,99,125,8,233,1 ; vroundps $0x1,%ymm1,%ymm13 + DB 196,65,116,92,237 ; vsubps %ymm13,%ymm1,%ymm13 + DB 196,65,20,89,244 ; vmulps %ymm12,%ymm13,%ymm14 + DB 196,65,124,92,254 ; vsubps %ymm14,%ymm0,%ymm15 + DB 196,66,37,168,250 ; vfmadd213ps %ymm10,%ymm11,%ymm15 + DB 197,148,194,231,1 ; vcmpltps %ymm7,%ymm13,%ymm4 + DB 196,195,45,74,231,64 ; vblendvps %ymm4,%ymm15,%ymm10,%ymm4 + DB 196,65,20,194,248,1 ; vcmpltps %ymm8,%ymm13,%ymm15 + DB 196,195,93,74,225,240 ; vblendvps %ymm15,%ymm9,%ymm4,%ymm4 + DB 196,66,37,168,242 ; vfmadd213ps %ymm10,%ymm11,%ymm14 + DB 197,20,194,237,1 ; vcmpltps %ymm5,%ymm13,%ymm13 + DB 196,195,93,74,230,208 ; vblendvps %ymm13,%ymm14,%ymm4,%ymm4 + DB 196,98,125,24,45,98,47,0,0 ; vbroadcastss 0x2f62(%rip),%ymm13 # 3e48 <_sk_callback_hsw+0x1cd> + DB 196,193,116,88,205 ; vaddps %ymm13,%ymm1,%ymm1 + DB 196,99,125,8,233,1 ; vroundps $0x1,%ymm1,%ymm13 + DB 196,193,116,92,205 ; vsubps %ymm13,%ymm1,%ymm1 + DB 196,65,116,89,228 ; vmulps %ymm12,%ymm1,%ymm12 + DB 196,193,124,92,196 ; vsubps %ymm12,%ymm0,%ymm0 + DB 196,66,37,168,226 ; vfmadd213ps %ymm10,%ymm11,%ymm12 + DB 196,194,37,168,194 ; vfmadd213ps %ymm10,%ymm11,%ymm0 + DB 197,244,194,255,1 ; vcmpltps %ymm7,%ymm1,%ymm7 + DB 196,227,45,74,192,112 ; vblendvps %ymm7,%ymm0,%ymm10,%ymm0 DB 196,193,116,194,248,1 ; vcmpltps %ymm8,%ymm1,%ymm7 - DB 196,195,77,74,241,112 ; vblendvps %ymm7,%ymm9,%ymm6,%ymm6 - DB 197,244,194,251,1 ; vcmpltps %ymm3,%ymm1,%ymm7 - DB 196,194,13,168,203 ; vfmadd213ps %ymm11,%ymm14,%ymm1 - DB 196,227,77,74,201,112 ; vblendvps %ymm7,%ymm1,%ymm6,%ymm1 - DB 196,226,125,24,53,141,47,0,0 ; vbroadcastss 0x2f8d(%rip),%ymm6 # 3ed0 <_sk_callback_hsw+0x1d5> - DB 197,252,88,198 ; vaddps %ymm6,%ymm0,%ymm0 - DB 197,156,194,240,1 ; vcmpltps %ymm0,%ymm12,%ymm6 - DB 196,193,124,88,253 ; vaddps %ymm13,%ymm0,%ymm7 - DB 196,227,125,74,247,96 ; vblendvps %ymm6,%ymm7,%ymm0,%ymm6 - DB 196,193,124,194,255,1 ; vcmpltps %ymm15,%ymm0,%ymm7 - DB 196,193,124,88,194 ; vaddps %ymm10,%ymm0,%ymm0 - DB 196,227,77,74,192,112 ; vblendvps %ymm7,%ymm0,%ymm6,%ymm0 - DB 197,220,92,224 ; vsubps %ymm0,%ymm4,%ymm4 - DB 197,252,40,240 ; vmovaps %ymm0,%ymm6 - DB 196,194,13,168,243 ; vfmadd213ps %ymm11,%ymm14,%ymm6 - DB 196,194,13,168,227 ; vfmadd213ps %ymm11,%ymm14,%ymm4 - DB 197,252,194,237,1 ; vcmpltps %ymm5,%ymm0,%ymm5 - DB 196,227,37,74,228,80 ; vblendvps %ymm5,%ymm4,%ymm11,%ymm4 - DB 196,193,124,194,232,1 ; vcmpltps %ymm8,%ymm0,%ymm5 - DB 196,195,93,74,225,80 ; vblendvps %ymm5,%ymm9,%ymm4,%ymm4 - DB 197,252,194,195,1 ; vcmpltps %ymm3,%ymm0,%ymm0 - DB 196,227,93,74,222,0 ; vblendvps %ymm0,%ymm6,%ymm4,%ymm3 + DB 196,195,125,74,193,112 ; vblendvps %ymm7,%ymm9,%ymm0,%ymm0 + DB 197,244,194,205,1 ; vcmpltps %ymm5,%ymm1,%ymm1 + DB 196,195,125,74,236,16 ; vblendvps %ymm1,%ymm12,%ymm0,%ymm5 DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 - DB 197,252,194,100,36,32,0 ; vcmpeqps 0x20(%rsp),%ymm0,%ymm4 - DB 197,252,16,4,36 ; vmovups (%rsp),%ymm0 - DB 196,227,125,74,194,64 ; vblendvps %ymm4,%ymm2,%ymm0,%ymm0 - DB 196,227,117,74,202,64 ; vblendvps %ymm4,%ymm2,%ymm1,%ymm1 - DB 196,227,101,74,210,64 ; vblendvps %ymm4,%ymm2,%ymm3,%ymm2 + DB 197,228,194,216,0 ; vcmpeqps %ymm0,%ymm3,%ymm3 + DB 196,227,77,74,194,48 ; vblendvps %ymm3,%ymm2,%ymm6,%ymm0 + DB 196,227,93,74,202,48 ; vblendvps %ymm3,%ymm2,%ymm4,%ymm1 + DB 196,227,85,74,210,48 ; vblendvps %ymm3,%ymm2,%ymm5,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 197,252,16,92,36,64 ; vmovups 0x40(%rsp),%ymm3 - DB 197,252,16,100,36,96 ; vmovups 0x60(%rsp),%ymm4 - DB 197,252,16,172,36,128,0,0,0 ; vmovups 0x80(%rsp),%ymm5 - DB 197,252,16,180,36,160,0,0,0 ; vmovups 0xa0(%rsp),%ymm6 - DB 197,252,16,188,36,192,0,0,0 ; vmovups 0xc0(%rsp),%ymm7 - DB 72,129,196,248,0,0,0 ; add $0xf8,%rsp + DB 197,252,16,28,36 ; vmovups (%rsp),%ymm3 + DB 197,252,16,100,36,32 ; vmovups 0x20(%rsp),%ymm4 + DB 197,252,16,108,36,64 ; vmovups 0x40(%rsp),%ymm5 + DB 197,252,16,116,36,96 ; vmovups 0x60(%rsp),%ymm6 + DB 197,252,16,188,36,128,0,0,0 ; vmovups 0x80(%rsp),%ymm7 + DB 72,129,196,184,0,0,0 ; add $0xb8,%rsp DB 255,224 ; jmpq *%rax PUBLIC _sk_scale_1_float_hsw @@ -1035,11 +1015,11 @@ _sk_scale_u8_hsw LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 72,1,248 ; add %rdi,%rax DB 77,133,192 ; test %r8,%r8 - DB 117,51 ; jne 104e <_sk_scale_u8_hsw+0x43> + DB 117,51 ; jne fd0 <_sk_scale_u8_hsw+0x43> DB 197,122,126,0 ; vmovq (%rax),%xmm8 DB 196,66,125,49,192 ; vpmovzxbd %xmm8,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,162,46,0,0 ; vbroadcastss 0x2ea2(%rip),%ymm9 # 3ed4 <_sk_callback_hsw+0x1d9> + DB 196,98,125,24,13,152,46,0,0 ; vbroadcastss 0x2e98(%rip),%ymm9 # 3e4c <_sk_callback_hsw+0x1d1> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 @@ -1057,9 +1037,9 @@ _sk_scale_u8_hsw LABEL PROC DB 77,9,217 ; or %r11,%r9 DB 72,131,193,8 ; add $0x8,%rcx DB 73,255,202 ; dec %r10 - DB 117,234 ; jne 1056 <_sk_scale_u8_hsw+0x4b> + DB 117,234 ; jne fd8 <_sk_scale_u8_hsw+0x4b> DB 196,65,249,110,193 ; vmovq %r9,%xmm8 - DB 235,172 ; jmp 101f <_sk_scale_u8_hsw+0x14> + DB 235,172 ; jmp fa1 <_sk_scale_u8_hsw+0x14> PUBLIC _sk_lerp_1_float_hsw _sk_lerp_1_float_hsw LABEL PROC @@ -1083,11 +1063,11 @@ _sk_lerp_u8_hsw LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 72,1,248 ; add %rdi,%rax DB 77,133,192 ; test %r8,%r8 - DB 117,71 ; jne 10f9 <_sk_lerp_u8_hsw+0x57> + DB 117,71 ; jne 107b <_sk_lerp_u8_hsw+0x57> DB 197,122,126,0 ; vmovq (%rax),%xmm8 DB 196,66,125,49,192 ; vpmovzxbd %xmm8,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,15,46,0,0 ; vbroadcastss 0x2e0f(%rip),%ymm9 # 3ed8 <_sk_callback_hsw+0x1dd> + DB 196,98,125,24,13,5,46,0,0 ; vbroadcastss 0x2e05(%rip),%ymm9 # 3e50 <_sk_callback_hsw+0x1d5> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 DB 197,252,92,196 ; vsubps %ymm4,%ymm0,%ymm0 DB 196,226,61,168,196 ; vfmadd213ps %ymm4,%ymm8,%ymm0 @@ -1109,32 +1089,32 @@ _sk_lerp_u8_hsw LABEL PROC DB 77,9,217 ; or %r11,%r9 DB 72,131,193,8 ; add $0x8,%rcx DB 73,255,202 ; dec %r10 - DB 117,234 ; jne 1101 <_sk_lerp_u8_hsw+0x5f> + DB 117,234 ; jne 1083 <_sk_lerp_u8_hsw+0x5f> DB 196,65,249,110,193 ; vmovq %r9,%xmm8 - DB 235,152 ; jmp 10b6 <_sk_lerp_u8_hsw+0x14> + DB 235,152 ; jmp 1038 <_sk_lerp_u8_hsw+0x14> PUBLIC _sk_lerp_565_hsw _sk_lerp_565_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,149,0,0,0 ; jne 11c1 <_sk_lerp_565_hsw+0xa3> + DB 15,133,149,0,0,0 ; jne 1143 <_sk_lerp_565_hsw+0xa3> DB 196,193,122,111,28,122 ; vmovdqu (%r10,%rdi,2),%xmm3 DB 196,226,125,51,219 ; vpmovzxwd %xmm3,%ymm3 - DB 196,98,125,88,5,156,45,0,0 ; vpbroadcastd 0x2d9c(%rip),%ymm8 # 3edc <_sk_callback_hsw+0x1e1> + DB 196,98,125,88,5,146,45,0,0 ; vpbroadcastd 0x2d92(%rip),%ymm8 # 3e54 <_sk_callback_hsw+0x1d9> DB 196,65,101,219,192 ; vpand %ymm8,%ymm3,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,141,45,0,0 ; vbroadcastss 0x2d8d(%rip),%ymm9 # 3ee0 <_sk_callback_hsw+0x1e5> + DB 196,98,125,24,13,131,45,0,0 ; vbroadcastss 0x2d83(%rip),%ymm9 # 3e58 <_sk_callback_hsw+0x1dd> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 - DB 196,98,125,88,13,131,45,0,0 ; vpbroadcastd 0x2d83(%rip),%ymm9 # 3ee4 <_sk_callback_hsw+0x1e9> + DB 196,98,125,88,13,121,45,0,0 ; vpbroadcastd 0x2d79(%rip),%ymm9 # 3e5c <_sk_callback_hsw+0x1e1> DB 196,65,101,219,201 ; vpand %ymm9,%ymm3,%ymm9 DB 196,65,124,91,201 ; vcvtdq2ps %ymm9,%ymm9 - DB 196,98,125,24,21,116,45,0,0 ; vbroadcastss 0x2d74(%rip),%ymm10 # 3ee8 <_sk_callback_hsw+0x1ed> + DB 196,98,125,24,21,106,45,0,0 ; vbroadcastss 0x2d6a(%rip),%ymm10 # 3e60 <_sk_callback_hsw+0x1e5> DB 196,65,52,89,202 ; vmulps %ymm10,%ymm9,%ymm9 - DB 196,98,125,88,21,106,45,0,0 ; vpbroadcastd 0x2d6a(%rip),%ymm10 # 3eec <_sk_callback_hsw+0x1f1> + DB 196,98,125,88,21,96,45,0,0 ; vpbroadcastd 0x2d60(%rip),%ymm10 # 3e64 <_sk_callback_hsw+0x1e9> DB 196,193,101,219,218 ; vpand %ymm10,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,21,92,45,0,0 ; vbroadcastss 0x2d5c(%rip),%ymm10 # 3ef0 <_sk_callback_hsw+0x1f5> + DB 196,98,125,24,21,82,45,0,0 ; vbroadcastss 0x2d52(%rip),%ymm10 # 3e68 <_sk_callback_hsw+0x1ed> DB 196,193,100,89,218 ; vmulps %ymm10,%ymm3,%ymm3 DB 197,252,92,196 ; vsubps %ymm4,%ymm0,%ymm0 DB 196,226,61,168,196 ; vfmadd213ps %ymm4,%ymm8,%ymm0 @@ -1143,16 +1123,16 @@ _sk_lerp_565_hsw LABEL PROC DB 197,236,92,214 ; vsubps %ymm6,%ymm2,%ymm2 DB 196,226,101,168,214 ; vfmadd213ps %ymm6,%ymm3,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,53,45,0,0 ; vbroadcastss 0x2d35(%rip),%ymm3 # 3ef4 <_sk_callback_hsw+0x1f9> + DB 196,226,125,24,29,43,45,0,0 ; vbroadcastss 0x2d2b(%rip),%ymm3 # 3e6c <_sk_callback_hsw+0x1f1> DB 255,224 ; jmpq *%rax DB 65,137,200 ; mov %ecx,%r8d DB 65,128,224,7 ; and $0x7,%r8b DB 197,225,239,219 ; vpxor %xmm3,%xmm3,%xmm3 DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 15,135,89,255,255,255 ; ja 1132 <_sk_lerp_565_hsw+0x14> + DB 15,135,89,255,255,255 ; ja 10b4 <_sk_lerp_565_hsw+0x14> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,76,0,0,0 ; lea 0x4c(%rip),%r9 # 1230 <_sk_lerp_565_hsw+0x112> + DB 76,141,13,74,0,0,0 ; lea 0x4a(%rip),%r9 # 11b0 <_sk_lerp_565_hsw+0x110> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -1164,26 +1144,27 @@ _sk_lerp_565_hsw LABEL PROC DB 196,193,97,196,92,122,4,2 ; vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm3,%xmm3 DB 196,193,97,196,92,122,2,1 ; vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm3,%xmm3 DB 196,193,97,196,28,122,0 ; vpinsrw $0x0,(%r10,%rdi,2),%xmm3,%xmm3 - DB 233,5,255,255,255 ; jmpq 1132 <_sk_lerp_565_hsw+0x14> - DB 15,31,0 ; nopl (%rax) - DB 241 ; icebp + DB 233,5,255,255,255 ; jmpq 10b4 <_sk_lerp_565_hsw+0x14> + DB 144 ; nop + DB 243,255 ; repz (bad) DB 255 ; (bad) DB 255 ; (bad) + DB 235,255 ; jmp 11b5 <_sk_lerp_565_hsw+0x115> DB 255 ; (bad) - DB 233,255,255,255,225 ; jmpq ffffffffe2001238 <_sk_callback_hsw+0xffffffffe1ffd53d> + DB 255,227 ; jmpq *%rbx DB 255 ; (bad) DB 255 ; (bad) DB 255 ; (bad) - DB 217,255 ; fcos + DB 219,255 ; (bad) DB 255 ; (bad) - DB 255,209 ; callq *%rcx + DB 255,211 ; callq *%rbx DB 255 ; (bad) DB 255 ; (bad) - DB 255,201 ; dec %ecx + DB 255,203 ; dec %ebx DB 255 ; (bad) DB 255 ; (bad) DB 255 ; (bad) - DB 189 ; .byte 0xbd + DB 191 ; .byte 0xbf DB 255 ; (bad) DB 255 ; (bad) DB 255 ; .byte 0xff @@ -1195,23 +1176,23 @@ _sk_load_tables_hsw LABEL PROC DB 76,141,12,189,0,0,0,0 ; lea 0x0(,%rdi,4),%r9 DB 76,3,8 ; add (%rax),%r9 DB 77,133,192 ; test %r8,%r8 - DB 117,105 ; jne 12ca <_sk_load_tables_hsw+0x7e> + DB 117,105 ; jne 124a <_sk_load_tables_hsw+0x7e> DB 196,193,126,111,25 ; vmovdqu (%r9),%ymm3 - DB 197,229,219,13,18,47,0,0 ; vpand 0x2f12(%rip),%ymm3,%ymm1 # 4180 <_sk_callback_hsw+0x485> + DB 197,229,219,13,18,47,0,0 ; vpand 0x2f12(%rip),%ymm3,%ymm1 # 4100 <_sk_callback_hsw+0x485> DB 196,65,61,118,192 ; vpcmpeqd %ymm8,%ymm8,%ymm8 DB 72,139,72,8 ; mov 0x8(%rax),%rcx DB 76,139,72,16 ; mov 0x10(%rax),%r9 DB 197,237,118,210 ; vpcmpeqd %ymm2,%ymm2,%ymm2 DB 196,226,109,146,4,137 ; vgatherdps %ymm2,(%rcx,%ymm1,4),%ymm0 - DB 196,226,101,0,21,18,47,0,0 ; vpshufb 0x2f12(%rip),%ymm3,%ymm2 # 41a0 <_sk_callback_hsw+0x4a5> + DB 196,226,101,0,21,18,47,0,0 ; vpshufb 0x2f12(%rip),%ymm3,%ymm2 # 4120 <_sk_callback_hsw+0x4a5> DB 196,65,53,118,201 ; vpcmpeqd %ymm9,%ymm9,%ymm9 DB 196,194,53,146,12,145 ; vgatherdps %ymm9,(%r9,%ymm2,4),%ymm1 DB 72,139,64,24 ; mov 0x18(%rax),%rax - DB 196,98,101,0,13,26,47,0,0 ; vpshufb 0x2f1a(%rip),%ymm3,%ymm9 # 41c0 <_sk_callback_hsw+0x4c5> + DB 196,98,101,0,13,26,47,0,0 ; vpshufb 0x2f1a(%rip),%ymm3,%ymm9 # 4140 <_sk_callback_hsw+0x4c5> DB 196,162,61,146,20,136 ; vgatherdps %ymm8,(%rax,%ymm9,4),%ymm2 DB 197,229,114,211,24 ; vpsrld $0x18,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,58,44,0,0 ; vbroadcastss 0x2c3a(%rip),%ymm8 # 3ef8 <_sk_callback_hsw+0x1fd> + DB 196,98,125,24,5,50,44,0,0 ; vbroadcastss 0x2c32(%rip),%ymm8 # 3e70 <_sk_callback_hsw+0x1f5> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 76,137,193 ; mov %r8,%rcx @@ -1224,7 +1205,7 @@ _sk_load_tables_hsw LABEL PROC DB 196,193,249,110,194 ; vmovq %r10,%xmm0 DB 196,226,125,33,192 ; vpmovsxbd %xmm0,%ymm0 DB 196,194,125,140,25 ; vpmaskmovd (%r9),%ymm0,%ymm3 - DB 233,115,255,255,255 ; jmpq 1266 <_sk_load_tables_hsw+0x1a> + DB 233,115,255,255,255 ; jmpq 11e6 <_sk_load_tables_hsw+0x1a> PUBLIC _sk_load_tables_u16_be_hsw _sk_load_tables_u16_be_hsw LABEL PROC @@ -1232,7 +1213,7 @@ _sk_load_tables_u16_be_hsw LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 76,141,12,189,0,0,0,0 ; lea 0x0(,%rdi,4),%r9 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,201,0,0,0 ; jne 13d2 <_sk_load_tables_u16_be_hsw+0xdf> + DB 15,133,201,0,0,0 ; jne 1352 <_sk_load_tables_u16_be_hsw+0xdf> DB 196,1,121,16,4,72 ; vmovupd (%r8,%r9,2),%xmm8 DB 196,129,121,16,84,72,16 ; vmovupd 0x10(%r8,%r9,2),%xmm2 DB 196,129,121,16,92,72,32 ; vmovupd 0x20(%r8,%r9,2),%xmm3 @@ -1248,7 +1229,7 @@ _sk_load_tables_u16_be_hsw LABEL PROC DB 197,185,108,200 ; vpunpcklqdq %xmm0,%xmm8,%xmm1 DB 197,185,109,208 ; vpunpckhqdq %xmm0,%xmm8,%xmm2 DB 197,49,108,195 ; vpunpcklqdq %xmm3,%xmm9,%xmm8 - DB 197,121,111,21,166,47,0,0 ; vmovdqa 0x2fa6(%rip),%xmm10 # 4300 <_sk_callback_hsw+0x605> + DB 197,121,111,21,166,47,0,0 ; vmovdqa 0x2fa6(%rip),%xmm10 # 4280 <_sk_callback_hsw+0x605> DB 196,193,113,219,194 ; vpand %xmm10,%xmm1,%xmm0 DB 196,226,125,51,200 ; vpmovzxwd %xmm0,%ymm1 DB 196,65,37,118,219 ; vpcmpeqd %ymm11,%ymm11,%ymm11 @@ -1270,36 +1251,36 @@ _sk_load_tables_u16_be_hsw LABEL PROC DB 197,185,235,219 ; vpor %xmm3,%xmm8,%xmm3 DB 196,226,125,51,219 ; vpmovzxwd %xmm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,51,43,0,0 ; vbroadcastss 0x2b33(%rip),%ymm8 # 3efc <_sk_callback_hsw+0x201> + DB 196,98,125,24,5,43,43,0,0 ; vbroadcastss 0x2b2b(%rip),%ymm8 # 3e74 <_sk_callback_hsw+0x1f9> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax DB 196,1,123,16,4,72 ; vmovsd (%r8,%r9,2),%xmm8 DB 196,65,49,239,201 ; vpxor %xmm9,%xmm9,%xmm9 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,85 ; je 1438 <_sk_load_tables_u16_be_hsw+0x145> + DB 116,85 ; je 13b8 <_sk_load_tables_u16_be_hsw+0x145> DB 196,1,57,22,68,72,8 ; vmovhpd 0x8(%r8,%r9,2),%xmm8,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,72 ; jb 1438 <_sk_load_tables_u16_be_hsw+0x145> + DB 114,72 ; jb 13b8 <_sk_load_tables_u16_be_hsw+0x145> DB 196,129,123,16,84,72,16 ; vmovsd 0x10(%r8,%r9,2),%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 116,72 ; je 1445 <_sk_load_tables_u16_be_hsw+0x152> + DB 116,72 ; je 13c5 <_sk_load_tables_u16_be_hsw+0x152> DB 196,129,105,22,84,72,24 ; vmovhpd 0x18(%r8,%r9,2),%xmm2,%xmm2 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,59 ; jb 1445 <_sk_load_tables_u16_be_hsw+0x152> + DB 114,59 ; jb 13c5 <_sk_load_tables_u16_be_hsw+0x152> DB 196,129,123,16,92,72,32 ; vmovsd 0x20(%r8,%r9,2),%xmm3 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 15,132,9,255,255,255 ; je 1324 <_sk_load_tables_u16_be_hsw+0x31> + DB 15,132,9,255,255,255 ; je 12a4 <_sk_load_tables_u16_be_hsw+0x31> DB 196,129,97,22,92,72,40 ; vmovhpd 0x28(%r8,%r9,2),%xmm3,%xmm3 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 15,130,248,254,255,255 ; jb 1324 <_sk_load_tables_u16_be_hsw+0x31> + DB 15,130,248,254,255,255 ; jb 12a4 <_sk_load_tables_u16_be_hsw+0x31> DB 196,1,122,126,76,72,48 ; vmovq 0x30(%r8,%r9,2),%xmm9 - DB 233,236,254,255,255 ; jmpq 1324 <_sk_load_tables_u16_be_hsw+0x31> + DB 233,236,254,255,255 ; jmpq 12a4 <_sk_load_tables_u16_be_hsw+0x31> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 DB 197,233,87,210 ; vxorpd %xmm2,%xmm2,%xmm2 - DB 233,223,254,255,255 ; jmpq 1324 <_sk_load_tables_u16_be_hsw+0x31> + DB 233,223,254,255,255 ; jmpq 12a4 <_sk_load_tables_u16_be_hsw+0x31> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 - DB 233,214,254,255,255 ; jmpq 1324 <_sk_load_tables_u16_be_hsw+0x31> + DB 233,214,254,255,255 ; jmpq 12a4 <_sk_load_tables_u16_be_hsw+0x31> PUBLIC _sk_load_tables_rgb_u16_be_hsw _sk_load_tables_rgb_u16_be_hsw LABEL PROC @@ -1307,7 +1288,7 @@ _sk_load_tables_rgb_u16_be_hsw LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 76,141,12,127 ; lea (%rdi,%rdi,2),%r9 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,193,0,0,0 ; jne 1521 <_sk_load_tables_rgb_u16_be_hsw+0xd3> + DB 15,133,193,0,0,0 ; jne 14a1 <_sk_load_tables_rgb_u16_be_hsw+0xd3> DB 196,129,122,111,4,72 ; vmovdqu (%r8,%r9,2),%xmm0 DB 196,129,122,111,84,72,12 ; vmovdqu 0xc(%r8,%r9,2),%xmm2 DB 196,129,122,111,76,72,24 ; vmovdqu 0x18(%r8,%r9,2),%xmm1 @@ -1328,7 +1309,7 @@ _sk_load_tables_rgb_u16_be_hsw LABEL PROC DB 197,185,108,218 ; vpunpcklqdq %xmm2,%xmm8,%xmm3 DB 197,185,109,210 ; vpunpckhqdq %xmm2,%xmm8,%xmm2 DB 197,121,108,193 ; vpunpcklqdq %xmm1,%xmm0,%xmm8 - DB 197,121,111,13,70,46,0,0 ; vmovdqa 0x2e46(%rip),%xmm9 # 4310 <_sk_callback_hsw+0x615> + DB 197,121,111,13,70,46,0,0 ; vmovdqa 0x2e46(%rip),%xmm9 # 4290 <_sk_callback_hsw+0x615> DB 196,193,97,219,193 ; vpand %xmm9,%xmm3,%xmm0 DB 196,226,125,51,200 ; vpmovzxwd %xmm0,%ymm1 DB 197,229,118,219 ; vpcmpeqd %ymm3,%ymm3,%ymm3 @@ -1345,41 +1326,41 @@ _sk_load_tables_rgb_u16_be_hsw LABEL PROC DB 196,98,125,51,194 ; vpmovzxwd %xmm2,%ymm8 DB 196,162,101,146,20,128 ; vgatherdps %ymm3,(%rax,%ymm8,4),%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,225,41,0,0 ; vbroadcastss 0x29e1(%rip),%ymm3 # 3f00 <_sk_callback_hsw+0x205> + DB 196,226,125,24,29,217,41,0,0 ; vbroadcastss 0x29d9(%rip),%ymm3 # 3e78 <_sk_callback_hsw+0x1fd> DB 255,224 ; jmpq *%rax DB 196,129,121,110,4,72 ; vmovd (%r8,%r9,2),%xmm0 DB 196,129,121,196,68,72,4,2 ; vpinsrw $0x2,0x4(%r8,%r9,2),%xmm0,%xmm0 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 117,5 ; jne 153a <_sk_load_tables_rgb_u16_be_hsw+0xec> - DB 233,90,255,255,255 ; jmpq 1494 <_sk_load_tables_rgb_u16_be_hsw+0x46> + DB 117,5 ; jne 14ba <_sk_load_tables_rgb_u16_be_hsw+0xec> + DB 233,90,255,255,255 ; jmpq 1414 <_sk_load_tables_rgb_u16_be_hsw+0x46> DB 196,129,121,110,76,72,6 ; vmovd 0x6(%r8,%r9,2),%xmm1 DB 196,1,113,196,68,72,10,2 ; vpinsrw $0x2,0xa(%r8,%r9,2),%xmm1,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,26 ; jb 1569 <_sk_load_tables_rgb_u16_be_hsw+0x11b> + DB 114,26 ; jb 14e9 <_sk_load_tables_rgb_u16_be_hsw+0x11b> DB 196,129,121,110,76,72,12 ; vmovd 0xc(%r8,%r9,2),%xmm1 DB 196,129,113,196,84,72,16,2 ; vpinsrw $0x2,0x10(%r8,%r9,2),%xmm1,%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 117,10 ; jne 156e <_sk_load_tables_rgb_u16_be_hsw+0x120> - DB 233,43,255,255,255 ; jmpq 1494 <_sk_load_tables_rgb_u16_be_hsw+0x46> - DB 233,38,255,255,255 ; jmpq 1494 <_sk_load_tables_rgb_u16_be_hsw+0x46> + DB 117,10 ; jne 14ee <_sk_load_tables_rgb_u16_be_hsw+0x120> + DB 233,43,255,255,255 ; jmpq 1414 <_sk_load_tables_rgb_u16_be_hsw+0x46> + DB 233,38,255,255,255 ; jmpq 1414 <_sk_load_tables_rgb_u16_be_hsw+0x46> DB 196,129,121,110,76,72,18 ; vmovd 0x12(%r8,%r9,2),%xmm1 DB 196,1,113,196,76,72,22,2 ; vpinsrw $0x2,0x16(%r8,%r9,2),%xmm1,%xmm9 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,26 ; jb 159d <_sk_load_tables_rgb_u16_be_hsw+0x14f> + DB 114,26 ; jb 151d <_sk_load_tables_rgb_u16_be_hsw+0x14f> DB 196,129,121,110,76,72,24 ; vmovd 0x18(%r8,%r9,2),%xmm1 DB 196,129,113,196,76,72,28,2 ; vpinsrw $0x2,0x1c(%r8,%r9,2),%xmm1,%xmm1 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 117,10 ; jne 15a2 <_sk_load_tables_rgb_u16_be_hsw+0x154> - DB 233,247,254,255,255 ; jmpq 1494 <_sk_load_tables_rgb_u16_be_hsw+0x46> - DB 233,242,254,255,255 ; jmpq 1494 <_sk_load_tables_rgb_u16_be_hsw+0x46> + DB 117,10 ; jne 1522 <_sk_load_tables_rgb_u16_be_hsw+0x154> + DB 233,247,254,255,255 ; jmpq 1414 <_sk_load_tables_rgb_u16_be_hsw+0x46> + DB 233,242,254,255,255 ; jmpq 1414 <_sk_load_tables_rgb_u16_be_hsw+0x46> DB 196,129,121,110,92,72,30 ; vmovd 0x1e(%r8,%r9,2),%xmm3 DB 196,1,97,196,92,72,34,2 ; vpinsrw $0x2,0x22(%r8,%r9,2),%xmm3,%xmm11 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,20 ; jb 15cb <_sk_load_tables_rgb_u16_be_hsw+0x17d> + DB 114,20 ; jb 154b <_sk_load_tables_rgb_u16_be_hsw+0x17d> DB 196,129,121,110,92,72,36 ; vmovd 0x24(%r8,%r9,2),%xmm3 DB 196,129,97,196,92,72,40,2 ; vpinsrw $0x2,0x28(%r8,%r9,2),%xmm3,%xmm3 - DB 233,201,254,255,255 ; jmpq 1494 <_sk_load_tables_rgb_u16_be_hsw+0x46> - DB 233,196,254,255,255 ; jmpq 1494 <_sk_load_tables_rgb_u16_be_hsw+0x46> + DB 233,201,254,255,255 ; jmpq 1414 <_sk_load_tables_rgb_u16_be_hsw+0x46> + DB 233,196,254,255,255 ; jmpq 1414 <_sk_load_tables_rgb_u16_be_hsw+0x46> PUBLIC _sk_byte_tables_hsw _sk_byte_tables_hsw LABEL PROC @@ -1390,7 +1371,7 @@ _sk_byte_tables_hsw LABEL PROC DB 65,84 ; push %r12 DB 83 ; push %rbx DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,31,41,0,0 ; vbroadcastss 0x291f(%rip),%ymm8 # 3f04 <_sk_callback_hsw+0x209> + DB 196,98,125,24,5,23,41,0,0 ; vbroadcastss 0x2917(%rip),%ymm8 # 3e7c <_sk_callback_hsw+0x201> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 197,253,91,192 ; vcvtps2dq %ymm0,%ymm0 DB 196,195,249,22,192,1 ; vpextrq $0x1,%xmm0,%r8 @@ -1427,7 +1408,7 @@ _sk_byte_tables_hsw LABEL PROC DB 196,227,121,32,197,7 ; vpinsrb $0x7,%ebp,%xmm0,%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,112,40,0,0 ; vbroadcastss 0x2870(%rip),%ymm9 # 3f08 <_sk_callback_hsw+0x20d> + DB 196,98,125,24,13,104,40,0,0 ; vbroadcastss 0x2868(%rip),%ymm9 # 3e80 <_sk_callback_hsw+0x205> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 @@ -1586,7 +1567,7 @@ _sk_byte_tables_rgb_hsw LABEL PROC DB 196,227,121,32,197,7 ; vpinsrb $0x7,%ebp,%xmm0,%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,169,37,0,0 ; vbroadcastss 0x25a9(%rip),%ymm9 # 3f0c <_sk_callback_hsw+0x211> + DB 196,98,125,24,13,161,37,0,0 ; vbroadcastss 0x25a1(%rip),%ymm9 # 3e84 <_sk_callback_hsw+0x209> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 @@ -1739,33 +1720,33 @@ _sk_parametric_r_hsw LABEL PROC DB 196,66,125,168,211 ; vfmadd213ps %ymm11,%ymm0,%ymm10 DB 196,226,125,24,0 ; vbroadcastss (%rax),%ymm0 DB 196,65,124,91,218 ; vcvtdq2ps %ymm10,%ymm11 - DB 196,98,125,24,37,92,35,0,0 ; vbroadcastss 0x235c(%rip),%ymm12 # 3f10 <_sk_callback_hsw+0x215> - DB 196,98,125,24,45,87,35,0,0 ; vbroadcastss 0x2357(%rip),%ymm13 # 3f14 <_sk_callback_hsw+0x219> + DB 196,98,125,24,37,84,35,0,0 ; vbroadcastss 0x2354(%rip),%ymm12 # 3e88 <_sk_callback_hsw+0x20d> + DB 196,98,125,24,45,79,35,0,0 ; vbroadcastss 0x234f(%rip),%ymm13 # 3e8c <_sk_callback_hsw+0x211> DB 196,65,44,84,213 ; vandps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,77,35,0,0 ; vbroadcastss 0x234d(%rip),%ymm13 # 3f18 <_sk_callback_hsw+0x21d> + DB 196,98,125,24,45,69,35,0,0 ; vbroadcastss 0x2345(%rip),%ymm13 # 3e90 <_sk_callback_hsw+0x215> DB 196,65,44,86,213 ; vorps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,67,35,0,0 ; vbroadcastss 0x2343(%rip),%ymm13 # 3f1c <_sk_callback_hsw+0x221> + DB 196,98,125,24,45,59,35,0,0 ; vbroadcastss 0x233b(%rip),%ymm13 # 3e94 <_sk_callback_hsw+0x219> DB 196,66,37,184,236 ; vfmadd231ps %ymm12,%ymm11,%ymm13 - DB 196,98,125,24,29,57,35,0,0 ; vbroadcastss 0x2339(%rip),%ymm11 # 3f20 <_sk_callback_hsw+0x225> + DB 196,98,125,24,29,49,35,0,0 ; vbroadcastss 0x2331(%rip),%ymm11 # 3e98 <_sk_callback_hsw+0x21d> DB 196,66,45,172,221 ; vfnmadd213ps %ymm13,%ymm10,%ymm11 - DB 196,98,125,24,37,47,35,0,0 ; vbroadcastss 0x232f(%rip),%ymm12 # 3f24 <_sk_callback_hsw+0x229> + DB 196,98,125,24,37,39,35,0,0 ; vbroadcastss 0x2327(%rip),%ymm12 # 3e9c <_sk_callback_hsw+0x221> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,37,35,0,0 ; vbroadcastss 0x2325(%rip),%ymm12 # 3f28 <_sk_callback_hsw+0x22d> + DB 196,98,125,24,37,29,35,0,0 ; vbroadcastss 0x231d(%rip),%ymm12 # 3ea0 <_sk_callback_hsw+0x225> DB 196,65,28,94,210 ; vdivps %ymm10,%ymm12,%ymm10 DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 196,99,125,8,208,1 ; vroundps $0x1,%ymm0,%ymm10 DB 196,65,124,92,210 ; vsubps %ymm10,%ymm0,%ymm10 - DB 196,98,125,24,29,6,35,0,0 ; vbroadcastss 0x2306(%rip),%ymm11 # 3f2c <_sk_callback_hsw+0x231> + DB 196,98,125,24,29,254,34,0,0 ; vbroadcastss 0x22fe(%rip),%ymm11 # 3ea4 <_sk_callback_hsw+0x229> DB 196,193,124,88,195 ; vaddps %ymm11,%ymm0,%ymm0 - DB 196,98,125,24,29,252,34,0,0 ; vbroadcastss 0x22fc(%rip),%ymm11 # 3f30 <_sk_callback_hsw+0x235> + DB 196,98,125,24,29,244,34,0,0 ; vbroadcastss 0x22f4(%rip),%ymm11 # 3ea8 <_sk_callback_hsw+0x22d> DB 196,98,45,172,216 ; vfnmadd213ps %ymm0,%ymm10,%ymm11 - DB 196,226,125,24,5,242,34,0,0 ; vbroadcastss 0x22f2(%rip),%ymm0 # 3f34 <_sk_callback_hsw+0x239> + DB 196,226,125,24,5,234,34,0,0 ; vbroadcastss 0x22ea(%rip),%ymm0 # 3eac <_sk_callback_hsw+0x231> DB 196,193,124,92,194 ; vsubps %ymm10,%ymm0,%ymm0 - DB 196,98,125,24,21,232,34,0,0 ; vbroadcastss 0x22e8(%rip),%ymm10 # 3f38 <_sk_callback_hsw+0x23d> + DB 196,98,125,24,21,224,34,0,0 ; vbroadcastss 0x22e0(%rip),%ymm10 # 3eb0 <_sk_callback_hsw+0x235> DB 197,172,94,192 ; vdivps %ymm0,%ymm10,%ymm0 DB 197,164,88,192 ; vaddps %ymm0,%ymm11,%ymm0 - DB 196,98,125,24,21,219,34,0,0 ; vbroadcastss 0x22db(%rip),%ymm10 # 3f3c <_sk_callback_hsw+0x241> + DB 196,98,125,24,21,211,34,0,0 ; vbroadcastss 0x22d3(%rip),%ymm10 # 3eb4 <_sk_callback_hsw+0x239> DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 197,253,91,192 ; vcvtps2dq %ymm0,%ymm0 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -1773,7 +1754,7 @@ _sk_parametric_r_hsw LABEL PROC DB 196,195,125,74,193,128 ; vblendvps %ymm8,%ymm9,%ymm0,%ymm0 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,124,95,192 ; vmaxps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,178,34,0,0 ; vbroadcastss 0x22b2(%rip),%ymm8 # 3f40 <_sk_callback_hsw+0x245> + DB 196,98,125,24,5,170,34,0,0 ; vbroadcastss 0x22aa(%rip),%ymm8 # 3eb8 <_sk_callback_hsw+0x23d> DB 196,193,124,93,192 ; vminps %ymm8,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -1791,33 +1772,33 @@ _sk_parametric_g_hsw LABEL PROC DB 196,66,117,168,211 ; vfmadd213ps %ymm11,%ymm1,%ymm10 DB 196,226,125,24,8 ; vbroadcastss (%rax),%ymm1 DB 196,65,124,91,218 ; vcvtdq2ps %ymm10,%ymm11 - DB 196,98,125,24,37,106,34,0,0 ; vbroadcastss 0x226a(%rip),%ymm12 # 3f44 <_sk_callback_hsw+0x249> - DB 196,98,125,24,45,101,34,0,0 ; vbroadcastss 0x2265(%rip),%ymm13 # 3f48 <_sk_callback_hsw+0x24d> + DB 196,98,125,24,37,98,34,0,0 ; vbroadcastss 0x2262(%rip),%ymm12 # 3ebc <_sk_callback_hsw+0x241> + DB 196,98,125,24,45,93,34,0,0 ; vbroadcastss 0x225d(%rip),%ymm13 # 3ec0 <_sk_callback_hsw+0x245> DB 196,65,44,84,213 ; vandps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,91,34,0,0 ; vbroadcastss 0x225b(%rip),%ymm13 # 3f4c <_sk_callback_hsw+0x251> + DB 196,98,125,24,45,83,34,0,0 ; vbroadcastss 0x2253(%rip),%ymm13 # 3ec4 <_sk_callback_hsw+0x249> DB 196,65,44,86,213 ; vorps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,81,34,0,0 ; vbroadcastss 0x2251(%rip),%ymm13 # 3f50 <_sk_callback_hsw+0x255> + DB 196,98,125,24,45,73,34,0,0 ; vbroadcastss 0x2249(%rip),%ymm13 # 3ec8 <_sk_callback_hsw+0x24d> DB 196,66,37,184,236 ; vfmadd231ps %ymm12,%ymm11,%ymm13 - DB 196,98,125,24,29,71,34,0,0 ; vbroadcastss 0x2247(%rip),%ymm11 # 3f54 <_sk_callback_hsw+0x259> + DB 196,98,125,24,29,63,34,0,0 ; vbroadcastss 0x223f(%rip),%ymm11 # 3ecc <_sk_callback_hsw+0x251> DB 196,66,45,172,221 ; vfnmadd213ps %ymm13,%ymm10,%ymm11 - DB 196,98,125,24,37,61,34,0,0 ; vbroadcastss 0x223d(%rip),%ymm12 # 3f58 <_sk_callback_hsw+0x25d> + DB 196,98,125,24,37,53,34,0,0 ; vbroadcastss 0x2235(%rip),%ymm12 # 3ed0 <_sk_callback_hsw+0x255> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,51,34,0,0 ; vbroadcastss 0x2233(%rip),%ymm12 # 3f5c <_sk_callback_hsw+0x261> + DB 196,98,125,24,37,43,34,0,0 ; vbroadcastss 0x222b(%rip),%ymm12 # 3ed4 <_sk_callback_hsw+0x259> DB 196,65,28,94,210 ; vdivps %ymm10,%ymm12,%ymm10 DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 DB 196,193,116,89,202 ; vmulps %ymm10,%ymm1,%ymm1 DB 196,99,125,8,209,1 ; vroundps $0x1,%ymm1,%ymm10 DB 196,65,116,92,210 ; vsubps %ymm10,%ymm1,%ymm10 - DB 196,98,125,24,29,20,34,0,0 ; vbroadcastss 0x2214(%rip),%ymm11 # 3f60 <_sk_callback_hsw+0x265> + DB 196,98,125,24,29,12,34,0,0 ; vbroadcastss 0x220c(%rip),%ymm11 # 3ed8 <_sk_callback_hsw+0x25d> DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,10,34,0,0 ; vbroadcastss 0x220a(%rip),%ymm11 # 3f64 <_sk_callback_hsw+0x269> + DB 196,98,125,24,29,2,34,0,0 ; vbroadcastss 0x2202(%rip),%ymm11 # 3edc <_sk_callback_hsw+0x261> DB 196,98,45,172,217 ; vfnmadd213ps %ymm1,%ymm10,%ymm11 - DB 196,226,125,24,13,0,34,0,0 ; vbroadcastss 0x2200(%rip),%ymm1 # 3f68 <_sk_callback_hsw+0x26d> + DB 196,226,125,24,13,248,33,0,0 ; vbroadcastss 0x21f8(%rip),%ymm1 # 3ee0 <_sk_callback_hsw+0x265> DB 196,193,116,92,202 ; vsubps %ymm10,%ymm1,%ymm1 - DB 196,98,125,24,21,246,33,0,0 ; vbroadcastss 0x21f6(%rip),%ymm10 # 3f6c <_sk_callback_hsw+0x271> + DB 196,98,125,24,21,238,33,0,0 ; vbroadcastss 0x21ee(%rip),%ymm10 # 3ee4 <_sk_callback_hsw+0x269> DB 197,172,94,201 ; vdivps %ymm1,%ymm10,%ymm1 DB 197,164,88,201 ; vaddps %ymm1,%ymm11,%ymm1 - DB 196,98,125,24,21,233,33,0,0 ; vbroadcastss 0x21e9(%rip),%ymm10 # 3f70 <_sk_callback_hsw+0x275> + DB 196,98,125,24,21,225,33,0,0 ; vbroadcastss 0x21e1(%rip),%ymm10 # 3ee8 <_sk_callback_hsw+0x26d> DB 196,193,116,89,202 ; vmulps %ymm10,%ymm1,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -1825,7 +1806,7 @@ _sk_parametric_g_hsw LABEL PROC DB 196,195,117,74,201,128 ; vblendvps %ymm8,%ymm9,%ymm1,%ymm1 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,116,95,200 ; vmaxps %ymm8,%ymm1,%ymm1 - DB 196,98,125,24,5,192,33,0,0 ; vbroadcastss 0x21c0(%rip),%ymm8 # 3f74 <_sk_callback_hsw+0x279> + DB 196,98,125,24,5,184,33,0,0 ; vbroadcastss 0x21b8(%rip),%ymm8 # 3eec <_sk_callback_hsw+0x271> DB 196,193,116,93,200 ; vminps %ymm8,%ymm1,%ymm1 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -1843,33 +1824,33 @@ _sk_parametric_b_hsw LABEL PROC DB 196,66,109,168,211 ; vfmadd213ps %ymm11,%ymm2,%ymm10 DB 196,226,125,24,16 ; vbroadcastss (%rax),%ymm2 DB 196,65,124,91,218 ; vcvtdq2ps %ymm10,%ymm11 - DB 196,98,125,24,37,120,33,0,0 ; vbroadcastss 0x2178(%rip),%ymm12 # 3f78 <_sk_callback_hsw+0x27d> - DB 196,98,125,24,45,115,33,0,0 ; vbroadcastss 0x2173(%rip),%ymm13 # 3f7c <_sk_callback_hsw+0x281> + DB 196,98,125,24,37,112,33,0,0 ; vbroadcastss 0x2170(%rip),%ymm12 # 3ef0 <_sk_callback_hsw+0x275> + DB 196,98,125,24,45,107,33,0,0 ; vbroadcastss 0x216b(%rip),%ymm13 # 3ef4 <_sk_callback_hsw+0x279> DB 196,65,44,84,213 ; vandps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,105,33,0,0 ; vbroadcastss 0x2169(%rip),%ymm13 # 3f80 <_sk_callback_hsw+0x285> + DB 196,98,125,24,45,97,33,0,0 ; vbroadcastss 0x2161(%rip),%ymm13 # 3ef8 <_sk_callback_hsw+0x27d> DB 196,65,44,86,213 ; vorps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,95,33,0,0 ; vbroadcastss 0x215f(%rip),%ymm13 # 3f84 <_sk_callback_hsw+0x289> + DB 196,98,125,24,45,87,33,0,0 ; vbroadcastss 0x2157(%rip),%ymm13 # 3efc <_sk_callback_hsw+0x281> DB 196,66,37,184,236 ; vfmadd231ps %ymm12,%ymm11,%ymm13 - DB 196,98,125,24,29,85,33,0,0 ; vbroadcastss 0x2155(%rip),%ymm11 # 3f88 <_sk_callback_hsw+0x28d> + DB 196,98,125,24,29,77,33,0,0 ; vbroadcastss 0x214d(%rip),%ymm11 # 3f00 <_sk_callback_hsw+0x285> DB 196,66,45,172,221 ; vfnmadd213ps %ymm13,%ymm10,%ymm11 - DB 196,98,125,24,37,75,33,0,0 ; vbroadcastss 0x214b(%rip),%ymm12 # 3f8c <_sk_callback_hsw+0x291> + DB 196,98,125,24,37,67,33,0,0 ; vbroadcastss 0x2143(%rip),%ymm12 # 3f04 <_sk_callback_hsw+0x289> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,65,33,0,0 ; vbroadcastss 0x2141(%rip),%ymm12 # 3f90 <_sk_callback_hsw+0x295> + DB 196,98,125,24,37,57,33,0,0 ; vbroadcastss 0x2139(%rip),%ymm12 # 3f08 <_sk_callback_hsw+0x28d> DB 196,65,28,94,210 ; vdivps %ymm10,%ymm12,%ymm10 DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 DB 196,193,108,89,210 ; vmulps %ymm10,%ymm2,%ymm2 DB 196,99,125,8,210,1 ; vroundps $0x1,%ymm2,%ymm10 DB 196,65,108,92,210 ; vsubps %ymm10,%ymm2,%ymm10 - DB 196,98,125,24,29,34,33,0,0 ; vbroadcastss 0x2122(%rip),%ymm11 # 3f94 <_sk_callback_hsw+0x299> + DB 196,98,125,24,29,26,33,0,0 ; vbroadcastss 0x211a(%rip),%ymm11 # 3f0c <_sk_callback_hsw+0x291> DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 - DB 196,98,125,24,29,24,33,0,0 ; vbroadcastss 0x2118(%rip),%ymm11 # 3f98 <_sk_callback_hsw+0x29d> + DB 196,98,125,24,29,16,33,0,0 ; vbroadcastss 0x2110(%rip),%ymm11 # 3f10 <_sk_callback_hsw+0x295> DB 196,98,45,172,218 ; vfnmadd213ps %ymm2,%ymm10,%ymm11 - DB 196,226,125,24,21,14,33,0,0 ; vbroadcastss 0x210e(%rip),%ymm2 # 3f9c <_sk_callback_hsw+0x2a1> + DB 196,226,125,24,21,6,33,0,0 ; vbroadcastss 0x2106(%rip),%ymm2 # 3f14 <_sk_callback_hsw+0x299> DB 196,193,108,92,210 ; vsubps %ymm10,%ymm2,%ymm2 - DB 196,98,125,24,21,4,33,0,0 ; vbroadcastss 0x2104(%rip),%ymm10 # 3fa0 <_sk_callback_hsw+0x2a5> + DB 196,98,125,24,21,252,32,0,0 ; vbroadcastss 0x20fc(%rip),%ymm10 # 3f18 <_sk_callback_hsw+0x29d> DB 197,172,94,210 ; vdivps %ymm2,%ymm10,%ymm2 DB 197,164,88,210 ; vaddps %ymm2,%ymm11,%ymm2 - DB 196,98,125,24,21,247,32,0,0 ; vbroadcastss 0x20f7(%rip),%ymm10 # 3fa4 <_sk_callback_hsw+0x2a9> + DB 196,98,125,24,21,239,32,0,0 ; vbroadcastss 0x20ef(%rip),%ymm10 # 3f1c <_sk_callback_hsw+0x2a1> DB 196,193,108,89,210 ; vmulps %ymm10,%ymm2,%ymm2 DB 197,253,91,210 ; vcvtps2dq %ymm2,%ymm2 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -1877,7 +1858,7 @@ _sk_parametric_b_hsw LABEL PROC DB 196,195,109,74,209,128 ; vblendvps %ymm8,%ymm9,%ymm2,%ymm2 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,108,95,208 ; vmaxps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,206,32,0,0 ; vbroadcastss 0x20ce(%rip),%ymm8 # 3fa8 <_sk_callback_hsw+0x2ad> + DB 196,98,125,24,5,198,32,0,0 ; vbroadcastss 0x20c6(%rip),%ymm8 # 3f20 <_sk_callback_hsw+0x2a5> DB 196,193,108,93,208 ; vminps %ymm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -1895,33 +1876,33 @@ _sk_parametric_a_hsw LABEL PROC DB 196,66,101,168,211 ; vfmadd213ps %ymm11,%ymm3,%ymm10 DB 196,226,125,24,24 ; vbroadcastss (%rax),%ymm3 DB 196,65,124,91,218 ; vcvtdq2ps %ymm10,%ymm11 - DB 196,98,125,24,37,134,32,0,0 ; vbroadcastss 0x2086(%rip),%ymm12 # 3fac <_sk_callback_hsw+0x2b1> - DB 196,98,125,24,45,129,32,0,0 ; vbroadcastss 0x2081(%rip),%ymm13 # 3fb0 <_sk_callback_hsw+0x2b5> + DB 196,98,125,24,37,126,32,0,0 ; vbroadcastss 0x207e(%rip),%ymm12 # 3f24 <_sk_callback_hsw+0x2a9> + DB 196,98,125,24,45,121,32,0,0 ; vbroadcastss 0x2079(%rip),%ymm13 # 3f28 <_sk_callback_hsw+0x2ad> DB 196,65,44,84,213 ; vandps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,119,32,0,0 ; vbroadcastss 0x2077(%rip),%ymm13 # 3fb4 <_sk_callback_hsw+0x2b9> + DB 196,98,125,24,45,111,32,0,0 ; vbroadcastss 0x206f(%rip),%ymm13 # 3f2c <_sk_callback_hsw+0x2b1> DB 196,65,44,86,213 ; vorps %ymm13,%ymm10,%ymm10 - DB 196,98,125,24,45,109,32,0,0 ; vbroadcastss 0x206d(%rip),%ymm13 # 3fb8 <_sk_callback_hsw+0x2bd> + DB 196,98,125,24,45,101,32,0,0 ; vbroadcastss 0x2065(%rip),%ymm13 # 3f30 <_sk_callback_hsw+0x2b5> DB 196,66,37,184,236 ; vfmadd231ps %ymm12,%ymm11,%ymm13 - DB 196,98,125,24,29,99,32,0,0 ; vbroadcastss 0x2063(%rip),%ymm11 # 3fbc <_sk_callback_hsw+0x2c1> + DB 196,98,125,24,29,91,32,0,0 ; vbroadcastss 0x205b(%rip),%ymm11 # 3f34 <_sk_callback_hsw+0x2b9> DB 196,66,45,172,221 ; vfnmadd213ps %ymm13,%ymm10,%ymm11 - DB 196,98,125,24,37,89,32,0,0 ; vbroadcastss 0x2059(%rip),%ymm12 # 3fc0 <_sk_callback_hsw+0x2c5> + DB 196,98,125,24,37,81,32,0,0 ; vbroadcastss 0x2051(%rip),%ymm12 # 3f38 <_sk_callback_hsw+0x2bd> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,79,32,0,0 ; vbroadcastss 0x204f(%rip),%ymm12 # 3fc4 <_sk_callback_hsw+0x2c9> + DB 196,98,125,24,37,71,32,0,0 ; vbroadcastss 0x2047(%rip),%ymm12 # 3f3c <_sk_callback_hsw+0x2c1> DB 196,65,28,94,210 ; vdivps %ymm10,%ymm12,%ymm10 DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 DB 196,193,100,89,218 ; vmulps %ymm10,%ymm3,%ymm3 DB 196,99,125,8,211,1 ; vroundps $0x1,%ymm3,%ymm10 DB 196,65,100,92,210 ; vsubps %ymm10,%ymm3,%ymm10 - DB 196,98,125,24,29,48,32,0,0 ; vbroadcastss 0x2030(%rip),%ymm11 # 3fc8 <_sk_callback_hsw+0x2cd> + DB 196,98,125,24,29,40,32,0,0 ; vbroadcastss 0x2028(%rip),%ymm11 # 3f40 <_sk_callback_hsw+0x2c5> DB 196,193,100,88,219 ; vaddps %ymm11,%ymm3,%ymm3 - DB 196,98,125,24,29,38,32,0,0 ; vbroadcastss 0x2026(%rip),%ymm11 # 3fcc <_sk_callback_hsw+0x2d1> + DB 196,98,125,24,29,30,32,0,0 ; vbroadcastss 0x201e(%rip),%ymm11 # 3f44 <_sk_callback_hsw+0x2c9> DB 196,98,45,172,219 ; vfnmadd213ps %ymm3,%ymm10,%ymm11 - DB 196,226,125,24,29,28,32,0,0 ; vbroadcastss 0x201c(%rip),%ymm3 # 3fd0 <_sk_callback_hsw+0x2d5> + DB 196,226,125,24,29,20,32,0,0 ; vbroadcastss 0x2014(%rip),%ymm3 # 3f48 <_sk_callback_hsw+0x2cd> DB 196,193,100,92,218 ; vsubps %ymm10,%ymm3,%ymm3 - DB 196,98,125,24,21,18,32,0,0 ; vbroadcastss 0x2012(%rip),%ymm10 # 3fd4 <_sk_callback_hsw+0x2d9> + DB 196,98,125,24,21,10,32,0,0 ; vbroadcastss 0x200a(%rip),%ymm10 # 3f4c <_sk_callback_hsw+0x2d1> DB 197,172,94,219 ; vdivps %ymm3,%ymm10,%ymm3 DB 197,164,88,219 ; vaddps %ymm3,%ymm11,%ymm3 - DB 196,98,125,24,21,5,32,0,0 ; vbroadcastss 0x2005(%rip),%ymm10 # 3fd8 <_sk_callback_hsw+0x2dd> + DB 196,98,125,24,21,253,31,0,0 ; vbroadcastss 0x1ffd(%rip),%ymm10 # 3f50 <_sk_callback_hsw+0x2d5> DB 196,193,100,89,218 ; vmulps %ymm10,%ymm3,%ymm3 DB 197,253,91,219 ; vcvtps2dq %ymm3,%ymm3 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -1929,33 +1910,33 @@ _sk_parametric_a_hsw LABEL PROC DB 196,195,101,74,217,128 ; vblendvps %ymm8,%ymm9,%ymm3,%ymm3 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,100,95,216 ; vmaxps %ymm8,%ymm3,%ymm3 - DB 196,98,125,24,5,220,31,0,0 ; vbroadcastss 0x1fdc(%rip),%ymm8 # 3fdc <_sk_callback_hsw+0x2e1> + DB 196,98,125,24,5,212,31,0,0 ; vbroadcastss 0x1fd4(%rip),%ymm8 # 3f54 <_sk_callback_hsw+0x2d9> DB 196,193,100,93,216 ; vminps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax PUBLIC _sk_lab_to_xyz_hsw _sk_lab_to_xyz_hsw LABEL PROC - DB 196,98,125,24,5,206,31,0,0 ; vbroadcastss 0x1fce(%rip),%ymm8 # 3fe0 <_sk_callback_hsw+0x2e5> - DB 196,98,125,24,13,201,31,0,0 ; vbroadcastss 0x1fc9(%rip),%ymm9 # 3fe4 <_sk_callback_hsw+0x2e9> - DB 196,98,125,24,21,196,31,0,0 ; vbroadcastss 0x1fc4(%rip),%ymm10 # 3fe8 <_sk_callback_hsw+0x2ed> + DB 196,98,125,24,5,198,31,0,0 ; vbroadcastss 0x1fc6(%rip),%ymm8 # 3f58 <_sk_callback_hsw+0x2dd> + DB 196,98,125,24,13,193,31,0,0 ; vbroadcastss 0x1fc1(%rip),%ymm9 # 3f5c <_sk_callback_hsw+0x2e1> + DB 196,98,125,24,21,188,31,0,0 ; vbroadcastss 0x1fbc(%rip),%ymm10 # 3f60 <_sk_callback_hsw+0x2e5> DB 196,194,53,168,202 ; vfmadd213ps %ymm10,%ymm9,%ymm1 DB 196,194,53,168,210 ; vfmadd213ps %ymm10,%ymm9,%ymm2 - DB 196,98,125,24,13,181,31,0,0 ; vbroadcastss 0x1fb5(%rip),%ymm9 # 3fec <_sk_callback_hsw+0x2f1> + DB 196,98,125,24,13,173,31,0,0 ; vbroadcastss 0x1fad(%rip),%ymm9 # 3f64 <_sk_callback_hsw+0x2e9> DB 196,66,125,184,200 ; vfmadd231ps %ymm8,%ymm0,%ymm9 - DB 196,226,125,24,5,171,31,0,0 ; vbroadcastss 0x1fab(%rip),%ymm0 # 3ff0 <_sk_callback_hsw+0x2f5> + DB 196,226,125,24,5,163,31,0,0 ; vbroadcastss 0x1fa3(%rip),%ymm0 # 3f68 <_sk_callback_hsw+0x2ed> DB 197,180,89,192 ; vmulps %ymm0,%ymm9,%ymm0 - DB 196,98,125,24,5,162,31,0,0 ; vbroadcastss 0x1fa2(%rip),%ymm8 # 3ff4 <_sk_callback_hsw+0x2f9> + DB 196,98,125,24,5,154,31,0,0 ; vbroadcastss 0x1f9a(%rip),%ymm8 # 3f6c <_sk_callback_hsw+0x2f1> DB 196,98,117,168,192 ; vfmadd213ps %ymm0,%ymm1,%ymm8 - DB 196,98,125,24,13,152,31,0,0 ; vbroadcastss 0x1f98(%rip),%ymm9 # 3ff8 <_sk_callback_hsw+0x2fd> + DB 196,98,125,24,13,144,31,0,0 ; vbroadcastss 0x1f90(%rip),%ymm9 # 3f70 <_sk_callback_hsw+0x2f5> DB 196,98,109,172,200 ; vfnmadd213ps %ymm0,%ymm2,%ymm9 DB 196,193,60,89,200 ; vmulps %ymm8,%ymm8,%ymm1 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 - DB 196,226,125,24,21,133,31,0,0 ; vbroadcastss 0x1f85(%rip),%ymm2 # 3ffc <_sk_callback_hsw+0x301> + DB 196,226,125,24,21,125,31,0,0 ; vbroadcastss 0x1f7d(%rip),%ymm2 # 3f74 <_sk_callback_hsw+0x2f9> DB 197,108,194,209,1 ; vcmpltps %ymm1,%ymm2,%ymm10 - DB 196,98,125,24,29,123,31,0,0 ; vbroadcastss 0x1f7b(%rip),%ymm11 # 4000 <_sk_callback_hsw+0x305> + DB 196,98,125,24,29,115,31,0,0 ; vbroadcastss 0x1f73(%rip),%ymm11 # 3f78 <_sk_callback_hsw+0x2fd> DB 196,65,60,88,195 ; vaddps %ymm11,%ymm8,%ymm8 - DB 196,98,125,24,37,113,31,0,0 ; vbroadcastss 0x1f71(%rip),%ymm12 # 4004 <_sk_callback_hsw+0x309> + DB 196,98,125,24,37,105,31,0,0 ; vbroadcastss 0x1f69(%rip),%ymm12 # 3f7c <_sk_callback_hsw+0x301> DB 196,65,60,89,196 ; vmulps %ymm12,%ymm8,%ymm8 DB 196,99,61,74,193,160 ; vblendvps %ymm10,%ymm1,%ymm8,%ymm8 DB 197,252,89,200 ; vmulps %ymm0,%ymm0,%ymm1 @@ -1970,9 +1951,9 @@ _sk_lab_to_xyz_hsw LABEL PROC DB 196,65,52,88,203 ; vaddps %ymm11,%ymm9,%ymm9 DB 196,65,52,89,204 ; vmulps %ymm12,%ymm9,%ymm9 DB 196,227,53,74,208,32 ; vblendvps %ymm2,%ymm0,%ymm9,%ymm2 - DB 196,226,125,24,5,38,31,0,0 ; vbroadcastss 0x1f26(%rip),%ymm0 # 4008 <_sk_callback_hsw+0x30d> + DB 196,226,125,24,5,30,31,0,0 ; vbroadcastss 0x1f1e(%rip),%ymm0 # 3f80 <_sk_callback_hsw+0x305> DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 - DB 196,98,125,24,5,29,31,0,0 ; vbroadcastss 0x1f1d(%rip),%ymm8 # 400c <_sk_callback_hsw+0x311> + DB 196,98,125,24,5,21,31,0,0 ; vbroadcastss 0x1f15(%rip),%ymm8 # 3f84 <_sk_callback_hsw+0x309> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -1984,11 +1965,11 @@ _sk_load_a8_hsw LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 72,1,248 ; add %rdi,%rax DB 77,133,192 ; test %r8,%r8 - DB 117,45 ; jne 2135 <_sk_load_a8_hsw+0x3d> + DB 117,45 ; jne 20b5 <_sk_load_a8_hsw+0x3d> DB 197,250,126,0 ; vmovq (%rax),%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,242,30,0,0 ; vbroadcastss 0x1ef2(%rip),%ymm1 # 4010 <_sk_callback_hsw+0x315> + DB 196,226,125,24,13,234,30,0,0 ; vbroadcastss 0x1eea(%rip),%ymm1 # 3f88 <_sk_callback_hsw+0x30d> DB 197,252,89,217 ; vmulps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -2005,9 +1986,9 @@ _sk_load_a8_hsw LABEL PROC DB 77,9,217 ; or %r11,%r9 DB 72,131,193,8 ; add $0x8,%rcx DB 73,255,202 ; dec %r10 - DB 117,234 ; jne 213d <_sk_load_a8_hsw+0x45> + DB 117,234 ; jne 20bd <_sk_load_a8_hsw+0x45> DB 196,193,249,110,193 ; vmovq %r9,%xmm0 - DB 235,178 ; jmp 210c <_sk_load_a8_hsw+0x14> + DB 235,178 ; jmp 208c <_sk_load_a8_hsw+0x14> PUBLIC _sk_gather_a8_hsw _sk_gather_a8_hsw LABEL PROC @@ -2051,7 +2032,7 @@ _sk_gather_a8_hsw LABEL PROC DB 196,227,121,32,192,7 ; vpinsrb $0x7,%eax,%xmm0,%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,253,29,0,0 ; vbroadcastss 0x1dfd(%rip),%ymm1 # 4014 <_sk_callback_hsw+0x319> + DB 196,226,125,24,13,245,29,0,0 ; vbroadcastss 0x1df5(%rip),%ymm1 # 3f8c <_sk_callback_hsw+0x311> DB 197,252,89,217 ; vmulps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -2067,14 +2048,14 @@ PUBLIC _sk_store_a8_hsw _sk_store_a8_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,216,29,0,0 ; vbroadcastss 0x1dd8(%rip),%ymm8 # 4018 <_sk_callback_hsw+0x31d> + DB 196,98,125,24,5,208,29,0,0 ; vbroadcastss 0x1dd0(%rip),%ymm8 # 3f90 <_sk_callback_hsw+0x315> DB 196,65,100,89,192 ; vmulps %ymm8,%ymm3,%ymm8 DB 196,65,125,91,192 ; vcvtps2dq %ymm8,%ymm8 DB 196,67,125,25,193,1 ; vextractf128 $0x1,%ymm8,%xmm9 DB 196,66,57,43,193 ; vpackusdw %xmm9,%xmm8,%xmm8 DB 196,65,57,103,192 ; vpackuswb %xmm8,%xmm8,%xmm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,10 ; jne 2269 <_sk_store_a8_hsw+0x37> + DB 117,10 ; jne 21e9 <_sk_store_a8_hsw+0x37> DB 196,65,123,17,4,58 ; vmovsd %xmm8,(%r10,%rdi,1) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -2082,10 +2063,10 @@ _sk_store_a8_hsw LABEL PROC DB 65,128,224,7 ; and $0x7,%r8b DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 119,236 ; ja 2265 <_sk_store_a8_hsw+0x33> + DB 119,236 ; ja 21e5 <_sk_store_a8_hsw+0x33> DB 196,66,121,48,192 ; vpmovzxbw %xmm8,%xmm8 DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,67,0,0,0 ; lea 0x43(%rip),%r9 # 22cc <_sk_store_a8_hsw+0x9a> + DB 76,141,13,67,0,0,0 ; lea 0x43(%rip),%r9 # 224c <_sk_store_a8_hsw+0x9a> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -2096,7 +2077,7 @@ _sk_store_a8_hsw LABEL PROC DB 196,67,121,20,68,58,2,4 ; vpextrb $0x4,%xmm8,0x2(%r10,%rdi,1) DB 196,67,121,20,68,58,1,2 ; vpextrb $0x2,%xmm8,0x1(%r10,%rdi,1) DB 196,67,121,20,4,58,0 ; vpextrb $0x0,%xmm8,(%r10,%rdi,1) - DB 235,154 ; jmp 2265 <_sk_store_a8_hsw+0x33> + DB 235,154 ; jmp 21e5 <_sk_store_a8_hsw+0x33> DB 144 ; nop DB 246,255 ; idiv %bh DB 255 ; (bad) @@ -2128,14 +2109,14 @@ _sk_load_g8_hsw LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 72,1,248 ; add %rdi,%rax DB 77,133,192 ; test %r8,%r8 - DB 117,50 ; jne 232a <_sk_load_g8_hsw+0x42> + DB 117,50 ; jne 22aa <_sk_load_g8_hsw+0x42> DB 197,250,126,0 ; vmovq (%rax),%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,14,29,0,0 ; vbroadcastss 0x1d0e(%rip),%ymm1 # 401c <_sk_callback_hsw+0x321> + DB 196,226,125,24,13,6,29,0,0 ; vbroadcastss 0x1d06(%rip),%ymm1 # 3f94 <_sk_callback_hsw+0x319> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,3,29,0,0 ; vbroadcastss 0x1d03(%rip),%ymm3 # 4020 <_sk_callback_hsw+0x325> + DB 196,226,125,24,29,251,28,0,0 ; vbroadcastss 0x1cfb(%rip),%ymm3 # 3f98 <_sk_callback_hsw+0x31d> DB 76,137,193 ; mov %r8,%rcx DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 @@ -2149,9 +2130,9 @@ _sk_load_g8_hsw LABEL PROC DB 77,9,217 ; or %r11,%r9 DB 72,131,193,8 ; add $0x8,%rcx DB 73,255,202 ; dec %r10 - DB 117,234 ; jne 2332 <_sk_load_g8_hsw+0x4a> + DB 117,234 ; jne 22b2 <_sk_load_g8_hsw+0x4a> DB 196,193,249,110,193 ; vmovq %r9,%xmm0 - DB 235,173 ; jmp 22fc <_sk_load_g8_hsw+0x14> + DB 235,173 ; jmp 227c <_sk_load_g8_hsw+0x14> PUBLIC _sk_gather_g8_hsw _sk_gather_g8_hsw LABEL PROC @@ -2195,10 +2176,10 @@ _sk_gather_g8_hsw LABEL PROC DB 196,227,121,32,192,7 ; vpinsrb $0x7,%eax,%xmm0,%xmm0 DB 196,226,125,49,192 ; vpmovzxbd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,24,28,0,0 ; vbroadcastss 0x1c18(%rip),%ymm1 # 4024 <_sk_callback_hsw+0x329> + DB 196,226,125,24,13,16,28,0,0 ; vbroadcastss 0x1c10(%rip),%ymm1 # 3f9c <_sk_callback_hsw+0x321> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,13,28,0,0 ; vbroadcastss 0x1c0d(%rip),%ymm3 # 4028 <_sk_callback_hsw+0x32d> + DB 196,226,125,24,29,5,28,0,0 ; vbroadcastss 0x1c05(%rip),%ymm3 # 3fa0 <_sk_callback_hsw+0x325> DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 DB 91 ; pop %rbx @@ -2212,9 +2193,9 @@ _sk_gather_i8_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 73,137,192 ; mov %rax,%r8 DB 77,133,192 ; test %r8,%r8 - DB 116,5 ; je 243b <_sk_gather_i8_hsw+0xf> + DB 116,5 ; je 23bb <_sk_gather_i8_hsw+0xf> DB 76,137,192 ; mov %r8,%rax - DB 235,2 ; jmp 243d <_sk_gather_i8_hsw+0x11> + DB 235,2 ; jmp 23bd <_sk_gather_i8_hsw+0x11> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,87 ; push %r15 DB 65,86 ; push %r14 @@ -2252,14 +2233,14 @@ _sk_gather_i8_hsw LABEL PROC DB 73,139,64,8 ; mov 0x8(%r8),%rax DB 197,245,118,201 ; vpcmpeqd %ymm1,%ymm1,%ymm1 DB 196,226,117,144,28,128 ; vpgatherdd %ymm1,(%rax,%ymm0,4),%ymm3 - DB 197,229,219,5,245,28,0,0 ; vpand 0x1cf5(%rip),%ymm3,%ymm0 # 41e0 <_sk_callback_hsw+0x4e5> + DB 197,229,219,5,245,28,0,0 ; vpand 0x1cf5(%rip),%ymm3,%ymm0 # 4160 <_sk_callback_hsw+0x4e5> DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,5,52,27,0,0 ; vbroadcastss 0x1b34(%rip),%ymm8 # 402c <_sk_callback_hsw+0x331> + DB 196,98,125,24,5,44,27,0,0 ; vbroadcastss 0x1b2c(%rip),%ymm8 # 3fa4 <_sk_callback_hsw+0x329> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,226,101,0,13,250,28,0,0 ; vpshufb 0x1cfa(%rip),%ymm3,%ymm1 # 4200 <_sk_callback_hsw+0x505> + DB 196,226,101,0,13,250,28,0,0 ; vpshufb 0x1cfa(%rip),%ymm3,%ymm1 # 4180 <_sk_callback_hsw+0x505> DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 - DB 196,226,101,0,21,8,29,0,0 ; vpshufb 0x1d08(%rip),%ymm3,%ymm2 # 4220 <_sk_callback_hsw+0x525> + DB 196,226,101,0,21,8,29,0,0 ; vpshufb 0x1d08(%rip),%ymm3,%ymm2 # 41a0 <_sk_callback_hsw+0x525> DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 197,229,114,211,24 ; vpsrld $0x18,%ymm3,%ymm3 @@ -2278,35 +2259,35 @@ _sk_load_565_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 DB 72,133,201 ; test %rcx,%rcx - DB 117,114 ; jne 25b8 <_sk_load_565_hsw+0x7c> + DB 117,114 ; jne 2538 <_sk_load_565_hsw+0x7c> DB 196,193,122,111,4,122 ; vmovdqu (%r10,%rdi,2),%xmm0 DB 196,226,125,51,208 ; vpmovzxwd %xmm0,%ymm2 - DB 196,226,125,88,5,214,26,0,0 ; vpbroadcastd 0x1ad6(%rip),%ymm0 # 4030 <_sk_callback_hsw+0x335> + DB 196,226,125,88,5,206,26,0,0 ; vpbroadcastd 0x1ace(%rip),%ymm0 # 3fa8 <_sk_callback_hsw+0x32d> DB 197,237,219,192 ; vpand %ymm0,%ymm2,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,201,26,0,0 ; vbroadcastss 0x1ac9(%rip),%ymm1 # 4034 <_sk_callback_hsw+0x339> + DB 196,226,125,24,13,193,26,0,0 ; vbroadcastss 0x1ac1(%rip),%ymm1 # 3fac <_sk_callback_hsw+0x331> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,88,13,192,26,0,0 ; vpbroadcastd 0x1ac0(%rip),%ymm1 # 4038 <_sk_callback_hsw+0x33d> + DB 196,226,125,88,13,184,26,0,0 ; vpbroadcastd 0x1ab8(%rip),%ymm1 # 3fb0 <_sk_callback_hsw+0x335> DB 197,237,219,201 ; vpand %ymm1,%ymm2,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,29,179,26,0,0 ; vbroadcastss 0x1ab3(%rip),%ymm3 # 403c <_sk_callback_hsw+0x341> + DB 196,226,125,24,29,171,26,0,0 ; vbroadcastss 0x1aab(%rip),%ymm3 # 3fb4 <_sk_callback_hsw+0x339> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 - DB 196,226,125,88,29,170,26,0,0 ; vpbroadcastd 0x1aaa(%rip),%ymm3 # 4040 <_sk_callback_hsw+0x345> + DB 196,226,125,88,29,162,26,0,0 ; vpbroadcastd 0x1aa2(%rip),%ymm3 # 3fb8 <_sk_callback_hsw+0x33d> DB 197,237,219,211 ; vpand %ymm3,%ymm2,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,226,125,24,29,157,26,0,0 ; vbroadcastss 0x1a9d(%rip),%ymm3 # 4044 <_sk_callback_hsw+0x349> + DB 196,226,125,24,29,149,26,0,0 ; vbroadcastss 0x1a95(%rip),%ymm3 # 3fbc <_sk_callback_hsw+0x341> DB 197,236,89,211 ; vmulps %ymm3,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,146,26,0,0 ; vbroadcastss 0x1a92(%rip),%ymm3 # 4048 <_sk_callback_hsw+0x34d> + DB 196,226,125,24,29,138,26,0,0 ; vbroadcastss 0x1a8a(%rip),%ymm3 # 3fc0 <_sk_callback_hsw+0x345> DB 255,224 ; jmpq *%rax DB 65,137,200 ; mov %ecx,%r8d DB 65,128,224,7 ; and $0x7,%r8b DB 197,249,239,192 ; vpxor %xmm0,%xmm0,%xmm0 DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 119,128 ; ja 254c <_sk_load_565_hsw+0x10> + DB 119,128 ; ja 24cc <_sk_load_565_hsw+0x10> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,73,0,0,0 ; lea 0x49(%rip),%r9 # 2620 <_sk_load_565_hsw+0xe4> + DB 76,141,13,73,0,0,0 ; lea 0x49(%rip),%r9 # 25a0 <_sk_load_565_hsw+0xe4> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -2318,7 +2299,7 @@ _sk_load_565_hsw LABEL PROC DB 196,193,121,196,68,122,4,2 ; vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm0,%xmm0 DB 196,193,121,196,68,122,2,1 ; vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm0,%xmm0 DB 196,193,121,196,4,122,0 ; vpinsrw $0x0,(%r10,%rdi,2),%xmm0,%xmm0 - DB 233,44,255,255,255 ; jmpq 254c <_sk_load_565_hsw+0x10> + DB 233,44,255,255,255 ; jmpq 24cc <_sk_load_565_hsw+0x10> DB 244 ; hlt DB 255 ; (bad) DB 255 ; (bad) @@ -2386,23 +2367,23 @@ _sk_gather_565_hsw LABEL PROC DB 65,15,183,4,88 ; movzwl (%r8,%rbx,2),%eax DB 197,249,196,192,7 ; vpinsrw $0x7,%eax,%xmm0,%xmm0 DB 196,226,125,51,208 ; vpmovzxwd %xmm0,%ymm2 - DB 196,226,125,88,5,85,25,0,0 ; vpbroadcastd 0x1955(%rip),%ymm0 # 404c <_sk_callback_hsw+0x351> + DB 196,226,125,88,5,77,25,0,0 ; vpbroadcastd 0x194d(%rip),%ymm0 # 3fc4 <_sk_callback_hsw+0x349> DB 197,237,219,192 ; vpand %ymm0,%ymm2,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,72,25,0,0 ; vbroadcastss 0x1948(%rip),%ymm1 # 4050 <_sk_callback_hsw+0x355> + DB 196,226,125,24,13,64,25,0,0 ; vbroadcastss 0x1940(%rip),%ymm1 # 3fc8 <_sk_callback_hsw+0x34d> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,88,13,63,25,0,0 ; vpbroadcastd 0x193f(%rip),%ymm1 # 4054 <_sk_callback_hsw+0x359> + DB 196,226,125,88,13,55,25,0,0 ; vpbroadcastd 0x1937(%rip),%ymm1 # 3fcc <_sk_callback_hsw+0x351> DB 197,237,219,201 ; vpand %ymm1,%ymm2,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,29,50,25,0,0 ; vbroadcastss 0x1932(%rip),%ymm3 # 4058 <_sk_callback_hsw+0x35d> + DB 196,226,125,24,29,42,25,0,0 ; vbroadcastss 0x192a(%rip),%ymm3 # 3fd0 <_sk_callback_hsw+0x355> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 - DB 196,226,125,88,29,41,25,0,0 ; vpbroadcastd 0x1929(%rip),%ymm3 # 405c <_sk_callback_hsw+0x361> + DB 196,226,125,88,29,33,25,0,0 ; vpbroadcastd 0x1921(%rip),%ymm3 # 3fd4 <_sk_callback_hsw+0x359> DB 197,237,219,211 ; vpand %ymm3,%ymm2,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,226,125,24,29,28,25,0,0 ; vbroadcastss 0x191c(%rip),%ymm3 # 4060 <_sk_callback_hsw+0x365> + DB 196,226,125,24,29,20,25,0,0 ; vbroadcastss 0x1914(%rip),%ymm3 # 3fd8 <_sk_callback_hsw+0x35d> DB 197,236,89,211 ; vmulps %ymm3,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,17,25,0,0 ; vbroadcastss 0x1911(%rip),%ymm3 # 4064 <_sk_callback_hsw+0x369> + DB 196,226,125,24,29,9,25,0,0 ; vbroadcastss 0x1909(%rip),%ymm3 # 3fdc <_sk_callback_hsw+0x361> DB 91 ; pop %rbx DB 65,92 ; pop %r12 DB 65,94 ; pop %r14 @@ -2413,11 +2394,11 @@ PUBLIC _sk_store_565_hsw _sk_store_565_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,254,24,0,0 ; vbroadcastss 0x18fe(%rip),%ymm8 # 4068 <_sk_callback_hsw+0x36d> + DB 196,98,125,24,5,246,24,0,0 ; vbroadcastss 0x18f6(%rip),%ymm8 # 3fe0 <_sk_callback_hsw+0x365> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,193,53,114,241,11 ; vpslld $0xb,%ymm9,%ymm9 - DB 196,98,125,24,21,233,24,0,0 ; vbroadcastss 0x18e9(%rip),%ymm10 # 406c <_sk_callback_hsw+0x371> + DB 196,98,125,24,21,225,24,0,0 ; vbroadcastss 0x18e1(%rip),%ymm10 # 3fe4 <_sk_callback_hsw+0x369> DB 196,65,116,89,210 ; vmulps %ymm10,%ymm1,%ymm10 DB 196,65,125,91,210 ; vcvtps2dq %ymm10,%ymm10 DB 196,193,45,114,242,5 ; vpslld $0x5,%ymm10,%ymm10 @@ -2428,7 +2409,7 @@ _sk_store_565_hsw LABEL PROC DB 196,67,125,57,193,1 ; vextracti128 $0x1,%ymm8,%xmm9 DB 196,66,57,43,193 ; vpackusdw %xmm9,%xmm8,%xmm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,10 ; jne 27c1 <_sk_store_565_hsw+0x65> + DB 117,10 ; jne 2741 <_sk_store_565_hsw+0x65> DB 196,65,122,127,4,122 ; vmovdqu %xmm8,(%r10,%rdi,2) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -2436,9 +2417,9 @@ _sk_store_565_hsw LABEL PROC DB 65,128,224,7 ; and $0x7,%r8b DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 119,236 ; ja 27bd <_sk_store_565_hsw+0x61> + DB 119,236 ; ja 273d <_sk_store_565_hsw+0x61> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,68,0,0,0 ; lea 0x44(%rip),%r9 # 2820 <_sk_store_565_hsw+0xc4> + DB 76,141,13,68,0,0,0 ; lea 0x44(%rip),%r9 # 27a0 <_sk_store_565_hsw+0xc4> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -2449,7 +2430,7 @@ _sk_store_565_hsw LABEL PROC DB 196,67,121,21,68,122,4,2 ; vpextrw $0x2,%xmm8,0x4(%r10,%rdi,2) DB 196,67,121,21,68,122,2,1 ; vpextrw $0x1,%xmm8,0x2(%r10,%rdi,2) DB 196,67,121,21,4,122,0 ; vpextrw $0x0,%xmm8,(%r10,%rdi,2) - DB 235,159 ; jmp 27bd <_sk_store_565_hsw+0x61> + DB 235,159 ; jmp 273d <_sk_store_565_hsw+0x61> DB 102,144 ; xchg %ax,%ax DB 245 ; cmc DB 255 ; (bad) @@ -2480,28 +2461,28 @@ _sk_load_4444_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,138,0,0,0 ; jne 28d4 <_sk_load_4444_hsw+0x98> + DB 15,133,138,0,0,0 ; jne 2854 <_sk_load_4444_hsw+0x98> DB 196,193,122,111,4,122 ; vmovdqu (%r10,%rdi,2),%xmm0 DB 196,226,125,51,216 ; vpmovzxwd %xmm0,%ymm3 - DB 196,226,125,88,5,18,24,0,0 ; vpbroadcastd 0x1812(%rip),%ymm0 # 4070 <_sk_callback_hsw+0x375> + DB 196,226,125,88,5,10,24,0,0 ; vpbroadcastd 0x180a(%rip),%ymm0 # 3fe8 <_sk_callback_hsw+0x36d> DB 197,229,219,192 ; vpand %ymm0,%ymm3,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,5,24,0,0 ; vbroadcastss 0x1805(%rip),%ymm1 # 4074 <_sk_callback_hsw+0x379> + DB 196,226,125,24,13,253,23,0,0 ; vbroadcastss 0x17fd(%rip),%ymm1 # 3fec <_sk_callback_hsw+0x371> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,88,13,252,23,0,0 ; vpbroadcastd 0x17fc(%rip),%ymm1 # 4078 <_sk_callback_hsw+0x37d> + DB 196,226,125,88,13,244,23,0,0 ; vpbroadcastd 0x17f4(%rip),%ymm1 # 3ff0 <_sk_callback_hsw+0x375> DB 197,229,219,201 ; vpand %ymm1,%ymm3,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,21,239,23,0,0 ; vbroadcastss 0x17ef(%rip),%ymm2 # 407c <_sk_callback_hsw+0x381> + DB 196,226,125,24,21,231,23,0,0 ; vbroadcastss 0x17e7(%rip),%ymm2 # 3ff4 <_sk_callback_hsw+0x379> DB 197,244,89,202 ; vmulps %ymm2,%ymm1,%ymm1 - DB 196,226,125,88,21,230,23,0,0 ; vpbroadcastd 0x17e6(%rip),%ymm2 # 4080 <_sk_callback_hsw+0x385> + DB 196,226,125,88,21,222,23,0,0 ; vpbroadcastd 0x17de(%rip),%ymm2 # 3ff8 <_sk_callback_hsw+0x37d> DB 197,229,219,210 ; vpand %ymm2,%ymm3,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,98,125,24,5,217,23,0,0 ; vbroadcastss 0x17d9(%rip),%ymm8 # 4084 <_sk_callback_hsw+0x389> + DB 196,98,125,24,5,209,23,0,0 ; vbroadcastss 0x17d1(%rip),%ymm8 # 3ffc <_sk_callback_hsw+0x381> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 - DB 196,98,125,88,5,207,23,0,0 ; vpbroadcastd 0x17cf(%rip),%ymm8 # 4088 <_sk_callback_hsw+0x38d> + DB 196,98,125,88,5,199,23,0,0 ; vpbroadcastd 0x17c7(%rip),%ymm8 # 4000 <_sk_callback_hsw+0x385> DB 196,193,101,219,216 ; vpand %ymm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,193,23,0,0 ; vbroadcastss 0x17c1(%rip),%ymm8 # 408c <_sk_callback_hsw+0x391> + DB 196,98,125,24,5,185,23,0,0 ; vbroadcastss 0x17b9(%rip),%ymm8 # 4004 <_sk_callback_hsw+0x389> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -2510,9 +2491,9 @@ _sk_load_4444_hsw LABEL PROC DB 197,249,239,192 ; vpxor %xmm0,%xmm0,%xmm0 DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 15,135,100,255,255,255 ; ja 2850 <_sk_load_4444_hsw+0x14> + DB 15,135,100,255,255,255 ; ja 27d0 <_sk_load_4444_hsw+0x14> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,73,0,0,0 ; lea 0x49(%rip),%r9 # 2940 <_sk_load_4444_hsw+0x104> + DB 76,141,13,73,0,0,0 ; lea 0x49(%rip),%r9 # 28c0 <_sk_load_4444_hsw+0x104> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -2524,7 +2505,7 @@ _sk_load_4444_hsw LABEL PROC DB 196,193,121,196,68,122,4,2 ; vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm0,%xmm0 DB 196,193,121,196,68,122,2,1 ; vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm0,%xmm0 DB 196,193,121,196,4,122,0 ; vpinsrw $0x0,(%r10,%rdi,2),%xmm0,%xmm0 - DB 233,16,255,255,255 ; jmpq 2850 <_sk_load_4444_hsw+0x14> + DB 233,16,255,255,255 ; jmpq 27d0 <_sk_load_4444_hsw+0x14> DB 244 ; hlt DB 255 ; (bad) DB 255 ; (bad) @@ -2592,25 +2573,25 @@ _sk_gather_4444_hsw LABEL PROC DB 65,15,183,4,88 ; movzwl (%r8,%rbx,2),%eax DB 197,249,196,192,7 ; vpinsrw $0x7,%eax,%xmm0,%xmm0 DB 196,226,125,51,216 ; vpmovzxwd %xmm0,%ymm3 - DB 196,226,125,88,5,121,22,0,0 ; vpbroadcastd 0x1679(%rip),%ymm0 # 4090 <_sk_callback_hsw+0x395> + DB 196,226,125,88,5,113,22,0,0 ; vpbroadcastd 0x1671(%rip),%ymm0 # 4008 <_sk_callback_hsw+0x38d> DB 197,229,219,192 ; vpand %ymm0,%ymm3,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,108,22,0,0 ; vbroadcastss 0x166c(%rip),%ymm1 # 4094 <_sk_callback_hsw+0x399> + DB 196,226,125,24,13,100,22,0,0 ; vbroadcastss 0x1664(%rip),%ymm1 # 400c <_sk_callback_hsw+0x391> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,88,13,99,22,0,0 ; vpbroadcastd 0x1663(%rip),%ymm1 # 4098 <_sk_callback_hsw+0x39d> + DB 196,226,125,88,13,91,22,0,0 ; vpbroadcastd 0x165b(%rip),%ymm1 # 4010 <_sk_callback_hsw+0x395> DB 197,229,219,201 ; vpand %ymm1,%ymm3,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,21,86,22,0,0 ; vbroadcastss 0x1656(%rip),%ymm2 # 409c <_sk_callback_hsw+0x3a1> + DB 196,226,125,24,21,78,22,0,0 ; vbroadcastss 0x164e(%rip),%ymm2 # 4014 <_sk_callback_hsw+0x399> DB 197,244,89,202 ; vmulps %ymm2,%ymm1,%ymm1 - DB 196,226,125,88,21,77,22,0,0 ; vpbroadcastd 0x164d(%rip),%ymm2 # 40a0 <_sk_callback_hsw+0x3a5> + DB 196,226,125,88,21,69,22,0,0 ; vpbroadcastd 0x1645(%rip),%ymm2 # 4018 <_sk_callback_hsw+0x39d> DB 197,229,219,210 ; vpand %ymm2,%ymm3,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,98,125,24,5,64,22,0,0 ; vbroadcastss 0x1640(%rip),%ymm8 # 40a4 <_sk_callback_hsw+0x3a9> + DB 196,98,125,24,5,56,22,0,0 ; vbroadcastss 0x1638(%rip),%ymm8 # 401c <_sk_callback_hsw+0x3a1> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 - DB 196,98,125,88,5,54,22,0,0 ; vpbroadcastd 0x1636(%rip),%ymm8 # 40a8 <_sk_callback_hsw+0x3ad> + DB 196,98,125,88,5,46,22,0,0 ; vpbroadcastd 0x162e(%rip),%ymm8 # 4020 <_sk_callback_hsw+0x3a5> DB 196,193,101,219,216 ; vpand %ymm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,40,22,0,0 ; vbroadcastss 0x1628(%rip),%ymm8 # 40ac <_sk_callback_hsw+0x3b1> + DB 196,98,125,24,5,32,22,0,0 ; vbroadcastss 0x1620(%rip),%ymm8 # 4024 <_sk_callback_hsw+0x3a9> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 91 ; pop %rbx @@ -2623,7 +2604,7 @@ PUBLIC _sk_store_4444_hsw _sk_store_4444_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,14,22,0,0 ; vbroadcastss 0x160e(%rip),%ymm8 # 40b0 <_sk_callback_hsw+0x3b5> + DB 196,98,125,24,5,6,22,0,0 ; vbroadcastss 0x1606(%rip),%ymm8 # 4028 <_sk_callback_hsw+0x3ad> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,193,53,114,241,12 ; vpslld $0xc,%ymm9,%ymm9 @@ -2641,7 +2622,7 @@ _sk_store_4444_hsw LABEL PROC DB 196,67,125,57,193,1 ; vextracti128 $0x1,%ymm8,%xmm9 DB 196,66,57,43,193 ; vpackusdw %xmm9,%xmm8,%xmm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,10 ; jne 2b05 <_sk_store_4444_hsw+0x71> + DB 117,10 ; jne 2a85 <_sk_store_4444_hsw+0x71> DB 196,65,122,127,4,122 ; vmovdqu %xmm8,(%r10,%rdi,2) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -2649,9 +2630,9 @@ _sk_store_4444_hsw LABEL PROC DB 65,128,224,7 ; and $0x7,%r8b DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 119,236 ; ja 2b01 <_sk_store_4444_hsw+0x6d> + DB 119,236 ; ja 2a81 <_sk_store_4444_hsw+0x6d> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,68,0,0,0 ; lea 0x44(%rip),%r9 # 2b64 <_sk_store_4444_hsw+0xd0> + DB 76,141,13,68,0,0,0 ; lea 0x44(%rip),%r9 # 2ae4 <_sk_store_4444_hsw+0xd0> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -2662,7 +2643,7 @@ _sk_store_4444_hsw LABEL PROC DB 196,67,121,21,68,122,4,2 ; vpextrw $0x2,%xmm8,0x4(%r10,%rdi,2) DB 196,67,121,21,68,122,2,1 ; vpextrw $0x1,%xmm8,0x2(%r10,%rdi,2) DB 196,67,121,21,4,122,0 ; vpextrw $0x0,%xmm8,(%r10,%rdi,2) - DB 235,159 ; jmp 2b01 <_sk_store_4444_hsw+0x6d> + DB 235,159 ; jmp 2a81 <_sk_store_4444_hsw+0x6d> DB 102,144 ; xchg %ax,%ax DB 245 ; cmc DB 255 ; (bad) @@ -2695,16 +2676,16 @@ _sk_load_8888_hsw LABEL PROC DB 76,141,12,189,0,0,0,0 ; lea 0x0(,%rdi,4),%r9 DB 76,3,8 ; add (%rax),%r9 DB 77,133,192 ; test %r8,%r8 - DB 117,88 ; jne 2bed <_sk_load_8888_hsw+0x6d> + DB 117,88 ; jne 2b6d <_sk_load_8888_hsw+0x6d> DB 196,193,126,111,25 ; vmovdqu (%r9),%ymm3 - DB 197,229,219,5,158,22,0,0 ; vpand 0x169e(%rip),%ymm3,%ymm0 # 4240 <_sk_callback_hsw+0x545> + DB 197,229,219,5,158,22,0,0 ; vpand 0x169e(%rip),%ymm3,%ymm0 # 41c0 <_sk_callback_hsw+0x545> DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,5,5,21,0,0 ; vbroadcastss 0x1505(%rip),%ymm8 # 40b4 <_sk_callback_hsw+0x3b9> + DB 196,98,125,24,5,253,20,0,0 ; vbroadcastss 0x14fd(%rip),%ymm8 # 402c <_sk_callback_hsw+0x3b1> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,226,101,0,13,163,22,0,0 ; vpshufb 0x16a3(%rip),%ymm3,%ymm1 # 4260 <_sk_callback_hsw+0x565> + DB 196,226,101,0,13,163,22,0,0 ; vpshufb 0x16a3(%rip),%ymm3,%ymm1 # 41e0 <_sk_callback_hsw+0x565> DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 - DB 196,226,101,0,21,177,22,0,0 ; vpshufb 0x16b1(%rip),%ymm3,%ymm2 # 4280 <_sk_callback_hsw+0x585> + DB 196,226,101,0,21,177,22,0,0 ; vpshufb 0x16b1(%rip),%ymm3,%ymm2 # 4200 <_sk_callback_hsw+0x585> DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 197,229,114,211,24 ; vpsrld $0x18,%ymm3,%ymm3 @@ -2721,7 +2702,7 @@ _sk_load_8888_hsw LABEL PROC DB 196,225,249,110,192 ; vmovq %rax,%xmm0 DB 196,226,125,33,192 ; vpmovsxbd %xmm0,%ymm0 DB 196,194,125,140,25 ; vpmaskmovd (%r9),%ymm0,%ymm3 - DB 235,135 ; jmp 2b9a <_sk_load_8888_hsw+0x1a> + DB 235,135 ; jmp 2b1a <_sk_load_8888_hsw+0x1a> PUBLIC _sk_gather_8888_hsw _sk_gather_8888_hsw LABEL PROC @@ -2734,14 +2715,14 @@ _sk_gather_8888_hsw LABEL PROC DB 197,245,254,192 ; vpaddd %ymm0,%ymm1,%ymm0 DB 197,245,118,201 ; vpcmpeqd %ymm1,%ymm1,%ymm1 DB 196,194,117,144,28,128 ; vpgatherdd %ymm1,(%r8,%ymm0,4),%ymm3 - DB 197,229,219,5,95,22,0,0 ; vpand 0x165f(%rip),%ymm3,%ymm0 # 42a0 <_sk_callback_hsw+0x5a5> + DB 197,229,219,5,95,22,0,0 ; vpand 0x165f(%rip),%ymm3,%ymm0 # 4220 <_sk_callback_hsw+0x5a5> DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,5,106,20,0,0 ; vbroadcastss 0x146a(%rip),%ymm8 # 40b8 <_sk_callback_hsw+0x3bd> + DB 196,98,125,24,5,98,20,0,0 ; vbroadcastss 0x1462(%rip),%ymm8 # 4030 <_sk_callback_hsw+0x3b5> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,226,101,0,13,100,22,0,0 ; vpshufb 0x1664(%rip),%ymm3,%ymm1 # 42c0 <_sk_callback_hsw+0x5c5> + DB 196,226,101,0,13,100,22,0,0 ; vpshufb 0x1664(%rip),%ymm3,%ymm1 # 4240 <_sk_callback_hsw+0x5c5> DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 - DB 196,226,101,0,21,114,22,0,0 ; vpshufb 0x1672(%rip),%ymm3,%ymm2 # 42e0 <_sk_callback_hsw+0x5e5> + DB 196,226,101,0,21,114,22,0,0 ; vpshufb 0x1672(%rip),%ymm3,%ymm2 # 4260 <_sk_callback_hsw+0x5e5> DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 197,229,114,211,24 ; vpsrld $0x18,%ymm3,%ymm3 @@ -2756,7 +2737,7 @@ _sk_store_8888_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,141,12,189,0,0,0,0 ; lea 0x0(,%rdi,4),%r9 DB 76,3,8 ; add (%rax),%r9 - DB 196,98,125,24,5,26,20,0,0 ; vbroadcastss 0x141a(%rip),%ymm8 # 40bc <_sk_callback_hsw+0x3c1> + DB 196,98,125,24,5,18,20,0,0 ; vbroadcastss 0x1412(%rip),%ymm8 # 4034 <_sk_callback_hsw+0x3b9> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,65,116,89,208 ; vmulps %ymm8,%ymm1,%ymm10 @@ -2772,7 +2753,7 @@ _sk_store_8888_hsw LABEL PROC DB 196,65,45,235,192 ; vpor %ymm8,%ymm10,%ymm8 DB 196,65,53,235,192 ; vpor %ymm8,%ymm9,%ymm8 DB 77,133,192 ; test %r8,%r8 - DB 117,12 ; jne 2cfc <_sk_store_8888_hsw+0x73> + DB 117,12 ; jne 2c7c <_sk_store_8888_hsw+0x73> DB 196,65,126,127,1 ; vmovdqu %ymm8,(%r9) DB 72,173 ; lods %ds:(%rsi),%rax DB 76,137,193 ; mov %r8,%rcx @@ -2785,14 +2766,14 @@ _sk_store_8888_hsw LABEL PROC DB 196,97,249,110,200 ; vmovq %rax,%xmm9 DB 196,66,125,33,201 ; vpmovsxbd %xmm9,%ymm9 DB 196,66,53,142,1 ; vpmaskmovd %ymm8,%ymm9,(%r9) - DB 235,211 ; jmp 2cf5 <_sk_store_8888_hsw+0x6c> + DB 235,211 ; jmp 2c75 <_sk_store_8888_hsw+0x6c> PUBLIC _sk_load_f16_hsw _sk_load_f16_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 72,133,201 ; test %rcx,%rcx - DB 117,97 ; jne 2d8d <_sk_load_f16_hsw+0x6b> + DB 117,97 ; jne 2d0d <_sk_load_f16_hsw+0x6b> DB 197,121,16,4,248 ; vmovupd (%rax,%rdi,8),%xmm8 DB 197,249,16,84,248,16 ; vmovupd 0x10(%rax,%rdi,8),%xmm2 DB 197,249,16,92,248,32 ; vmovupd 0x20(%rax,%rdi,8),%xmm3 @@ -2818,29 +2799,29 @@ _sk_load_f16_hsw LABEL PROC DB 197,123,16,4,248 ; vmovsd (%rax,%rdi,8),%xmm8 DB 196,65,49,239,201 ; vpxor %xmm9,%xmm9,%xmm9 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,79 ; je 2dec <_sk_load_f16_hsw+0xca> + DB 116,79 ; je 2d6c <_sk_load_f16_hsw+0xca> DB 197,57,22,68,248,8 ; vmovhpd 0x8(%rax,%rdi,8),%xmm8,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,67 ; jb 2dec <_sk_load_f16_hsw+0xca> + DB 114,67 ; jb 2d6c <_sk_load_f16_hsw+0xca> DB 197,251,16,84,248,16 ; vmovsd 0x10(%rax,%rdi,8),%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 116,68 ; je 2df9 <_sk_load_f16_hsw+0xd7> + DB 116,68 ; je 2d79 <_sk_load_f16_hsw+0xd7> DB 197,233,22,84,248,24 ; vmovhpd 0x18(%rax,%rdi,8),%xmm2,%xmm2 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,56 ; jb 2df9 <_sk_load_f16_hsw+0xd7> + DB 114,56 ; jb 2d79 <_sk_load_f16_hsw+0xd7> DB 197,251,16,92,248,32 ; vmovsd 0x20(%rax,%rdi,8),%xmm3 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 15,132,114,255,255,255 ; je 2d43 <_sk_load_f16_hsw+0x21> + DB 15,132,114,255,255,255 ; je 2cc3 <_sk_load_f16_hsw+0x21> DB 197,225,22,92,248,40 ; vmovhpd 0x28(%rax,%rdi,8),%xmm3,%xmm3 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 15,130,98,255,255,255 ; jb 2d43 <_sk_load_f16_hsw+0x21> + DB 15,130,98,255,255,255 ; jb 2cc3 <_sk_load_f16_hsw+0x21> DB 197,122,126,76,248,48 ; vmovq 0x30(%rax,%rdi,8),%xmm9 - DB 233,87,255,255,255 ; jmpq 2d43 <_sk_load_f16_hsw+0x21> + DB 233,87,255,255,255 ; jmpq 2cc3 <_sk_load_f16_hsw+0x21> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 DB 197,233,87,210 ; vxorpd %xmm2,%xmm2,%xmm2 - DB 233,74,255,255,255 ; jmpq 2d43 <_sk_load_f16_hsw+0x21> + DB 233,74,255,255,255 ; jmpq 2cc3 <_sk_load_f16_hsw+0x21> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 - DB 233,65,255,255,255 ; jmpq 2d43 <_sk_load_f16_hsw+0x21> + DB 233,65,255,255,255 ; jmpq 2cc3 <_sk_load_f16_hsw+0x21> PUBLIC _sk_gather_f16_hsw _sk_gather_f16_hsw LABEL PROC @@ -2894,7 +2875,7 @@ _sk_store_f16_hsw LABEL PROC DB 196,65,57,98,205 ; vpunpckldq %xmm13,%xmm8,%xmm9 DB 196,65,57,106,197 ; vpunpckhdq %xmm13,%xmm8,%xmm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,27 ; jne 2ef1 <_sk_store_f16_hsw+0x65> + DB 117,27 ; jne 2e71 <_sk_store_f16_hsw+0x65> DB 197,120,17,28,248 ; vmovups %xmm11,(%rax,%rdi,8) DB 197,120,17,84,248,16 ; vmovups %xmm10,0x10(%rax,%rdi,8) DB 197,120,17,76,248,32 ; vmovups %xmm9,0x20(%rax,%rdi,8) @@ -2903,22 +2884,22 @@ _sk_store_f16_hsw LABEL PROC DB 255,224 ; jmpq *%rax DB 197,121,214,28,248 ; vmovq %xmm11,(%rax,%rdi,8) DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,241 ; je 2eed <_sk_store_f16_hsw+0x61> + DB 116,241 ; je 2e6d <_sk_store_f16_hsw+0x61> DB 197,121,23,92,248,8 ; vmovhpd %xmm11,0x8(%rax,%rdi,8) DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,229 ; jb 2eed <_sk_store_f16_hsw+0x61> + DB 114,229 ; jb 2e6d <_sk_store_f16_hsw+0x61> DB 197,121,214,84,248,16 ; vmovq %xmm10,0x10(%rax,%rdi,8) - DB 116,221 ; je 2eed <_sk_store_f16_hsw+0x61> + DB 116,221 ; je 2e6d <_sk_store_f16_hsw+0x61> DB 197,121,23,84,248,24 ; vmovhpd %xmm10,0x18(%rax,%rdi,8) DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,209 ; jb 2eed <_sk_store_f16_hsw+0x61> + DB 114,209 ; jb 2e6d <_sk_store_f16_hsw+0x61> DB 197,121,214,76,248,32 ; vmovq %xmm9,0x20(%rax,%rdi,8) - DB 116,201 ; je 2eed <_sk_store_f16_hsw+0x61> + DB 116,201 ; je 2e6d <_sk_store_f16_hsw+0x61> DB 197,121,23,76,248,40 ; vmovhpd %xmm9,0x28(%rax,%rdi,8) DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,189 ; jb 2eed <_sk_store_f16_hsw+0x61> + DB 114,189 ; jb 2e6d <_sk_store_f16_hsw+0x61> DB 197,121,214,68,248,48 ; vmovq %xmm8,0x30(%rax,%rdi,8) - DB 235,181 ; jmp 2eed <_sk_store_f16_hsw+0x61> + DB 235,181 ; jmp 2e6d <_sk_store_f16_hsw+0x61> PUBLIC _sk_load_u16_be_hsw _sk_load_u16_be_hsw LABEL PROC @@ -2926,7 +2907,7 @@ _sk_load_u16_be_hsw LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 72,141,4,189,0,0,0,0 ; lea 0x0(,%rdi,4),%rax DB 72,133,201 ; test %rcx,%rcx - DB 15,133,204,0,0,0 ; jne 301a <_sk_load_u16_be_hsw+0xe2> + DB 15,133,204,0,0,0 ; jne 2f9a <_sk_load_u16_be_hsw+0xe2> DB 196,65,121,16,4,64 ; vmovupd (%r8,%rax,2),%xmm8 DB 196,193,121,16,84,64,16 ; vmovupd 0x10(%r8,%rax,2),%xmm2 DB 196,193,121,16,92,64,32 ; vmovupd 0x20(%r8,%rax,2),%xmm3 @@ -2945,7 +2926,7 @@ _sk_load_u16_be_hsw LABEL PROC DB 197,241,235,192 ; vpor %xmm0,%xmm1,%xmm0 DB 196,226,125,51,192 ; vpmovzxwd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,21,17,17,0,0 ; vbroadcastss 0x1111(%rip),%ymm10 # 40c0 <_sk_callback_hsw+0x3c5> + DB 196,98,125,24,21,9,17,0,0 ; vbroadcastss 0x1109(%rip),%ymm10 # 4038 <_sk_callback_hsw+0x3bd> DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 197,185,109,202 ; vpunpckhqdq %xmm2,%xmm8,%xmm1 DB 197,233,113,241,8 ; vpsllw $0x8,%xmm1,%xmm2 @@ -2973,29 +2954,29 @@ _sk_load_u16_be_hsw LABEL PROC DB 196,65,123,16,4,64 ; vmovsd (%r8,%rax,2),%xmm8 DB 196,65,49,239,201 ; vpxor %xmm9,%xmm9,%xmm9 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,85 ; je 3080 <_sk_load_u16_be_hsw+0x148> + DB 116,85 ; je 3000 <_sk_load_u16_be_hsw+0x148> DB 196,65,57,22,68,64,8 ; vmovhpd 0x8(%r8,%rax,2),%xmm8,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,72 ; jb 3080 <_sk_load_u16_be_hsw+0x148> + DB 114,72 ; jb 3000 <_sk_load_u16_be_hsw+0x148> DB 196,193,123,16,84,64,16 ; vmovsd 0x10(%r8,%rax,2),%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 116,72 ; je 308d <_sk_load_u16_be_hsw+0x155> + DB 116,72 ; je 300d <_sk_load_u16_be_hsw+0x155> DB 196,193,105,22,84,64,24 ; vmovhpd 0x18(%r8,%rax,2),%xmm2,%xmm2 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,59 ; jb 308d <_sk_load_u16_be_hsw+0x155> + DB 114,59 ; jb 300d <_sk_load_u16_be_hsw+0x155> DB 196,193,123,16,92,64,32 ; vmovsd 0x20(%r8,%rax,2),%xmm3 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 15,132,6,255,255,255 ; je 2f69 <_sk_load_u16_be_hsw+0x31> + DB 15,132,6,255,255,255 ; je 2ee9 <_sk_load_u16_be_hsw+0x31> DB 196,193,97,22,92,64,40 ; vmovhpd 0x28(%r8,%rax,2),%xmm3,%xmm3 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 15,130,245,254,255,255 ; jb 2f69 <_sk_load_u16_be_hsw+0x31> + DB 15,130,245,254,255,255 ; jb 2ee9 <_sk_load_u16_be_hsw+0x31> DB 196,65,122,126,76,64,48 ; vmovq 0x30(%r8,%rax,2),%xmm9 - DB 233,233,254,255,255 ; jmpq 2f69 <_sk_load_u16_be_hsw+0x31> + DB 233,233,254,255,255 ; jmpq 2ee9 <_sk_load_u16_be_hsw+0x31> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 DB 197,233,87,210 ; vxorpd %xmm2,%xmm2,%xmm2 - DB 233,220,254,255,255 ; jmpq 2f69 <_sk_load_u16_be_hsw+0x31> + DB 233,220,254,255,255 ; jmpq 2ee9 <_sk_load_u16_be_hsw+0x31> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 - DB 233,211,254,255,255 ; jmpq 2f69 <_sk_load_u16_be_hsw+0x31> + DB 233,211,254,255,255 ; jmpq 2ee9 <_sk_load_u16_be_hsw+0x31> PUBLIC _sk_load_rgb_u16_be_hsw _sk_load_rgb_u16_be_hsw LABEL PROC @@ -3003,7 +2984,7 @@ _sk_load_rgb_u16_be_hsw LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 72,141,4,127 ; lea (%rdi,%rdi,2),%rax DB 72,133,201 ; test %rcx,%rcx - DB 15,133,204,0,0,0 ; jne 3174 <_sk_load_rgb_u16_be_hsw+0xde> + DB 15,133,204,0,0,0 ; jne 30f4 <_sk_load_rgb_u16_be_hsw+0xde> DB 196,193,122,111,4,64 ; vmovdqu (%r8,%rax,2),%xmm0 DB 196,193,122,111,84,64,12 ; vmovdqu 0xc(%r8,%rax,2),%xmm2 DB 196,193,122,111,76,64,24 ; vmovdqu 0x18(%r8,%rax,2),%xmm1 @@ -3027,7 +3008,7 @@ _sk_load_rgb_u16_be_hsw LABEL PROC DB 197,241,235,192 ; vpor %xmm0,%xmm1,%xmm0 DB 196,226,125,51,192 ; vpmovzxwd %xmm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,21,162,15,0,0 ; vbroadcastss 0xfa2(%rip),%ymm10 # 40c4 <_sk_callback_hsw+0x3c9> + DB 196,98,125,24,21,154,15,0,0 ; vbroadcastss 0xf9a(%rip),%ymm10 # 403c <_sk_callback_hsw+0x3c1> DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 197,185,109,202 ; vpunpckhqdq %xmm2,%xmm8,%xmm1 DB 197,233,113,241,8 ; vpsllw $0x8,%xmm1,%xmm2 @@ -3044,48 +3025,48 @@ _sk_load_rgb_u16_be_hsw LABEL PROC DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,210 ; vmulps %ymm10,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,86,15,0,0 ; vbroadcastss 0xf56(%rip),%ymm3 # 40c8 <_sk_callback_hsw+0x3cd> + DB 196,226,125,24,29,78,15,0,0 ; vbroadcastss 0xf4e(%rip),%ymm3 # 4040 <_sk_callback_hsw+0x3c5> DB 255,224 ; jmpq *%rax DB 196,193,121,110,4,64 ; vmovd (%r8,%rax,2),%xmm0 DB 196,193,121,196,68,64,4,2 ; vpinsrw $0x2,0x4(%r8,%rax,2),%xmm0,%xmm0 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 117,5 ; jne 318d <_sk_load_rgb_u16_be_hsw+0xf7> - DB 233,79,255,255,255 ; jmpq 30dc <_sk_load_rgb_u16_be_hsw+0x46> + DB 117,5 ; jne 310d <_sk_load_rgb_u16_be_hsw+0xf7> + DB 233,79,255,255,255 ; jmpq 305c <_sk_load_rgb_u16_be_hsw+0x46> DB 196,193,121,110,76,64,6 ; vmovd 0x6(%r8,%rax,2),%xmm1 DB 196,65,113,196,68,64,10,2 ; vpinsrw $0x2,0xa(%r8,%rax,2),%xmm1,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,26 ; jb 31bc <_sk_load_rgb_u16_be_hsw+0x126> + DB 114,26 ; jb 313c <_sk_load_rgb_u16_be_hsw+0x126> DB 196,193,121,110,76,64,12 ; vmovd 0xc(%r8,%rax,2),%xmm1 DB 196,193,113,196,84,64,16,2 ; vpinsrw $0x2,0x10(%r8,%rax,2),%xmm1,%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 117,10 ; jne 31c1 <_sk_load_rgb_u16_be_hsw+0x12b> - DB 233,32,255,255,255 ; jmpq 30dc <_sk_load_rgb_u16_be_hsw+0x46> - DB 233,27,255,255,255 ; jmpq 30dc <_sk_load_rgb_u16_be_hsw+0x46> + DB 117,10 ; jne 3141 <_sk_load_rgb_u16_be_hsw+0x12b> + DB 233,32,255,255,255 ; jmpq 305c <_sk_load_rgb_u16_be_hsw+0x46> + DB 233,27,255,255,255 ; jmpq 305c <_sk_load_rgb_u16_be_hsw+0x46> DB 196,193,121,110,76,64,18 ; vmovd 0x12(%r8,%rax,2),%xmm1 DB 196,65,113,196,76,64,22,2 ; vpinsrw $0x2,0x16(%r8,%rax,2),%xmm1,%xmm9 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,26 ; jb 31f0 <_sk_load_rgb_u16_be_hsw+0x15a> + DB 114,26 ; jb 3170 <_sk_load_rgb_u16_be_hsw+0x15a> DB 196,193,121,110,76,64,24 ; vmovd 0x18(%r8,%rax,2),%xmm1 DB 196,193,113,196,76,64,28,2 ; vpinsrw $0x2,0x1c(%r8,%rax,2),%xmm1,%xmm1 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 117,10 ; jne 31f5 <_sk_load_rgb_u16_be_hsw+0x15f> - DB 233,236,254,255,255 ; jmpq 30dc <_sk_load_rgb_u16_be_hsw+0x46> - DB 233,231,254,255,255 ; jmpq 30dc <_sk_load_rgb_u16_be_hsw+0x46> + DB 117,10 ; jne 3175 <_sk_load_rgb_u16_be_hsw+0x15f> + DB 233,236,254,255,255 ; jmpq 305c <_sk_load_rgb_u16_be_hsw+0x46> + DB 233,231,254,255,255 ; jmpq 305c <_sk_load_rgb_u16_be_hsw+0x46> DB 196,193,121,110,92,64,30 ; vmovd 0x1e(%r8,%rax,2),%xmm3 DB 196,65,97,196,92,64,34,2 ; vpinsrw $0x2,0x22(%r8,%rax,2),%xmm3,%xmm11 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,20 ; jb 321e <_sk_load_rgb_u16_be_hsw+0x188> + DB 114,20 ; jb 319e <_sk_load_rgb_u16_be_hsw+0x188> DB 196,193,121,110,92,64,36 ; vmovd 0x24(%r8,%rax,2),%xmm3 DB 196,193,97,196,92,64,40,2 ; vpinsrw $0x2,0x28(%r8,%rax,2),%xmm3,%xmm3 - DB 233,190,254,255,255 ; jmpq 30dc <_sk_load_rgb_u16_be_hsw+0x46> - DB 233,185,254,255,255 ; jmpq 30dc <_sk_load_rgb_u16_be_hsw+0x46> + DB 233,190,254,255,255 ; jmpq 305c <_sk_load_rgb_u16_be_hsw+0x46> + DB 233,185,254,255,255 ; jmpq 305c <_sk_load_rgb_u16_be_hsw+0x46> PUBLIC _sk_store_u16_be_hsw _sk_store_u16_be_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,0 ; mov (%rax),%r8 DB 72,141,4,189,0,0,0,0 ; lea 0x0(,%rdi,4),%rax - DB 196,98,125,24,5,147,14,0,0 ; vbroadcastss 0xe93(%rip),%ymm8 # 40cc <_sk_callback_hsw+0x3d1> + DB 196,98,125,24,5,139,14,0,0 ; vbroadcastss 0xe8b(%rip),%ymm8 # 4044 <_sk_callback_hsw+0x3c9> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,67,125,25,202,1 ; vextractf128 $0x1,%ymm9,%xmm10 @@ -3123,7 +3104,7 @@ _sk_store_u16_be_hsw LABEL PROC DB 196,65,17,98,200 ; vpunpckldq %xmm8,%xmm13,%xmm9 DB 196,65,17,106,192 ; vpunpckhdq %xmm8,%xmm13,%xmm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,31 ; jne 331d <_sk_store_u16_be_hsw+0xfa> + DB 117,31 ; jne 329d <_sk_store_u16_be_hsw+0xfa> DB 196,65,120,17,28,64 ; vmovups %xmm11,(%r8,%rax,2) DB 196,65,120,17,84,64,16 ; vmovups %xmm10,0x10(%r8,%rax,2) DB 196,65,120,17,76,64,32 ; vmovups %xmm9,0x20(%r8,%rax,2) @@ -3132,31 +3113,31 @@ _sk_store_u16_be_hsw LABEL PROC DB 255,224 ; jmpq *%rax DB 196,65,121,214,28,64 ; vmovq %xmm11,(%r8,%rax,2) DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,240 ; je 3319 <_sk_store_u16_be_hsw+0xf6> + DB 116,240 ; je 3299 <_sk_store_u16_be_hsw+0xf6> DB 196,65,121,23,92,64,8 ; vmovhpd %xmm11,0x8(%r8,%rax,2) DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,227 ; jb 3319 <_sk_store_u16_be_hsw+0xf6> + DB 114,227 ; jb 3299 <_sk_store_u16_be_hsw+0xf6> DB 196,65,121,214,84,64,16 ; vmovq %xmm10,0x10(%r8,%rax,2) - DB 116,218 ; je 3319 <_sk_store_u16_be_hsw+0xf6> + DB 116,218 ; je 3299 <_sk_store_u16_be_hsw+0xf6> DB 196,65,121,23,84,64,24 ; vmovhpd %xmm10,0x18(%r8,%rax,2) DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,205 ; jb 3319 <_sk_store_u16_be_hsw+0xf6> + DB 114,205 ; jb 3299 <_sk_store_u16_be_hsw+0xf6> DB 196,65,121,214,76,64,32 ; vmovq %xmm9,0x20(%r8,%rax,2) - DB 116,196 ; je 3319 <_sk_store_u16_be_hsw+0xf6> + DB 116,196 ; je 3299 <_sk_store_u16_be_hsw+0xf6> DB 196,65,121,23,76,64,40 ; vmovhpd %xmm9,0x28(%r8,%rax,2) DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,183 ; jb 3319 <_sk_store_u16_be_hsw+0xf6> + DB 114,183 ; jb 3299 <_sk_store_u16_be_hsw+0xf6> DB 196,65,121,214,68,64,48 ; vmovq %xmm8,0x30(%r8,%rax,2) - DB 235,174 ; jmp 3319 <_sk_store_u16_be_hsw+0xf6> + DB 235,174 ; jmp 3299 <_sk_store_u16_be_hsw+0xf6> PUBLIC _sk_load_f32_hsw _sk_load_f32_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,131,249,7 ; cmp $0x7,%rcx - DB 119,110 ; ja 33e1 <_sk_load_f32_hsw+0x76> + DB 119,110 ; ja 3361 <_sk_load_f32_hsw+0x76> DB 76,139,0 ; mov (%rax),%r8 DB 76,141,12,189,0,0,0,0 ; lea 0x0(,%rdi,4),%r9 - DB 76,141,21,135,0,0,0 ; lea 0x87(%rip),%r10 # 340c <_sk_load_f32_hsw+0xa1> + DB 76,141,21,135,0,0,0 ; lea 0x87(%rip),%r10 # 338c <_sk_load_f32_hsw+0xa1> DB 73,99,4,138 ; movslq (%r10,%rcx,4),%rax DB 76,1,208 ; add %r10,%rax DB 255,224 ; jmpq *%rax @@ -3215,7 +3196,7 @@ _sk_store_f32_hsw LABEL PROC DB 196,65,37,20,196 ; vunpcklpd %ymm12,%ymm11,%ymm8 DB 196,65,37,21,220 ; vunpckhpd %ymm12,%ymm11,%ymm11 DB 72,133,201 ; test %rcx,%rcx - DB 117,55 ; jne 3499 <_sk_store_f32_hsw+0x6d> + DB 117,55 ; jne 3419 <_sk_store_f32_hsw+0x6d> DB 196,67,45,24,225,1 ; vinsertf128 $0x1,%xmm9,%ymm10,%ymm12 DB 196,67,61,24,235,1 ; vinsertf128 $0x1,%xmm11,%ymm8,%ymm13 DB 196,67,45,6,201,49 ; vperm2f128 $0x31,%ymm9,%ymm10,%ymm9 @@ -3228,22 +3209,22 @@ _sk_store_f32_hsw LABEL PROC DB 255,224 ; jmpq *%rax DB 196,65,121,17,20,128 ; vmovupd %xmm10,(%r8,%rax,4) DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,240 ; je 3495 <_sk_store_f32_hsw+0x69> + DB 116,240 ; je 3415 <_sk_store_f32_hsw+0x69> DB 196,65,121,17,76,128,16 ; vmovupd %xmm9,0x10(%r8,%rax,4) DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,227 ; jb 3495 <_sk_store_f32_hsw+0x69> + DB 114,227 ; jb 3415 <_sk_store_f32_hsw+0x69> DB 196,65,121,17,68,128,32 ; vmovupd %xmm8,0x20(%r8,%rax,4) - DB 116,218 ; je 3495 <_sk_store_f32_hsw+0x69> + DB 116,218 ; je 3415 <_sk_store_f32_hsw+0x69> DB 196,65,121,17,92,128,48 ; vmovupd %xmm11,0x30(%r8,%rax,4) DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,205 ; jb 3495 <_sk_store_f32_hsw+0x69> + DB 114,205 ; jb 3415 <_sk_store_f32_hsw+0x69> DB 196,67,125,25,84,128,64,1 ; vextractf128 $0x1,%ymm10,0x40(%r8,%rax,4) - DB 116,195 ; je 3495 <_sk_store_f32_hsw+0x69> + DB 116,195 ; je 3415 <_sk_store_f32_hsw+0x69> DB 196,67,125,25,76,128,80,1 ; vextractf128 $0x1,%ymm9,0x50(%r8,%rax,4) DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,181 ; jb 3495 <_sk_store_f32_hsw+0x69> + DB 114,181 ; jb 3415 <_sk_store_f32_hsw+0x69> DB 196,67,125,25,68,128,96,1 ; vextractf128 $0x1,%ymm8,0x60(%r8,%rax,4) - DB 235,171 ; jmp 3495 <_sk_store_f32_hsw+0x69> + DB 235,171 ; jmp 3415 <_sk_store_f32_hsw+0x69> PUBLIC _sk_clamp_x_hsw _sk_clamp_x_hsw LABEL PROC @@ -3339,11 +3320,11 @@ _sk_mirror_y_hsw LABEL PROC PUBLIC _sk_luminance_to_alpha_hsw _sk_luminance_to_alpha_hsw LABEL PROC - DB 196,226,125,24,29,173,10,0,0 ; vbroadcastss 0xaad(%rip),%ymm3 # 40d0 <_sk_callback_hsw+0x3d5> - DB 196,98,125,24,5,168,10,0,0 ; vbroadcastss 0xaa8(%rip),%ymm8 # 40d4 <_sk_callback_hsw+0x3d9> + DB 196,226,125,24,29,165,10,0,0 ; vbroadcastss 0xaa5(%rip),%ymm3 # 4048 <_sk_callback_hsw+0x3cd> + DB 196,98,125,24,5,160,10,0,0 ; vbroadcastss 0xaa0(%rip),%ymm8 # 404c <_sk_callback_hsw+0x3d1> DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 DB 196,226,125,184,203 ; vfmadd231ps %ymm3,%ymm0,%ymm1 - DB 196,226,125,24,29,153,10,0,0 ; vbroadcastss 0xa99(%rip),%ymm3 # 40d8 <_sk_callback_hsw+0x3dd> + DB 196,226,125,24,29,145,10,0,0 ; vbroadcastss 0xa91(%rip),%ymm3 # 4050 <_sk_callback_hsw+0x3d5> DB 196,226,109,168,217 ; vfmadd213ps %ymm1,%ymm2,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -3478,7 +3459,7 @@ _sk_linear_gradient_hsw LABEL PROC DB 196,98,125,24,72,28 ; vbroadcastss 0x1c(%rax),%ymm9 DB 76,139,0 ; mov (%rax),%r8 DB 77,133,192 ; test %r8,%r8 - DB 15,132,143,0,0,0 ; je 3917 <_sk_linear_gradient_hsw+0xb5> + DB 15,132,143,0,0,0 ; je 3897 <_sk_linear_gradient_hsw+0xb5> DB 72,139,64,8 ; mov 0x8(%rax),%rax DB 72,131,192,32 ; add $0x20,%rax DB 196,65,28,87,228 ; vxorps %ymm12,%ymm12,%ymm12 @@ -3505,8 +3486,8 @@ _sk_linear_gradient_hsw LABEL PROC DB 196,67,13,74,201,208 ; vblendvps %ymm13,%ymm9,%ymm14,%ymm9 DB 72,131,192,36 ; add $0x24,%rax DB 73,255,200 ; dec %r8 - DB 117,140 ; jne 38a1 <_sk_linear_gradient_hsw+0x3f> - DB 235,17 ; jmp 3928 <_sk_linear_gradient_hsw+0xc6> + DB 117,140 ; jne 3821 <_sk_linear_gradient_hsw+0x3f> + DB 235,17 ; jmp 38a8 <_sk_linear_gradient_hsw+0xc6> DB 197,244,87,201 ; vxorps %ymm1,%ymm1,%ymm1 DB 197,236,87,210 ; vxorps %ymm2,%ymm2,%ymm2 DB 197,228,87,219 ; vxorps %ymm3,%ymm3,%ymm3 @@ -3541,7 +3522,7 @@ _sk_linear_gradient_2stops_hsw LABEL PROC PUBLIC _sk_save_xy_hsw _sk_save_xy_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,64,7,0,0 ; vbroadcastss 0x740(%rip),%ymm8 # 40dc <_sk_callback_hsw+0x3e1> + DB 196,98,125,24,5,56,7,0,0 ; vbroadcastss 0x738(%rip),%ymm8 # 4054 <_sk_callback_hsw+0x3d9> DB 196,65,124,88,200 ; vaddps %ymm8,%ymm0,%ymm9 DB 196,67,125,8,209,1 ; vroundps $0x1,%ymm9,%ymm10 DB 196,65,52,92,202 ; vsubps %ymm10,%ymm9,%ymm9 @@ -3571,9 +3552,9 @@ _sk_accumulate_hsw LABEL PROC PUBLIC _sk_bilinear_nx_hsw _sk_bilinear_nx_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,212,6,0,0 ; vbroadcastss 0x6d4(%rip),%ymm0 # 40e0 <_sk_callback_hsw+0x3e5> + DB 196,226,125,24,5,204,6,0,0 ; vbroadcastss 0x6cc(%rip),%ymm0 # 4058 <_sk_callback_hsw+0x3dd> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,203,6,0,0 ; vbroadcastss 0x6cb(%rip),%ymm8 # 40e4 <_sk_callback_hsw+0x3e9> + DB 196,98,125,24,5,195,6,0,0 ; vbroadcastss 0x6c3(%rip),%ymm8 # 405c <_sk_callback_hsw+0x3e1> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -3582,7 +3563,7 @@ _sk_bilinear_nx_hsw LABEL PROC PUBLIC _sk_bilinear_px_hsw _sk_bilinear_px_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,179,6,0,0 ; vbroadcastss 0x6b3(%rip),%ymm0 # 40e8 <_sk_callback_hsw+0x3ed> + DB 196,226,125,24,5,171,6,0,0 ; vbroadcastss 0x6ab(%rip),%ymm0 # 4060 <_sk_callback_hsw+0x3e5> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 DB 197,124,16,64,64 ; vmovups 0x40(%rax),%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -3592,9 +3573,9 @@ _sk_bilinear_px_hsw LABEL PROC PUBLIC _sk_bilinear_ny_hsw _sk_bilinear_ny_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,151,6,0,0 ; vbroadcastss 0x697(%rip),%ymm1 # 40ec <_sk_callback_hsw+0x3f1> + DB 196,226,125,24,13,143,6,0,0 ; vbroadcastss 0x68f(%rip),%ymm1 # 4064 <_sk_callback_hsw+0x3e9> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,141,6,0,0 ; vbroadcastss 0x68d(%rip),%ymm8 # 40f0 <_sk_callback_hsw+0x3f5> + DB 196,98,125,24,5,133,6,0,0 ; vbroadcastss 0x685(%rip),%ymm8 # 4068 <_sk_callback_hsw+0x3ed> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -3603,7 +3584,7 @@ _sk_bilinear_ny_hsw LABEL PROC PUBLIC _sk_bilinear_py_hsw _sk_bilinear_py_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,117,6,0,0 ; vbroadcastss 0x675(%rip),%ymm1 # 40f4 <_sk_callback_hsw+0x3f9> + DB 196,226,125,24,13,109,6,0,0 ; vbroadcastss 0x66d(%rip),%ymm1 # 406c <_sk_callback_hsw+0x3f1> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 DB 197,124,16,64,96 ; vmovups 0x60(%rax),%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -3613,13 +3594,13 @@ _sk_bilinear_py_hsw LABEL PROC PUBLIC _sk_bicubic_n3x_hsw _sk_bicubic_n3x_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,88,6,0,0 ; vbroadcastss 0x658(%rip),%ymm0 # 40f8 <_sk_callback_hsw+0x3fd> + DB 196,226,125,24,5,80,6,0,0 ; vbroadcastss 0x650(%rip),%ymm0 # 4070 <_sk_callback_hsw+0x3f5> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,79,6,0,0 ; vbroadcastss 0x64f(%rip),%ymm8 # 40fc <_sk_callback_hsw+0x401> + DB 196,98,125,24,5,71,6,0,0 ; vbroadcastss 0x647(%rip),%ymm8 # 4074 <_sk_callback_hsw+0x3f9> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,64,6,0,0 ; vbroadcastss 0x640(%rip),%ymm10 # 4100 <_sk_callback_hsw+0x405> - DB 196,98,125,24,29,59,6,0,0 ; vbroadcastss 0x63b(%rip),%ymm11 # 4104 <_sk_callback_hsw+0x409> + DB 196,98,125,24,21,56,6,0,0 ; vbroadcastss 0x638(%rip),%ymm10 # 4078 <_sk_callback_hsw+0x3fd> + DB 196,98,125,24,29,51,6,0,0 ; vbroadcastss 0x633(%rip),%ymm11 # 407c <_sk_callback_hsw+0x401> DB 196,66,61,168,218 ; vfmadd213ps %ymm10,%ymm8,%ymm11 DB 196,65,36,89,193 ; vmulps %ymm9,%ymm11,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -3629,16 +3610,16 @@ _sk_bicubic_n3x_hsw LABEL PROC PUBLIC _sk_bicubic_n1x_hsw _sk_bicubic_n1x_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,30,6,0,0 ; vbroadcastss 0x61e(%rip),%ymm0 # 4108 <_sk_callback_hsw+0x40d> + DB 196,226,125,24,5,22,6,0,0 ; vbroadcastss 0x616(%rip),%ymm0 # 4080 <_sk_callback_hsw+0x405> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,21,6,0,0 ; vbroadcastss 0x615(%rip),%ymm8 # 410c <_sk_callback_hsw+0x411> + DB 196,98,125,24,5,13,6,0,0 ; vbroadcastss 0x60d(%rip),%ymm8 # 4084 <_sk_callback_hsw+0x409> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 - DB 196,98,125,24,13,11,6,0,0 ; vbroadcastss 0x60b(%rip),%ymm9 # 4110 <_sk_callback_hsw+0x415> - DB 196,98,125,24,21,6,6,0,0 ; vbroadcastss 0x606(%rip),%ymm10 # 4114 <_sk_callback_hsw+0x419> + DB 196,98,125,24,13,3,6,0,0 ; vbroadcastss 0x603(%rip),%ymm9 # 4088 <_sk_callback_hsw+0x40d> + DB 196,98,125,24,21,254,5,0,0 ; vbroadcastss 0x5fe(%rip),%ymm10 # 408c <_sk_callback_hsw+0x411> DB 196,66,61,168,209 ; vfmadd213ps %ymm9,%ymm8,%ymm10 - DB 196,98,125,24,13,252,5,0,0 ; vbroadcastss 0x5fc(%rip),%ymm9 # 4118 <_sk_callback_hsw+0x41d> + DB 196,98,125,24,13,244,5,0,0 ; vbroadcastss 0x5f4(%rip),%ymm9 # 4090 <_sk_callback_hsw+0x415> DB 196,66,61,184,202 ; vfmadd231ps %ymm10,%ymm8,%ymm9 - DB 196,98,125,24,21,242,5,0,0 ; vbroadcastss 0x5f2(%rip),%ymm10 # 411c <_sk_callback_hsw+0x421> + DB 196,98,125,24,21,234,5,0,0 ; vbroadcastss 0x5ea(%rip),%ymm10 # 4094 <_sk_callback_hsw+0x419> DB 196,66,61,184,209 ; vfmadd231ps %ymm9,%ymm8,%ymm10 DB 197,124,17,144,128,0,0,0 ; vmovups %ymm10,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -3647,14 +3628,14 @@ _sk_bicubic_n1x_hsw LABEL PROC PUBLIC _sk_bicubic_p1x_hsw _sk_bicubic_p1x_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,218,5,0,0 ; vbroadcastss 0x5da(%rip),%ymm8 # 4120 <_sk_callback_hsw+0x425> + DB 196,98,125,24,5,210,5,0,0 ; vbroadcastss 0x5d2(%rip),%ymm8 # 4098 <_sk_callback_hsw+0x41d> DB 197,188,88,0 ; vaddps (%rax),%ymm8,%ymm0 DB 197,124,16,72,64 ; vmovups 0x40(%rax),%ymm9 - DB 196,98,125,24,21,204,5,0,0 ; vbroadcastss 0x5cc(%rip),%ymm10 # 4124 <_sk_callback_hsw+0x429> - DB 196,98,125,24,29,199,5,0,0 ; vbroadcastss 0x5c7(%rip),%ymm11 # 4128 <_sk_callback_hsw+0x42d> + DB 196,98,125,24,21,196,5,0,0 ; vbroadcastss 0x5c4(%rip),%ymm10 # 409c <_sk_callback_hsw+0x421> + DB 196,98,125,24,29,191,5,0,0 ; vbroadcastss 0x5bf(%rip),%ymm11 # 40a0 <_sk_callback_hsw+0x425> DB 196,66,53,168,218 ; vfmadd213ps %ymm10,%ymm9,%ymm11 DB 196,66,53,168,216 ; vfmadd213ps %ymm8,%ymm9,%ymm11 - DB 196,98,125,24,5,184,5,0,0 ; vbroadcastss 0x5b8(%rip),%ymm8 # 412c <_sk_callback_hsw+0x431> + DB 196,98,125,24,5,176,5,0,0 ; vbroadcastss 0x5b0(%rip),%ymm8 # 40a4 <_sk_callback_hsw+0x429> DB 196,66,53,184,195 ; vfmadd231ps %ymm11,%ymm9,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -3663,12 +3644,12 @@ _sk_bicubic_p1x_hsw LABEL PROC PUBLIC _sk_bicubic_p3x_hsw _sk_bicubic_p3x_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,160,5,0,0 ; vbroadcastss 0x5a0(%rip),%ymm0 # 4130 <_sk_callback_hsw+0x435> + DB 196,226,125,24,5,152,5,0,0 ; vbroadcastss 0x598(%rip),%ymm0 # 40a8 <_sk_callback_hsw+0x42d> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 DB 197,124,16,64,64 ; vmovups 0x40(%rax),%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,141,5,0,0 ; vbroadcastss 0x58d(%rip),%ymm10 # 4134 <_sk_callback_hsw+0x439> - DB 196,98,125,24,29,136,5,0,0 ; vbroadcastss 0x588(%rip),%ymm11 # 4138 <_sk_callback_hsw+0x43d> + DB 196,98,125,24,21,133,5,0,0 ; vbroadcastss 0x585(%rip),%ymm10 # 40ac <_sk_callback_hsw+0x431> + DB 196,98,125,24,29,128,5,0,0 ; vbroadcastss 0x580(%rip),%ymm11 # 40b0 <_sk_callback_hsw+0x435> DB 196,66,61,168,218 ; vfmadd213ps %ymm10,%ymm8,%ymm11 DB 196,65,52,89,195 ; vmulps %ymm11,%ymm9,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -3678,13 +3659,13 @@ _sk_bicubic_p3x_hsw LABEL PROC PUBLIC _sk_bicubic_n3y_hsw _sk_bicubic_n3y_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,107,5,0,0 ; vbroadcastss 0x56b(%rip),%ymm1 # 413c <_sk_callback_hsw+0x441> + DB 196,226,125,24,13,99,5,0,0 ; vbroadcastss 0x563(%rip),%ymm1 # 40b4 <_sk_callback_hsw+0x439> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,97,5,0,0 ; vbroadcastss 0x561(%rip),%ymm8 # 4140 <_sk_callback_hsw+0x445> + DB 196,98,125,24,5,89,5,0,0 ; vbroadcastss 0x559(%rip),%ymm8 # 40b8 <_sk_callback_hsw+0x43d> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,82,5,0,0 ; vbroadcastss 0x552(%rip),%ymm10 # 4144 <_sk_callback_hsw+0x449> - DB 196,98,125,24,29,77,5,0,0 ; vbroadcastss 0x54d(%rip),%ymm11 # 4148 <_sk_callback_hsw+0x44d> + DB 196,98,125,24,21,74,5,0,0 ; vbroadcastss 0x54a(%rip),%ymm10 # 40bc <_sk_callback_hsw+0x441> + DB 196,98,125,24,29,69,5,0,0 ; vbroadcastss 0x545(%rip),%ymm11 # 40c0 <_sk_callback_hsw+0x445> DB 196,66,61,168,218 ; vfmadd213ps %ymm10,%ymm8,%ymm11 DB 196,65,36,89,193 ; vmulps %ymm9,%ymm11,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -3694,16 +3675,16 @@ _sk_bicubic_n3y_hsw LABEL PROC PUBLIC _sk_bicubic_n1y_hsw _sk_bicubic_n1y_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,48,5,0,0 ; vbroadcastss 0x530(%rip),%ymm1 # 414c <_sk_callback_hsw+0x451> + DB 196,226,125,24,13,40,5,0,0 ; vbroadcastss 0x528(%rip),%ymm1 # 40c4 <_sk_callback_hsw+0x449> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,38,5,0,0 ; vbroadcastss 0x526(%rip),%ymm8 # 4150 <_sk_callback_hsw+0x455> + DB 196,98,125,24,5,30,5,0,0 ; vbroadcastss 0x51e(%rip),%ymm8 # 40c8 <_sk_callback_hsw+0x44d> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 - DB 196,98,125,24,13,28,5,0,0 ; vbroadcastss 0x51c(%rip),%ymm9 # 4154 <_sk_callback_hsw+0x459> - DB 196,98,125,24,21,23,5,0,0 ; vbroadcastss 0x517(%rip),%ymm10 # 4158 <_sk_callback_hsw+0x45d> + DB 196,98,125,24,13,20,5,0,0 ; vbroadcastss 0x514(%rip),%ymm9 # 40cc <_sk_callback_hsw+0x451> + DB 196,98,125,24,21,15,5,0,0 ; vbroadcastss 0x50f(%rip),%ymm10 # 40d0 <_sk_callback_hsw+0x455> DB 196,66,61,168,209 ; vfmadd213ps %ymm9,%ymm8,%ymm10 - DB 196,98,125,24,13,13,5,0,0 ; vbroadcastss 0x50d(%rip),%ymm9 # 415c <_sk_callback_hsw+0x461> + DB 196,98,125,24,13,5,5,0,0 ; vbroadcastss 0x505(%rip),%ymm9 # 40d4 <_sk_callback_hsw+0x459> DB 196,66,61,184,202 ; vfmadd231ps %ymm10,%ymm8,%ymm9 - DB 196,98,125,24,21,3,5,0,0 ; vbroadcastss 0x503(%rip),%ymm10 # 4160 <_sk_callback_hsw+0x465> + DB 196,98,125,24,21,251,4,0,0 ; vbroadcastss 0x4fb(%rip),%ymm10 # 40d8 <_sk_callback_hsw+0x45d> DB 196,66,61,184,209 ; vfmadd231ps %ymm9,%ymm8,%ymm10 DB 197,124,17,144,160,0,0,0 ; vmovups %ymm10,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -3712,14 +3693,14 @@ _sk_bicubic_n1y_hsw LABEL PROC PUBLIC _sk_bicubic_p1y_hsw _sk_bicubic_p1y_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,235,4,0,0 ; vbroadcastss 0x4eb(%rip),%ymm8 # 4164 <_sk_callback_hsw+0x469> + DB 196,98,125,24,5,227,4,0,0 ; vbroadcastss 0x4e3(%rip),%ymm8 # 40dc <_sk_callback_hsw+0x461> DB 197,188,88,72,32 ; vaddps 0x20(%rax),%ymm8,%ymm1 DB 197,124,16,72,96 ; vmovups 0x60(%rax),%ymm9 - DB 196,98,125,24,21,220,4,0,0 ; vbroadcastss 0x4dc(%rip),%ymm10 # 4168 <_sk_callback_hsw+0x46d> - DB 196,98,125,24,29,215,4,0,0 ; vbroadcastss 0x4d7(%rip),%ymm11 # 416c <_sk_callback_hsw+0x471> + DB 196,98,125,24,21,212,4,0,0 ; vbroadcastss 0x4d4(%rip),%ymm10 # 40e0 <_sk_callback_hsw+0x465> + DB 196,98,125,24,29,207,4,0,0 ; vbroadcastss 0x4cf(%rip),%ymm11 # 40e4 <_sk_callback_hsw+0x469> DB 196,66,53,168,218 ; vfmadd213ps %ymm10,%ymm9,%ymm11 DB 196,66,53,168,216 ; vfmadd213ps %ymm8,%ymm9,%ymm11 - DB 196,98,125,24,5,200,4,0,0 ; vbroadcastss 0x4c8(%rip),%ymm8 # 4170 <_sk_callback_hsw+0x475> + DB 196,98,125,24,5,192,4,0,0 ; vbroadcastss 0x4c0(%rip),%ymm8 # 40e8 <_sk_callback_hsw+0x46d> DB 196,66,53,184,195 ; vfmadd231ps %ymm11,%ymm9,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -3728,12 +3709,12 @@ _sk_bicubic_p1y_hsw LABEL PROC PUBLIC _sk_bicubic_p3y_hsw _sk_bicubic_p3y_hsw LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,176,4,0,0 ; vbroadcastss 0x4b0(%rip),%ymm1 # 4174 <_sk_callback_hsw+0x479> + DB 196,226,125,24,13,168,4,0,0 ; vbroadcastss 0x4a8(%rip),%ymm1 # 40ec <_sk_callback_hsw+0x471> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 DB 197,124,16,64,96 ; vmovups 0x60(%rax),%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,156,4,0,0 ; vbroadcastss 0x49c(%rip),%ymm10 # 4178 <_sk_callback_hsw+0x47d> - DB 196,98,125,24,29,151,4,0,0 ; vbroadcastss 0x497(%rip),%ymm11 # 417c <_sk_callback_hsw+0x481> + DB 196,98,125,24,21,148,4,0,0 ; vbroadcastss 0x494(%rip),%ymm10 # 40f0 <_sk_callback_hsw+0x475> + DB 196,98,125,24,29,143,4,0,0 ; vbroadcastss 0x48f(%rip),%ymm11 # 40f4 <_sk_callback_hsw+0x479> DB 196,66,61,168,218 ; vfmadd213ps %ymm10,%ymm8,%ymm11 DB 196,65,52,89,195 ; vmulps %ymm11,%ymm9,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -3864,22 +3845,17 @@ ALIGN 4 DB 62,0,0 ; add %al,%ds:(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) - DB 128,63,0 ; cmpb $0x0,(%rdi) - DB 0,0 ; add %al,(%rax) - DB 64,171 ; rex stos %eax,%es:(%rdi) + DB 0,64,171 ; add %al,-0x55(%rax) DB 170 ; stos %al,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) DB 62,0,0 ; add %al,%ds:(%rax) - DB 128,191,0,0,192,64,171 ; cmpb $0xab,0x40c00000(%rdi) - DB 170 ; stos %al,%es:(%rdi) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) + DB 192,64,0,0 ; rolb $0x0,0x0(%rax) + DB 128,64,171,170 ; addb $0xaa,-0x55(%rax) DB 170 ; stos %al,%es:(%rdi) DB 190,129,128,128,59 ; mov $0x3b808081,%esi DB 129,128,128,59,0,248,0,0,8,33 ; addl $0x21080000,-0x7ffc480(%rax) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 3eed <.literal4+0xd9> + DB 224,7 ; loopne 3e65 <.literal4+0xd1> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -3893,10 +3869,10 @@ ALIGN 4 DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) DB 0,52,255 ; add %dh,(%rdi,%rdi,8) DB 255 ; (bad) - DB 127,0 ; jg 3f18 <.literal4+0x104> + DB 127,0 ; jg 3e90 <.literal4+0xfc> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 3f91 <.literal4+0x17d> + DB 119,115 ; ja 3f09 <.literal4+0x175> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -3910,10 +3886,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 3f4c <.literal4+0x138> + DB 127,0 ; jg 3ec4 <.literal4+0x130> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 3fc5 <.literal4+0x1b1> + DB 119,115 ; ja 3f3d <.literal4+0x1a9> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -3927,10 +3903,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 3f80 <.literal4+0x16c> + DB 127,0 ; jg 3ef8 <.literal4+0x164> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 3ff9 <.literal4+0x1e5> + DB 119,115 ; ja 3f71 <.literal4+0x1dd> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -3944,10 +3920,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 3fb4 <.literal4+0x1a0> + DB 127,0 ; jg 3f2c <.literal4+0x198> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 402d <.literal4+0x219> + DB 119,115 ; ja 3fa5 <.literal4+0x211> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -3960,7 +3936,7 @@ ALIGN 4 DB 0,75,0 ; add %cl,0x0(%rbx) DB 0,128,63,0,0,200 ; add %al,-0x37ffffc1(%rax) DB 66,0,0 ; rex.X add %al,(%rax) - DB 127,67 ; jg 402b <.literal4+0x217> + DB 127,67 ; jg 3fa3 <.literal4+0x20f> DB 0,0 ; add %al,(%rax) DB 0,195 ; add %al,%bl DB 0,0 ; add %al,(%rax) @@ -3972,10 +3948,10 @@ ALIGN 4 DB 190,80,128,3,62 ; mov $0x3e038050,%esi DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 404b <.literal4+0x237> + DB 118,63 ; jbe 3fc3 <.literal4+0x22f> DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) - DB 127,67 ; jg 405f <.literal4+0x24b> + DB 127,67 ; jg 3fd7 <.literal4+0x243> DB 129,128,128,59,0,0,128,63,129,128 ; addl $0x80813f80,0x3b80(%rax) DB 128,59,0 ; cmpb $0x0,(%rbx) DB 0,128,63,129,128,128 ; add %al,-0x7f7f7ec1(%rax) @@ -3984,7 +3960,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 4041 <.literal4+0x22d> + DB 224,7 ; loopne 3fb9 <.literal4+0x225> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -3996,7 +3972,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 405d <.literal4+0x249> + DB 224,7 ; loopne 3fd5 <.literal4+0x241> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -4007,7 +3983,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 248 ; clc DB 65,0,0 ; add %al,(%r8) - DB 124,66 ; jl 40b2 <.literal4+0x29e> + DB 124,66 ; jl 402a <.literal4+0x296> DB 0,240 ; add %dh,%al DB 0,0 ; add %al,(%rax) DB 137,136,136,55,0,15 ; mov %ecx,0xf003788(%rax) @@ -4025,9 +4001,9 @@ ALIGN 4 DB 137,136,136,59,15,0 ; mov %ecx,0xf3b88(%rax) DB 0,0 ; add %al,(%rax) DB 137,136,136,61,0,0 ; mov %ecx,0x3d88(%rax) - DB 112,65 ; jo 40f5 <.literal4+0x2e1> + DB 112,65 ; jo 406d <.literal4+0x2d9> DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) - DB 127,67 ; jg 4103 <.literal4+0x2ef> + DB 127,67 ; jg 407b <.literal4+0x2e7> DB 128,0,128 ; addb $0x80,(%rax) DB 55 ; (bad) DB 128,0,128 ; addb $0x80,(%rax) @@ -4035,7 +4011,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 255 ; (bad) - DB 127,71 ; jg 4117 <.literal4+0x303> + DB 127,71 ; jg 408f <.literal4+0x2fb> DB 208 ; (bad) DB 179,89 ; mov $0x59,%bl DB 62,89 ; ds pop %rcx @@ -4121,16 +4097,16 @@ ALIGN 32 DB 0,0 ; add %al,(%rax) DB 1,255 ; add %edi,%edi DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a0041a8 <_sk_callback_hsw+0xa0004ad> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004128 <_sk_callback_hsw+0xa0004ad> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 120041b0 <_sk_callback_hsw+0x120004b5> + DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004130 <_sk_callback_hsw+0x120004b5> DB 255 ; (bad) DB 255 ; (bad) - DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a0041b8 <_sk_callback_hsw+0x1a0004bd> + DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004138 <_sk_callback_hsw+0x1a0004bd> DB 255 ; (bad) DB 255 ; (bad) - DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 30041c0 <_sk_callback_hsw+0x30004c5> + DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004140 <_sk_callback_hsw+0x30004c5> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -4173,16 +4149,16 @@ ALIGN 32 DB 0,0 ; add %al,(%rax) DB 1,255 ; add %edi,%edi DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004208 <_sk_callback_hsw+0xa00050d> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004188 <_sk_callback_hsw+0xa00050d> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004210 <_sk_callback_hsw+0x12000515> + DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004190 <_sk_callback_hsw+0x12000515> DB 255 ; (bad) DB 255 ; (bad) - DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004218 <_sk_callback_hsw+0x1a00051d> + DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004198 <_sk_callback_hsw+0x1a00051d> DB 255 ; (bad) DB 255 ; (bad) - DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004220 <_sk_callback_hsw+0x3000525> + DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 30041a0 <_sk_callback_hsw+0x3000525> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -4225,16 +4201,16 @@ ALIGN 32 DB 0,0 ; add %al,(%rax) DB 1,255 ; add %edi,%edi DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004268 <_sk_callback_hsw+0xa00056d> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a0041e8 <_sk_callback_hsw+0xa00056d> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004270 <_sk_callback_hsw+0x12000575> + DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 120041f0 <_sk_callback_hsw+0x12000575> DB 255 ; (bad) DB 255 ; (bad) - DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004278 <_sk_callback_hsw+0x1a00057d> + DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a0041f8 <_sk_callback_hsw+0x1a00057d> DB 255 ; (bad) DB 255 ; (bad) - DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004280 <_sk_callback_hsw+0x3000585> + DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004200 <_sk_callback_hsw+0x3000585> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -4277,16 +4253,16 @@ ALIGN 32 DB 0,0 ; add %al,(%rax) DB 1,255 ; add %edi,%edi DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a0042c8 <_sk_callback_hsw+0xa0005cd> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a004248 <_sk_callback_hsw+0xa0005cd> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 120042d0 <_sk_callback_hsw+0x120005d5> + DB 255,13,255,255,255,17 ; decl 0x11ffffff(%rip) # 12004250 <_sk_callback_hsw+0x120005d5> DB 255 ; (bad) DB 255 ; (bad) - DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a0042d8 <_sk_callback_hsw+0x1a0005dd> + DB 255,21,255,255,255,25 ; callq *0x19ffffff(%rip) # 1a004258 <_sk_callback_hsw+0x1a0005dd> DB 255 ; (bad) DB 255 ; (bad) - DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 30042e0 <_sk_callback_hsw+0x30005e5> + DB 255,29,255,255,255,2 ; lcall *0x2ffffff(%rip) # 3004260 <_sk_callback_hsw+0x30005e5> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -4428,14 +4404,14 @@ _sk_seed_shader_avx LABEL PROC DB 197,249,112,192,0 ; vpshufd $0x0,%xmm0,%xmm0 DB 196,227,125,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,156,83,0,0 ; vbroadcastss 0x539c(%rip),%ymm1 # 54fc <_sk_callback_avx+0x11a> + DB 196,226,125,24,13,8,83,0,0 ; vbroadcastss 0x5308(%rip),%ymm1 # 5468 <_sk_callback_avx+0x11a> DB 197,252,88,193 ; vaddps %ymm1,%ymm0,%ymm0 DB 197,252,88,2 ; vaddps (%rdx),%ymm0,%ymm0 DB 196,226,125,24,16 ; vbroadcastss (%rax),%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 197,236,88,201 ; vaddps %ymm1,%ymm2,%ymm1 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,21,128,83,0,0 ; vbroadcastss 0x5380(%rip),%ymm2 # 5500 <_sk_callback_avx+0x11e> + DB 196,226,125,24,21,236,82,0,0 ; vbroadcastss 0x52ec(%rip),%ymm2 # 546c <_sk_callback_avx+0x11e> DB 197,228,87,219 ; vxorps %ymm3,%ymm3,%ymm3 DB 197,220,87,228 ; vxorps %ymm4,%ymm4,%ymm4 DB 197,212,87,237 ; vxorps %ymm5,%ymm5,%ymm5 @@ -4465,7 +4441,7 @@ _sk_clear_avx LABEL PROC PUBLIC _sk_srcatop_avx _sk_srcatop_avx LABEL PROC DB 197,252,89,199 ; vmulps %ymm7,%ymm0,%ymm0 - DB 196,98,125,24,5,48,83,0,0 ; vbroadcastss 0x5330(%rip),%ymm8 # 5504 <_sk_callback_avx+0x122> + DB 196,98,125,24,5,156,82,0,0 ; vbroadcastss 0x529c(%rip),%ymm8 # 5470 <_sk_callback_avx+0x122> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,204 ; vmulps %ymm4,%ymm8,%ymm9 DB 197,180,88,192 ; vaddps %ymm0,%ymm9,%ymm0 @@ -4484,7 +4460,7 @@ _sk_srcatop_avx LABEL PROC PUBLIC _sk_dstatop_avx _sk_dstatop_avx LABEL PROC DB 197,100,89,196 ; vmulps %ymm4,%ymm3,%ymm8 - DB 196,98,125,24,13,242,82,0,0 ; vbroadcastss 0x52f2(%rip),%ymm9 # 5508 <_sk_callback_avx+0x126> + DB 196,98,125,24,13,94,82,0,0 ; vbroadcastss 0x525e(%rip),%ymm9 # 5474 <_sk_callback_avx+0x126> DB 197,52,92,207 ; vsubps %ymm7,%ymm9,%ymm9 DB 197,180,89,192 ; vmulps %ymm0,%ymm9,%ymm0 DB 197,188,88,192 ; vaddps %ymm0,%ymm8,%ymm0 @@ -4520,7 +4496,7 @@ _sk_dstin_avx LABEL PROC PUBLIC _sk_srcout_avx _sk_srcout_avx LABEL PROC - DB 196,98,125,24,5,145,82,0,0 ; vbroadcastss 0x5291(%rip),%ymm8 # 550c <_sk_callback_avx+0x12a> + DB 196,98,125,24,5,253,81,0,0 ; vbroadcastss 0x51fd(%rip),%ymm8 # 5478 <_sk_callback_avx+0x12a> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 @@ -4531,7 +4507,7 @@ _sk_srcout_avx LABEL PROC PUBLIC _sk_dstout_avx _sk_dstout_avx LABEL PROC - DB 196,226,125,24,5,116,82,0,0 ; vbroadcastss 0x5274(%rip),%ymm0 # 5510 <_sk_callback_avx+0x12e> + DB 196,226,125,24,5,224,81,0,0 ; vbroadcastss 0x51e0(%rip),%ymm0 # 547c <_sk_callback_avx+0x12e> DB 197,252,92,219 ; vsubps %ymm3,%ymm0,%ymm3 DB 197,228,89,196 ; vmulps %ymm4,%ymm3,%ymm0 DB 197,228,89,205 ; vmulps %ymm5,%ymm3,%ymm1 @@ -4542,7 +4518,7 @@ _sk_dstout_avx LABEL PROC PUBLIC _sk_srcover_avx _sk_srcover_avx LABEL PROC - DB 196,98,125,24,5,87,82,0,0 ; vbroadcastss 0x5257(%rip),%ymm8 # 5514 <_sk_callback_avx+0x132> + DB 196,98,125,24,5,195,81,0,0 ; vbroadcastss 0x51c3(%rip),%ymm8 # 5480 <_sk_callback_avx+0x132> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,204 ; vmulps %ymm4,%ymm8,%ymm9 DB 197,180,88,192 ; vaddps %ymm0,%ymm9,%ymm0 @@ -4557,7 +4533,7 @@ _sk_srcover_avx LABEL PROC PUBLIC _sk_dstover_avx _sk_dstover_avx LABEL PROC - DB 196,98,125,24,5,42,82,0,0 ; vbroadcastss 0x522a(%rip),%ymm8 # 5518 <_sk_callback_avx+0x136> + DB 196,98,125,24,5,150,81,0,0 ; vbroadcastss 0x5196(%rip),%ymm8 # 5484 <_sk_callback_avx+0x136> DB 197,60,92,199 ; vsubps %ymm7,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,252,88,196 ; vaddps %ymm4,%ymm0,%ymm0 @@ -4581,7 +4557,7 @@ _sk_modulate_avx LABEL PROC PUBLIC _sk_multiply_avx _sk_multiply_avx LABEL PROC - DB 196,98,125,24,5,233,81,0,0 ; vbroadcastss 0x51e9(%rip),%ymm8 # 551c <_sk_callback_avx+0x13a> + DB 196,98,125,24,5,85,81,0,0 ; vbroadcastss 0x5155(%rip),%ymm8 # 5488 <_sk_callback_avx+0x13a> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,52,89,208 ; vmulps %ymm0,%ymm9,%ymm10 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -4635,7 +4611,7 @@ _sk_screen_avx LABEL PROC PUBLIC _sk_xor__avx _sk_xor__avx LABEL PROC - DB 196,98,125,24,5,56,81,0,0 ; vbroadcastss 0x5138(%rip),%ymm8 # 5520 <_sk_callback_avx+0x13e> + DB 196,98,125,24,5,164,80,0,0 ; vbroadcastss 0x50a4(%rip),%ymm8 # 548c <_sk_callback_avx+0x13e> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,180,89,192 ; vmulps %ymm0,%ymm9,%ymm0 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -4670,7 +4646,7 @@ _sk_darken_avx LABEL PROC DB 197,100,89,206 ; vmulps %ymm6,%ymm3,%ymm9 DB 196,193,108,95,209 ; vmaxps %ymm9,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,184,80,0,0 ; vbroadcastss 0x50b8(%rip),%ymm8 # 5524 <_sk_callback_avx+0x142> + DB 196,98,125,24,5,36,80,0,0 ; vbroadcastss 0x5024(%rip),%ymm8 # 5490 <_sk_callback_avx+0x142> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,199 ; vmulps %ymm7,%ymm8,%ymm8 DB 197,188,88,219 ; vaddps %ymm3,%ymm8,%ymm3 @@ -4694,7 +4670,7 @@ _sk_lighten_avx LABEL PROC DB 197,100,89,206 ; vmulps %ymm6,%ymm3,%ymm9 DB 196,193,108,93,209 ; vminps %ymm9,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,100,80,0,0 ; vbroadcastss 0x5064(%rip),%ymm8 # 5528 <_sk_callback_avx+0x146> + DB 196,98,125,24,5,208,79,0,0 ; vbroadcastss 0x4fd0(%rip),%ymm8 # 5494 <_sk_callback_avx+0x146> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,199 ; vmulps %ymm7,%ymm8,%ymm8 DB 197,188,88,219 ; vaddps %ymm3,%ymm8,%ymm3 @@ -4721,7 +4697,7 @@ _sk_difference_avx LABEL PROC DB 196,193,108,93,209 ; vminps %ymm9,%ymm2,%ymm2 DB 197,236,88,210 ; vaddps %ymm2,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,4,80,0,0 ; vbroadcastss 0x5004(%rip),%ymm8 # 552c <_sk_callback_avx+0x14a> + DB 196,98,125,24,5,112,79,0,0 ; vbroadcastss 0x4f70(%rip),%ymm8 # 5498 <_sk_callback_avx+0x14a> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,199 ; vmulps %ymm7,%ymm8,%ymm8 DB 197,188,88,219 ; vaddps %ymm3,%ymm8,%ymm3 @@ -4742,7 +4718,7 @@ _sk_exclusion_avx LABEL PROC DB 197,236,89,214 ; vmulps %ymm6,%ymm2,%ymm2 DB 197,236,88,210 ; vaddps %ymm2,%ymm2,%ymm2 DB 197,188,92,210 ; vsubps %ymm2,%ymm8,%ymm2 - DB 196,98,125,24,5,191,79,0,0 ; vbroadcastss 0x4fbf(%rip),%ymm8 # 5530 <_sk_callback_avx+0x14e> + DB 196,98,125,24,5,43,79,0,0 ; vbroadcastss 0x4f2b(%rip),%ymm8 # 549c <_sk_callback_avx+0x14e> DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 DB 197,60,89,199 ; vmulps %ymm7,%ymm8,%ymm8 DB 197,188,88,219 ; vaddps %ymm3,%ymm8,%ymm3 @@ -4751,7 +4727,7 @@ _sk_exclusion_avx LABEL PROC PUBLIC _sk_colorburn_avx _sk_colorburn_avx LABEL PROC - DB 196,98,125,24,5,170,79,0,0 ; vbroadcastss 0x4faa(%rip),%ymm8 # 5534 <_sk_callback_avx+0x152> + DB 196,98,125,24,5,22,79,0,0 ; vbroadcastss 0x4f16(%rip),%ymm8 # 54a0 <_sk_callback_avx+0x152> DB 197,60,92,207 ; vsubps %ymm7,%ymm8,%ymm9 DB 197,52,89,216 ; vmulps %ymm0,%ymm9,%ymm11 DB 196,65,44,87,210 ; vxorps %ymm10,%ymm10,%ymm10 @@ -4811,7 +4787,7 @@ _sk_colorburn_avx LABEL PROC PUBLIC _sk_colordodge_avx _sk_colordodge_avx LABEL PROC DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 - DB 196,98,125,24,13,166,78,0,0 ; vbroadcastss 0x4ea6(%rip),%ymm9 # 5538 <_sk_callback_avx+0x156> + DB 196,98,125,24,13,18,78,0,0 ; vbroadcastss 0x4e12(%rip),%ymm9 # 54a4 <_sk_callback_avx+0x156> DB 197,52,92,215 ; vsubps %ymm7,%ymm9,%ymm10 DB 197,44,89,216 ; vmulps %ymm0,%ymm10,%ymm11 DB 197,52,92,203 ; vsubps %ymm3,%ymm9,%ymm9 @@ -4866,7 +4842,7 @@ _sk_colordodge_avx LABEL PROC PUBLIC _sk_hardlight_avx _sk_hardlight_avx LABEL PROC - DB 196,98,125,24,5,184,77,0,0 ; vbroadcastss 0x4db8(%rip),%ymm8 # 553c <_sk_callback_avx+0x15a> + DB 196,98,125,24,5,36,77,0,0 ; vbroadcastss 0x4d24(%rip),%ymm8 # 54a8 <_sk_callback_avx+0x15a> DB 197,60,92,215 ; vsubps %ymm7,%ymm8,%ymm10 DB 197,44,89,200 ; vmulps %ymm0,%ymm10,%ymm9 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -4919,7 +4895,7 @@ _sk_hardlight_avx LABEL PROC PUBLIC _sk_overlay_avx _sk_overlay_avx LABEL PROC - DB 196,98,125,24,5,225,76,0,0 ; vbroadcastss 0x4ce1(%rip),%ymm8 # 5540 <_sk_callback_avx+0x15e> + DB 196,98,125,24,5,77,76,0,0 ; vbroadcastss 0x4c4d(%rip),%ymm8 # 54ac <_sk_callback_avx+0x15e> DB 197,60,92,215 ; vsubps %ymm7,%ymm8,%ymm10 DB 197,44,89,200 ; vmulps %ymm0,%ymm10,%ymm9 DB 197,60,92,195 ; vsubps %ymm3,%ymm8,%ymm8 @@ -4984,10 +4960,10 @@ _sk_softlight_avx LABEL PROC DB 196,65,60,88,192 ; vaddps %ymm8,%ymm8,%ymm8 DB 196,65,60,89,216 ; vmulps %ymm8,%ymm8,%ymm11 DB 196,65,60,88,195 ; vaddps %ymm11,%ymm8,%ymm8 - DB 196,98,125,24,29,212,75,0,0 ; vbroadcastss 0x4bd4(%rip),%ymm11 # 5548 <_sk_callback_avx+0x166> + DB 196,98,125,24,29,64,75,0,0 ; vbroadcastss 0x4b40(%rip),%ymm11 # 54b4 <_sk_callback_avx+0x166> DB 196,65,28,88,235 ; vaddps %ymm11,%ymm12,%ymm13 DB 196,65,20,89,192 ; vmulps %ymm8,%ymm13,%ymm8 - DB 196,98,125,24,45,197,75,0,0 ; vbroadcastss 0x4bc5(%rip),%ymm13 # 554c <_sk_callback_avx+0x16a> + DB 196,98,125,24,45,49,75,0,0 ; vbroadcastss 0x4b31(%rip),%ymm13 # 54b8 <_sk_callback_avx+0x16a> DB 196,65,28,89,245 ; vmulps %ymm13,%ymm12,%ymm14 DB 196,65,12,88,192 ; vaddps %ymm8,%ymm14,%ymm8 DB 196,65,124,82,244 ; vrsqrtps %ymm12,%ymm14 @@ -4998,7 +4974,7 @@ _sk_softlight_avx LABEL PROC DB 197,4,194,255,2 ; vcmpleps %ymm7,%ymm15,%ymm15 DB 196,67,13,74,240,240 ; vblendvps %ymm15,%ymm8,%ymm14,%ymm14 DB 197,116,88,249 ; vaddps %ymm1,%ymm1,%ymm15 - DB 196,98,125,24,5,131,75,0,0 ; vbroadcastss 0x4b83(%rip),%ymm8 # 5544 <_sk_callback_avx+0x162> + DB 196,98,125,24,5,239,74,0,0 ; vbroadcastss 0x4aef(%rip),%ymm8 # 54b0 <_sk_callback_avx+0x162> DB 196,65,60,92,228 ; vsubps %ymm12,%ymm8,%ymm12 DB 197,132,92,195 ; vsubps %ymm3,%ymm15,%ymm0 DB 196,65,124,89,228 ; vmulps %ymm12,%ymm0,%ymm12 @@ -5102,7 +5078,7 @@ _sk_clamp_0_avx LABEL PROC PUBLIC _sk_clamp_1_avx _sk_clamp_1_avx LABEL PROC - DB 196,98,125,24,5,209,73,0,0 ; vbroadcastss 0x49d1(%rip),%ymm8 # 5550 <_sk_callback_avx+0x16e> + DB 196,98,125,24,5,61,73,0,0 ; vbroadcastss 0x493d(%rip),%ymm8 # 54bc <_sk_callback_avx+0x16e> DB 196,193,124,93,192 ; vminps %ymm8,%ymm0,%ymm0 DB 196,193,116,93,200 ; vminps %ymm8,%ymm1,%ymm1 DB 196,193,108,93,208 ; vminps %ymm8,%ymm2,%ymm2 @@ -5112,7 +5088,7 @@ _sk_clamp_1_avx LABEL PROC PUBLIC _sk_clamp_a_avx _sk_clamp_a_avx LABEL PROC - DB 196,98,125,24,5,180,73,0,0 ; vbroadcastss 0x49b4(%rip),%ymm8 # 5554 <_sk_callback_avx+0x172> + DB 196,98,125,24,5,32,73,0,0 ; vbroadcastss 0x4920(%rip),%ymm8 # 54c0 <_sk_callback_avx+0x172> DB 196,193,100,93,216 ; vminps %ymm8,%ymm3,%ymm3 DB 197,252,93,195 ; vminps %ymm3,%ymm0,%ymm0 DB 197,244,93,203 ; vminps %ymm3,%ymm1,%ymm1 @@ -5184,7 +5160,7 @@ PUBLIC _sk_unpremul_avx _sk_unpremul_avx LABEL PROC DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,65,100,194,200,0 ; vcmpeqps %ymm8,%ymm3,%ymm9 - DB 196,98,125,24,21,252,72,0,0 ; vbroadcastss 0x48fc(%rip),%ymm10 # 5558 <_sk_callback_avx+0x176> + DB 196,98,125,24,21,104,72,0,0 ; vbroadcastss 0x4868(%rip),%ymm10 # 54c4 <_sk_callback_avx+0x176> DB 197,44,94,211 ; vdivps %ymm3,%ymm10,%ymm10 DB 196,67,45,74,192,144 ; vblendvps %ymm9,%ymm8,%ymm10,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 @@ -5195,17 +5171,17 @@ _sk_unpremul_avx LABEL PROC PUBLIC _sk_from_srgb_avx _sk_from_srgb_avx LABEL PROC - DB 196,98,125,24,5,221,72,0,0 ; vbroadcastss 0x48dd(%rip),%ymm8 # 555c <_sk_callback_avx+0x17a> + DB 196,98,125,24,5,73,72,0,0 ; vbroadcastss 0x4849(%rip),%ymm8 # 54c8 <_sk_callback_avx+0x17a> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 197,124,89,208 ; vmulps %ymm0,%ymm0,%ymm10 - DB 196,98,125,24,29,207,72,0,0 ; vbroadcastss 0x48cf(%rip),%ymm11 # 5560 <_sk_callback_avx+0x17e> + DB 196,98,125,24,29,59,72,0,0 ; vbroadcastss 0x483b(%rip),%ymm11 # 54cc <_sk_callback_avx+0x17e> DB 196,65,124,89,227 ; vmulps %ymm11,%ymm0,%ymm12 - DB 196,98,125,24,45,197,72,0,0 ; vbroadcastss 0x48c5(%rip),%ymm13 # 5564 <_sk_callback_avx+0x182> + DB 196,98,125,24,45,49,72,0,0 ; vbroadcastss 0x4831(%rip),%ymm13 # 54d0 <_sk_callback_avx+0x182> DB 196,65,28,88,229 ; vaddps %ymm13,%ymm12,%ymm12 DB 196,65,44,89,212 ; vmulps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,37,182,72,0,0 ; vbroadcastss 0x48b6(%rip),%ymm12 # 5568 <_sk_callback_avx+0x186> + DB 196,98,125,24,37,34,72,0,0 ; vbroadcastss 0x4822(%rip),%ymm12 # 54d4 <_sk_callback_avx+0x186> DB 196,65,44,88,212 ; vaddps %ymm12,%ymm10,%ymm10 - DB 196,98,125,24,53,172,72,0,0 ; vbroadcastss 0x48ac(%rip),%ymm14 # 556c <_sk_callback_avx+0x18a> + DB 196,98,125,24,53,24,72,0,0 ; vbroadcastss 0x4818(%rip),%ymm14 # 54d8 <_sk_callback_avx+0x18a> DB 196,193,124,194,198,1 ; vcmpltps %ymm14,%ymm0,%ymm0 DB 196,195,45,74,193,0 ; vblendvps %ymm0,%ymm9,%ymm10,%ymm0 DB 196,65,116,89,200 ; vmulps %ymm8,%ymm1,%ymm9 @@ -5232,18 +5208,18 @@ _sk_to_srgb_avx LABEL PROC DB 197,124,82,192 ; vrsqrtps %ymm0,%ymm8 DB 196,65,124,83,200 ; vrcpps %ymm8,%ymm9 DB 196,65,124,82,208 ; vrsqrtps %ymm8,%ymm10 - DB 196,98,125,24,5,55,72,0,0 ; vbroadcastss 0x4837(%rip),%ymm8 # 5570 <_sk_callback_avx+0x18e> + DB 196,98,125,24,5,163,71,0,0 ; vbroadcastss 0x47a3(%rip),%ymm8 # 54dc <_sk_callback_avx+0x18e> DB 196,65,124,89,216 ; vmulps %ymm8,%ymm0,%ymm11 - DB 196,98,125,24,37,45,72,0,0 ; vbroadcastss 0x482d(%rip),%ymm12 # 5574 <_sk_callback_avx+0x192> + DB 196,98,125,24,37,153,71,0,0 ; vbroadcastss 0x4799(%rip),%ymm12 # 54e0 <_sk_callback_avx+0x192> DB 196,65,52,89,204 ; vmulps %ymm12,%ymm9,%ymm9 - DB 196,98,125,24,45,35,72,0,0 ; vbroadcastss 0x4823(%rip),%ymm13 # 5578 <_sk_callback_avx+0x196> + DB 196,98,125,24,45,143,71,0,0 ; vbroadcastss 0x478f(%rip),%ymm13 # 54e4 <_sk_callback_avx+0x196> DB 196,65,52,88,205 ; vaddps %ymm13,%ymm9,%ymm9 - DB 196,98,125,24,53,25,72,0,0 ; vbroadcastss 0x4819(%rip),%ymm14 # 557c <_sk_callback_avx+0x19a> + DB 196,98,125,24,53,133,71,0,0 ; vbroadcastss 0x4785(%rip),%ymm14 # 54e8 <_sk_callback_avx+0x19a> DB 196,65,44,89,214 ; vmulps %ymm14,%ymm10,%ymm10 DB 196,65,44,88,201 ; vaddps %ymm9,%ymm10,%ymm9 - DB 196,98,125,24,21,10,72,0,0 ; vbroadcastss 0x480a(%rip),%ymm10 # 5580 <_sk_callback_avx+0x19e> + DB 196,98,125,24,21,118,71,0,0 ; vbroadcastss 0x4776(%rip),%ymm10 # 54ec <_sk_callback_avx+0x19e> DB 196,65,44,93,201 ; vminps %ymm9,%ymm10,%ymm9 - DB 196,98,125,24,61,0,72,0,0 ; vbroadcastss 0x4800(%rip),%ymm15 # 5584 <_sk_callback_avx+0x1a2> + DB 196,98,125,24,61,108,71,0,0 ; vbroadcastss 0x476c(%rip),%ymm15 # 54f0 <_sk_callback_avx+0x1a2> DB 196,193,124,194,199,1 ; vcmpltps %ymm15,%ymm0,%ymm0 DB 196,195,53,74,195,0 ; vblendvps %ymm0,%ymm11,%ymm9,%ymm0 DB 197,124,82,201 ; vrsqrtps %ymm1,%ymm9 @@ -5278,7 +5254,7 @@ _sk_rgb_to_hsl_avx LABEL PROC DB 197,124,93,201 ; vminps %ymm1,%ymm0,%ymm9 DB 197,52,93,202 ; vminps %ymm2,%ymm9,%ymm9 DB 196,65,60,92,209 ; vsubps %ymm9,%ymm8,%ymm10 - DB 196,98,125,24,29,102,71,0,0 ; vbroadcastss 0x4766(%rip),%ymm11 # 5588 <_sk_callback_avx+0x1a6> + DB 196,98,125,24,29,210,70,0,0 ; vbroadcastss 0x46d2(%rip),%ymm11 # 54f4 <_sk_callback_avx+0x1a6> DB 196,65,36,94,218 ; vdivps %ymm10,%ymm11,%ymm11 DB 197,116,92,226 ; vsubps %ymm2,%ymm1,%ymm12 DB 196,65,28,89,227 ; vmulps %ymm11,%ymm12,%ymm12 @@ -5288,19 +5264,19 @@ _sk_rgb_to_hsl_avx LABEL PROC DB 196,193,108,89,211 ; vmulps %ymm11,%ymm2,%ymm2 DB 197,252,92,201 ; vsubps %ymm1,%ymm0,%ymm1 DB 196,193,116,89,203 ; vmulps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,63,71,0,0 ; vbroadcastss 0x473f(%rip),%ymm11 # 5594 <_sk_callback_avx+0x1b2> + DB 196,98,125,24,29,171,70,0,0 ; vbroadcastss 0x46ab(%rip),%ymm11 # 5500 <_sk_callback_avx+0x1b2> DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,45,71,0,0 ; vbroadcastss 0x472d(%rip),%ymm11 # 5590 <_sk_callback_avx+0x1ae> + DB 196,98,125,24,29,153,70,0,0 ; vbroadcastss 0x4699(%rip),%ymm11 # 54fc <_sk_callback_avx+0x1ae> DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 DB 196,227,117,74,202,224 ; vblendvps %ymm14,%ymm2,%ymm1,%ymm1 - DB 196,226,125,24,21,21,71,0,0 ; vbroadcastss 0x4715(%rip),%ymm2 # 558c <_sk_callback_avx+0x1aa> + DB 196,226,125,24,21,129,70,0,0 ; vbroadcastss 0x4681(%rip),%ymm2 # 54f8 <_sk_callback_avx+0x1aa> DB 196,65,12,87,246 ; vxorps %ymm14,%ymm14,%ymm14 DB 196,227,13,74,210,208 ; vblendvps %ymm13,%ymm2,%ymm14,%ymm2 DB 197,188,194,192,0 ; vcmpeqps %ymm0,%ymm8,%ymm0 DB 196,193,108,88,212 ; vaddps %ymm12,%ymm2,%ymm2 DB 196,227,117,74,194,0 ; vblendvps %ymm0,%ymm2,%ymm1,%ymm0 DB 196,193,60,88,201 ; vaddps %ymm9,%ymm8,%ymm1 - DB 196,98,125,24,37,252,70,0,0 ; vbroadcastss 0x46fc(%rip),%ymm12 # 559c <_sk_callback_avx+0x1ba> + DB 196,98,125,24,37,104,70,0,0 ; vbroadcastss 0x4668(%rip),%ymm12 # 5508 <_sk_callback_avx+0x1ba> DB 196,193,116,89,212 ; vmulps %ymm12,%ymm1,%ymm2 DB 197,28,194,226,1 ; vcmpltps %ymm2,%ymm12,%ymm12 DB 196,65,36,92,216 ; vsubps %ymm8,%ymm11,%ymm11 @@ -5310,126 +5286,101 @@ _sk_rgb_to_hsl_avx LABEL PROC DB 197,172,94,201 ; vdivps %ymm1,%ymm10,%ymm1 DB 196,195,125,74,198,128 ; vblendvps %ymm8,%ymm14,%ymm0,%ymm0 DB 196,195,117,74,206,128 ; vblendvps %ymm8,%ymm14,%ymm1,%ymm1 - DB 196,98,125,24,5,191,70,0,0 ; vbroadcastss 0x46bf(%rip),%ymm8 # 5598 <_sk_callback_avx+0x1b6> + DB 196,98,125,24,5,43,70,0,0 ; vbroadcastss 0x462b(%rip),%ymm8 # 5504 <_sk_callback_avx+0x1b6> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax PUBLIC _sk_hsl_to_rgb_avx _sk_hsl_to_rgb_avx LABEL PROC - DB 72,129,236,248,0,0,0 ; sub $0xf8,%rsp - DB 197,252,17,188,36,192,0,0,0 ; vmovups %ymm7,0xc0(%rsp) - DB 197,252,17,180,36,160,0,0,0 ; vmovups %ymm6,0xa0(%rsp) - DB 197,252,17,172,36,128,0,0,0 ; vmovups %ymm5,0x80(%rsp) - DB 197,252,17,100,36,96 ; vmovups %ymm4,0x60(%rsp) - DB 197,252,17,92,36,64 ; vmovups %ymm3,0x40(%rsp) - DB 197,252,40,234 ; vmovaps %ymm2,%ymm5 - DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 + DB 72,129,236,184,0,0,0 ; sub $0xb8,%rsp + DB 197,252,17,188,36,128,0,0,0 ; vmovups %ymm7,0x80(%rsp) + DB 197,252,17,116,36,96 ; vmovups %ymm6,0x60(%rsp) + DB 197,252,17,108,36,64 ; vmovups %ymm5,0x40(%rsp) + DB 197,252,17,100,36,32 ; vmovups %ymm4,0x20(%rsp) + DB 197,252,17,28,36 ; vmovups %ymm3,(%rsp) + DB 197,252,40,217 ; vmovaps %ymm1,%ymm3 + DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 184,0,0,0,63 ; mov $0x3f000000,%eax - DB 197,249,110,192 ; vmovd %eax,%xmm0 - DB 196,227,121,4,192,0 ; vpermilps $0x0,%xmm0,%xmm0 - DB 196,99,125,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm0,%ymm8 - DB 196,193,84,194,192,1 ; vcmpltps %ymm8,%ymm5,%ymm0 - DB 196,98,125,24,21,100,70,0,0 ; vbroadcastss 0x4664(%rip),%ymm10 # 55a0 <_sk_callback_avx+0x1be> - DB 197,252,17,76,36,32 ; vmovups %ymm1,0x20(%rsp) - DB 196,193,116,88,218 ; vaddps %ymm10,%ymm1,%ymm3 - DB 197,228,89,221 ; vmulps %ymm5,%ymm3,%ymm3 - DB 197,244,88,229 ; vaddps %ymm5,%ymm1,%ymm4 - DB 197,244,89,245 ; vmulps %ymm5,%ymm1,%ymm6 - DB 197,220,92,230 ; vsubps %ymm6,%ymm4,%ymm4 - DB 196,99,93,74,203,0 ; vblendvps %ymm0,%ymm3,%ymm4,%ymm9 - DB 196,226,125,24,13,62,70,0,0 ; vbroadcastss 0x463e(%rip),%ymm1 # 55a4 <_sk_callback_avx+0x1c2> - DB 197,236,88,201 ; vaddps %ymm1,%ymm2,%ymm1 - DB 65,184,0,0,0,0 ; mov $0x0,%r8d - DB 184,0,0,128,63 ; mov $0x3f800000,%eax - DB 197,249,110,216 ; vmovd %eax,%xmm3 - DB 196,227,121,4,219,0 ; vpermilps $0x0,%xmm3,%xmm3 - DB 196,99,101,24,227,1 ; vinsertf128 $0x1,%xmm3,%ymm3,%ymm12 - DB 197,156,194,217,1 ; vcmpltps %ymm1,%ymm12,%ymm3 - DB 196,98,125,24,53,21,70,0,0 ; vbroadcastss 0x4615(%rip),%ymm14 # 55a8 <_sk_callback_avx+0x1c6> - DB 196,193,116,88,230 ; vaddps %ymm14,%ymm1,%ymm4 - DB 196,227,117,74,220,48 ; vblendvps %ymm3,%ymm4,%ymm1,%ymm3 - DB 196,193,121,110,224 ; vmovd %r8d,%xmm4 - DB 196,227,121,4,228,0 ; vpermilps $0x0,%xmm4,%xmm4 - DB 196,99,93,24,252,1 ; vinsertf128 $0x1,%xmm4,%ymm4,%ymm15 - DB 196,193,116,194,231,1 ; vcmpltps %ymm15,%ymm1,%ymm4 - DB 196,193,116,88,202 ; vaddps %ymm10,%ymm1,%ymm1 - DB 196,227,101,74,241,64 ; vblendvps %ymm4,%ymm1,%ymm3,%ymm6 - DB 197,212,88,205 ; vaddps %ymm5,%ymm5,%ymm1 - DB 196,65,116,92,217 ; vsubps %ymm9,%ymm1,%ymm11 - DB 196,193,52,92,203 ; vsubps %ymm11,%ymm9,%ymm1 - DB 196,226,125,24,29,213,69,0,0 ; vbroadcastss 0x45d5(%rip),%ymm3 # 55ac <_sk_callback_avx+0x1ca> - DB 197,116,89,235 ; vmulps %ymm3,%ymm1,%ymm13 + DB 197,121,110,192 ; vmovd %eax,%xmm8 DB 65,184,171,170,42,62 ; mov $0x3e2aaaab,%r8d DB 184,171,170,42,63 ; mov $0x3f2aaaab,%eax - DB 197,249,110,200 ; vmovd %eax,%xmm1 - DB 196,227,121,4,201,0 ; vpermilps $0x0,%xmm1,%xmm1 - DB 196,227,117,24,225,1 ; vinsertf128 $0x1,%xmm1,%ymm1,%ymm4 - DB 196,226,125,24,29,177,69,0,0 ; vbroadcastss 0x45b1(%rip),%ymm3 # 55b0 <_sk_callback_avx+0x1ce> - DB 197,228,92,206 ; vsubps %ymm6,%ymm3,%ymm1 - DB 197,148,89,201 ; vmulps %ymm1,%ymm13,%ymm1 - DB 197,164,88,201 ; vaddps %ymm1,%ymm11,%ymm1 - DB 197,204,194,252,1 ; vcmpltps %ymm4,%ymm6,%ymm7 - DB 196,227,37,74,201,112 ; vblendvps %ymm7,%ymm1,%ymm11,%ymm1 - DB 196,193,76,194,248,1 ; vcmpltps %ymm8,%ymm6,%ymm7 - DB 196,195,117,74,249,112 ; vblendvps %ymm7,%ymm9,%ymm1,%ymm7 - DB 196,193,121,110,200 ; vmovd %r8d,%xmm1 - DB 196,227,121,4,201,0 ; vpermilps $0x0,%xmm1,%xmm1 - DB 196,227,117,24,201,1 ; vinsertf128 $0x1,%xmm1,%ymm1,%ymm1 - DB 197,204,194,193,1 ; vcmpltps %ymm1,%ymm6,%ymm0 - DB 197,148,89,246 ; vmulps %ymm6,%ymm13,%ymm6 - DB 197,164,88,246 ; vaddps %ymm6,%ymm11,%ymm6 - DB 196,227,69,74,198,0 ; vblendvps %ymm0,%ymm6,%ymm7,%ymm0 - DB 197,252,17,4,36 ; vmovups %ymm0,(%rsp) - DB 197,156,194,194,1 ; vcmpltps %ymm2,%ymm12,%ymm0 - DB 196,193,108,88,254 ; vaddps %ymm14,%ymm2,%ymm7 - DB 196,227,109,74,199,0 ; vblendvps %ymm0,%ymm7,%ymm2,%ymm0 - DB 196,193,108,194,255,1 ; vcmpltps %ymm15,%ymm2,%ymm7 - DB 196,193,108,88,242 ; vaddps %ymm10,%ymm2,%ymm6 - DB 196,227,125,74,198,112 ; vblendvps %ymm7,%ymm6,%ymm0,%ymm0 - DB 197,228,92,240 ; vsubps %ymm0,%ymm3,%ymm6 - DB 197,148,89,246 ; vmulps %ymm6,%ymm13,%ymm6 - DB 197,164,88,246 ; vaddps %ymm6,%ymm11,%ymm6 - DB 197,252,194,252,1 ; vcmpltps %ymm4,%ymm0,%ymm7 - DB 196,227,37,74,246,112 ; vblendvps %ymm7,%ymm6,%ymm11,%ymm6 - DB 196,193,124,194,248,1 ; vcmpltps %ymm8,%ymm0,%ymm7 - DB 196,195,77,74,241,112 ; vblendvps %ymm7,%ymm9,%ymm6,%ymm6 - DB 197,252,194,249,1 ; vcmpltps %ymm1,%ymm0,%ymm7 - DB 197,148,89,192 ; vmulps %ymm0,%ymm13,%ymm0 - DB 197,164,88,192 ; vaddps %ymm0,%ymm11,%ymm0 - DB 196,227,77,74,240,112 ; vblendvps %ymm7,%ymm0,%ymm6,%ymm6 - DB 196,226,125,24,5,9,69,0,0 ; vbroadcastss 0x4509(%rip),%ymm0 # 55b4 <_sk_callback_avx+0x1d2> - DB 197,236,88,192 ; vaddps %ymm0,%ymm2,%ymm0 - DB 197,156,194,208,1 ; vcmpltps %ymm0,%ymm12,%ymm2 - DB 196,193,124,88,254 ; vaddps %ymm14,%ymm0,%ymm7 - DB 196,227,125,74,215,32 ; vblendvps %ymm2,%ymm7,%ymm0,%ymm2 - DB 196,193,124,194,255,1 ; vcmpltps %ymm15,%ymm0,%ymm7 - DB 196,193,124,88,194 ; vaddps %ymm10,%ymm0,%ymm0 - DB 196,227,109,74,192,112 ; vblendvps %ymm7,%ymm0,%ymm2,%ymm0 - DB 197,252,194,212,1 ; vcmpltps %ymm4,%ymm0,%ymm2 - DB 197,228,92,216 ; vsubps %ymm0,%ymm3,%ymm3 - DB 197,148,89,219 ; vmulps %ymm3,%ymm13,%ymm3 - DB 197,164,88,219 ; vaddps %ymm3,%ymm11,%ymm3 - DB 196,227,37,74,211,32 ; vblendvps %ymm2,%ymm3,%ymm11,%ymm2 - DB 196,193,124,194,216,1 ; vcmpltps %ymm8,%ymm0,%ymm3 - DB 196,195,109,74,209,48 ; vblendvps %ymm3,%ymm9,%ymm2,%ymm2 - DB 197,252,194,201,1 ; vcmpltps %ymm1,%ymm0,%ymm1 - DB 197,148,89,192 ; vmulps %ymm0,%ymm13,%ymm0 - DB 197,164,88,192 ; vaddps %ymm0,%ymm11,%ymm0 - DB 196,227,109,74,208,16 ; vblendvps %ymm1,%ymm0,%ymm2,%ymm2 + DB 197,121,110,224 ; vmovd %eax,%xmm12 + DB 196,67,121,4,192,0 ; vpermilps $0x0,%xmm8,%xmm8 + DB 196,67,61,24,192,1 ; vinsertf128 $0x1,%xmm8,%ymm8,%ymm8 + DB 196,65,108,194,200,1 ; vcmpltps %ymm8,%ymm2,%ymm9 + DB 197,100,89,210 ; vmulps %ymm2,%ymm3,%ymm10 + DB 196,65,100,92,218 ; vsubps %ymm10,%ymm3,%ymm11 + DB 196,67,37,74,202,144 ; vblendvps %ymm9,%ymm10,%ymm11,%ymm9 + DB 197,52,88,210 ; vaddps %ymm2,%ymm9,%ymm10 + DB 197,108,88,202 ; vaddps %ymm2,%ymm2,%ymm9 + DB 196,65,52,92,202 ; vsubps %ymm10,%ymm9,%ymm9 + DB 196,98,125,24,29,172,69,0,0 ; vbroadcastss 0x45ac(%rip),%ymm11 # 550c <_sk_callback_avx+0x1be> + DB 196,65,116,88,219 ; vaddps %ymm11,%ymm1,%ymm11 + DB 196,67,125,8,235,1 ; vroundps $0x1,%ymm11,%ymm13 + DB 196,65,36,92,237 ; vsubps %ymm13,%ymm11,%ymm13 + DB 196,65,44,92,217 ; vsubps %ymm9,%ymm10,%ymm11 + DB 196,98,125,24,53,146,69,0,0 ; vbroadcastss 0x4592(%rip),%ymm14 # 5510 <_sk_callback_avx+0x1c2> + DB 196,65,20,89,254 ; vmulps %ymm14,%ymm13,%ymm15 + DB 196,67,121,4,228,0 ; vpermilps $0x0,%xmm12,%xmm12 + DB 196,67,29,24,228,1 ; vinsertf128 $0x1,%xmm12,%ymm12,%ymm12 + DB 196,226,125,24,5,124,69,0,0 ; vbroadcastss 0x457c(%rip),%ymm0 # 5514 <_sk_callback_avx+0x1c6> + DB 196,193,124,92,255 ; vsubps %ymm15,%ymm0,%ymm7 + DB 197,164,89,255 ; vmulps %ymm7,%ymm11,%ymm7 + DB 197,180,88,255 ; vaddps %ymm7,%ymm9,%ymm7 + DB 196,193,20,194,244,1 ; vcmpltps %ymm12,%ymm13,%ymm6 + DB 196,227,53,74,247,96 ; vblendvps %ymm6,%ymm7,%ymm9,%ymm6 + DB 196,193,20,194,248,1 ; vcmpltps %ymm8,%ymm13,%ymm7 + DB 196,195,77,74,242,112 ; vblendvps %ymm7,%ymm10,%ymm6,%ymm6 + DB 196,193,121,110,248 ; vmovd %r8d,%xmm7 + DB 196,227,121,4,255,0 ; vpermilps $0x0,%xmm7,%xmm7 + DB 196,227,69,24,255,1 ; vinsertf128 $0x1,%xmm7,%ymm7,%ymm7 + DB 197,20,194,239,1 ; vcmpltps %ymm7,%ymm13,%ymm13 + DB 196,65,4,89,251 ; vmulps %ymm11,%ymm15,%ymm15 + DB 196,65,52,88,255 ; vaddps %ymm15,%ymm9,%ymm15 + DB 196,195,77,74,247,208 ; vblendvps %ymm13,%ymm15,%ymm6,%ymm6 + DB 196,99,125,8,233,1 ; vroundps $0x1,%ymm1,%ymm13 + DB 196,65,116,92,237 ; vsubps %ymm13,%ymm1,%ymm13 + DB 196,65,20,89,254 ; vmulps %ymm14,%ymm13,%ymm15 + DB 196,193,124,92,239 ; vsubps %ymm15,%ymm0,%ymm5 + DB 197,164,89,237 ; vmulps %ymm5,%ymm11,%ymm5 + DB 197,180,88,237 ; vaddps %ymm5,%ymm9,%ymm5 + DB 196,193,20,194,228,1 ; vcmpltps %ymm12,%ymm13,%ymm4 + DB 196,227,53,74,229,64 ; vblendvps %ymm4,%ymm5,%ymm9,%ymm4 + DB 196,193,20,194,232,1 ; vcmpltps %ymm8,%ymm13,%ymm5 + DB 196,195,93,74,226,80 ; vblendvps %ymm5,%ymm10,%ymm4,%ymm4 + DB 197,148,194,239,1 ; vcmpltps %ymm7,%ymm13,%ymm5 + DB 196,65,36,89,239 ; vmulps %ymm15,%ymm11,%ymm13 + DB 196,65,52,88,237 ; vaddps %ymm13,%ymm9,%ymm13 + DB 196,195,93,74,229,80 ; vblendvps %ymm5,%ymm13,%ymm4,%ymm4 + DB 196,226,125,24,45,226,68,0,0 ; vbroadcastss 0x44e2(%rip),%ymm5 # 5518 <_sk_callback_avx+0x1ca> + DB 197,244,88,205 ; vaddps %ymm5,%ymm1,%ymm1 + DB 196,227,125,8,233,1 ; vroundps $0x1,%ymm1,%ymm5 + DB 197,244,92,205 ; vsubps %ymm5,%ymm1,%ymm1 + DB 196,193,116,89,238 ; vmulps %ymm14,%ymm1,%ymm5 + DB 196,65,116,194,228,1 ; vcmpltps %ymm12,%ymm1,%ymm12 + DB 197,252,92,197 ; vsubps %ymm5,%ymm0,%ymm0 + DB 197,164,89,192 ; vmulps %ymm0,%ymm11,%ymm0 + DB 197,180,88,192 ; vaddps %ymm0,%ymm9,%ymm0 + DB 196,227,53,74,192,192 ; vblendvps %ymm12,%ymm0,%ymm9,%ymm0 + DB 196,65,116,194,192,1 ; vcmpltps %ymm8,%ymm1,%ymm8 + DB 196,195,125,74,194,128 ; vblendvps %ymm8,%ymm10,%ymm0,%ymm0 + DB 197,244,194,207,1 ; vcmpltps %ymm7,%ymm1,%ymm1 + DB 197,164,89,237 ; vmulps %ymm5,%ymm11,%ymm5 + DB 197,180,88,237 ; vaddps %ymm5,%ymm9,%ymm5 + DB 196,227,125,74,237,16 ; vblendvps %ymm1,%ymm5,%ymm0,%ymm5 DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 - DB 197,252,194,92,36,32,0 ; vcmpeqps 0x20(%rsp),%ymm0,%ymm3 - DB 197,252,16,4,36 ; vmovups (%rsp),%ymm0 - DB 196,227,125,74,197,48 ; vblendvps %ymm3,%ymm5,%ymm0,%ymm0 - DB 196,227,77,74,205,48 ; vblendvps %ymm3,%ymm5,%ymm6,%ymm1 - DB 196,227,109,74,213,48 ; vblendvps %ymm3,%ymm5,%ymm2,%ymm2 + DB 197,228,194,216,0 ; vcmpeqps %ymm0,%ymm3,%ymm3 + DB 196,227,77,74,194,48 ; vblendvps %ymm3,%ymm2,%ymm6,%ymm0 + DB 196,227,93,74,202,48 ; vblendvps %ymm3,%ymm2,%ymm4,%ymm1 + DB 196,227,85,74,210,48 ; vblendvps %ymm3,%ymm2,%ymm5,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 197,252,16,92,36,64 ; vmovups 0x40(%rsp),%ymm3 - DB 197,252,16,100,36,96 ; vmovups 0x60(%rsp),%ymm4 - DB 197,252,16,172,36,128,0,0,0 ; vmovups 0x80(%rsp),%ymm5 - DB 197,252,16,180,36,160,0,0,0 ; vmovups 0xa0(%rsp),%ymm6 - DB 197,252,16,188,36,192,0,0,0 ; vmovups 0xc0(%rsp),%ymm7 - DB 72,129,196,248,0,0,0 ; add $0xf8,%rsp + DB 197,252,16,28,36 ; vmovups (%rsp),%ymm3 + DB 197,252,16,100,36,32 ; vmovups 0x20(%rsp),%ymm4 + DB 197,252,16,108,36,64 ; vmovups 0x40(%rsp),%ymm5 + DB 197,252,16,116,36,96 ; vmovups 0x60(%rsp),%ymm6 + DB 197,252,16,188,36,128,0,0,0 ; vmovups 0x80(%rsp),%ymm7 + DB 72,129,196,184,0,0,0 ; add $0xb8,%rsp DB 255,224 ; jmpq *%rax PUBLIC _sk_scale_1_float_avx @@ -5450,14 +5401,14 @@ _sk_scale_u8_avx LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 72,1,248 ; add %rdi,%rax DB 77,133,192 ; test %r8,%r8 - DB 117,68 ; jne 11c9 <_sk_scale_u8_avx+0x54> + DB 117,68 ; jne 1135 <_sk_scale_u8_avx+0x54> DB 197,122,126,0 ; vmovq (%rax),%xmm8 DB 196,66,121,49,200 ; vpmovzxbd %xmm8,%xmm9 DB 196,67,121,4,192,229 ; vpermilps $0xe5,%xmm8,%xmm8 DB 196,66,121,49,192 ; vpmovzxbd %xmm8,%xmm8 DB 196,67,53,24,192,1 ; vinsertf128 $0x1,%xmm8,%ymm9,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,11,68,0,0 ; vbroadcastss 0x440b(%rip),%ymm9 # 55b8 <_sk_callback_avx+0x1d6> + DB 196,98,125,24,13,3,68,0,0 ; vbroadcastss 0x4403(%rip),%ymm9 # 551c <_sk_callback_avx+0x1ce> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 @@ -5475,9 +5426,9 @@ _sk_scale_u8_avx LABEL PROC DB 77,9,217 ; or %r11,%r9 DB 72,131,193,8 ; add $0x8,%rcx DB 73,255,202 ; dec %r10 - DB 117,234 ; jne 11d1 <_sk_scale_u8_avx+0x5c> + DB 117,234 ; jne 113d <_sk_scale_u8_avx+0x5c> DB 196,65,249,110,193 ; vmovq %r9,%xmm8 - DB 235,155 ; jmp 1189 <_sk_scale_u8_avx+0x14> + DB 235,155 ; jmp 10f5 <_sk_scale_u8_avx+0x14> PUBLIC _sk_lerp_1_float_avx _sk_lerp_1_float_avx LABEL PROC @@ -5505,14 +5456,14 @@ _sk_lerp_u8_avx LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 72,1,248 ; add %rdi,%rax DB 77,133,192 ; test %r8,%r8 - DB 117,104 ; jne 12a5 <_sk_lerp_u8_avx+0x78> + DB 117,104 ; jne 1211 <_sk_lerp_u8_avx+0x78> DB 197,122,126,0 ; vmovq (%rax),%xmm8 DB 196,66,121,49,200 ; vpmovzxbd %xmm8,%xmm9 DB 196,67,121,4,192,229 ; vpermilps $0xe5,%xmm8,%xmm8 DB 196,66,121,49,192 ; vpmovzxbd %xmm8,%xmm8 DB 196,67,53,24,192,1 ; vinsertf128 $0x1,%xmm8,%ymm9,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,87,67,0,0 ; vbroadcastss 0x4357(%rip),%ymm9 # 55bc <_sk_callback_avx+0x1da> + DB 196,98,125,24,13,79,67,0,0 ; vbroadcastss 0x434f(%rip),%ymm9 # 5520 <_sk_callback_avx+0x1d2> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 DB 197,252,92,196 ; vsubps %ymm4,%ymm0,%ymm0 DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 @@ -5538,35 +5489,35 @@ _sk_lerp_u8_avx LABEL PROC DB 77,9,217 ; or %r11,%r9 DB 72,131,193,8 ; add $0x8,%rcx DB 73,255,202 ; dec %r10 - DB 117,234 ; jne 12ad <_sk_lerp_u8_avx+0x80> + DB 117,234 ; jne 1219 <_sk_lerp_u8_avx+0x80> DB 196,65,249,110,193 ; vmovq %r9,%xmm8 - DB 233,116,255,255,255 ; jmpq 1241 <_sk_lerp_u8_avx+0x14> + DB 233,116,255,255,255 ; jmpq 11ad <_sk_lerp_u8_avx+0x14> PUBLIC _sk_lerp_565_avx _sk_lerp_565_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,174,0,0,0 ; jne 1389 <_sk_lerp_565_avx+0xbc> + DB 15,133,174,0,0,0 ; jne 12f5 <_sk_lerp_565_avx+0xbc> DB 196,65,122,111,4,122 ; vmovdqu (%r10,%rdi,2),%xmm8 DB 197,225,239,219 ; vpxor %xmm3,%xmm3,%xmm3 DB 197,185,105,219 ; vpunpckhwd %xmm3,%xmm8,%xmm3 DB 196,66,121,51,192 ; vpmovzxwd %xmm8,%xmm8 DB 196,227,61,24,219,1 ; vinsertf128 $0x1,%xmm3,%ymm8,%ymm3 - DB 196,98,125,24,5,195,66,0,0 ; vbroadcastss 0x42c3(%rip),%ymm8 # 55c0 <_sk_callback_avx+0x1de> + DB 196,98,125,24,5,187,66,0,0 ; vbroadcastss 0x42bb(%rip),%ymm8 # 5524 <_sk_callback_avx+0x1d6> DB 196,65,100,84,192 ; vandps %ymm8,%ymm3,%ymm8 DB 196,65,124,91,192 ; vcvtdq2ps %ymm8,%ymm8 - DB 196,98,125,24,13,180,66,0,0 ; vbroadcastss 0x42b4(%rip),%ymm9 # 55c4 <_sk_callback_avx+0x1e2> + DB 196,98,125,24,13,172,66,0,0 ; vbroadcastss 0x42ac(%rip),%ymm9 # 5528 <_sk_callback_avx+0x1da> DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 - DB 196,98,125,24,13,170,66,0,0 ; vbroadcastss 0x42aa(%rip),%ymm9 # 55c8 <_sk_callback_avx+0x1e6> + DB 196,98,125,24,13,162,66,0,0 ; vbroadcastss 0x42a2(%rip),%ymm9 # 552c <_sk_callback_avx+0x1de> DB 196,65,100,84,201 ; vandps %ymm9,%ymm3,%ymm9 DB 196,65,124,91,201 ; vcvtdq2ps %ymm9,%ymm9 - DB 196,98,125,24,21,155,66,0,0 ; vbroadcastss 0x429b(%rip),%ymm10 # 55cc <_sk_callback_avx+0x1ea> + DB 196,98,125,24,21,147,66,0,0 ; vbroadcastss 0x4293(%rip),%ymm10 # 5530 <_sk_callback_avx+0x1e2> DB 196,65,52,89,202 ; vmulps %ymm10,%ymm9,%ymm9 - DB 196,98,125,24,21,145,66,0,0 ; vbroadcastss 0x4291(%rip),%ymm10 # 55d0 <_sk_callback_avx+0x1ee> + DB 196,98,125,24,21,137,66,0,0 ; vbroadcastss 0x4289(%rip),%ymm10 # 5534 <_sk_callback_avx+0x1e6> DB 196,193,100,84,218 ; vandps %ymm10,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,21,131,66,0,0 ; vbroadcastss 0x4283(%rip),%ymm10 # 55d4 <_sk_callback_avx+0x1f2> + DB 196,98,125,24,21,123,66,0,0 ; vbroadcastss 0x427b(%rip),%ymm10 # 5538 <_sk_callback_avx+0x1ea> DB 196,193,100,89,218 ; vmulps %ymm10,%ymm3,%ymm3 DB 197,252,92,196 ; vsubps %ymm4,%ymm0,%ymm0 DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 @@ -5578,16 +5529,16 @@ _sk_lerp_565_avx LABEL PROC DB 197,236,89,211 ; vmulps %ymm3,%ymm2,%ymm2 DB 197,236,88,214 ; vaddps %ymm6,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,81,66,0,0 ; vbroadcastss 0x4251(%rip),%ymm3 # 55d8 <_sk_callback_avx+0x1f6> + DB 196,226,125,24,29,73,66,0,0 ; vbroadcastss 0x4249(%rip),%ymm3 # 553c <_sk_callback_avx+0x1ee> DB 255,224 ; jmpq *%rax DB 65,137,200 ; mov %ecx,%r8d DB 65,128,224,7 ; and $0x7,%r8b DB 196,65,57,239,192 ; vpxor %xmm8,%xmm8,%xmm8 DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 15,135,63,255,255,255 ; ja 12e1 <_sk_lerp_565_avx+0x14> + DB 15,135,63,255,255,255 ; ja 124d <_sk_lerp_565_avx+0x14> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,75,0,0,0 ; lea 0x4b(%rip),%r9 # 13f8 <_sk_lerp_565_avx+0x12b> + DB 76,141,13,75,0,0,0 ; lea 0x4b(%rip),%r9 # 1364 <_sk_lerp_565_avx+0x12b> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -5599,7 +5550,7 @@ _sk_lerp_565_avx LABEL PROC DB 196,65,57,196,68,122,4,2 ; vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm8,%xmm8 DB 196,65,57,196,68,122,2,1 ; vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm8,%xmm8 DB 196,65,57,196,4,122,0 ; vpinsrw $0x0,(%r10,%rdi,2),%xmm8,%xmm8 - DB 233,235,254,255,255 ; jmpq 12e1 <_sk_lerp_565_avx+0x14> + DB 233,235,254,255,255 ; jmpq 124d <_sk_lerp_565_avx+0x14> DB 102,144 ; xchg %ax,%ax DB 242,255 ; repnz (bad) DB 255 ; (bad) @@ -5630,7 +5581,7 @@ _sk_load_tables_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,0 ; mov (%rax),%r8 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,26,2,0,0 ; jne 163c <_sk_load_tables_avx+0x228> + DB 15,133,26,2,0,0 ; jne 15a8 <_sk_load_tables_avx+0x228> DB 196,65,124,16,4,184 ; vmovups (%r8,%rdi,4),%ymm8 DB 85 ; push %rbp DB 65,87 ; push %r15 @@ -5638,7 +5589,7 @@ _sk_load_tables_avx LABEL PROC DB 65,85 ; push %r13 DB 65,84 ; push %r12 DB 83 ; push %rbx - DB 197,124,40,13,102,68,0,0 ; vmovaps 0x4466(%rip),%ymm9 # 58a0 <_sk_callback_avx+0x4be> + DB 197,124,40,13,90,68,0,0 ; vmovaps 0x445a(%rip),%ymm9 # 5800 <_sk_callback_avx+0x4b2> DB 196,193,60,84,193 ; vandps %ymm9,%ymm8,%ymm0 DB 196,193,249,126,193 ; vmovq %xmm0,%r9 DB 69,137,203 ; mov %r9d,%r11d @@ -5730,7 +5681,7 @@ _sk_load_tables_avx LABEL PROC DB 196,193,97,114,210,24 ; vpsrld $0x18,%xmm10,%xmm3 DB 196,227,61,24,219,1 ; vinsertf128 $0x1,%xmm3,%ymm8,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,179,63,0,0 ; vbroadcastss 0x3fb3(%rip),%ymm8 # 55dc <_sk_callback_avx+0x1fa> + DB 196,98,125,24,5,171,63,0,0 ; vbroadcastss 0x3fab(%rip),%ymm8 # 5540 <_sk_callback_avx+0x1f2> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 91 ; pop %rbx @@ -5745,9 +5696,9 @@ _sk_load_tables_avx LABEL PROC DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 65,254,201 ; dec %r9b DB 65,128,249,6 ; cmp $0x6,%r9b - DB 15,135,211,253,255,255 ; ja 1428 <_sk_load_tables_avx+0x14> + DB 15,135,211,253,255,255 ; ja 1394 <_sk_load_tables_avx+0x14> DB 69,15,182,201 ; movzbl %r9b,%r9d - DB 76,141,21,140,0,0,0 ; lea 0x8c(%rip),%r10 # 16ec <_sk_load_tables_avx+0x2d8> + DB 76,141,21,140,0,0,0 ; lea 0x8c(%rip),%r10 # 1658 <_sk_load_tables_avx+0x2d8> DB 79,99,12,138 ; movslq (%r10,%r9,4),%r9 DB 77,1,209 ; add %r10,%r9 DB 65,255,225 ; jmpq *%r9 @@ -5770,7 +5721,7 @@ _sk_load_tables_avx LABEL PROC DB 196,99,61,12,192,15 ; vblendps $0xf,%ymm0,%ymm8,%ymm8 DB 196,195,57,34,4,184,0 ; vpinsrd $0x0,(%r8,%rdi,4),%xmm8,%xmm0 DB 196,99,61,12,192,15 ; vblendps $0xf,%ymm0,%ymm8,%ymm8 - DB 233,62,253,255,255 ; jmpq 1428 <_sk_load_tables_avx+0x14> + DB 233,62,253,255,255 ; jmpq 1394 <_sk_load_tables_avx+0x14> DB 102,144 ; xchg %ax,%ax DB 236 ; in (%dx),%al DB 255 ; (bad) @@ -5788,7 +5739,7 @@ _sk_load_tables_avx LABEL PROC DB 255 ; (bad) DB 255 ; (bad) DB 255 ; (bad) - DB 126,255 ; jle 1705 <_sk_load_tables_avx+0x2f1> + DB 126,255 ; jle 1671 <_sk_load_tables_avx+0x2f1> DB 255 ; (bad) DB 255 ; .byte 0xff @@ -5798,7 +5749,7 @@ _sk_load_tables_u16_be_avx LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 76,141,12,189,0,0,0,0 ; lea 0x0(,%rdi,4),%r9 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,113,2,0,0 ; jne 198f <_sk_load_tables_u16_be_avx+0x287> + DB 15,133,113,2,0,0 ; jne 18fb <_sk_load_tables_u16_be_avx+0x287> DB 196,1,121,16,4,72 ; vmovupd (%r8,%r9,2),%xmm8 DB 196,129,121,16,84,72,16 ; vmovupd 0x10(%r8,%r9,2),%xmm2 DB 196,129,121,16,92,72,32 ; vmovupd 0x20(%r8,%r9,2),%xmm3 @@ -5820,7 +5771,7 @@ _sk_load_tables_u16_be_avx LABEL PROC DB 197,177,108,208 ; vpunpcklqdq %xmm0,%xmm9,%xmm2 DB 197,177,109,200 ; vpunpckhqdq %xmm0,%xmm9,%xmm1 DB 196,65,57,108,212 ; vpunpcklqdq %xmm12,%xmm8,%xmm10 - DB 197,121,111,29,166,65,0,0 ; vmovdqa 0x41a6(%rip),%xmm11 # 5920 <_sk_callback_avx+0x53e> + DB 197,121,111,29,154,65,0,0 ; vmovdqa 0x419a(%rip),%xmm11 # 5880 <_sk_callback_avx+0x532> DB 196,193,105,219,195 ; vpand %xmm11,%xmm2,%xmm0 DB 196,65,49,239,201 ; vpxor %xmm9,%xmm9,%xmm9 DB 196,193,121,105,209 ; vpunpckhwd %xmm9,%xmm0,%xmm2 @@ -5919,7 +5870,7 @@ _sk_load_tables_u16_be_avx LABEL PROC DB 196,226,121,51,219 ; vpmovzxwd %xmm3,%xmm3 DB 196,195,101,24,216,1 ; vinsertf128 $0x1,%xmm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,100,60,0,0 ; vbroadcastss 0x3c64(%rip),%ymm8 # 55e0 <_sk_callback_avx+0x1fe> + DB 196,98,125,24,5,92,60,0,0 ; vbroadcastss 0x3c5c(%rip),%ymm8 # 5544 <_sk_callback_avx+0x1f6> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 91 ; pop %rbx @@ -5932,29 +5883,29 @@ _sk_load_tables_u16_be_avx LABEL PROC DB 196,1,123,16,4,72 ; vmovsd (%r8,%r9,2),%xmm8 DB 196,65,49,239,201 ; vpxor %xmm9,%xmm9,%xmm9 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,85 ; je 19f5 <_sk_load_tables_u16_be_avx+0x2ed> + DB 116,85 ; je 1961 <_sk_load_tables_u16_be_avx+0x2ed> DB 196,1,57,22,68,72,8 ; vmovhpd 0x8(%r8,%r9,2),%xmm8,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,72 ; jb 19f5 <_sk_load_tables_u16_be_avx+0x2ed> + DB 114,72 ; jb 1961 <_sk_load_tables_u16_be_avx+0x2ed> DB 196,129,123,16,84,72,16 ; vmovsd 0x10(%r8,%r9,2),%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 116,72 ; je 1a02 <_sk_load_tables_u16_be_avx+0x2fa> + DB 116,72 ; je 196e <_sk_load_tables_u16_be_avx+0x2fa> DB 196,129,105,22,84,72,24 ; vmovhpd 0x18(%r8,%r9,2),%xmm2,%xmm2 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,59 ; jb 1a02 <_sk_load_tables_u16_be_avx+0x2fa> + DB 114,59 ; jb 196e <_sk_load_tables_u16_be_avx+0x2fa> DB 196,129,123,16,92,72,32 ; vmovsd 0x20(%r8,%r9,2),%xmm3 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 15,132,97,253,255,255 ; je 1739 <_sk_load_tables_u16_be_avx+0x31> + DB 15,132,97,253,255,255 ; je 16a5 <_sk_load_tables_u16_be_avx+0x31> DB 196,129,97,22,92,72,40 ; vmovhpd 0x28(%r8,%r9,2),%xmm3,%xmm3 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 15,130,80,253,255,255 ; jb 1739 <_sk_load_tables_u16_be_avx+0x31> + DB 15,130,80,253,255,255 ; jb 16a5 <_sk_load_tables_u16_be_avx+0x31> DB 196,1,122,126,76,72,48 ; vmovq 0x30(%r8,%r9,2),%xmm9 - DB 233,68,253,255,255 ; jmpq 1739 <_sk_load_tables_u16_be_avx+0x31> + DB 233,68,253,255,255 ; jmpq 16a5 <_sk_load_tables_u16_be_avx+0x31> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 DB 197,233,87,210 ; vxorpd %xmm2,%xmm2,%xmm2 - DB 233,55,253,255,255 ; jmpq 1739 <_sk_load_tables_u16_be_avx+0x31> + DB 233,55,253,255,255 ; jmpq 16a5 <_sk_load_tables_u16_be_avx+0x31> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 - DB 233,46,253,255,255 ; jmpq 1739 <_sk_load_tables_u16_be_avx+0x31> + DB 233,46,253,255,255 ; jmpq 16a5 <_sk_load_tables_u16_be_avx+0x31> PUBLIC _sk_load_tables_rgb_u16_be_avx _sk_load_tables_rgb_u16_be_avx LABEL PROC @@ -5962,7 +5913,7 @@ _sk_load_tables_rgb_u16_be_avx LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 76,141,12,127 ; lea (%rdi,%rdi,2),%r9 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,93,2,0,0 ; jne 1c7a <_sk_load_tables_rgb_u16_be_avx+0x26f> + DB 15,133,93,2,0,0 ; jne 1be6 <_sk_load_tables_rgb_u16_be_avx+0x26f> DB 196,129,122,111,4,72 ; vmovdqu (%r8,%r9,2),%xmm0 DB 196,129,122,111,84,72,12 ; vmovdqu 0xc(%r8,%r9,2),%xmm2 DB 196,129,122,111,76,72,24 ; vmovdqu 0x18(%r8,%r9,2),%xmm1 @@ -5989,7 +5940,7 @@ _sk_load_tables_rgb_u16_be_avx LABEL PROC DB 197,185,108,202 ; vpunpcklqdq %xmm2,%xmm8,%xmm1 DB 197,185,109,210 ; vpunpckhqdq %xmm2,%xmm8,%xmm2 DB 197,121,108,195 ; vpunpcklqdq %xmm3,%xmm0,%xmm8 - DB 197,121,111,13,159,62,0,0 ; vmovdqa 0x3e9f(%rip),%xmm9 # 5930 <_sk_callback_avx+0x54e> + DB 197,121,111,13,147,62,0,0 ; vmovdqa 0x3e93(%rip),%xmm9 # 5890 <_sk_callback_avx+0x542> DB 196,193,113,219,193 ; vpand %xmm9,%xmm1,%xmm0 DB 196,65,41,239,210 ; vpxor %xmm10,%xmm10,%xmm10 DB 196,193,121,105,202 ; vpunpckhwd %xmm10,%xmm0,%xmm1 @@ -6081,7 +6032,7 @@ _sk_load_tables_rgb_u16_be_avx LABEL PROC DB 196,227,105,33,211,48 ; vinsertps $0x30,%xmm3,%xmm2,%xmm2 DB 196,195,109,24,208,1 ; vinsertf128 $0x1,%xmm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,118,57,0,0 ; vbroadcastss 0x3976(%rip),%ymm3 # 55e4 <_sk_callback_avx+0x202> + DB 196,226,125,24,29,110,57,0,0 ; vbroadcastss 0x396e(%rip),%ymm3 # 5548 <_sk_callback_avx+0x1fa> DB 91 ; pop %rbx DB 65,92 ; pop %r12 DB 65,93 ; pop %r13 @@ -6092,36 +6043,36 @@ _sk_load_tables_rgb_u16_be_avx LABEL PROC DB 196,129,121,110,4,72 ; vmovd (%r8,%r9,2),%xmm0 DB 196,129,121,196,68,72,4,2 ; vpinsrw $0x2,0x4(%r8,%r9,2),%xmm0,%xmm0 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 117,5 ; jne 1c93 <_sk_load_tables_rgb_u16_be_avx+0x288> - DB 233,190,253,255,255 ; jmpq 1a51 <_sk_load_tables_rgb_u16_be_avx+0x46> + DB 117,5 ; jne 1bff <_sk_load_tables_rgb_u16_be_avx+0x288> + DB 233,190,253,255,255 ; jmpq 19bd <_sk_load_tables_rgb_u16_be_avx+0x46> DB 196,129,121,110,76,72,6 ; vmovd 0x6(%r8,%r9,2),%xmm1 DB 196,1,113,196,68,72,10,2 ; vpinsrw $0x2,0xa(%r8,%r9,2),%xmm1,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,26 ; jb 1cc2 <_sk_load_tables_rgb_u16_be_avx+0x2b7> + DB 114,26 ; jb 1c2e <_sk_load_tables_rgb_u16_be_avx+0x2b7> DB 196,129,121,110,76,72,12 ; vmovd 0xc(%r8,%r9,2),%xmm1 DB 196,129,113,196,84,72,16,2 ; vpinsrw $0x2,0x10(%r8,%r9,2),%xmm1,%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 117,10 ; jne 1cc7 <_sk_load_tables_rgb_u16_be_avx+0x2bc> - DB 233,143,253,255,255 ; jmpq 1a51 <_sk_load_tables_rgb_u16_be_avx+0x46> - DB 233,138,253,255,255 ; jmpq 1a51 <_sk_load_tables_rgb_u16_be_avx+0x46> + DB 117,10 ; jne 1c33 <_sk_load_tables_rgb_u16_be_avx+0x2bc> + DB 233,143,253,255,255 ; jmpq 19bd <_sk_load_tables_rgb_u16_be_avx+0x46> + DB 233,138,253,255,255 ; jmpq 19bd <_sk_load_tables_rgb_u16_be_avx+0x46> DB 196,129,121,110,76,72,18 ; vmovd 0x12(%r8,%r9,2),%xmm1 DB 196,1,113,196,76,72,22,2 ; vpinsrw $0x2,0x16(%r8,%r9,2),%xmm1,%xmm9 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,26 ; jb 1cf6 <_sk_load_tables_rgb_u16_be_avx+0x2eb> + DB 114,26 ; jb 1c62 <_sk_load_tables_rgb_u16_be_avx+0x2eb> DB 196,129,121,110,76,72,24 ; vmovd 0x18(%r8,%r9,2),%xmm1 DB 196,129,113,196,76,72,28,2 ; vpinsrw $0x2,0x1c(%r8,%r9,2),%xmm1,%xmm1 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 117,10 ; jne 1cfb <_sk_load_tables_rgb_u16_be_avx+0x2f0> - DB 233,91,253,255,255 ; jmpq 1a51 <_sk_load_tables_rgb_u16_be_avx+0x46> - DB 233,86,253,255,255 ; jmpq 1a51 <_sk_load_tables_rgb_u16_be_avx+0x46> + DB 117,10 ; jne 1c67 <_sk_load_tables_rgb_u16_be_avx+0x2f0> + DB 233,91,253,255,255 ; jmpq 19bd <_sk_load_tables_rgb_u16_be_avx+0x46> + DB 233,86,253,255,255 ; jmpq 19bd <_sk_load_tables_rgb_u16_be_avx+0x46> DB 196,129,121,110,92,72,30 ; vmovd 0x1e(%r8,%r9,2),%xmm3 DB 196,1,97,196,92,72,34,2 ; vpinsrw $0x2,0x22(%r8,%r9,2),%xmm3,%xmm11 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,20 ; jb 1d24 <_sk_load_tables_rgb_u16_be_avx+0x319> + DB 114,20 ; jb 1c90 <_sk_load_tables_rgb_u16_be_avx+0x319> DB 196,129,121,110,92,72,36 ; vmovd 0x24(%r8,%r9,2),%xmm3 DB 196,129,97,196,92,72,40,2 ; vpinsrw $0x2,0x28(%r8,%r9,2),%xmm3,%xmm3 - DB 233,45,253,255,255 ; jmpq 1a51 <_sk_load_tables_rgb_u16_be_avx+0x46> - DB 233,40,253,255,255 ; jmpq 1a51 <_sk_load_tables_rgb_u16_be_avx+0x46> + DB 233,45,253,255,255 ; jmpq 19bd <_sk_load_tables_rgb_u16_be_avx+0x46> + DB 233,40,253,255,255 ; jmpq 19bd <_sk_load_tables_rgb_u16_be_avx+0x46> PUBLIC _sk_byte_tables_avx _sk_byte_tables_avx LABEL PROC @@ -6132,7 +6083,7 @@ _sk_byte_tables_avx LABEL PROC DB 65,84 ; push %r12 DB 83 ; push %rbx DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,170,56,0,0 ; vbroadcastss 0x38aa(%rip),%ymm8 # 55e8 <_sk_callback_avx+0x206> + DB 196,98,125,24,5,162,56,0,0 ; vbroadcastss 0x38a2(%rip),%ymm8 # 554c <_sk_callback_avx+0x1fe> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 197,253,91,192 ; vcvtps2dq %ymm0,%ymm0 DB 196,195,249,22,192,1 ; vpextrq $0x1,%xmm0,%r8 @@ -6169,7 +6120,7 @@ _sk_byte_tables_avx LABEL PROC DB 196,226,121,49,192 ; vpmovzxbd %xmm0,%xmm0 DB 196,227,53,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm9,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,248,55,0,0 ; vbroadcastss 0x37f8(%rip),%ymm9 # 55ec <_sk_callback_avx+0x20a> + DB 196,98,125,24,13,240,55,0,0 ; vbroadcastss 0x37f0(%rip),%ymm9 # 5550 <_sk_callback_avx+0x202> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 @@ -6329,7 +6280,7 @@ _sk_byte_tables_rgb_avx LABEL PROC DB 196,226,121,49,192 ; vpmovzxbd %xmm0,%xmm0 DB 196,227,53,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm9,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,30,53,0,0 ; vbroadcastss 0x351e(%rip),%ymm9 # 55f0 <_sk_callback_avx+0x20e> + DB 196,98,125,24,13,22,53,0,0 ; vbroadcastss 0x3516(%rip),%ymm9 # 5554 <_sk_callback_avx+0x206> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 197,188,89,201 ; vmulps %ymm1,%ymm8,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 @@ -6616,36 +6567,36 @@ _sk_parametric_r_avx LABEL PROC DB 196,193,124,88,195 ; vaddps %ymm11,%ymm0,%ymm0 DB 196,98,125,24,16 ; vbroadcastss (%rax),%ymm10 DB 197,124,91,216 ; vcvtdq2ps %ymm0,%ymm11 - DB 196,98,125,24,37,124,48,0,0 ; vbroadcastss 0x307c(%rip),%ymm12 # 55f4 <_sk_callback_avx+0x212> + DB 196,98,125,24,37,116,48,0,0 ; vbroadcastss 0x3074(%rip),%ymm12 # 5558 <_sk_callback_avx+0x20a> DB 196,65,36,89,220 ; vmulps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,114,48,0,0 ; vbroadcastss 0x3072(%rip),%ymm12 # 55f8 <_sk_callback_avx+0x216> + DB 196,98,125,24,37,106,48,0,0 ; vbroadcastss 0x306a(%rip),%ymm12 # 555c <_sk_callback_avx+0x20e> DB 196,193,124,84,196 ; vandps %ymm12,%ymm0,%ymm0 - DB 196,98,125,24,37,104,48,0,0 ; vbroadcastss 0x3068(%rip),%ymm12 # 55fc <_sk_callback_avx+0x21a> + DB 196,98,125,24,37,96,48,0,0 ; vbroadcastss 0x3060(%rip),%ymm12 # 5560 <_sk_callback_avx+0x212> DB 196,193,124,86,196 ; vorps %ymm12,%ymm0,%ymm0 - DB 196,98,125,24,37,94,48,0,0 ; vbroadcastss 0x305e(%rip),%ymm12 # 5600 <_sk_callback_avx+0x21e> + DB 196,98,125,24,37,86,48,0,0 ; vbroadcastss 0x3056(%rip),%ymm12 # 5564 <_sk_callback_avx+0x216> DB 196,65,36,88,220 ; vaddps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,84,48,0,0 ; vbroadcastss 0x3054(%rip),%ymm12 # 5604 <_sk_callback_avx+0x222> + DB 196,98,125,24,37,76,48,0,0 ; vbroadcastss 0x304c(%rip),%ymm12 # 5568 <_sk_callback_avx+0x21a> DB 196,65,124,89,228 ; vmulps %ymm12,%ymm0,%ymm12 DB 196,65,36,92,220 ; vsubps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,69,48,0,0 ; vbroadcastss 0x3045(%rip),%ymm12 # 5608 <_sk_callback_avx+0x226> + DB 196,98,125,24,37,61,48,0,0 ; vbroadcastss 0x303d(%rip),%ymm12 # 556c <_sk_callback_avx+0x21e> DB 196,193,124,88,196 ; vaddps %ymm12,%ymm0,%ymm0 - DB 196,98,125,24,37,59,48,0,0 ; vbroadcastss 0x303b(%rip),%ymm12 # 560c <_sk_callback_avx+0x22a> + DB 196,98,125,24,37,51,48,0,0 ; vbroadcastss 0x3033(%rip),%ymm12 # 5570 <_sk_callback_avx+0x222> DB 197,156,94,192 ; vdivps %ymm0,%ymm12,%ymm0 DB 197,164,92,192 ; vsubps %ymm0,%ymm11,%ymm0 DB 197,172,89,192 ; vmulps %ymm0,%ymm10,%ymm0 DB 196,99,125,8,208,1 ; vroundps $0x1,%ymm0,%ymm10 DB 196,65,124,92,210 ; vsubps %ymm10,%ymm0,%ymm10 - DB 196,98,125,24,29,31,48,0,0 ; vbroadcastss 0x301f(%rip),%ymm11 # 5610 <_sk_callback_avx+0x22e> + DB 196,98,125,24,29,23,48,0,0 ; vbroadcastss 0x3017(%rip),%ymm11 # 5574 <_sk_callback_avx+0x226> DB 196,193,124,88,195 ; vaddps %ymm11,%ymm0,%ymm0 - DB 196,98,125,24,29,21,48,0,0 ; vbroadcastss 0x3015(%rip),%ymm11 # 5614 <_sk_callback_avx+0x232> + DB 196,98,125,24,29,13,48,0,0 ; vbroadcastss 0x300d(%rip),%ymm11 # 5578 <_sk_callback_avx+0x22a> DB 196,65,44,89,219 ; vmulps %ymm11,%ymm10,%ymm11 DB 196,193,124,92,195 ; vsubps %ymm11,%ymm0,%ymm0 - DB 196,98,125,24,29,6,48,0,0 ; vbroadcastss 0x3006(%rip),%ymm11 # 5618 <_sk_callback_avx+0x236> + DB 196,98,125,24,29,254,47,0,0 ; vbroadcastss 0x2ffe(%rip),%ymm11 # 557c <_sk_callback_avx+0x22e> DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 - DB 196,98,125,24,29,252,47,0,0 ; vbroadcastss 0x2ffc(%rip),%ymm11 # 561c <_sk_callback_avx+0x23a> + DB 196,98,125,24,29,244,47,0,0 ; vbroadcastss 0x2ff4(%rip),%ymm11 # 5580 <_sk_callback_avx+0x232> DB 196,65,36,94,210 ; vdivps %ymm10,%ymm11,%ymm10 DB 196,193,124,88,194 ; vaddps %ymm10,%ymm0,%ymm0 - DB 196,98,125,24,21,237,47,0,0 ; vbroadcastss 0x2fed(%rip),%ymm10 # 5620 <_sk_callback_avx+0x23e> + DB 196,98,125,24,21,229,47,0,0 ; vbroadcastss 0x2fe5(%rip),%ymm10 # 5584 <_sk_callback_avx+0x236> DB 196,193,124,89,194 ; vmulps %ymm10,%ymm0,%ymm0 DB 197,253,91,192 ; vcvtps2dq %ymm0,%ymm0 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -6653,7 +6604,7 @@ _sk_parametric_r_avx LABEL PROC DB 196,195,125,74,193,128 ; vblendvps %ymm8,%ymm9,%ymm0,%ymm0 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,124,95,192 ; vmaxps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,196,47,0,0 ; vbroadcastss 0x2fc4(%rip),%ymm8 # 5624 <_sk_callback_avx+0x242> + DB 196,98,125,24,5,188,47,0,0 ; vbroadcastss 0x2fbc(%rip),%ymm8 # 5588 <_sk_callback_avx+0x23a> DB 196,193,124,93,192 ; vminps %ymm8,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -6673,36 +6624,36 @@ _sk_parametric_g_avx LABEL PROC DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 DB 196,98,125,24,16 ; vbroadcastss (%rax),%ymm10 DB 197,124,91,217 ; vcvtdq2ps %ymm1,%ymm11 - DB 196,98,125,24,37,117,47,0,0 ; vbroadcastss 0x2f75(%rip),%ymm12 # 5628 <_sk_callback_avx+0x246> + DB 196,98,125,24,37,109,47,0,0 ; vbroadcastss 0x2f6d(%rip),%ymm12 # 558c <_sk_callback_avx+0x23e> DB 196,65,36,89,220 ; vmulps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,107,47,0,0 ; vbroadcastss 0x2f6b(%rip),%ymm12 # 562c <_sk_callback_avx+0x24a> + DB 196,98,125,24,37,99,47,0,0 ; vbroadcastss 0x2f63(%rip),%ymm12 # 5590 <_sk_callback_avx+0x242> DB 196,193,116,84,204 ; vandps %ymm12,%ymm1,%ymm1 - DB 196,98,125,24,37,97,47,0,0 ; vbroadcastss 0x2f61(%rip),%ymm12 # 5630 <_sk_callback_avx+0x24e> + DB 196,98,125,24,37,89,47,0,0 ; vbroadcastss 0x2f59(%rip),%ymm12 # 5594 <_sk_callback_avx+0x246> DB 196,193,116,86,204 ; vorps %ymm12,%ymm1,%ymm1 - DB 196,98,125,24,37,87,47,0,0 ; vbroadcastss 0x2f57(%rip),%ymm12 # 5634 <_sk_callback_avx+0x252> + DB 196,98,125,24,37,79,47,0,0 ; vbroadcastss 0x2f4f(%rip),%ymm12 # 5598 <_sk_callback_avx+0x24a> DB 196,65,36,88,220 ; vaddps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,77,47,0,0 ; vbroadcastss 0x2f4d(%rip),%ymm12 # 5638 <_sk_callback_avx+0x256> + DB 196,98,125,24,37,69,47,0,0 ; vbroadcastss 0x2f45(%rip),%ymm12 # 559c <_sk_callback_avx+0x24e> DB 196,65,116,89,228 ; vmulps %ymm12,%ymm1,%ymm12 DB 196,65,36,92,220 ; vsubps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,62,47,0,0 ; vbroadcastss 0x2f3e(%rip),%ymm12 # 563c <_sk_callback_avx+0x25a> + DB 196,98,125,24,37,54,47,0,0 ; vbroadcastss 0x2f36(%rip),%ymm12 # 55a0 <_sk_callback_avx+0x252> DB 196,193,116,88,204 ; vaddps %ymm12,%ymm1,%ymm1 - DB 196,98,125,24,37,52,47,0,0 ; vbroadcastss 0x2f34(%rip),%ymm12 # 5640 <_sk_callback_avx+0x25e> + DB 196,98,125,24,37,44,47,0,0 ; vbroadcastss 0x2f2c(%rip),%ymm12 # 55a4 <_sk_callback_avx+0x256> DB 197,156,94,201 ; vdivps %ymm1,%ymm12,%ymm1 DB 197,164,92,201 ; vsubps %ymm1,%ymm11,%ymm1 DB 197,172,89,201 ; vmulps %ymm1,%ymm10,%ymm1 DB 196,99,125,8,209,1 ; vroundps $0x1,%ymm1,%ymm10 DB 196,65,116,92,210 ; vsubps %ymm10,%ymm1,%ymm10 - DB 196,98,125,24,29,24,47,0,0 ; vbroadcastss 0x2f18(%rip),%ymm11 # 5644 <_sk_callback_avx+0x262> + DB 196,98,125,24,29,16,47,0,0 ; vbroadcastss 0x2f10(%rip),%ymm11 # 55a8 <_sk_callback_avx+0x25a> DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,14,47,0,0 ; vbroadcastss 0x2f0e(%rip),%ymm11 # 5648 <_sk_callback_avx+0x266> + DB 196,98,125,24,29,6,47,0,0 ; vbroadcastss 0x2f06(%rip),%ymm11 # 55ac <_sk_callback_avx+0x25e> DB 196,65,44,89,219 ; vmulps %ymm11,%ymm10,%ymm11 DB 196,193,116,92,203 ; vsubps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,29,255,46,0,0 ; vbroadcastss 0x2eff(%rip),%ymm11 # 564c <_sk_callback_avx+0x26a> + DB 196,98,125,24,29,247,46,0,0 ; vbroadcastss 0x2ef7(%rip),%ymm11 # 55b0 <_sk_callback_avx+0x262> DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 - DB 196,98,125,24,29,245,46,0,0 ; vbroadcastss 0x2ef5(%rip),%ymm11 # 5650 <_sk_callback_avx+0x26e> + DB 196,98,125,24,29,237,46,0,0 ; vbroadcastss 0x2eed(%rip),%ymm11 # 55b4 <_sk_callback_avx+0x266> DB 196,65,36,94,210 ; vdivps %ymm10,%ymm11,%ymm10 DB 196,193,116,88,202 ; vaddps %ymm10,%ymm1,%ymm1 - DB 196,98,125,24,21,230,46,0,0 ; vbroadcastss 0x2ee6(%rip),%ymm10 # 5654 <_sk_callback_avx+0x272> + DB 196,98,125,24,21,222,46,0,0 ; vbroadcastss 0x2ede(%rip),%ymm10 # 55b8 <_sk_callback_avx+0x26a> DB 196,193,116,89,202 ; vmulps %ymm10,%ymm1,%ymm1 DB 197,253,91,201 ; vcvtps2dq %ymm1,%ymm1 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -6710,7 +6661,7 @@ _sk_parametric_g_avx LABEL PROC DB 196,195,117,74,201,128 ; vblendvps %ymm8,%ymm9,%ymm1,%ymm1 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,116,95,200 ; vmaxps %ymm8,%ymm1,%ymm1 - DB 196,98,125,24,5,189,46,0,0 ; vbroadcastss 0x2ebd(%rip),%ymm8 # 5658 <_sk_callback_avx+0x276> + DB 196,98,125,24,5,181,46,0,0 ; vbroadcastss 0x2eb5(%rip),%ymm8 # 55bc <_sk_callback_avx+0x26e> DB 196,193,116,93,200 ; vminps %ymm8,%ymm1,%ymm1 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -6730,36 +6681,36 @@ _sk_parametric_b_avx LABEL PROC DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 DB 196,98,125,24,16 ; vbroadcastss (%rax),%ymm10 DB 197,124,91,218 ; vcvtdq2ps %ymm2,%ymm11 - DB 196,98,125,24,37,110,46,0,0 ; vbroadcastss 0x2e6e(%rip),%ymm12 # 565c <_sk_callback_avx+0x27a> + DB 196,98,125,24,37,102,46,0,0 ; vbroadcastss 0x2e66(%rip),%ymm12 # 55c0 <_sk_callback_avx+0x272> DB 196,65,36,89,220 ; vmulps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,100,46,0,0 ; vbroadcastss 0x2e64(%rip),%ymm12 # 5660 <_sk_callback_avx+0x27e> + DB 196,98,125,24,37,92,46,0,0 ; vbroadcastss 0x2e5c(%rip),%ymm12 # 55c4 <_sk_callback_avx+0x276> DB 196,193,108,84,212 ; vandps %ymm12,%ymm2,%ymm2 - DB 196,98,125,24,37,90,46,0,0 ; vbroadcastss 0x2e5a(%rip),%ymm12 # 5664 <_sk_callback_avx+0x282> + DB 196,98,125,24,37,82,46,0,0 ; vbroadcastss 0x2e52(%rip),%ymm12 # 55c8 <_sk_callback_avx+0x27a> DB 196,193,108,86,212 ; vorps %ymm12,%ymm2,%ymm2 - DB 196,98,125,24,37,80,46,0,0 ; vbroadcastss 0x2e50(%rip),%ymm12 # 5668 <_sk_callback_avx+0x286> + DB 196,98,125,24,37,72,46,0,0 ; vbroadcastss 0x2e48(%rip),%ymm12 # 55cc <_sk_callback_avx+0x27e> DB 196,65,36,88,220 ; vaddps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,70,46,0,0 ; vbroadcastss 0x2e46(%rip),%ymm12 # 566c <_sk_callback_avx+0x28a> + DB 196,98,125,24,37,62,46,0,0 ; vbroadcastss 0x2e3e(%rip),%ymm12 # 55d0 <_sk_callback_avx+0x282> DB 196,65,108,89,228 ; vmulps %ymm12,%ymm2,%ymm12 DB 196,65,36,92,220 ; vsubps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,55,46,0,0 ; vbroadcastss 0x2e37(%rip),%ymm12 # 5670 <_sk_callback_avx+0x28e> + DB 196,98,125,24,37,47,46,0,0 ; vbroadcastss 0x2e2f(%rip),%ymm12 # 55d4 <_sk_callback_avx+0x286> DB 196,193,108,88,212 ; vaddps %ymm12,%ymm2,%ymm2 - DB 196,98,125,24,37,45,46,0,0 ; vbroadcastss 0x2e2d(%rip),%ymm12 # 5674 <_sk_callback_avx+0x292> + DB 196,98,125,24,37,37,46,0,0 ; vbroadcastss 0x2e25(%rip),%ymm12 # 55d8 <_sk_callback_avx+0x28a> DB 197,156,94,210 ; vdivps %ymm2,%ymm12,%ymm2 DB 197,164,92,210 ; vsubps %ymm2,%ymm11,%ymm2 DB 197,172,89,210 ; vmulps %ymm2,%ymm10,%ymm2 DB 196,99,125,8,210,1 ; vroundps $0x1,%ymm2,%ymm10 DB 196,65,108,92,210 ; vsubps %ymm10,%ymm2,%ymm10 - DB 196,98,125,24,29,17,46,0,0 ; vbroadcastss 0x2e11(%rip),%ymm11 # 5678 <_sk_callback_avx+0x296> + DB 196,98,125,24,29,9,46,0,0 ; vbroadcastss 0x2e09(%rip),%ymm11 # 55dc <_sk_callback_avx+0x28e> DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 - DB 196,98,125,24,29,7,46,0,0 ; vbroadcastss 0x2e07(%rip),%ymm11 # 567c <_sk_callback_avx+0x29a> + DB 196,98,125,24,29,255,45,0,0 ; vbroadcastss 0x2dff(%rip),%ymm11 # 55e0 <_sk_callback_avx+0x292> DB 196,65,44,89,219 ; vmulps %ymm11,%ymm10,%ymm11 DB 196,193,108,92,211 ; vsubps %ymm11,%ymm2,%ymm2 - DB 196,98,125,24,29,248,45,0,0 ; vbroadcastss 0x2df8(%rip),%ymm11 # 5680 <_sk_callback_avx+0x29e> + DB 196,98,125,24,29,240,45,0,0 ; vbroadcastss 0x2df0(%rip),%ymm11 # 55e4 <_sk_callback_avx+0x296> DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 - DB 196,98,125,24,29,238,45,0,0 ; vbroadcastss 0x2dee(%rip),%ymm11 # 5684 <_sk_callback_avx+0x2a2> + DB 196,98,125,24,29,230,45,0,0 ; vbroadcastss 0x2de6(%rip),%ymm11 # 55e8 <_sk_callback_avx+0x29a> DB 196,65,36,94,210 ; vdivps %ymm10,%ymm11,%ymm10 DB 196,193,108,88,210 ; vaddps %ymm10,%ymm2,%ymm2 - DB 196,98,125,24,21,223,45,0,0 ; vbroadcastss 0x2ddf(%rip),%ymm10 # 5688 <_sk_callback_avx+0x2a6> + DB 196,98,125,24,21,215,45,0,0 ; vbroadcastss 0x2dd7(%rip),%ymm10 # 55ec <_sk_callback_avx+0x29e> DB 196,193,108,89,210 ; vmulps %ymm10,%ymm2,%ymm2 DB 197,253,91,210 ; vcvtps2dq %ymm2,%ymm2 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -6767,7 +6718,7 @@ _sk_parametric_b_avx LABEL PROC DB 196,195,109,74,209,128 ; vblendvps %ymm8,%ymm9,%ymm2,%ymm2 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,108,95,208 ; vmaxps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,182,45,0,0 ; vbroadcastss 0x2db6(%rip),%ymm8 # 568c <_sk_callback_avx+0x2aa> + DB 196,98,125,24,5,174,45,0,0 ; vbroadcastss 0x2dae(%rip),%ymm8 # 55f0 <_sk_callback_avx+0x2a2> DB 196,193,108,93,208 ; vminps %ymm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -6787,36 +6738,36 @@ _sk_parametric_a_avx LABEL PROC DB 196,193,100,88,219 ; vaddps %ymm11,%ymm3,%ymm3 DB 196,98,125,24,16 ; vbroadcastss (%rax),%ymm10 DB 197,124,91,219 ; vcvtdq2ps %ymm3,%ymm11 - DB 196,98,125,24,37,103,45,0,0 ; vbroadcastss 0x2d67(%rip),%ymm12 # 5690 <_sk_callback_avx+0x2ae> + DB 196,98,125,24,37,95,45,0,0 ; vbroadcastss 0x2d5f(%rip),%ymm12 # 55f4 <_sk_callback_avx+0x2a6> DB 196,65,36,89,220 ; vmulps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,93,45,0,0 ; vbroadcastss 0x2d5d(%rip),%ymm12 # 5694 <_sk_callback_avx+0x2b2> + DB 196,98,125,24,37,85,45,0,0 ; vbroadcastss 0x2d55(%rip),%ymm12 # 55f8 <_sk_callback_avx+0x2aa> DB 196,193,100,84,220 ; vandps %ymm12,%ymm3,%ymm3 - DB 196,98,125,24,37,83,45,0,0 ; vbroadcastss 0x2d53(%rip),%ymm12 # 5698 <_sk_callback_avx+0x2b6> + DB 196,98,125,24,37,75,45,0,0 ; vbroadcastss 0x2d4b(%rip),%ymm12 # 55fc <_sk_callback_avx+0x2ae> DB 196,193,100,86,220 ; vorps %ymm12,%ymm3,%ymm3 - DB 196,98,125,24,37,73,45,0,0 ; vbroadcastss 0x2d49(%rip),%ymm12 # 569c <_sk_callback_avx+0x2ba> + DB 196,98,125,24,37,65,45,0,0 ; vbroadcastss 0x2d41(%rip),%ymm12 # 5600 <_sk_callback_avx+0x2b2> DB 196,65,36,88,220 ; vaddps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,63,45,0,0 ; vbroadcastss 0x2d3f(%rip),%ymm12 # 56a0 <_sk_callback_avx+0x2be> + DB 196,98,125,24,37,55,45,0,0 ; vbroadcastss 0x2d37(%rip),%ymm12 # 5604 <_sk_callback_avx+0x2b6> DB 196,65,100,89,228 ; vmulps %ymm12,%ymm3,%ymm12 DB 196,65,36,92,220 ; vsubps %ymm12,%ymm11,%ymm11 - DB 196,98,125,24,37,48,45,0,0 ; vbroadcastss 0x2d30(%rip),%ymm12 # 56a4 <_sk_callback_avx+0x2c2> + DB 196,98,125,24,37,40,45,0,0 ; vbroadcastss 0x2d28(%rip),%ymm12 # 5608 <_sk_callback_avx+0x2ba> DB 196,193,100,88,220 ; vaddps %ymm12,%ymm3,%ymm3 - DB 196,98,125,24,37,38,45,0,0 ; vbroadcastss 0x2d26(%rip),%ymm12 # 56a8 <_sk_callback_avx+0x2c6> + DB 196,98,125,24,37,30,45,0,0 ; vbroadcastss 0x2d1e(%rip),%ymm12 # 560c <_sk_callback_avx+0x2be> DB 197,156,94,219 ; vdivps %ymm3,%ymm12,%ymm3 DB 197,164,92,219 ; vsubps %ymm3,%ymm11,%ymm3 DB 197,172,89,219 ; vmulps %ymm3,%ymm10,%ymm3 DB 196,99,125,8,211,1 ; vroundps $0x1,%ymm3,%ymm10 DB 196,65,100,92,210 ; vsubps %ymm10,%ymm3,%ymm10 - DB 196,98,125,24,29,10,45,0,0 ; vbroadcastss 0x2d0a(%rip),%ymm11 # 56ac <_sk_callback_avx+0x2ca> + DB 196,98,125,24,29,2,45,0,0 ; vbroadcastss 0x2d02(%rip),%ymm11 # 5610 <_sk_callback_avx+0x2c2> DB 196,193,100,88,219 ; vaddps %ymm11,%ymm3,%ymm3 - DB 196,98,125,24,29,0,45,0,0 ; vbroadcastss 0x2d00(%rip),%ymm11 # 56b0 <_sk_callback_avx+0x2ce> + DB 196,98,125,24,29,248,44,0,0 ; vbroadcastss 0x2cf8(%rip),%ymm11 # 5614 <_sk_callback_avx+0x2c6> DB 196,65,44,89,219 ; vmulps %ymm11,%ymm10,%ymm11 DB 196,193,100,92,219 ; vsubps %ymm11,%ymm3,%ymm3 - DB 196,98,125,24,29,241,44,0,0 ; vbroadcastss 0x2cf1(%rip),%ymm11 # 56b4 <_sk_callback_avx+0x2d2> + DB 196,98,125,24,29,233,44,0,0 ; vbroadcastss 0x2ce9(%rip),%ymm11 # 5618 <_sk_callback_avx+0x2ca> DB 196,65,36,92,210 ; vsubps %ymm10,%ymm11,%ymm10 - DB 196,98,125,24,29,231,44,0,0 ; vbroadcastss 0x2ce7(%rip),%ymm11 # 56b8 <_sk_callback_avx+0x2d6> + DB 196,98,125,24,29,223,44,0,0 ; vbroadcastss 0x2cdf(%rip),%ymm11 # 561c <_sk_callback_avx+0x2ce> DB 196,65,36,94,210 ; vdivps %ymm10,%ymm11,%ymm10 DB 196,193,100,88,218 ; vaddps %ymm10,%ymm3,%ymm3 - DB 196,98,125,24,21,216,44,0,0 ; vbroadcastss 0x2cd8(%rip),%ymm10 # 56bc <_sk_callback_avx+0x2da> + DB 196,98,125,24,21,208,44,0,0 ; vbroadcastss 0x2cd0(%rip),%ymm10 # 5620 <_sk_callback_avx+0x2d2> DB 196,193,100,89,218 ; vmulps %ymm10,%ymm3,%ymm3 DB 197,253,91,219 ; vcvtps2dq %ymm3,%ymm3 DB 196,98,125,24,80,20 ; vbroadcastss 0x14(%rax),%ymm10 @@ -6824,38 +6775,38 @@ _sk_parametric_a_avx LABEL PROC DB 196,195,101,74,217,128 ; vblendvps %ymm8,%ymm9,%ymm3,%ymm3 DB 196,65,60,87,192 ; vxorps %ymm8,%ymm8,%ymm8 DB 196,193,100,95,216 ; vmaxps %ymm8,%ymm3,%ymm3 - DB 196,98,125,24,5,175,44,0,0 ; vbroadcastss 0x2caf(%rip),%ymm8 # 56c0 <_sk_callback_avx+0x2de> + DB 196,98,125,24,5,167,44,0,0 ; vbroadcastss 0x2ca7(%rip),%ymm8 # 5624 <_sk_callback_avx+0x2d6> DB 196,193,100,93,216 ; vminps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax PUBLIC _sk_lab_to_xyz_avx _sk_lab_to_xyz_avx LABEL PROC - DB 196,98,125,24,5,161,44,0,0 ; vbroadcastss 0x2ca1(%rip),%ymm8 # 56c4 <_sk_callback_avx+0x2e2> + DB 196,98,125,24,5,153,44,0,0 ; vbroadcastss 0x2c99(%rip),%ymm8 # 5628 <_sk_callback_avx+0x2da> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,151,44,0,0 ; vbroadcastss 0x2c97(%rip),%ymm8 # 56c8 <_sk_callback_avx+0x2e6> + DB 196,98,125,24,5,143,44,0,0 ; vbroadcastss 0x2c8f(%rip),%ymm8 # 562c <_sk_callback_avx+0x2de> DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 - DB 196,98,125,24,13,141,44,0,0 ; vbroadcastss 0x2c8d(%rip),%ymm9 # 56cc <_sk_callback_avx+0x2ea> + DB 196,98,125,24,13,133,44,0,0 ; vbroadcastss 0x2c85(%rip),%ymm9 # 5630 <_sk_callback_avx+0x2e2> DB 196,193,116,88,201 ; vaddps %ymm9,%ymm1,%ymm1 DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 196,193,108,88,209 ; vaddps %ymm9,%ymm2,%ymm2 - DB 196,98,125,24,5,121,44,0,0 ; vbroadcastss 0x2c79(%rip),%ymm8 # 56d0 <_sk_callback_avx+0x2ee> + DB 196,98,125,24,5,113,44,0,0 ; vbroadcastss 0x2c71(%rip),%ymm8 # 5634 <_sk_callback_avx+0x2e6> DB 196,193,124,88,192 ; vaddps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,111,44,0,0 ; vbroadcastss 0x2c6f(%rip),%ymm8 # 56d4 <_sk_callback_avx+0x2f2> + DB 196,98,125,24,5,103,44,0,0 ; vbroadcastss 0x2c67(%rip),%ymm8 # 5638 <_sk_callback_avx+0x2ea> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 - DB 196,98,125,24,5,101,44,0,0 ; vbroadcastss 0x2c65(%rip),%ymm8 # 56d8 <_sk_callback_avx+0x2f6> + DB 196,98,125,24,5,93,44,0,0 ; vbroadcastss 0x2c5d(%rip),%ymm8 # 563c <_sk_callback_avx+0x2ee> DB 196,193,116,89,200 ; vmulps %ymm8,%ymm1,%ymm1 DB 197,252,88,201 ; vaddps %ymm1,%ymm0,%ymm1 - DB 196,98,125,24,5,87,44,0,0 ; vbroadcastss 0x2c57(%rip),%ymm8 # 56dc <_sk_callback_avx+0x2fa> + DB 196,98,125,24,5,79,44,0,0 ; vbroadcastss 0x2c4f(%rip),%ymm8 # 5640 <_sk_callback_avx+0x2f2> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 197,252,92,210 ; vsubps %ymm2,%ymm0,%ymm2 DB 197,116,89,193 ; vmulps %ymm1,%ymm1,%ymm8 DB 196,65,116,89,192 ; vmulps %ymm8,%ymm1,%ymm8 - DB 196,98,125,24,13,64,44,0,0 ; vbroadcastss 0x2c40(%rip),%ymm9 # 56e0 <_sk_callback_avx+0x2fe> + DB 196,98,125,24,13,56,44,0,0 ; vbroadcastss 0x2c38(%rip),%ymm9 # 5644 <_sk_callback_avx+0x2f6> DB 196,65,52,194,208,1 ; vcmpltps %ymm8,%ymm9,%ymm10 - DB 196,98,125,24,29,53,44,0,0 ; vbroadcastss 0x2c35(%rip),%ymm11 # 56e4 <_sk_callback_avx+0x302> + DB 196,98,125,24,29,45,44,0,0 ; vbroadcastss 0x2c2d(%rip),%ymm11 # 5648 <_sk_callback_avx+0x2fa> DB 196,193,116,88,203 ; vaddps %ymm11,%ymm1,%ymm1 - DB 196,98,125,24,37,43,44,0,0 ; vbroadcastss 0x2c2b(%rip),%ymm12 # 56e8 <_sk_callback_avx+0x306> + DB 196,98,125,24,37,35,44,0,0 ; vbroadcastss 0x2c23(%rip),%ymm12 # 564c <_sk_callback_avx+0x2fe> DB 196,193,116,89,204 ; vmulps %ymm12,%ymm1,%ymm1 DB 196,67,117,74,192,160 ; vblendvps %ymm10,%ymm8,%ymm1,%ymm8 DB 197,252,89,200 ; vmulps %ymm0,%ymm0,%ymm1 @@ -6870,9 +6821,9 @@ _sk_lab_to_xyz_avx LABEL PROC DB 196,193,108,88,211 ; vaddps %ymm11,%ymm2,%ymm2 DB 196,193,108,89,212 ; vmulps %ymm12,%ymm2,%ymm2 DB 196,227,109,74,208,144 ; vblendvps %ymm9,%ymm0,%ymm2,%ymm2 - DB 196,226,125,24,5,225,43,0,0 ; vbroadcastss 0x2be1(%rip),%ymm0 # 56ec <_sk_callback_avx+0x30a> + DB 196,226,125,24,5,217,43,0,0 ; vbroadcastss 0x2bd9(%rip),%ymm0 # 5650 <_sk_callback_avx+0x302> DB 197,188,89,192 ; vmulps %ymm0,%ymm8,%ymm0 - DB 196,98,125,24,5,216,43,0,0 ; vbroadcastss 0x2bd8(%rip),%ymm8 # 56f0 <_sk_callback_avx+0x30e> + DB 196,98,125,24,5,208,43,0,0 ; vbroadcastss 0x2bd0(%rip),%ymm8 # 5654 <_sk_callback_avx+0x306> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -6884,14 +6835,14 @@ _sk_load_a8_avx LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 72,1,248 ; add %rdi,%rax DB 77,133,192 ; test %r8,%r8 - DB 117,62 ; jne 2b6f <_sk_load_a8_avx+0x4e> + DB 117,62 ; jne 2adb <_sk_load_a8_avx+0x4e> DB 197,250,126,0 ; vmovq (%rax),%xmm0 DB 196,226,121,49,200 ; vpmovzxbd %xmm0,%xmm1 DB 196,227,121,4,192,229 ; vpermilps $0xe5,%xmm0,%xmm0 DB 196,226,121,49,192 ; vpmovzxbd %xmm0,%xmm0 DB 196,227,117,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm1,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,156,43,0,0 ; vbroadcastss 0x2b9c(%rip),%ymm1 # 56f4 <_sk_callback_avx+0x312> + DB 196,226,125,24,13,148,43,0,0 ; vbroadcastss 0x2b94(%rip),%ymm1 # 5658 <_sk_callback_avx+0x30a> DB 197,252,89,217 ; vmulps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -6908,9 +6859,9 @@ _sk_load_a8_avx LABEL PROC DB 77,9,217 ; or %r11,%r9 DB 72,131,193,8 ; add $0x8,%rcx DB 73,255,202 ; dec %r10 - DB 117,234 ; jne 2b77 <_sk_load_a8_avx+0x56> + DB 117,234 ; jne 2ae3 <_sk_load_a8_avx+0x56> DB 196,193,249,110,193 ; vmovq %r9,%xmm0 - DB 235,161 ; jmp 2b35 <_sk_load_a8_avx+0x14> + DB 235,161 ; jmp 2aa1 <_sk_load_a8_avx+0x14> PUBLIC _sk_gather_a8_avx _sk_gather_a8_avx LABEL PROC @@ -6958,7 +6909,7 @@ _sk_gather_a8_avx LABEL PROC DB 196,226,121,49,201 ; vpmovzxbd %xmm1,%xmm1 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,145,42,0,0 ; vbroadcastss 0x2a91(%rip),%ymm1 # 56f8 <_sk_callback_avx+0x316> + DB 196,226,125,24,13,137,42,0,0 ; vbroadcastss 0x2a89(%rip),%ymm1 # 565c <_sk_callback_avx+0x30e> DB 197,252,89,217 ; vmulps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 197,252,87,192 ; vxorps %ymm0,%ymm0,%ymm0 @@ -6974,14 +6925,14 @@ PUBLIC _sk_store_a8_avx _sk_store_a8_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,108,42,0,0 ; vbroadcastss 0x2a6c(%rip),%ymm8 # 56fc <_sk_callback_avx+0x31a> + DB 196,98,125,24,5,100,42,0,0 ; vbroadcastss 0x2a64(%rip),%ymm8 # 5660 <_sk_callback_avx+0x312> DB 196,65,100,89,192 ; vmulps %ymm8,%ymm3,%ymm8 DB 196,65,125,91,192 ; vcvtps2dq %ymm8,%ymm8 DB 196,67,125,25,193,1 ; vextractf128 $0x1,%ymm8,%xmm9 DB 196,66,57,43,193 ; vpackusdw %xmm9,%xmm8,%xmm8 DB 196,65,57,103,192 ; vpackuswb %xmm8,%xmm8,%xmm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,10 ; jne 2cb9 <_sk_store_a8_avx+0x37> + DB 117,10 ; jne 2c25 <_sk_store_a8_avx+0x37> DB 196,65,123,17,4,58 ; vmovsd %xmm8,(%r10,%rdi,1) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -6989,10 +6940,10 @@ _sk_store_a8_avx LABEL PROC DB 65,128,224,7 ; and $0x7,%r8b DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 119,236 ; ja 2cb5 <_sk_store_a8_avx+0x33> + DB 119,236 ; ja 2c21 <_sk_store_a8_avx+0x33> DB 196,66,121,48,192 ; vpmovzxbw %xmm8,%xmm8 DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,67,0,0,0 ; lea 0x43(%rip),%r9 # 2d1c <_sk_store_a8_avx+0x9a> + DB 76,141,13,67,0,0,0 ; lea 0x43(%rip),%r9 # 2c88 <_sk_store_a8_avx+0x9a> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -7003,7 +6954,7 @@ _sk_store_a8_avx LABEL PROC DB 196,67,121,20,68,58,2,4 ; vpextrb $0x4,%xmm8,0x2(%r10,%rdi,1) DB 196,67,121,20,68,58,1,2 ; vpextrb $0x2,%xmm8,0x1(%r10,%rdi,1) DB 196,67,121,20,4,58,0 ; vpextrb $0x0,%xmm8,(%r10,%rdi,1) - DB 235,154 ; jmp 2cb5 <_sk_store_a8_avx+0x33> + DB 235,154 ; jmp 2c21 <_sk_store_a8_avx+0x33> DB 144 ; nop DB 246,255 ; idiv %bh DB 255 ; (bad) @@ -7035,17 +6986,17 @@ _sk_load_g8_avx LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 72,1,248 ; add %rdi,%rax DB 77,133,192 ; test %r8,%r8 - DB 117,67 ; jne 2d8b <_sk_load_g8_avx+0x53> + DB 117,67 ; jne 2cf7 <_sk_load_g8_avx+0x53> DB 197,250,126,0 ; vmovq (%rax),%xmm0 DB 196,226,121,49,200 ; vpmovzxbd %xmm0,%xmm1 DB 196,227,121,4,192,229 ; vpermilps $0xe5,%xmm0,%xmm0 DB 196,226,121,49,192 ; vpmovzxbd %xmm0,%xmm0 DB 196,227,117,24,192,1 ; vinsertf128 $0x1,%xmm0,%ymm1,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,145,41,0,0 ; vbroadcastss 0x2991(%rip),%ymm1 # 5700 <_sk_callback_avx+0x31e> + DB 196,226,125,24,13,137,41,0,0 ; vbroadcastss 0x2989(%rip),%ymm1 # 5664 <_sk_callback_avx+0x316> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,134,41,0,0 ; vbroadcastss 0x2986(%rip),%ymm3 # 5704 <_sk_callback_avx+0x322> + DB 196,226,125,24,29,126,41,0,0 ; vbroadcastss 0x297e(%rip),%ymm3 # 5668 <_sk_callback_avx+0x31a> DB 76,137,193 ; mov %r8,%rcx DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 @@ -7059,9 +7010,9 @@ _sk_load_g8_avx LABEL PROC DB 77,9,217 ; or %r11,%r9 DB 72,131,193,8 ; add $0x8,%rcx DB 73,255,202 ; dec %r10 - DB 117,234 ; jne 2d93 <_sk_load_g8_avx+0x5b> + DB 117,234 ; jne 2cff <_sk_load_g8_avx+0x5b> DB 196,193,249,110,193 ; vmovq %r9,%xmm0 - DB 235,156 ; jmp 2d4c <_sk_load_g8_avx+0x14> + DB 235,156 ; jmp 2cb8 <_sk_load_g8_avx+0x14> PUBLIC _sk_gather_g8_avx _sk_gather_g8_avx LABEL PROC @@ -7109,10 +7060,10 @@ _sk_gather_g8_avx LABEL PROC DB 196,226,121,49,201 ; vpmovzxbd %xmm1,%xmm1 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,133,40,0,0 ; vbroadcastss 0x2885(%rip),%ymm1 # 5708 <_sk_callback_avx+0x326> + DB 196,226,125,24,13,125,40,0,0 ; vbroadcastss 0x287d(%rip),%ymm1 # 566c <_sk_callback_avx+0x31e> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,122,40,0,0 ; vbroadcastss 0x287a(%rip),%ymm3 # 570c <_sk_callback_avx+0x32a> + DB 196,226,125,24,29,114,40,0,0 ; vbroadcastss 0x2872(%rip),%ymm3 # 5670 <_sk_callback_avx+0x322> DB 197,252,40,200 ; vmovaps %ymm0,%ymm1 DB 197,252,40,208 ; vmovaps %ymm0,%ymm2 DB 91 ; pop %rbx @@ -7126,9 +7077,9 @@ _sk_gather_i8_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 73,137,192 ; mov %rax,%r8 DB 77,133,192 ; test %r8,%r8 - DB 116,5 ; je 2eb2 <_sk_gather_i8_avx+0xf> + DB 116,5 ; je 2e1e <_sk_gather_i8_avx+0xf> DB 76,137,192 ; mov %r8,%rax - DB 235,2 ; jmp 2eb4 <_sk_gather_i8_avx+0x11> + DB 235,2 ; jmp 2e20 <_sk_gather_i8_avx+0x11> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,87 ; push %r15 DB 65,86 ; push %r14 @@ -7190,10 +7141,10 @@ _sk_gather_i8_avx LABEL PROC DB 196,163,121,34,4,163,2 ; vpinsrd $0x2,(%rbx,%r12,4),%xmm0,%xmm0 DB 196,163,121,34,28,19,3 ; vpinsrd $0x3,(%rbx,%r10,1),%xmm0,%xmm3 DB 196,227,61,24,195,1 ; vinsertf128 $0x1,%xmm3,%ymm8,%ymm0 - DB 197,124,40,21,226,40,0,0 ; vmovaps 0x28e2(%rip),%ymm10 # 58c0 <_sk_callback_avx+0x4de> + DB 197,124,40,21,214,40,0,0 ; vmovaps 0x28d6(%rip),%ymm10 # 5820 <_sk_callback_avx+0x4d2> DB 196,193,124,84,194 ; vandps %ymm10,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,32,39,0,0 ; vbroadcastss 0x2720(%rip),%ymm9 # 5710 <_sk_callback_avx+0x32e> + DB 196,98,125,24,13,24,39,0,0 ; vbroadcastss 0x2718(%rip),%ymm9 # 5674 <_sk_callback_avx+0x326> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 196,193,113,114,208,8 ; vpsrld $0x8,%xmm8,%xmm1 DB 197,233,114,211,8 ; vpsrld $0x8,%xmm3,%xmm2 @@ -7225,38 +7176,38 @@ _sk_load_565_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,128,0,0,0 ; jne 30e8 <_sk_load_565_avx+0x8e> + DB 15,133,128,0,0,0 ; jne 3054 <_sk_load_565_avx+0x8e> DB 196,193,122,111,4,122 ; vmovdqu (%r10,%rdi,2),%xmm0 DB 197,241,239,201 ; vpxor %xmm1,%xmm1,%xmm1 DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,209,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm2 - DB 196,226,125,24,5,138,38,0,0 ; vbroadcastss 0x268a(%rip),%ymm0 # 5714 <_sk_callback_avx+0x332> + DB 196,226,125,24,5,130,38,0,0 ; vbroadcastss 0x2682(%rip),%ymm0 # 5678 <_sk_callback_avx+0x32a> DB 197,236,84,192 ; vandps %ymm0,%ymm2,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,125,38,0,0 ; vbroadcastss 0x267d(%rip),%ymm1 # 5718 <_sk_callback_avx+0x336> + DB 196,226,125,24,13,117,38,0,0 ; vbroadcastss 0x2675(%rip),%ymm1 # 567c <_sk_callback_avx+0x32e> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,116,38,0,0 ; vbroadcastss 0x2674(%rip),%ymm1 # 571c <_sk_callback_avx+0x33a> + DB 196,226,125,24,13,108,38,0,0 ; vbroadcastss 0x266c(%rip),%ymm1 # 5680 <_sk_callback_avx+0x332> DB 197,236,84,201 ; vandps %ymm1,%ymm2,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,29,103,38,0,0 ; vbroadcastss 0x2667(%rip),%ymm3 # 5720 <_sk_callback_avx+0x33e> + DB 196,226,125,24,29,95,38,0,0 ; vbroadcastss 0x265f(%rip),%ymm3 # 5684 <_sk_callback_avx+0x336> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 - DB 196,226,125,24,29,94,38,0,0 ; vbroadcastss 0x265e(%rip),%ymm3 # 5724 <_sk_callback_avx+0x342> + DB 196,226,125,24,29,86,38,0,0 ; vbroadcastss 0x2656(%rip),%ymm3 # 5688 <_sk_callback_avx+0x33a> DB 197,236,84,211 ; vandps %ymm3,%ymm2,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,226,125,24,29,81,38,0,0 ; vbroadcastss 0x2651(%rip),%ymm3 # 5728 <_sk_callback_avx+0x346> + DB 196,226,125,24,29,73,38,0,0 ; vbroadcastss 0x2649(%rip),%ymm3 # 568c <_sk_callback_avx+0x33e> DB 197,236,89,211 ; vmulps %ymm3,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,70,38,0,0 ; vbroadcastss 0x2646(%rip),%ymm3 # 572c <_sk_callback_avx+0x34a> + DB 196,226,125,24,29,62,38,0,0 ; vbroadcastss 0x263e(%rip),%ymm3 # 5690 <_sk_callback_avx+0x342> DB 255,224 ; jmpq *%rax DB 65,137,200 ; mov %ecx,%r8d DB 65,128,224,7 ; and $0x7,%r8b DB 197,249,239,192 ; vpxor %xmm0,%xmm0,%xmm0 DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 15,135,110,255,255,255 ; ja 306e <_sk_load_565_avx+0x14> + DB 15,135,110,255,255,255 ; ja 2fda <_sk_load_565_avx+0x14> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,73,0,0,0 ; lea 0x49(%rip),%r9 # 3154 <_sk_load_565_avx+0xfa> + DB 76,141,13,73,0,0,0 ; lea 0x49(%rip),%r9 # 30c0 <_sk_load_565_avx+0xfa> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -7268,7 +7219,7 @@ _sk_load_565_avx LABEL PROC DB 196,193,121,196,68,122,4,2 ; vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm0,%xmm0 DB 196,193,121,196,68,122,2,1 ; vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm0,%xmm0 DB 196,193,121,196,4,122,0 ; vpinsrw $0x0,(%r10,%rdi,2),%xmm0,%xmm0 - DB 233,26,255,255,255 ; jmpq 306e <_sk_load_565_avx+0x14> + DB 233,26,255,255,255 ; jmpq 2fda <_sk_load_565_avx+0x14> DB 244 ; hlt DB 255 ; (bad) DB 255 ; (bad) @@ -7344,23 +7295,23 @@ _sk_gather_565_avx LABEL PROC DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,209,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm2 - DB 196,226,125,24,5,230,36,0,0 ; vbroadcastss 0x24e6(%rip),%ymm0 # 5730 <_sk_callback_avx+0x34e> + DB 196,226,125,24,5,222,36,0,0 ; vbroadcastss 0x24de(%rip),%ymm0 # 5694 <_sk_callback_avx+0x346> DB 197,236,84,192 ; vandps %ymm0,%ymm2,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,217,36,0,0 ; vbroadcastss 0x24d9(%rip),%ymm1 # 5734 <_sk_callback_avx+0x352> + DB 196,226,125,24,13,209,36,0,0 ; vbroadcastss 0x24d1(%rip),%ymm1 # 5698 <_sk_callback_avx+0x34a> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,208,36,0,0 ; vbroadcastss 0x24d0(%rip),%ymm1 # 5738 <_sk_callback_avx+0x356> + DB 196,226,125,24,13,200,36,0,0 ; vbroadcastss 0x24c8(%rip),%ymm1 # 569c <_sk_callback_avx+0x34e> DB 197,236,84,201 ; vandps %ymm1,%ymm2,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,29,195,36,0,0 ; vbroadcastss 0x24c3(%rip),%ymm3 # 573c <_sk_callback_avx+0x35a> + DB 196,226,125,24,29,187,36,0,0 ; vbroadcastss 0x24bb(%rip),%ymm3 # 56a0 <_sk_callback_avx+0x352> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 - DB 196,226,125,24,29,186,36,0,0 ; vbroadcastss 0x24ba(%rip),%ymm3 # 5740 <_sk_callback_avx+0x35e> + DB 196,226,125,24,29,178,36,0,0 ; vbroadcastss 0x24b2(%rip),%ymm3 # 56a4 <_sk_callback_avx+0x356> DB 197,236,84,211 ; vandps %ymm3,%ymm2,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,226,125,24,29,173,36,0,0 ; vbroadcastss 0x24ad(%rip),%ymm3 # 5744 <_sk_callback_avx+0x362> + DB 196,226,125,24,29,165,36,0,0 ; vbroadcastss 0x24a5(%rip),%ymm3 # 56a8 <_sk_callback_avx+0x35a> DB 197,236,89,211 ; vmulps %ymm3,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,162,36,0,0 ; vbroadcastss 0x24a2(%rip),%ymm3 # 5748 <_sk_callback_avx+0x366> + DB 196,226,125,24,29,154,36,0,0 ; vbroadcastss 0x249a(%rip),%ymm3 # 56ac <_sk_callback_avx+0x35e> DB 91 ; pop %rbx DB 65,92 ; pop %r12 DB 65,94 ; pop %r14 @@ -7372,14 +7323,14 @@ PUBLIC _sk_store_565_avx _sk_store_565_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,142,36,0,0 ; vbroadcastss 0x248e(%rip),%ymm8 # 574c <_sk_callback_avx+0x36a> + DB 196,98,125,24,5,134,36,0,0 ; vbroadcastss 0x2486(%rip),%ymm8 # 56b0 <_sk_callback_avx+0x362> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,193,41,114,241,11 ; vpslld $0xb,%xmm9,%xmm10 DB 196,67,125,25,201,1 ; vextractf128 $0x1,%ymm9,%xmm9 DB 196,193,49,114,241,11 ; vpslld $0xb,%xmm9,%xmm9 DB 196,67,45,24,201,1 ; vinsertf128 $0x1,%xmm9,%ymm10,%ymm9 - DB 196,98,125,24,21,103,36,0,0 ; vbroadcastss 0x2467(%rip),%ymm10 # 5750 <_sk_callback_avx+0x36e> + DB 196,98,125,24,21,95,36,0,0 ; vbroadcastss 0x245f(%rip),%ymm10 # 56b4 <_sk_callback_avx+0x366> DB 196,65,116,89,210 ; vmulps %ymm10,%ymm1,%ymm10 DB 196,65,125,91,210 ; vcvtps2dq %ymm10,%ymm10 DB 196,193,33,114,242,5 ; vpslld $0x5,%xmm10,%xmm11 @@ -7393,7 +7344,7 @@ _sk_store_565_avx LABEL PROC DB 196,67,125,25,193,1 ; vextractf128 $0x1,%ymm8,%xmm9 DB 196,66,57,43,193 ; vpackusdw %xmm9,%xmm8,%xmm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,10 ; jne 3339 <_sk_store_565_avx+0x89> + DB 117,10 ; jne 32a5 <_sk_store_565_avx+0x89> DB 196,65,122,127,4,122 ; vmovdqu %xmm8,(%r10,%rdi,2) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -7401,9 +7352,9 @@ _sk_store_565_avx LABEL PROC DB 65,128,224,7 ; and $0x7,%r8b DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 119,236 ; ja 3335 <_sk_store_565_avx+0x85> + DB 119,236 ; ja 32a1 <_sk_store_565_avx+0x85> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,68,0,0,0 ; lea 0x44(%rip),%r9 # 3398 <_sk_store_565_avx+0xe8> + DB 76,141,13,68,0,0,0 ; lea 0x44(%rip),%r9 # 3304 <_sk_store_565_avx+0xe8> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -7414,7 +7365,7 @@ _sk_store_565_avx LABEL PROC DB 196,67,121,21,68,122,4,2 ; vpextrw $0x2,%xmm8,0x4(%r10,%rdi,2) DB 196,67,121,21,68,122,2,1 ; vpextrw $0x1,%xmm8,0x2(%r10,%rdi,2) DB 196,67,121,21,4,122,0 ; vpextrw $0x0,%xmm8,(%r10,%rdi,2) - DB 235,159 ; jmp 3335 <_sk_store_565_avx+0x85> + DB 235,159 ; jmp 32a1 <_sk_store_565_avx+0x85> DB 102,144 ; xchg %ax,%ax DB 245 ; cmc DB 255 ; (bad) @@ -7445,31 +7396,31 @@ _sk_load_4444_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,152,0,0,0 ; jne 345a <_sk_load_4444_avx+0xa6> + DB 15,133,152,0,0,0 ; jne 33c6 <_sk_load_4444_avx+0xa6> DB 196,193,122,111,4,122 ; vmovdqu (%r10,%rdi,2),%xmm0 DB 197,241,239,201 ; vpxor %xmm1,%xmm1,%xmm1 DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,217,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm3 - DB 196,226,125,24,5,112,35,0,0 ; vbroadcastss 0x2370(%rip),%ymm0 # 5754 <_sk_callback_avx+0x372> + DB 196,226,125,24,5,104,35,0,0 ; vbroadcastss 0x2368(%rip),%ymm0 # 56b8 <_sk_callback_avx+0x36a> DB 197,228,84,192 ; vandps %ymm0,%ymm3,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,99,35,0,0 ; vbroadcastss 0x2363(%rip),%ymm1 # 5758 <_sk_callback_avx+0x376> + DB 196,226,125,24,13,91,35,0,0 ; vbroadcastss 0x235b(%rip),%ymm1 # 56bc <_sk_callback_avx+0x36e> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,90,35,0,0 ; vbroadcastss 0x235a(%rip),%ymm1 # 575c <_sk_callback_avx+0x37a> + DB 196,226,125,24,13,82,35,0,0 ; vbroadcastss 0x2352(%rip),%ymm1 # 56c0 <_sk_callback_avx+0x372> DB 197,228,84,201 ; vandps %ymm1,%ymm3,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,21,77,35,0,0 ; vbroadcastss 0x234d(%rip),%ymm2 # 5760 <_sk_callback_avx+0x37e> + DB 196,226,125,24,21,69,35,0,0 ; vbroadcastss 0x2345(%rip),%ymm2 # 56c4 <_sk_callback_avx+0x376> DB 197,244,89,202 ; vmulps %ymm2,%ymm1,%ymm1 - DB 196,226,125,24,21,68,35,0,0 ; vbroadcastss 0x2344(%rip),%ymm2 # 5764 <_sk_callback_avx+0x382> + DB 196,226,125,24,21,60,35,0,0 ; vbroadcastss 0x233c(%rip),%ymm2 # 56c8 <_sk_callback_avx+0x37a> DB 197,228,84,210 ; vandps %ymm2,%ymm3,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,98,125,24,5,55,35,0,0 ; vbroadcastss 0x2337(%rip),%ymm8 # 5768 <_sk_callback_avx+0x386> + DB 196,98,125,24,5,47,35,0,0 ; vbroadcastss 0x232f(%rip),%ymm8 # 56cc <_sk_callback_avx+0x37e> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,45,35,0,0 ; vbroadcastss 0x232d(%rip),%ymm8 # 576c <_sk_callback_avx+0x38a> + DB 196,98,125,24,5,37,35,0,0 ; vbroadcastss 0x2325(%rip),%ymm8 # 56d0 <_sk_callback_avx+0x382> DB 196,193,100,84,216 ; vandps %ymm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,31,35,0,0 ; vbroadcastss 0x231f(%rip),%ymm8 # 5770 <_sk_callback_avx+0x38e> + DB 196,98,125,24,5,23,35,0,0 ; vbroadcastss 0x2317(%rip),%ymm8 # 56d4 <_sk_callback_avx+0x386> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -7478,9 +7429,9 @@ _sk_load_4444_avx LABEL PROC DB 197,249,239,192 ; vpxor %xmm0,%xmm0,%xmm0 DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 15,135,86,255,255,255 ; ja 33c8 <_sk_load_4444_avx+0x14> + DB 15,135,86,255,255,255 ; ja 3334 <_sk_load_4444_avx+0x14> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,75,0,0,0 ; lea 0x4b(%rip),%r9 # 34c8 <_sk_load_4444_avx+0x114> + DB 76,141,13,75,0,0,0 ; lea 0x4b(%rip),%r9 # 3434 <_sk_load_4444_avx+0x114> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -7492,7 +7443,7 @@ _sk_load_4444_avx LABEL PROC DB 196,193,121,196,68,122,4,2 ; vpinsrw $0x2,0x4(%r10,%rdi,2),%xmm0,%xmm0 DB 196,193,121,196,68,122,2,1 ; vpinsrw $0x1,0x2(%r10,%rdi,2),%xmm0,%xmm0 DB 196,193,121,196,4,122,0 ; vpinsrw $0x0,(%r10,%rdi,2),%xmm0,%xmm0 - DB 233,2,255,255,255 ; jmpq 33c8 <_sk_load_4444_avx+0x14> + DB 233,2,255,255,255 ; jmpq 3334 <_sk_load_4444_avx+0x14> DB 102,144 ; xchg %ax,%ax DB 242,255 ; repnz (bad) DB 255 ; (bad) @@ -7569,25 +7520,25 @@ _sk_gather_4444_avx LABEL PROC DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,217,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm3 - DB 196,226,125,24,5,182,33,0,0 ; vbroadcastss 0x21b6(%rip),%ymm0 # 5774 <_sk_callback_avx+0x392> + DB 196,226,125,24,5,174,33,0,0 ; vbroadcastss 0x21ae(%rip),%ymm0 # 56d8 <_sk_callback_avx+0x38a> DB 197,228,84,192 ; vandps %ymm0,%ymm3,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,226,125,24,13,169,33,0,0 ; vbroadcastss 0x21a9(%rip),%ymm1 # 5778 <_sk_callback_avx+0x396> + DB 196,226,125,24,13,161,33,0,0 ; vbroadcastss 0x21a1(%rip),%ymm1 # 56dc <_sk_callback_avx+0x38e> DB 197,252,89,193 ; vmulps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,160,33,0,0 ; vbroadcastss 0x21a0(%rip),%ymm1 # 577c <_sk_callback_avx+0x39a> + DB 196,226,125,24,13,152,33,0,0 ; vbroadcastss 0x2198(%rip),%ymm1 # 56e0 <_sk_callback_avx+0x392> DB 197,228,84,201 ; vandps %ymm1,%ymm3,%ymm1 DB 197,252,91,201 ; vcvtdq2ps %ymm1,%ymm1 - DB 196,226,125,24,21,147,33,0,0 ; vbroadcastss 0x2193(%rip),%ymm2 # 5780 <_sk_callback_avx+0x39e> + DB 196,226,125,24,21,139,33,0,0 ; vbroadcastss 0x218b(%rip),%ymm2 # 56e4 <_sk_callback_avx+0x396> DB 197,244,89,202 ; vmulps %ymm2,%ymm1,%ymm1 - DB 196,226,125,24,21,138,33,0,0 ; vbroadcastss 0x218a(%rip),%ymm2 # 5784 <_sk_callback_avx+0x3a2> + DB 196,226,125,24,21,130,33,0,0 ; vbroadcastss 0x2182(%rip),%ymm2 # 56e8 <_sk_callback_avx+0x39a> DB 197,228,84,210 ; vandps %ymm2,%ymm3,%ymm2 DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 - DB 196,98,125,24,5,125,33,0,0 ; vbroadcastss 0x217d(%rip),%ymm8 # 5788 <_sk_callback_avx+0x3a6> + DB 196,98,125,24,5,117,33,0,0 ; vbroadcastss 0x2175(%rip),%ymm8 # 56ec <_sk_callback_avx+0x39e> DB 196,193,108,89,208 ; vmulps %ymm8,%ymm2,%ymm2 - DB 196,98,125,24,5,115,33,0,0 ; vbroadcastss 0x2173(%rip),%ymm8 # 578c <_sk_callback_avx+0x3aa> + DB 196,98,125,24,5,107,33,0,0 ; vbroadcastss 0x216b(%rip),%ymm8 # 56f0 <_sk_callback_avx+0x3a2> DB 196,193,100,84,216 ; vandps %ymm8,%ymm3,%ymm3 DB 197,252,91,219 ; vcvtdq2ps %ymm3,%ymm3 - DB 196,98,125,24,5,101,33,0,0 ; vbroadcastss 0x2165(%rip),%ymm8 # 5790 <_sk_callback_avx+0x3ae> + DB 196,98,125,24,5,93,33,0,0 ; vbroadcastss 0x215d(%rip),%ymm8 # 56f4 <_sk_callback_avx+0x3a6> DB 196,193,100,89,216 ; vmulps %ymm8,%ymm3,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 91 ; pop %rbx @@ -7601,7 +7552,7 @@ PUBLIC _sk_store_4444_avx _sk_store_4444_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,74,33,0,0 ; vbroadcastss 0x214a(%rip),%ymm8 # 5794 <_sk_callback_avx+0x3b2> + DB 196,98,125,24,5,66,33,0,0 ; vbroadcastss 0x2142(%rip),%ymm8 # 56f8 <_sk_callback_avx+0x3aa> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,193,41,114,241,12 ; vpslld $0xc,%xmm9,%xmm10 @@ -7628,7 +7579,7 @@ _sk_store_4444_avx LABEL PROC DB 196,67,125,25,193,1 ; vextractf128 $0x1,%ymm8,%xmm9 DB 196,66,57,43,193 ; vpackusdw %xmm9,%xmm8,%xmm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,10 ; jne 36e3 <_sk_store_4444_avx+0xa7> + DB 117,10 ; jne 364f <_sk_store_4444_avx+0xa7> DB 196,65,122,127,4,122 ; vmovdqu %xmm8,(%r10,%rdi,2) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -7636,9 +7587,9 @@ _sk_store_4444_avx LABEL PROC DB 65,128,224,7 ; and $0x7,%r8b DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 119,236 ; ja 36df <_sk_store_4444_avx+0xa3> + DB 119,236 ; ja 364b <_sk_store_4444_avx+0xa3> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,66,0,0,0 ; lea 0x42(%rip),%r9 # 3740 <_sk_store_4444_avx+0x104> + DB 76,141,13,66,0,0,0 ; lea 0x42(%rip),%r9 # 36ac <_sk_store_4444_avx+0x104> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -7649,7 +7600,7 @@ _sk_store_4444_avx LABEL PROC DB 196,67,121,21,68,122,4,2 ; vpextrw $0x2,%xmm8,0x4(%r10,%rdi,2) DB 196,67,121,21,68,122,2,1 ; vpextrw $0x1,%xmm8,0x2(%r10,%rdi,2) DB 196,67,121,21,4,122,0 ; vpextrw $0x0,%xmm8,(%r10,%rdi,2) - DB 235,159 ; jmp 36df <_sk_store_4444_avx+0xa3> + DB 235,159 ; jmp 364b <_sk_store_4444_avx+0xa3> DB 247,255 ; idiv %edi DB 255 ; (bad) DB 255 ; (bad) @@ -7678,12 +7629,12 @@ _sk_load_8888_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 DB 72,133,201 ; test %rcx,%rcx - DB 15,133,135,0,0,0 ; jne 37f1 <_sk_load_8888_avx+0x95> + DB 15,133,135,0,0,0 ; jne 375d <_sk_load_8888_avx+0x95> DB 196,65,124,16,12,186 ; vmovups (%r10,%rdi,4),%ymm9 - DB 197,124,40,21,104,33,0,0 ; vmovaps 0x2168(%rip),%ymm10 # 58e0 <_sk_callback_avx+0x4fe> + DB 197,124,40,21,92,33,0,0 ; vmovaps 0x215c(%rip),%ymm10 # 5840 <_sk_callback_avx+0x4f2> DB 196,193,52,84,194 ; vandps %ymm10,%ymm9,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,5,14,32,0,0 ; vbroadcastss 0x200e(%rip),%ymm8 # 5798 <_sk_callback_avx+0x3b6> + DB 196,98,125,24,5,6,32,0,0 ; vbroadcastss 0x2006(%rip),%ymm8 # 56fc <_sk_callback_avx+0x3ae> DB 196,193,124,89,192 ; vmulps %ymm8,%ymm0,%ymm0 DB 196,193,113,114,209,8 ; vpsrld $0x8,%xmm9,%xmm1 DB 196,99,125,25,203,1 ; vextractf128 $0x1,%ymm9,%xmm3 @@ -7710,9 +7661,9 @@ _sk_load_8888_avx LABEL PROC DB 196,65,52,87,201 ; vxorps %ymm9,%ymm9,%ymm9 DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 15,135,102,255,255,255 ; ja 3770 <_sk_load_8888_avx+0x14> + DB 15,135,102,255,255,255 ; ja 36dc <_sk_load_8888_avx+0x14> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,139,0,0,0 ; lea 0x8b(%rip),%r9 # 38a0 <_sk_load_8888_avx+0x144> + DB 76,141,13,139,0,0,0 ; lea 0x8b(%rip),%r9 # 380c <_sk_load_8888_avx+0x144> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -7735,7 +7686,7 @@ _sk_load_8888_avx LABEL PROC DB 196,99,53,12,200,15 ; vblendps $0xf,%ymm0,%ymm9,%ymm9 DB 196,195,49,34,4,186,0 ; vpinsrd $0x0,(%r10,%rdi,4),%xmm9,%xmm0 DB 196,99,53,12,200,15 ; vblendps $0xf,%ymm0,%ymm9,%ymm9 - DB 233,210,254,255,255 ; jmpq 3770 <_sk_load_8888_avx+0x14> + DB 233,210,254,255,255 ; jmpq 36dc <_sk_load_8888_avx+0x14> DB 102,144 ; xchg %ax,%ax DB 236 ; in (%dx),%al DB 255 ; (bad) @@ -7753,7 +7704,7 @@ _sk_load_8888_avx LABEL PROC DB 255 ; (bad) DB 255 ; (bad) DB 255 ; (bad) - DB 126,255 ; jle 38b9 <_sk_load_8888_avx+0x15d> + DB 126,255 ; jle 3825 <_sk_load_8888_avx+0x15d> DB 255 ; (bad) DB 255 ; .byte 0xff @@ -7796,10 +7747,10 @@ _sk_gather_8888_avx LABEL PROC DB 196,131,121,34,4,152,2 ; vpinsrd $0x2,(%r8,%r11,4),%xmm0,%xmm0 DB 196,131,121,34,28,144,3 ; vpinsrd $0x3,(%r8,%r10,4),%xmm0,%xmm3 DB 196,227,61,24,195,1 ; vinsertf128 $0x1,%xmm3,%ymm8,%ymm0 - DB 197,124,40,21,146,31,0,0 ; vmovaps 0x1f92(%rip),%ymm10 # 5900 <_sk_callback_avx+0x51e> + DB 197,124,40,21,134,31,0,0 ; vmovaps 0x1f86(%rip),%ymm10 # 5860 <_sk_callback_avx+0x512> DB 196,193,124,84,194 ; vandps %ymm10,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,13,28,30,0,0 ; vbroadcastss 0x1e1c(%rip),%ymm9 # 579c <_sk_callback_avx+0x3ba> + DB 196,98,125,24,13,20,30,0,0 ; vbroadcastss 0x1e14(%rip),%ymm9 # 5700 <_sk_callback_avx+0x3b2> DB 196,193,124,89,193 ; vmulps %ymm9,%ymm0,%ymm0 DB 196,193,113,114,208,8 ; vpsrld $0x8,%xmm8,%xmm1 DB 197,233,114,211,8 ; vpsrld $0x8,%xmm3,%xmm2 @@ -7829,7 +7780,7 @@ PUBLIC _sk_store_8888_avx _sk_store_8888_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 - DB 196,98,125,24,5,170,29,0,0 ; vbroadcastss 0x1daa(%rip),%ymm8 # 57a0 <_sk_callback_avx+0x3be> + DB 196,98,125,24,5,162,29,0,0 ; vbroadcastss 0x1da2(%rip),%ymm8 # 5704 <_sk_callback_avx+0x3b6> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,65,116,89,208 ; vmulps %ymm8,%ymm1,%ymm10 @@ -7854,7 +7805,7 @@ _sk_store_8888_avx LABEL PROC DB 196,65,45,86,192 ; vorpd %ymm8,%ymm10,%ymm8 DB 196,65,53,86,192 ; vorpd %ymm8,%ymm9,%ymm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,10 ; jne 3a84 <_sk_store_8888_avx+0x9c> + DB 117,10 ; jne 39f0 <_sk_store_8888_avx+0x9c> DB 196,65,124,17,4,186 ; vmovups %ymm8,(%r10,%rdi,4) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -7862,9 +7813,9 @@ _sk_store_8888_avx LABEL PROC DB 65,128,224,7 ; and $0x7,%r8b DB 65,254,200 ; dec %r8b DB 65,128,248,6 ; cmp $0x6,%r8b - DB 119,236 ; ja 3a80 <_sk_store_8888_avx+0x98> + DB 119,236 ; ja 39ec <_sk_store_8888_avx+0x98> DB 69,15,182,192 ; movzbl %r8b,%r8d - DB 76,141,13,85,0,0,0 ; lea 0x55(%rip),%r9 # 3af4 <_sk_store_8888_avx+0x10c> + DB 76,141,13,85,0,0,0 ; lea 0x55(%rip),%r9 # 3a60 <_sk_store_8888_avx+0x10c> DB 75,99,4,129 ; movslq (%r9,%r8,4),%rax DB 76,1,200 ; add %r9,%rax DB 255,224 ; jmpq *%rax @@ -7878,7 +7829,7 @@ _sk_store_8888_avx LABEL PROC DB 196,67,121,22,68,186,8,2 ; vpextrd $0x2,%xmm8,0x8(%r10,%rdi,4) DB 196,67,121,22,68,186,4,1 ; vpextrd $0x1,%xmm8,0x4(%r10,%rdi,4) DB 196,65,121,126,4,186 ; vmovd %xmm8,(%r10,%rdi,4) - DB 235,143 ; jmp 3a80 <_sk_store_8888_avx+0x98> + DB 235,143 ; jmp 39ec <_sk_store_8888_avx+0x98> DB 15,31,0 ; nopl (%rax) DB 245 ; cmc DB 255 ; (bad) @@ -7914,7 +7865,7 @@ _sk_load_f16_avx LABEL PROC DB 197,252,17,116,36,64 ; vmovups %ymm6,0x40(%rsp) DB 197,252,17,108,36,32 ; vmovups %ymm5,0x20(%rsp) DB 197,254,127,36,36 ; vmovdqu %ymm4,(%rsp) - DB 15,133,143,2,0,0 ; jne 3dcb <_sk_load_f16_avx+0x2bb> + DB 15,133,143,2,0,0 ; jne 3d37 <_sk_load_f16_avx+0x2bb> DB 197,121,16,4,248 ; vmovupd (%rax,%rdi,8),%xmm8 DB 197,249,16,84,248,16 ; vmovupd 0x10(%rax,%rdi,8),%xmm2 DB 197,249,16,76,248,32 ; vmovupd 0x20(%rax,%rdi,8),%xmm1 @@ -7932,13 +7883,13 @@ _sk_load_f16_avx LABEL PROC DB 197,249,105,201 ; vpunpckhwd %xmm1,%xmm0,%xmm1 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 - DB 196,98,125,24,37,15,28,0,0 ; vbroadcastss 0x1c0f(%rip),%ymm12 # 57a4 <_sk_callback_avx+0x3c2> + DB 196,98,125,24,37,7,28,0,0 ; vbroadcastss 0x1c07(%rip),%ymm12 # 5708 <_sk_callback_avx+0x3ba> DB 196,193,124,84,204 ; vandps %ymm12,%ymm0,%ymm1 DB 197,252,87,193 ; vxorps %ymm1,%ymm0,%ymm0 DB 196,195,125,25,198,1 ; vextractf128 $0x1,%ymm0,%xmm14 - DB 196,98,121,24,29,251,27,0,0 ; vbroadcastss 0x1bfb(%rip),%xmm11 # 57a8 <_sk_callback_avx+0x3c6> + DB 196,98,121,24,29,243,27,0,0 ; vbroadcastss 0x1bf3(%rip),%xmm11 # 570c <_sk_callback_avx+0x3be> DB 196,193,8,87,219 ; vxorps %xmm11,%xmm14,%xmm3 - DB 196,98,121,24,45,241,27,0,0 ; vbroadcastss 0x1bf1(%rip),%xmm13 # 57ac <_sk_callback_avx+0x3ca> + DB 196,98,121,24,45,233,27,0,0 ; vbroadcastss 0x1be9(%rip),%xmm13 # 5710 <_sk_callback_avx+0x3c2> DB 197,145,102,219 ; vpcmpgtd %xmm3,%xmm13,%xmm3 DB 196,65,120,87,211 ; vxorps %xmm11,%xmm0,%xmm10 DB 196,65,17,102,210 ; vpcmpgtd %xmm10,%xmm13,%xmm10 @@ -7952,7 +7903,7 @@ _sk_load_f16_avx LABEL PROC DB 196,227,125,24,195,1 ; vinsertf128 $0x1,%xmm3,%ymm0,%ymm0 DB 197,252,86,193 ; vorps %ymm1,%ymm0,%ymm0 DB 196,227,125,25,193,1 ; vextractf128 $0x1,%ymm0,%xmm1 - DB 196,226,121,24,29,167,27,0,0 ; vbroadcastss 0x1ba7(%rip),%xmm3 # 57b0 <_sk_callback_avx+0x3ce> + DB 196,226,121,24,29,159,27,0,0 ; vbroadcastss 0x1b9f(%rip),%xmm3 # 5714 <_sk_callback_avx+0x3c6> DB 197,241,254,203 ; vpaddd %xmm3,%xmm1,%xmm1 DB 197,249,254,195 ; vpaddd %xmm3,%xmm0,%xmm0 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 @@ -8045,29 +7996,29 @@ _sk_load_f16_avx LABEL PROC DB 197,123,16,4,248 ; vmovsd (%rax,%rdi,8),%xmm8 DB 196,65,49,239,201 ; vpxor %xmm9,%xmm9,%xmm9 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,79 ; je 3e2a <_sk_load_f16_avx+0x31a> + DB 116,79 ; je 3d96 <_sk_load_f16_avx+0x31a> DB 197,57,22,68,248,8 ; vmovhpd 0x8(%rax,%rdi,8),%xmm8,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,67 ; jb 3e2a <_sk_load_f16_avx+0x31a> + DB 114,67 ; jb 3d96 <_sk_load_f16_avx+0x31a> DB 197,251,16,84,248,16 ; vmovsd 0x10(%rax,%rdi,8),%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 116,68 ; je 3e37 <_sk_load_f16_avx+0x327> + DB 116,68 ; je 3da3 <_sk_load_f16_avx+0x327> DB 197,233,22,84,248,24 ; vmovhpd 0x18(%rax,%rdi,8),%xmm2,%xmm2 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,56 ; jb 3e37 <_sk_load_f16_avx+0x327> + DB 114,56 ; jb 3da3 <_sk_load_f16_avx+0x327> DB 197,251,16,76,248,32 ; vmovsd 0x20(%rax,%rdi,8),%xmm1 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 15,132,68,253,255,255 ; je 3b53 <_sk_load_f16_avx+0x43> + DB 15,132,68,253,255,255 ; je 3abf <_sk_load_f16_avx+0x43> DB 197,241,22,76,248,40 ; vmovhpd 0x28(%rax,%rdi,8),%xmm1,%xmm1 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 15,130,52,253,255,255 ; jb 3b53 <_sk_load_f16_avx+0x43> + DB 15,130,52,253,255,255 ; jb 3abf <_sk_load_f16_avx+0x43> DB 197,122,126,76,248,48 ; vmovq 0x30(%rax,%rdi,8),%xmm9 - DB 233,41,253,255,255 ; jmpq 3b53 <_sk_load_f16_avx+0x43> + DB 233,41,253,255,255 ; jmpq 3abf <_sk_load_f16_avx+0x43> DB 197,241,87,201 ; vxorpd %xmm1,%xmm1,%xmm1 DB 197,233,87,210 ; vxorpd %xmm2,%xmm2,%xmm2 - DB 233,28,253,255,255 ; jmpq 3b53 <_sk_load_f16_avx+0x43> + DB 233,28,253,255,255 ; jmpq 3abf <_sk_load_f16_avx+0x43> DB 197,241,87,201 ; vxorpd %xmm1,%xmm1,%xmm1 - DB 233,19,253,255,255 ; jmpq 3b53 <_sk_load_f16_avx+0x43> + DB 233,19,253,255,255 ; jmpq 3abf <_sk_load_f16_avx+0x43> PUBLIC _sk_gather_f16_avx _sk_gather_f16_avx LABEL PROC @@ -8129,13 +8080,13 @@ _sk_gather_f16_avx LABEL PROC DB 197,249,105,210 ; vpunpckhwd %xmm2,%xmm0,%xmm2 DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,194,1 ; vinsertf128 $0x1,%xmm2,%ymm0,%ymm0 - DB 196,98,125,24,37,103,24,0,0 ; vbroadcastss 0x1867(%rip),%ymm12 # 57b4 <_sk_callback_avx+0x3d2> + DB 196,98,125,24,37,95,24,0,0 ; vbroadcastss 0x185f(%rip),%ymm12 # 5718 <_sk_callback_avx+0x3ca> DB 196,193,124,84,212 ; vandps %ymm12,%ymm0,%ymm2 DB 197,252,87,194 ; vxorps %ymm2,%ymm0,%ymm0 DB 196,195,125,25,198,1 ; vextractf128 $0x1,%ymm0,%xmm14 - DB 196,98,121,24,29,83,24,0,0 ; vbroadcastss 0x1853(%rip),%xmm11 # 57b8 <_sk_callback_avx+0x3d6> + DB 196,98,121,24,29,75,24,0,0 ; vbroadcastss 0x184b(%rip),%xmm11 # 571c <_sk_callback_avx+0x3ce> DB 196,193,8,87,219 ; vxorps %xmm11,%xmm14,%xmm3 - DB 196,98,121,24,45,73,24,0,0 ; vbroadcastss 0x1849(%rip),%xmm13 # 57bc <_sk_callback_avx+0x3da> + DB 196,98,121,24,45,65,24,0,0 ; vbroadcastss 0x1841(%rip),%xmm13 # 5720 <_sk_callback_avx+0x3d2> DB 197,145,102,219 ; vpcmpgtd %xmm3,%xmm13,%xmm3 DB 196,65,120,87,211 ; vxorps %xmm11,%xmm0,%xmm10 DB 196,65,17,102,210 ; vpcmpgtd %xmm10,%xmm13,%xmm10 @@ -8149,7 +8100,7 @@ _sk_gather_f16_avx LABEL PROC DB 196,227,125,24,195,1 ; vinsertf128 $0x1,%xmm3,%ymm0,%ymm0 DB 197,252,86,194 ; vorps %ymm2,%ymm0,%ymm0 DB 196,227,125,25,194,1 ; vextractf128 $0x1,%ymm0,%xmm2 - DB 196,226,121,24,29,255,23,0,0 ; vbroadcastss 0x17ff(%rip),%xmm3 # 57c0 <_sk_callback_avx+0x3de> + DB 196,226,121,24,29,247,23,0,0 ; vbroadcastss 0x17f7(%rip),%xmm3 # 5724 <_sk_callback_avx+0x3d6> DB 197,233,254,211 ; vpaddd %xmm3,%xmm2,%xmm2 DB 197,249,254,195 ; vpaddd %xmm3,%xmm0,%xmm0 DB 196,227,125,24,194,1 ; vinsertf128 $0x1,%xmm2,%ymm0,%ymm0 @@ -8251,12 +8202,12 @@ _sk_store_f16_avx LABEL PROC DB 197,252,17,180,36,128,0,0,0 ; vmovups %ymm6,0x80(%rsp) DB 197,252,17,108,36,96 ; vmovups %ymm5,0x60(%rsp) DB 197,252,17,100,36,64 ; vmovups %ymm4,0x40(%rsp) - DB 196,98,125,24,13,12,22,0,0 ; vbroadcastss 0x160c(%rip),%ymm9 # 57c4 <_sk_callback_avx+0x3e2> + DB 196,98,125,24,13,4,22,0,0 ; vbroadcastss 0x1604(%rip),%ymm9 # 5728 <_sk_callback_avx+0x3da> DB 196,65,124,84,209 ; vandps %ymm9,%ymm0,%ymm10 DB 197,252,17,4,36 ; vmovups %ymm0,(%rsp) DB 196,65,124,87,218 ; vxorps %ymm10,%ymm0,%ymm11 DB 196,67,125,25,220,1 ; vextractf128 $0x1,%ymm11,%xmm12 - DB 196,98,121,24,5,242,21,0,0 ; vbroadcastss 0x15f2(%rip),%xmm8 # 57c8 <_sk_callback_avx+0x3e6> + DB 196,98,121,24,5,234,21,0,0 ; vbroadcastss 0x15ea(%rip),%xmm8 # 572c <_sk_callback_avx+0x3de> DB 196,65,57,102,236 ; vpcmpgtd %xmm12,%xmm8,%xmm13 DB 196,65,57,102,243 ; vpcmpgtd %xmm11,%xmm8,%xmm14 DB 196,67,13,24,237,1 ; vinsertf128 $0x1,%xmm13,%ymm14,%ymm13 @@ -8266,7 +8217,7 @@ _sk_store_f16_avx LABEL PROC DB 196,67,13,24,242,1 ; vinsertf128 $0x1,%xmm10,%ymm14,%ymm14 DB 196,193,33,114,211,13 ; vpsrld $0xd,%xmm11,%xmm11 DB 196,193,25,114,212,13 ; vpsrld $0xd,%xmm12,%xmm12 - DB 196,98,125,24,21,185,21,0,0 ; vbroadcastss 0x15b9(%rip),%ymm10 # 57cc <_sk_callback_avx+0x3ea> + DB 196,98,125,24,21,177,21,0,0 ; vbroadcastss 0x15b1(%rip),%ymm10 # 5730 <_sk_callback_avx+0x3e2> DB 196,65,12,86,242 ; vorps %ymm10,%ymm14,%ymm14 DB 196,67,125,25,247,1 ; vextractf128 $0x1,%ymm14,%xmm15 DB 196,65,1,254,228 ; vpaddd %xmm12,%xmm15,%xmm12 @@ -8348,7 +8299,7 @@ _sk_store_f16_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 72,133,201 ; test %rcx,%rcx - DB 117,75 ; jne 43fa <_sk_store_f16_avx+0x270> + DB 117,75 ; jne 4366 <_sk_store_f16_avx+0x270> DB 197,120,17,28,248 ; vmovups %xmm11,(%rax,%rdi,8) DB 197,120,17,84,248,16 ; vmovups %xmm10,0x10(%rax,%rdi,8) DB 197,120,17,76,248,32 ; vmovups %xmm9,0x20(%rax,%rdi,8) @@ -8364,22 +8315,22 @@ _sk_store_f16_avx LABEL PROC DB 255,224 ; jmpq *%rax DB 197,121,214,28,248 ; vmovq %xmm11,(%rax,%rdi,8) DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,193 ; je 43c6 <_sk_store_f16_avx+0x23c> + DB 116,193 ; je 4332 <_sk_store_f16_avx+0x23c> DB 197,121,23,92,248,8 ; vmovhpd %xmm11,0x8(%rax,%rdi,8) DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,181 ; jb 43c6 <_sk_store_f16_avx+0x23c> + DB 114,181 ; jb 4332 <_sk_store_f16_avx+0x23c> DB 197,121,214,84,248,16 ; vmovq %xmm10,0x10(%rax,%rdi,8) - DB 116,173 ; je 43c6 <_sk_store_f16_avx+0x23c> + DB 116,173 ; je 4332 <_sk_store_f16_avx+0x23c> DB 197,121,23,84,248,24 ; vmovhpd %xmm10,0x18(%rax,%rdi,8) DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,161 ; jb 43c6 <_sk_store_f16_avx+0x23c> + DB 114,161 ; jb 4332 <_sk_store_f16_avx+0x23c> DB 197,121,214,76,248,32 ; vmovq %xmm9,0x20(%rax,%rdi,8) - DB 116,153 ; je 43c6 <_sk_store_f16_avx+0x23c> + DB 116,153 ; je 4332 <_sk_store_f16_avx+0x23c> DB 197,121,23,76,248,40 ; vmovhpd %xmm9,0x28(%rax,%rdi,8) DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,141 ; jb 43c6 <_sk_store_f16_avx+0x23c> + DB 114,141 ; jb 4332 <_sk_store_f16_avx+0x23c> DB 197,121,214,68,248,48 ; vmovq %xmm8,0x30(%rax,%rdi,8) - DB 235,133 ; jmp 43c6 <_sk_store_f16_avx+0x23c> + DB 235,133 ; jmp 4332 <_sk_store_f16_avx+0x23c> PUBLIC _sk_load_u16_be_avx _sk_load_u16_be_avx LABEL PROC @@ -8387,7 +8338,7 @@ _sk_load_u16_be_avx LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 72,141,4,189,0,0,0,0 ; lea 0x0(,%rdi,4),%rax DB 72,133,201 ; test %rcx,%rcx - DB 15,133,253,0,0,0 ; jne 4554 <_sk_load_u16_be_avx+0x113> + DB 15,133,253,0,0,0 ; jne 44c0 <_sk_load_u16_be_avx+0x113> DB 196,65,121,16,4,64 ; vmovupd (%r8,%rax,2),%xmm8 DB 196,193,121,16,84,64,16 ; vmovupd 0x10(%r8,%rax,2),%xmm2 DB 196,193,121,16,92,64,32 ; vmovupd 0x20(%r8,%rax,2),%xmm3 @@ -8409,7 +8360,7 @@ _sk_load_u16_be_avx LABEL PROC DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,29,8,19,0,0 ; vbroadcastss 0x1308(%rip),%ymm11 # 57d0 <_sk_callback_avx+0x3ee> + DB 196,98,125,24,29,0,19,0,0 ; vbroadcastss 0x1300(%rip),%ymm11 # 5734 <_sk_callback_avx+0x3e6> DB 196,193,124,89,195 ; vmulps %ymm11,%ymm0,%ymm0 DB 197,177,109,202 ; vpunpckhqdq %xmm2,%xmm9,%xmm1 DB 197,233,113,241,8 ; vpsllw $0x8,%xmm1,%xmm2 @@ -8443,29 +8394,29 @@ _sk_load_u16_be_avx LABEL PROC DB 196,65,123,16,4,64 ; vmovsd (%r8,%rax,2),%xmm8 DB 196,65,49,239,201 ; vpxor %xmm9,%xmm9,%xmm9 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,85 ; je 45ba <_sk_load_u16_be_avx+0x179> + DB 116,85 ; je 4526 <_sk_load_u16_be_avx+0x179> DB 196,65,57,22,68,64,8 ; vmovhpd 0x8(%r8,%rax,2),%xmm8,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,72 ; jb 45ba <_sk_load_u16_be_avx+0x179> + DB 114,72 ; jb 4526 <_sk_load_u16_be_avx+0x179> DB 196,193,123,16,84,64,16 ; vmovsd 0x10(%r8,%rax,2),%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 116,72 ; je 45c7 <_sk_load_u16_be_avx+0x186> + DB 116,72 ; je 4533 <_sk_load_u16_be_avx+0x186> DB 196,193,105,22,84,64,24 ; vmovhpd 0x18(%r8,%rax,2),%xmm2,%xmm2 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,59 ; jb 45c7 <_sk_load_u16_be_avx+0x186> + DB 114,59 ; jb 4533 <_sk_load_u16_be_avx+0x186> DB 196,193,123,16,92,64,32 ; vmovsd 0x20(%r8,%rax,2),%xmm3 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 15,132,213,254,255,255 ; je 4472 <_sk_load_u16_be_avx+0x31> + DB 15,132,213,254,255,255 ; je 43de <_sk_load_u16_be_avx+0x31> DB 196,193,97,22,92,64,40 ; vmovhpd 0x28(%r8,%rax,2),%xmm3,%xmm3 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 15,130,196,254,255,255 ; jb 4472 <_sk_load_u16_be_avx+0x31> + DB 15,130,196,254,255,255 ; jb 43de <_sk_load_u16_be_avx+0x31> DB 196,65,122,126,76,64,48 ; vmovq 0x30(%r8,%rax,2),%xmm9 - DB 233,184,254,255,255 ; jmpq 4472 <_sk_load_u16_be_avx+0x31> + DB 233,184,254,255,255 ; jmpq 43de <_sk_load_u16_be_avx+0x31> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 DB 197,233,87,210 ; vxorpd %xmm2,%xmm2,%xmm2 - DB 233,171,254,255,255 ; jmpq 4472 <_sk_load_u16_be_avx+0x31> + DB 233,171,254,255,255 ; jmpq 43de <_sk_load_u16_be_avx+0x31> DB 197,225,87,219 ; vxorpd %xmm3,%xmm3,%xmm3 - DB 233,162,254,255,255 ; jmpq 4472 <_sk_load_u16_be_avx+0x31> + DB 233,162,254,255,255 ; jmpq 43de <_sk_load_u16_be_avx+0x31> PUBLIC _sk_load_rgb_u16_be_avx _sk_load_rgb_u16_be_avx LABEL PROC @@ -8473,7 +8424,7 @@ _sk_load_rgb_u16_be_avx LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 72,141,4,127 ; lea (%rdi,%rdi,2),%rax DB 72,133,201 ; test %rcx,%rcx - DB 15,133,243,0,0,0 ; jne 46d5 <_sk_load_rgb_u16_be_avx+0x105> + DB 15,133,243,0,0,0 ; jne 4641 <_sk_load_rgb_u16_be_avx+0x105> DB 196,193,122,111,4,64 ; vmovdqu (%r8,%rax,2),%xmm0 DB 196,193,122,111,84,64,12 ; vmovdqu 0xc(%r8,%rax,2),%xmm2 DB 196,193,122,111,76,64,24 ; vmovdqu 0x18(%r8,%rax,2),%xmm1 @@ -8500,7 +8451,7 @@ _sk_load_rgb_u16_be_avx LABEL PROC DB 196,226,121,51,192 ; vpmovzxwd %xmm0,%xmm0 DB 196,227,125,24,193,1 ; vinsertf128 $0x1,%xmm1,%ymm0,%ymm0 DB 197,252,91,192 ; vcvtdq2ps %ymm0,%ymm0 - DB 196,98,125,24,29,104,17,0,0 ; vbroadcastss 0x1168(%rip),%ymm11 # 57d4 <_sk_callback_avx+0x3f2> + DB 196,98,125,24,29,96,17,0,0 ; vbroadcastss 0x1160(%rip),%ymm11 # 5738 <_sk_callback_avx+0x3ea> DB 196,193,124,89,195 ; vmulps %ymm11,%ymm0,%ymm0 DB 197,185,109,202 ; vpunpckhqdq %xmm2,%xmm8,%xmm1 DB 197,233,113,241,8 ; vpsllw $0x8,%xmm1,%xmm2 @@ -8521,48 +8472,48 @@ _sk_load_rgb_u16_be_avx LABEL PROC DB 197,252,91,210 ; vcvtdq2ps %ymm2,%ymm2 DB 196,193,108,89,211 ; vmulps %ymm11,%ymm2,%ymm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,29,5,17,0,0 ; vbroadcastss 0x1105(%rip),%ymm3 # 57d8 <_sk_callback_avx+0x3f6> + DB 196,226,125,24,29,253,16,0,0 ; vbroadcastss 0x10fd(%rip),%ymm3 # 573c <_sk_callback_avx+0x3ee> DB 255,224 ; jmpq *%rax DB 196,193,121,110,4,64 ; vmovd (%r8,%rax,2),%xmm0 DB 196,193,121,196,68,64,4,2 ; vpinsrw $0x2,0x4(%r8,%rax,2),%xmm0,%xmm0 DB 72,131,249,1 ; cmp $0x1,%rcx - DB 117,5 ; jne 46ee <_sk_load_rgb_u16_be_avx+0x11e> - DB 233,40,255,255,255 ; jmpq 4616 <_sk_load_rgb_u16_be_avx+0x46> + DB 117,5 ; jne 465a <_sk_load_rgb_u16_be_avx+0x11e> + DB 233,40,255,255,255 ; jmpq 4582 <_sk_load_rgb_u16_be_avx+0x46> DB 196,193,121,110,76,64,6 ; vmovd 0x6(%r8,%rax,2),%xmm1 DB 196,65,113,196,68,64,10,2 ; vpinsrw $0x2,0xa(%r8,%rax,2),%xmm1,%xmm8 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,26 ; jb 471d <_sk_load_rgb_u16_be_avx+0x14d> + DB 114,26 ; jb 4689 <_sk_load_rgb_u16_be_avx+0x14d> DB 196,193,121,110,76,64,12 ; vmovd 0xc(%r8,%rax,2),%xmm1 DB 196,193,113,196,84,64,16,2 ; vpinsrw $0x2,0x10(%r8,%rax,2),%xmm1,%xmm2 DB 72,131,249,3 ; cmp $0x3,%rcx - DB 117,10 ; jne 4722 <_sk_load_rgb_u16_be_avx+0x152> - DB 233,249,254,255,255 ; jmpq 4616 <_sk_load_rgb_u16_be_avx+0x46> - DB 233,244,254,255,255 ; jmpq 4616 <_sk_load_rgb_u16_be_avx+0x46> + DB 117,10 ; jne 468e <_sk_load_rgb_u16_be_avx+0x152> + DB 233,249,254,255,255 ; jmpq 4582 <_sk_load_rgb_u16_be_avx+0x46> + DB 233,244,254,255,255 ; jmpq 4582 <_sk_load_rgb_u16_be_avx+0x46> DB 196,193,121,110,76,64,18 ; vmovd 0x12(%r8,%rax,2),%xmm1 DB 196,65,113,196,76,64,22,2 ; vpinsrw $0x2,0x16(%r8,%rax,2),%xmm1,%xmm9 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,26 ; jb 4751 <_sk_load_rgb_u16_be_avx+0x181> + DB 114,26 ; jb 46bd <_sk_load_rgb_u16_be_avx+0x181> DB 196,193,121,110,76,64,24 ; vmovd 0x18(%r8,%rax,2),%xmm1 DB 196,193,113,196,76,64,28,2 ; vpinsrw $0x2,0x1c(%r8,%rax,2),%xmm1,%xmm1 DB 72,131,249,5 ; cmp $0x5,%rcx - DB 117,10 ; jne 4756 <_sk_load_rgb_u16_be_avx+0x186> - DB 233,197,254,255,255 ; jmpq 4616 <_sk_load_rgb_u16_be_avx+0x46> - DB 233,192,254,255,255 ; jmpq 4616 <_sk_load_rgb_u16_be_avx+0x46> + DB 117,10 ; jne 46c2 <_sk_load_rgb_u16_be_avx+0x186> + DB 233,197,254,255,255 ; jmpq 4582 <_sk_load_rgb_u16_be_avx+0x46> + DB 233,192,254,255,255 ; jmpq 4582 <_sk_load_rgb_u16_be_avx+0x46> DB 196,193,121,110,92,64,30 ; vmovd 0x1e(%r8,%rax,2),%xmm3 DB 196,65,97,196,92,64,34,2 ; vpinsrw $0x2,0x22(%r8,%rax,2),%xmm3,%xmm11 DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,20 ; jb 477f <_sk_load_rgb_u16_be_avx+0x1af> + DB 114,20 ; jb 46eb <_sk_load_rgb_u16_be_avx+0x1af> DB 196,193,121,110,92,64,36 ; vmovd 0x24(%r8,%rax,2),%xmm3 DB 196,193,97,196,92,64,40,2 ; vpinsrw $0x2,0x28(%r8,%rax,2),%xmm3,%xmm3 - DB 233,151,254,255,255 ; jmpq 4616 <_sk_load_rgb_u16_be_avx+0x46> - DB 233,146,254,255,255 ; jmpq 4616 <_sk_load_rgb_u16_be_avx+0x46> + DB 233,151,254,255,255 ; jmpq 4582 <_sk_load_rgb_u16_be_avx+0x46> + DB 233,146,254,255,255 ; jmpq 4582 <_sk_load_rgb_u16_be_avx+0x46> PUBLIC _sk_store_u16_be_avx _sk_store_u16_be_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,0 ; mov (%rax),%r8 DB 72,141,4,189,0,0,0,0 ; lea 0x0(,%rdi,4),%rax - DB 196,98,125,24,5,66,16,0,0 ; vbroadcastss 0x1042(%rip),%ymm8 # 57dc <_sk_callback_avx+0x3fa> + DB 196,98,125,24,5,58,16,0,0 ; vbroadcastss 0x103a(%rip),%ymm8 # 5740 <_sk_callback_avx+0x3f2> DB 196,65,124,89,200 ; vmulps %ymm8,%ymm0,%ymm9 DB 196,65,125,91,201 ; vcvtps2dq %ymm9,%ymm9 DB 196,67,125,25,202,1 ; vextractf128 $0x1,%ymm9,%xmm10 @@ -8600,7 +8551,7 @@ _sk_store_u16_be_avx LABEL PROC DB 196,65,17,98,200 ; vpunpckldq %xmm8,%xmm13,%xmm9 DB 196,65,17,106,192 ; vpunpckhdq %xmm8,%xmm13,%xmm8 DB 72,133,201 ; test %rcx,%rcx - DB 117,31 ; jne 487e <_sk_store_u16_be_avx+0xfa> + DB 117,31 ; jne 47ea <_sk_store_u16_be_avx+0xfa> DB 196,65,120,17,28,64 ; vmovups %xmm11,(%r8,%rax,2) DB 196,65,120,17,84,64,16 ; vmovups %xmm10,0x10(%r8,%rax,2) DB 196,65,120,17,76,64,32 ; vmovups %xmm9,0x20(%r8,%rax,2) @@ -8609,31 +8560,31 @@ _sk_store_u16_be_avx LABEL PROC DB 255,224 ; jmpq *%rax DB 196,65,121,214,28,64 ; vmovq %xmm11,(%r8,%rax,2) DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,240 ; je 487a <_sk_store_u16_be_avx+0xf6> + DB 116,240 ; je 47e6 <_sk_store_u16_be_avx+0xf6> DB 196,65,121,23,92,64,8 ; vmovhpd %xmm11,0x8(%r8,%rax,2) DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,227 ; jb 487a <_sk_store_u16_be_avx+0xf6> + DB 114,227 ; jb 47e6 <_sk_store_u16_be_avx+0xf6> DB 196,65,121,214,84,64,16 ; vmovq %xmm10,0x10(%r8,%rax,2) - DB 116,218 ; je 487a <_sk_store_u16_be_avx+0xf6> + DB 116,218 ; je 47e6 <_sk_store_u16_be_avx+0xf6> DB 196,65,121,23,84,64,24 ; vmovhpd %xmm10,0x18(%r8,%rax,2) DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,205 ; jb 487a <_sk_store_u16_be_avx+0xf6> + DB 114,205 ; jb 47e6 <_sk_store_u16_be_avx+0xf6> DB 196,65,121,214,76,64,32 ; vmovq %xmm9,0x20(%r8,%rax,2) - DB 116,196 ; je 487a <_sk_store_u16_be_avx+0xf6> + DB 116,196 ; je 47e6 <_sk_store_u16_be_avx+0xf6> DB 196,65,121,23,76,64,40 ; vmovhpd %xmm9,0x28(%r8,%rax,2) DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,183 ; jb 487a <_sk_store_u16_be_avx+0xf6> + DB 114,183 ; jb 47e6 <_sk_store_u16_be_avx+0xf6> DB 196,65,121,214,68,64,48 ; vmovq %xmm8,0x30(%r8,%rax,2) - DB 235,174 ; jmp 487a <_sk_store_u16_be_avx+0xf6> + DB 235,174 ; jmp 47e6 <_sk_store_u16_be_avx+0xf6> PUBLIC _sk_load_f32_avx _sk_load_f32_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,131,249,7 ; cmp $0x7,%rcx - DB 119,110 ; ja 4942 <_sk_load_f32_avx+0x76> + DB 119,110 ; ja 48ae <_sk_load_f32_avx+0x76> DB 76,139,0 ; mov (%rax),%r8 DB 76,141,12,189,0,0,0,0 ; lea 0x0(,%rdi,4),%r9 - DB 76,141,21,134,0,0,0 ; lea 0x86(%rip),%r10 # 496c <_sk_load_f32_avx+0xa0> + DB 76,141,21,134,0,0,0 ; lea 0x86(%rip),%r10 # 48d8 <_sk_load_f32_avx+0xa0> DB 73,99,4,138 ; movslq (%r10,%rcx,4),%rax DB 76,1,208 ; add %r10,%rax DB 255,224 ; jmpq *%rax @@ -8690,7 +8641,7 @@ _sk_store_f32_avx LABEL PROC DB 196,65,37,20,196 ; vunpcklpd %ymm12,%ymm11,%ymm8 DB 196,65,37,21,220 ; vunpckhpd %ymm12,%ymm11,%ymm11 DB 72,133,201 ; test %rcx,%rcx - DB 117,55 ; jne 49f9 <_sk_store_f32_avx+0x6d> + DB 117,55 ; jne 4965 <_sk_store_f32_avx+0x6d> DB 196,67,45,24,225,1 ; vinsertf128 $0x1,%xmm9,%ymm10,%ymm12 DB 196,67,61,24,235,1 ; vinsertf128 $0x1,%xmm11,%ymm8,%ymm13 DB 196,67,45,6,201,49 ; vperm2f128 $0x31,%ymm9,%ymm10,%ymm9 @@ -8703,22 +8654,22 @@ _sk_store_f32_avx LABEL PROC DB 255,224 ; jmpq *%rax DB 196,65,121,17,20,128 ; vmovupd %xmm10,(%r8,%rax,4) DB 72,131,249,1 ; cmp $0x1,%rcx - DB 116,240 ; je 49f5 <_sk_store_f32_avx+0x69> + DB 116,240 ; je 4961 <_sk_store_f32_avx+0x69> DB 196,65,121,17,76,128,16 ; vmovupd %xmm9,0x10(%r8,%rax,4) DB 72,131,249,3 ; cmp $0x3,%rcx - DB 114,227 ; jb 49f5 <_sk_store_f32_avx+0x69> + DB 114,227 ; jb 4961 <_sk_store_f32_avx+0x69> DB 196,65,121,17,68,128,32 ; vmovupd %xmm8,0x20(%r8,%rax,4) - DB 116,218 ; je 49f5 <_sk_store_f32_avx+0x69> + DB 116,218 ; je 4961 <_sk_store_f32_avx+0x69> DB 196,65,121,17,92,128,48 ; vmovupd %xmm11,0x30(%r8,%rax,4) DB 72,131,249,5 ; cmp $0x5,%rcx - DB 114,205 ; jb 49f5 <_sk_store_f32_avx+0x69> + DB 114,205 ; jb 4961 <_sk_store_f32_avx+0x69> DB 196,67,125,25,84,128,64,1 ; vextractf128 $0x1,%ymm10,0x40(%r8,%rax,4) - DB 116,195 ; je 49f5 <_sk_store_f32_avx+0x69> + DB 116,195 ; je 4961 <_sk_store_f32_avx+0x69> DB 196,67,125,25,76,128,80,1 ; vextractf128 $0x1,%ymm9,0x50(%r8,%rax,4) DB 72,131,249,7 ; cmp $0x7,%rcx - DB 114,181 ; jb 49f5 <_sk_store_f32_avx+0x69> + DB 114,181 ; jb 4961 <_sk_store_f32_avx+0x69> DB 196,67,125,25,68,128,96,1 ; vextractf128 $0x1,%ymm8,0x60(%r8,%rax,4) - DB 235,171 ; jmp 49f5 <_sk_store_f32_avx+0x69> + DB 235,171 ; jmp 4961 <_sk_store_f32_avx+0x69> PUBLIC _sk_clamp_x_avx _sk_clamp_x_avx LABEL PROC @@ -8840,12 +8791,12 @@ _sk_mirror_y_avx LABEL PROC PUBLIC _sk_luminance_to_alpha_avx _sk_luminance_to_alpha_avx LABEL PROC - DB 196,226,125,24,29,203,11,0,0 ; vbroadcastss 0xbcb(%rip),%ymm3 # 57e0 <_sk_callback_avx+0x3fe> + DB 196,226,125,24,29,195,11,0,0 ; vbroadcastss 0xbc3(%rip),%ymm3 # 5744 <_sk_callback_avx+0x3f6> DB 197,252,89,195 ; vmulps %ymm3,%ymm0,%ymm0 - DB 196,226,125,24,29,194,11,0,0 ; vbroadcastss 0xbc2(%rip),%ymm3 # 57e4 <_sk_callback_avx+0x402> + DB 196,226,125,24,29,186,11,0,0 ; vbroadcastss 0xbba(%rip),%ymm3 # 5748 <_sk_callback_avx+0x3fa> DB 197,244,89,203 ; vmulps %ymm3,%ymm1,%ymm1 DB 197,252,88,193 ; vaddps %ymm1,%ymm0,%ymm0 - DB 196,226,125,24,13,181,11,0,0 ; vbroadcastss 0xbb5(%rip),%ymm1 # 57e8 <_sk_callback_avx+0x406> + DB 196,226,125,24,13,173,11,0,0 ; vbroadcastss 0xbad(%rip),%ymm1 # 574c <_sk_callback_avx+0x3fe> DB 197,236,89,201 ; vmulps %ymm1,%ymm2,%ymm1 DB 197,252,88,217 ; vaddps %ymm1,%ymm0,%ymm3 DB 72,173 ; lods %ds:(%rsi),%rax @@ -9013,7 +8964,7 @@ _sk_linear_gradient_avx LABEL PROC DB 196,226,125,24,88,28 ; vbroadcastss 0x1c(%rax),%ymm3 DB 76,139,0 ; mov (%rax),%r8 DB 77,133,192 ; test %r8,%r8 - DB 15,132,146,0,0,0 ; je 4f89 <_sk_linear_gradient_avx+0xb8> + DB 15,132,146,0,0,0 ; je 4ef5 <_sk_linear_gradient_avx+0xb8> DB 72,139,64,8 ; mov 0x8(%rax),%rax DB 72,131,192,32 ; add $0x20,%rax DB 196,65,28,87,228 ; vxorps %ymm12,%ymm12,%ymm12 @@ -9040,8 +8991,8 @@ _sk_linear_gradient_avx LABEL PROC DB 196,227,13,74,219,208 ; vblendvps %ymm13,%ymm3,%ymm14,%ymm3 DB 72,131,192,36 ; add $0x24,%rax DB 73,255,200 ; dec %r8 - DB 117,140 ; jne 4f13 <_sk_linear_gradient_avx+0x42> - DB 235,20 ; jmp 4f9d <_sk_linear_gradient_avx+0xcc> + DB 117,140 ; jne 4e7f <_sk_linear_gradient_avx+0x42> + DB 235,20 ; jmp 4f09 <_sk_linear_gradient_avx+0xcc> DB 196,65,36,87,219 ; vxorps %ymm11,%ymm11,%ymm11 DB 196,65,44,87,210 ; vxorps %ymm10,%ymm10,%ymm10 DB 196,65,52,87,201 ; vxorps %ymm9,%ymm9,%ymm9 @@ -9084,7 +9035,7 @@ _sk_linear_gradient_2stops_avx LABEL PROC PUBLIC _sk_save_xy_avx _sk_save_xy_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,193,7,0,0 ; vbroadcastss 0x7c1(%rip),%ymm8 # 57ec <_sk_callback_avx+0x40a> + DB 196,98,125,24,5,185,7,0,0 ; vbroadcastss 0x7b9(%rip),%ymm8 # 5750 <_sk_callback_avx+0x402> DB 196,65,124,88,200 ; vaddps %ymm8,%ymm0,%ymm9 DB 196,67,125,8,209,1 ; vroundps $0x1,%ymm9,%ymm10 DB 196,65,52,92,202 ; vsubps %ymm10,%ymm9,%ymm9 @@ -9117,9 +9068,9 @@ _sk_accumulate_avx LABEL PROC PUBLIC _sk_bilinear_nx_avx _sk_bilinear_nx_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,77,7,0,0 ; vbroadcastss 0x74d(%rip),%ymm0 # 57f0 <_sk_callback_avx+0x40e> + DB 196,226,125,24,5,69,7,0,0 ; vbroadcastss 0x745(%rip),%ymm0 # 5754 <_sk_callback_avx+0x406> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,68,7,0,0 ; vbroadcastss 0x744(%rip),%ymm8 # 57f4 <_sk_callback_avx+0x412> + DB 196,98,125,24,5,60,7,0,0 ; vbroadcastss 0x73c(%rip),%ymm8 # 5758 <_sk_callback_avx+0x40a> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -9128,7 +9079,7 @@ _sk_bilinear_nx_avx LABEL PROC PUBLIC _sk_bilinear_px_avx _sk_bilinear_px_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,44,7,0,0 ; vbroadcastss 0x72c(%rip),%ymm0 # 57f8 <_sk_callback_avx+0x416> + DB 196,226,125,24,5,36,7,0,0 ; vbroadcastss 0x724(%rip),%ymm0 # 575c <_sk_callback_avx+0x40e> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 DB 197,124,16,64,64 ; vmovups 0x40(%rax),%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -9138,9 +9089,9 @@ _sk_bilinear_px_avx LABEL PROC PUBLIC _sk_bilinear_ny_avx _sk_bilinear_ny_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,16,7,0,0 ; vbroadcastss 0x710(%rip),%ymm1 # 57fc <_sk_callback_avx+0x41a> + DB 196,226,125,24,13,8,7,0,0 ; vbroadcastss 0x708(%rip),%ymm1 # 5760 <_sk_callback_avx+0x412> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,6,7,0,0 ; vbroadcastss 0x706(%rip),%ymm8 # 5800 <_sk_callback_avx+0x41e> + DB 196,98,125,24,5,254,6,0,0 ; vbroadcastss 0x6fe(%rip),%ymm8 # 5764 <_sk_callback_avx+0x416> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -9149,7 +9100,7 @@ _sk_bilinear_ny_avx LABEL PROC PUBLIC _sk_bilinear_py_avx _sk_bilinear_py_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,238,6,0,0 ; vbroadcastss 0x6ee(%rip),%ymm1 # 5804 <_sk_callback_avx+0x422> + DB 196,226,125,24,13,230,6,0,0 ; vbroadcastss 0x6e6(%rip),%ymm1 # 5768 <_sk_callback_avx+0x41a> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 DB 197,124,16,64,96 ; vmovups 0x60(%rax),%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -9159,14 +9110,14 @@ _sk_bilinear_py_avx LABEL PROC PUBLIC _sk_bicubic_n3x_avx _sk_bicubic_n3x_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,209,6,0,0 ; vbroadcastss 0x6d1(%rip),%ymm0 # 5808 <_sk_callback_avx+0x426> + DB 196,226,125,24,5,201,6,0,0 ; vbroadcastss 0x6c9(%rip),%ymm0 # 576c <_sk_callback_avx+0x41e> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,200,6,0,0 ; vbroadcastss 0x6c8(%rip),%ymm8 # 580c <_sk_callback_avx+0x42a> + DB 196,98,125,24,5,192,6,0,0 ; vbroadcastss 0x6c0(%rip),%ymm8 # 5770 <_sk_callback_avx+0x422> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,185,6,0,0 ; vbroadcastss 0x6b9(%rip),%ymm10 # 5810 <_sk_callback_avx+0x42e> + DB 196,98,125,24,21,177,6,0,0 ; vbroadcastss 0x6b1(%rip),%ymm10 # 5774 <_sk_callback_avx+0x426> DB 196,65,60,89,194 ; vmulps %ymm10,%ymm8,%ymm8 - DB 196,98,125,24,21,175,6,0,0 ; vbroadcastss 0x6af(%rip),%ymm10 # 5814 <_sk_callback_avx+0x432> + DB 196,98,125,24,21,167,6,0,0 ; vbroadcastss 0x6a7(%rip),%ymm10 # 5778 <_sk_callback_avx+0x42a> DB 196,65,60,88,194 ; vaddps %ymm10,%ymm8,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -9176,19 +9127,19 @@ _sk_bicubic_n3x_avx LABEL PROC PUBLIC _sk_bicubic_n1x_avx _sk_bicubic_n1x_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,146,6,0,0 ; vbroadcastss 0x692(%rip),%ymm0 # 5818 <_sk_callback_avx+0x436> + DB 196,226,125,24,5,138,6,0,0 ; vbroadcastss 0x68a(%rip),%ymm0 # 577c <_sk_callback_avx+0x42e> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 - DB 196,98,125,24,5,137,6,0,0 ; vbroadcastss 0x689(%rip),%ymm8 # 581c <_sk_callback_avx+0x43a> + DB 196,98,125,24,5,129,6,0,0 ; vbroadcastss 0x681(%rip),%ymm8 # 5780 <_sk_callback_avx+0x432> DB 197,60,92,64,64 ; vsubps 0x40(%rax),%ymm8,%ymm8 - DB 196,98,125,24,13,127,6,0,0 ; vbroadcastss 0x67f(%rip),%ymm9 # 5820 <_sk_callback_avx+0x43e> + DB 196,98,125,24,13,119,6,0,0 ; vbroadcastss 0x677(%rip),%ymm9 # 5784 <_sk_callback_avx+0x436> DB 196,65,60,89,201 ; vmulps %ymm9,%ymm8,%ymm9 - DB 196,98,125,24,21,117,6,0,0 ; vbroadcastss 0x675(%rip),%ymm10 # 5824 <_sk_callback_avx+0x442> + DB 196,98,125,24,21,109,6,0,0 ; vbroadcastss 0x66d(%rip),%ymm10 # 5788 <_sk_callback_avx+0x43a> DB 196,65,52,88,202 ; vaddps %ymm10,%ymm9,%ymm9 DB 196,65,60,89,201 ; vmulps %ymm9,%ymm8,%ymm9 - DB 196,98,125,24,21,102,6,0,0 ; vbroadcastss 0x666(%rip),%ymm10 # 5828 <_sk_callback_avx+0x446> + DB 196,98,125,24,21,94,6,0,0 ; vbroadcastss 0x65e(%rip),%ymm10 # 578c <_sk_callback_avx+0x43e> DB 196,65,52,88,202 ; vaddps %ymm10,%ymm9,%ymm9 DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 - DB 196,98,125,24,13,87,6,0,0 ; vbroadcastss 0x657(%rip),%ymm9 # 582c <_sk_callback_avx+0x44a> + DB 196,98,125,24,13,79,6,0,0 ; vbroadcastss 0x64f(%rip),%ymm9 # 5790 <_sk_callback_avx+0x442> DB 196,65,60,88,193 ; vaddps %ymm9,%ymm8,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -9197,17 +9148,17 @@ _sk_bicubic_n1x_avx LABEL PROC PUBLIC _sk_bicubic_p1x_avx _sk_bicubic_p1x_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,63,6,0,0 ; vbroadcastss 0x63f(%rip),%ymm8 # 5830 <_sk_callback_avx+0x44e> + DB 196,98,125,24,5,55,6,0,0 ; vbroadcastss 0x637(%rip),%ymm8 # 5794 <_sk_callback_avx+0x446> DB 197,188,88,0 ; vaddps (%rax),%ymm8,%ymm0 DB 197,124,16,72,64 ; vmovups 0x40(%rax),%ymm9 - DB 196,98,125,24,21,49,6,0,0 ; vbroadcastss 0x631(%rip),%ymm10 # 5834 <_sk_callback_avx+0x452> + DB 196,98,125,24,21,41,6,0,0 ; vbroadcastss 0x629(%rip),%ymm10 # 5798 <_sk_callback_avx+0x44a> DB 196,65,52,89,210 ; vmulps %ymm10,%ymm9,%ymm10 - DB 196,98,125,24,29,39,6,0,0 ; vbroadcastss 0x627(%rip),%ymm11 # 5838 <_sk_callback_avx+0x456> + DB 196,98,125,24,29,31,6,0,0 ; vbroadcastss 0x61f(%rip),%ymm11 # 579c <_sk_callback_avx+0x44e> DB 196,65,44,88,211 ; vaddps %ymm11,%ymm10,%ymm10 DB 196,65,52,89,210 ; vmulps %ymm10,%ymm9,%ymm10 DB 196,65,44,88,192 ; vaddps %ymm8,%ymm10,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 - DB 196,98,125,24,13,14,6,0,0 ; vbroadcastss 0x60e(%rip),%ymm9 # 583c <_sk_callback_avx+0x45a> + DB 196,98,125,24,13,6,6,0,0 ; vbroadcastss 0x606(%rip),%ymm9 # 57a0 <_sk_callback_avx+0x452> DB 196,65,60,88,193 ; vaddps %ymm9,%ymm8,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -9216,13 +9167,13 @@ _sk_bicubic_p1x_avx LABEL PROC PUBLIC _sk_bicubic_p3x_avx _sk_bicubic_p3x_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,5,246,5,0,0 ; vbroadcastss 0x5f6(%rip),%ymm0 # 5840 <_sk_callback_avx+0x45e> + DB 196,226,125,24,5,238,5,0,0 ; vbroadcastss 0x5ee(%rip),%ymm0 # 57a4 <_sk_callback_avx+0x456> DB 197,252,88,0 ; vaddps (%rax),%ymm0,%ymm0 DB 197,124,16,64,64 ; vmovups 0x40(%rax),%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,227,5,0,0 ; vbroadcastss 0x5e3(%rip),%ymm10 # 5844 <_sk_callback_avx+0x462> + DB 196,98,125,24,21,219,5,0,0 ; vbroadcastss 0x5db(%rip),%ymm10 # 57a8 <_sk_callback_avx+0x45a> DB 196,65,60,89,194 ; vmulps %ymm10,%ymm8,%ymm8 - DB 196,98,125,24,21,217,5,0,0 ; vbroadcastss 0x5d9(%rip),%ymm10 # 5848 <_sk_callback_avx+0x466> + DB 196,98,125,24,21,209,5,0,0 ; vbroadcastss 0x5d1(%rip),%ymm10 # 57ac <_sk_callback_avx+0x45e> DB 196,65,60,88,194 ; vaddps %ymm10,%ymm8,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 DB 197,124,17,128,128,0,0,0 ; vmovups %ymm8,0x80(%rax) @@ -9232,14 +9183,14 @@ _sk_bicubic_p3x_avx LABEL PROC PUBLIC _sk_bicubic_n3y_avx _sk_bicubic_n3y_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,188,5,0,0 ; vbroadcastss 0x5bc(%rip),%ymm1 # 584c <_sk_callback_avx+0x46a> + DB 196,226,125,24,13,180,5,0,0 ; vbroadcastss 0x5b4(%rip),%ymm1 # 57b0 <_sk_callback_avx+0x462> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,178,5,0,0 ; vbroadcastss 0x5b2(%rip),%ymm8 # 5850 <_sk_callback_avx+0x46e> + DB 196,98,125,24,5,170,5,0,0 ; vbroadcastss 0x5aa(%rip),%ymm8 # 57b4 <_sk_callback_avx+0x466> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,163,5,0,0 ; vbroadcastss 0x5a3(%rip),%ymm10 # 5854 <_sk_callback_avx+0x472> + DB 196,98,125,24,21,155,5,0,0 ; vbroadcastss 0x59b(%rip),%ymm10 # 57b8 <_sk_callback_avx+0x46a> DB 196,65,60,89,194 ; vmulps %ymm10,%ymm8,%ymm8 - DB 196,98,125,24,21,153,5,0,0 ; vbroadcastss 0x599(%rip),%ymm10 # 5858 <_sk_callback_avx+0x476> + DB 196,98,125,24,21,145,5,0,0 ; vbroadcastss 0x591(%rip),%ymm10 # 57bc <_sk_callback_avx+0x46e> DB 196,65,60,88,194 ; vaddps %ymm10,%ymm8,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -9249,19 +9200,19 @@ _sk_bicubic_n3y_avx LABEL PROC PUBLIC _sk_bicubic_n1y_avx _sk_bicubic_n1y_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,124,5,0,0 ; vbroadcastss 0x57c(%rip),%ymm1 # 585c <_sk_callback_avx+0x47a> + DB 196,226,125,24,13,116,5,0,0 ; vbroadcastss 0x574(%rip),%ymm1 # 57c0 <_sk_callback_avx+0x472> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 - DB 196,98,125,24,5,114,5,0,0 ; vbroadcastss 0x572(%rip),%ymm8 # 5860 <_sk_callback_avx+0x47e> + DB 196,98,125,24,5,106,5,0,0 ; vbroadcastss 0x56a(%rip),%ymm8 # 57c4 <_sk_callback_avx+0x476> DB 197,60,92,64,96 ; vsubps 0x60(%rax),%ymm8,%ymm8 - DB 196,98,125,24,13,104,5,0,0 ; vbroadcastss 0x568(%rip),%ymm9 # 5864 <_sk_callback_avx+0x482> + DB 196,98,125,24,13,96,5,0,0 ; vbroadcastss 0x560(%rip),%ymm9 # 57c8 <_sk_callback_avx+0x47a> DB 196,65,60,89,201 ; vmulps %ymm9,%ymm8,%ymm9 - DB 196,98,125,24,21,94,5,0,0 ; vbroadcastss 0x55e(%rip),%ymm10 # 5868 <_sk_callback_avx+0x486> + DB 196,98,125,24,21,86,5,0,0 ; vbroadcastss 0x556(%rip),%ymm10 # 57cc <_sk_callback_avx+0x47e> DB 196,65,52,88,202 ; vaddps %ymm10,%ymm9,%ymm9 DB 196,65,60,89,201 ; vmulps %ymm9,%ymm8,%ymm9 - DB 196,98,125,24,21,79,5,0,0 ; vbroadcastss 0x54f(%rip),%ymm10 # 586c <_sk_callback_avx+0x48a> + DB 196,98,125,24,21,71,5,0,0 ; vbroadcastss 0x547(%rip),%ymm10 # 57d0 <_sk_callback_avx+0x482> DB 196,65,52,88,202 ; vaddps %ymm10,%ymm9,%ymm9 DB 196,65,60,89,193 ; vmulps %ymm9,%ymm8,%ymm8 - DB 196,98,125,24,13,64,5,0,0 ; vbroadcastss 0x540(%rip),%ymm9 # 5870 <_sk_callback_avx+0x48e> + DB 196,98,125,24,13,56,5,0,0 ; vbroadcastss 0x538(%rip),%ymm9 # 57d4 <_sk_callback_avx+0x486> DB 196,65,60,88,193 ; vaddps %ymm9,%ymm8,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -9270,17 +9221,17 @@ _sk_bicubic_n1y_avx LABEL PROC PUBLIC _sk_bicubic_p1y_avx _sk_bicubic_p1y_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,98,125,24,5,40,5,0,0 ; vbroadcastss 0x528(%rip),%ymm8 # 5874 <_sk_callback_avx+0x492> + DB 196,98,125,24,5,32,5,0,0 ; vbroadcastss 0x520(%rip),%ymm8 # 57d8 <_sk_callback_avx+0x48a> DB 197,188,88,72,32 ; vaddps 0x20(%rax),%ymm8,%ymm1 DB 197,124,16,72,96 ; vmovups 0x60(%rax),%ymm9 - DB 196,98,125,24,21,25,5,0,0 ; vbroadcastss 0x519(%rip),%ymm10 # 5878 <_sk_callback_avx+0x496> + DB 196,98,125,24,21,17,5,0,0 ; vbroadcastss 0x511(%rip),%ymm10 # 57dc <_sk_callback_avx+0x48e> DB 196,65,52,89,210 ; vmulps %ymm10,%ymm9,%ymm10 - DB 196,98,125,24,29,15,5,0,0 ; vbroadcastss 0x50f(%rip),%ymm11 # 587c <_sk_callback_avx+0x49a> + DB 196,98,125,24,29,7,5,0,0 ; vbroadcastss 0x507(%rip),%ymm11 # 57e0 <_sk_callback_avx+0x492> DB 196,65,44,88,211 ; vaddps %ymm11,%ymm10,%ymm10 DB 196,65,52,89,210 ; vmulps %ymm10,%ymm9,%ymm10 DB 196,65,44,88,192 ; vaddps %ymm8,%ymm10,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 - DB 196,98,125,24,13,246,4,0,0 ; vbroadcastss 0x4f6(%rip),%ymm9 # 5880 <_sk_callback_avx+0x49e> + DB 196,98,125,24,13,238,4,0,0 ; vbroadcastss 0x4ee(%rip),%ymm9 # 57e4 <_sk_callback_avx+0x496> DB 196,65,60,88,193 ; vaddps %ymm9,%ymm8,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -9289,13 +9240,13 @@ _sk_bicubic_p1y_avx LABEL PROC PUBLIC _sk_bicubic_p3y_avx _sk_bicubic_p3y_avx LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 196,226,125,24,13,222,4,0,0 ; vbroadcastss 0x4de(%rip),%ymm1 # 5884 <_sk_callback_avx+0x4a2> + DB 196,226,125,24,13,214,4,0,0 ; vbroadcastss 0x4d6(%rip),%ymm1 # 57e8 <_sk_callback_avx+0x49a> DB 197,244,88,72,32 ; vaddps 0x20(%rax),%ymm1,%ymm1 DB 197,124,16,64,96 ; vmovups 0x60(%rax),%ymm8 DB 196,65,60,89,200 ; vmulps %ymm8,%ymm8,%ymm9 - DB 196,98,125,24,21,202,4,0,0 ; vbroadcastss 0x4ca(%rip),%ymm10 # 5888 <_sk_callback_avx+0x4a6> + DB 196,98,125,24,21,194,4,0,0 ; vbroadcastss 0x4c2(%rip),%ymm10 # 57ec <_sk_callback_avx+0x49e> DB 196,65,60,89,194 ; vmulps %ymm10,%ymm8,%ymm8 - DB 196,98,125,24,21,192,4,0,0 ; vbroadcastss 0x4c0(%rip),%ymm10 # 588c <_sk_callback_avx+0x4aa> + DB 196,98,125,24,21,184,4,0,0 ; vbroadcastss 0x4b8(%rip),%ymm10 # 57f0 <_sk_callback_avx+0x4a2> DB 196,65,60,88,194 ; vaddps %ymm10,%ymm8,%ymm8 DB 196,65,52,89,192 ; vmulps %ymm8,%ymm9,%ymm8 DB 197,124,17,128,160,0,0,0 ; vmovups %ymm8,0xa0(%rax) @@ -9426,21 +9377,17 @@ ALIGN 4 DB 0,128,64,171,170,42 ; add %al,0x2aaaab40(%rax) DB 62,0,0 ; add %al,%ds:(%rax) DB 0,63 ; add %bh,(%rdi) - DB 0,0 ; add %al,(%rax) - DB 128,63,171 ; cmpb $0xab,(%rdi) + DB 171 ; stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) DB 62,0,0 ; add %al,%ds:(%rax) - DB 128,191,0,0,192,64,171 ; cmpb $0xab,0x40c00000(%rdi) - DB 170 ; stos %al,%es:(%rdi) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) + DB 192,64,0,0 ; rolb $0x0,0x0(%rax) + DB 128,64,171,170 ; addb $0xaa,-0x55(%rax) DB 170 ; stos %al,%es:(%rdi) DB 190,129,128,128,59 ; mov $0x3b808081,%esi DB 129,128,128,59,0,248,0,0,8,33 ; addl $0x21080000,-0x7ffc480(%rax) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 55d1 <.literal4+0xd5> + DB 224,7 ; loopne 5535 <.literal4+0xcd> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -9454,10 +9401,10 @@ ALIGN 4 DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) DB 0,52,255 ; add %dh,(%rdi,%rdi,8) DB 255 ; (bad) - DB 127,0 ; jg 55fc <.literal4+0x100> + DB 127,0 ; jg 5560 <.literal4+0xf8> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 5675 <.literal4+0x179> + DB 119,115 ; ja 55d9 <.literal4+0x171> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -9471,10 +9418,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 5630 <.literal4+0x134> + DB 127,0 ; jg 5594 <.literal4+0x12c> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 56a9 <.literal4+0x1ad> + DB 119,115 ; ja 560d <.literal4+0x1a5> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -9488,10 +9435,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 5664 <.literal4+0x168> + DB 127,0 ; jg 55c8 <.literal4+0x160> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 56dd <.literal4+0x1e1> + DB 119,115 ; ja 5641 <.literal4+0x1d9> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -9505,10 +9452,10 @@ ALIGN 4 DB 0,128,63,0,0,0 ; add %al,0x3f(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 5698 <.literal4+0x19c> + DB 127,0 ; jg 55fc <.literal4+0x194> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 5711 <.literal4+0x215> + DB 119,115 ; ja 5675 <.literal4+0x20d> DB 248 ; clc DB 194,117,191 ; retq $0xbf75 DB 191,63,249,68,180 ; mov $0xb444f93f,%edi @@ -9521,7 +9468,7 @@ ALIGN 4 DB 0,75,0 ; add %cl,0x0(%rbx) DB 0,128,63,0,0,200 ; add %al,-0x37ffffc1(%rax) DB 66,0,0 ; rex.X add %al,(%rax) - DB 127,67 ; jg 570f <.literal4+0x213> + DB 127,67 ; jg 5673 <.literal4+0x20b> DB 0,0 ; add %al,(%rax) DB 0,195 ; add %al,%bl DB 0,0 ; add %al,(%rax) @@ -9533,10 +9480,10 @@ ALIGN 4 DB 190,80,128,3,62 ; mov $0x3e038050,%esi DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 572f <.literal4+0x233> + DB 118,63 ; jbe 5693 <.literal4+0x22b> DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) - DB 127,67 ; jg 5743 <.literal4+0x247> + DB 127,67 ; jg 56a7 <.literal4+0x23f> DB 129,128,128,59,0,0,128,63,129,128 ; addl $0x80813f80,0x3b80(%rax) DB 128,59,0 ; cmpb $0x0,(%rbx) DB 0,128,63,129,128,128 ; add %al,-0x7f7f7ec1(%rax) @@ -9545,7 +9492,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 5725 <.literal4+0x229> + DB 224,7 ; loopne 5689 <.literal4+0x221> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -9557,7 +9504,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 5741 <.literal4+0x245> + DB 224,7 ; loopne 56a5 <.literal4+0x23d> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -9568,7 +9515,7 @@ ALIGN 4 DB 0,0 ; add %al,(%rax) DB 248 ; clc DB 65,0,0 ; add %al,(%r8) - DB 124,66 ; jl 5796 <.literal4+0x29a> + DB 124,66 ; jl 56fa <.literal4+0x292> DB 0,240 ; add %dh,%al DB 0,0 ; add %al,(%rax) DB 137,136,136,55,0,15 ; mov %ecx,0xf003788(%rax) @@ -9586,9 +9533,9 @@ ALIGN 4 DB 137,136,136,59,15,0 ; mov %ecx,0xf3b88(%rax) DB 0,0 ; add %al,(%rax) DB 137,136,136,61,0,0 ; mov %ecx,0x3d88(%rax) - DB 112,65 ; jo 57d9 <.literal4+0x2dd> + DB 112,65 ; jo 573d <.literal4+0x2d5> DB 129,128,128,59,129,128,128,59,0,0 ; addl $0x3b80,-0x7f7ec480(%rax) - DB 127,67 ; jg 57e7 <.literal4+0x2eb> + DB 127,67 ; jg 574b <.literal4+0x2e3> DB 0,128,0,0,0,0 ; add %al,0x0(%rax) DB 0,128,0,4,0,128 ; add %al,-0x7ffffc00(%rax) DB 0,0 ; add %al,(%rax) @@ -9604,7 +9551,7 @@ ALIGN 4 DB 0,128,55,0,0,128 ; add %al,-0x7fffffc9(%rax) DB 63 ; (bad) DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 5827 <.literal4+0x32b> + DB 127,71 ; jg 578b <.literal4+0x323> DB 208 ; (bad) DB 179,89 ; mov $0x59,%bl DB 62,89 ; ds pop %rcx @@ -9841,7 +9788,7 @@ _sk_seed_shader_sse41 LABEL PROC DB 102,15,110,199 ; movd %edi,%xmm0 DB 102,15,112,192,0 ; pshufd $0x0,%xmm0,%xmm0 DB 15,91,200 ; cvtdq2ps %xmm0,%xmm1 - DB 15,40,21,129,57,0,0 ; movaps 0x3981(%rip),%xmm2 # 3a90 <_sk_callback_sse41+0xae> + DB 15,40,21,193,56,0,0 ; movaps 0x38c1(%rip),%xmm2 # 39d0 <_sk_callback_sse41+0xad> DB 15,88,202 ; addps %xmm2,%xmm1 DB 15,16,2 ; movups (%rdx),%xmm0 DB 15,88,193 ; addps %xmm1,%xmm0 @@ -9850,7 +9797,7 @@ _sk_seed_shader_sse41 LABEL PROC DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 15,88,202 ; addps %xmm2,%xmm1 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,21,112,57,0,0 ; movaps 0x3970(%rip),%xmm2 # 3aa0 <_sk_callback_sse41+0xbe> + DB 15,40,21,176,56,0,0 ; movaps 0x38b0(%rip),%xmm2 # 39e0 <_sk_callback_sse41+0xbd> DB 15,87,219 ; xorps %xmm3,%xmm3 DB 15,87,228 ; xorps %xmm4,%xmm4 DB 15,87,237 ; xorps %xmm5,%xmm5 @@ -9884,7 +9831,7 @@ _sk_clear_sse41 LABEL PROC PUBLIC _sk_srcatop_sse41 _sk_srcatop_sse41 LABEL PROC DB 15,89,199 ; mulps %xmm7,%xmm0 - DB 68,15,40,5,43,57,0,0 ; movaps 0x392b(%rip),%xmm8 # 3ab0 <_sk_callback_sse41+0xce> + DB 68,15,40,5,107,56,0,0 ; movaps 0x386b(%rip),%xmm8 # 39f0 <_sk_callback_sse41+0xcd> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,89,204 ; mulps %xmm4,%xmm9 @@ -9907,7 +9854,7 @@ PUBLIC _sk_dstatop_sse41 _sk_dstatop_sse41 LABEL PROC DB 68,15,40,195 ; movaps %xmm3,%xmm8 DB 68,15,89,196 ; mulps %xmm4,%xmm8 - DB 68,15,40,13,238,56,0,0 ; movaps 0x38ee(%rip),%xmm9 # 3ac0 <_sk_callback_sse41+0xde> + DB 68,15,40,13,46,56,0,0 ; movaps 0x382e(%rip),%xmm9 # 3a00 <_sk_callback_sse41+0xdd> DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 65,15,88,192 ; addps %xmm8,%xmm0 @@ -9948,7 +9895,7 @@ _sk_dstin_sse41 LABEL PROC PUBLIC _sk_srcout_sse41 _sk_srcout_sse41 LABEL PROC - DB 68,15,40,5,146,56,0,0 ; movaps 0x3892(%rip),%xmm8 # 3ad0 <_sk_callback_sse41+0xee> + DB 68,15,40,5,210,55,0,0 ; movaps 0x37d2(%rip),%xmm8 # 3a10 <_sk_callback_sse41+0xed> DB 68,15,92,199 ; subps %xmm7,%xmm8 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 @@ -9959,7 +9906,7 @@ _sk_srcout_sse41 LABEL PROC PUBLIC _sk_dstout_sse41 _sk_dstout_sse41 LABEL PROC - DB 68,15,40,5,130,56,0,0 ; movaps 0x3882(%rip),%xmm8 # 3ae0 <_sk_callback_sse41+0xfe> + DB 68,15,40,5,194,55,0,0 ; movaps 0x37c2(%rip),%xmm8 # 3a20 <_sk_callback_sse41+0xfd> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 15,89,196 ; mulps %xmm4,%xmm0 @@ -9974,7 +9921,7 @@ _sk_dstout_sse41 LABEL PROC PUBLIC _sk_srcover_sse41 _sk_srcover_sse41 LABEL PROC - DB 68,15,40,5,101,56,0,0 ; movaps 0x3865(%rip),%xmm8 # 3af0 <_sk_callback_sse41+0x10e> + DB 68,15,40,5,165,55,0,0 ; movaps 0x37a5(%rip),%xmm8 # 3a30 <_sk_callback_sse41+0x10d> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,89,204 ; mulps %xmm4,%xmm9 @@ -9992,7 +9939,7 @@ _sk_srcover_sse41 LABEL PROC PUBLIC _sk_dstover_sse41 _sk_dstover_sse41 LABEL PROC - DB 68,15,40,5,57,56,0,0 ; movaps 0x3839(%rip),%xmm8 # 3b00 <_sk_callback_sse41+0x11e> + DB 68,15,40,5,121,55,0,0 ; movaps 0x3779(%rip),%xmm8 # 3a40 <_sk_callback_sse41+0x11d> DB 68,15,92,199 ; subps %xmm7,%xmm8 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -10016,7 +9963,7 @@ _sk_modulate_sse41 LABEL PROC PUBLIC _sk_multiply_sse41 _sk_multiply_sse41 LABEL PROC - DB 68,15,40,5,13,56,0,0 ; movaps 0x380d(%rip),%xmm8 # 3b10 <_sk_callback_sse41+0x12e> + DB 68,15,40,5,77,55,0,0 ; movaps 0x374d(%rip),%xmm8 # 3a50 <_sk_callback_sse41+0x12d> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 69,15,40,209 ; movaps %xmm9,%xmm10 @@ -10086,7 +10033,7 @@ _sk_screen_sse41 LABEL PROC PUBLIC _sk_xor__sse41 _sk_xor__sse41 LABEL PROC DB 68,15,40,195 ; movaps %xmm3,%xmm8 - DB 15,40,29,62,55,0,0 ; movaps 0x373e(%rip),%xmm3 # 3b20 <_sk_callback_sse41+0x13e> + DB 15,40,29,126,54,0,0 ; movaps 0x367e(%rip),%xmm3 # 3a60 <_sk_callback_sse41+0x13d> DB 68,15,40,203 ; movaps %xmm3,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 65,15,89,193 ; mulps %xmm9,%xmm0 @@ -10132,7 +10079,7 @@ _sk_darken_sse41 LABEL PROC DB 68,15,89,206 ; mulps %xmm6,%xmm9 DB 65,15,95,209 ; maxps %xmm9,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,169,54,0,0 ; movaps 0x36a9(%rip),%xmm2 # 3b30 <_sk_callback_sse41+0x14e> + DB 15,40,21,233,53,0,0 ; movaps 0x35e9(%rip),%xmm2 # 3a70 <_sk_callback_sse41+0x14d> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -10164,7 +10111,7 @@ _sk_lighten_sse41 LABEL PROC DB 68,15,89,206 ; mulps %xmm6,%xmm9 DB 65,15,93,209 ; minps %xmm9,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,78,54,0,0 ; movaps 0x364e(%rip),%xmm2 # 3b40 <_sk_callback_sse41+0x15e> + DB 15,40,21,142,53,0,0 ; movaps 0x358e(%rip),%xmm2 # 3a80 <_sk_callback_sse41+0x15d> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -10199,7 +10146,7 @@ _sk_difference_sse41 LABEL PROC DB 65,15,93,209 ; minps %xmm9,%xmm2 DB 15,88,210 ; addps %xmm2,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,232,53,0,0 ; movaps 0x35e8(%rip),%xmm2 # 3b50 <_sk_callback_sse41+0x16e> + DB 15,40,21,40,53,0,0 ; movaps 0x3528(%rip),%xmm2 # 3a90 <_sk_callback_sse41+0x16d> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -10224,7 +10171,7 @@ _sk_exclusion_sse41 LABEL PROC DB 15,89,214 ; mulps %xmm6,%xmm2 DB 15,88,210 ; addps %xmm2,%xmm2 DB 68,15,92,202 ; subps %xmm2,%xmm9 - DB 15,40,13,169,53,0,0 ; movaps 0x35a9(%rip),%xmm1 # 3b60 <_sk_callback_sse41+0x17e> + DB 15,40,13,233,52,0,0 ; movaps 0x34e9(%rip),%xmm1 # 3aa0 <_sk_callback_sse41+0x17d> DB 15,92,203 ; subps %xmm3,%xmm1 DB 15,89,207 ; mulps %xmm7,%xmm1 DB 15,88,217 ; addps %xmm1,%xmm3 @@ -10236,7 +10183,7 @@ _sk_exclusion_sse41 LABEL PROC PUBLIC _sk_colorburn_sse41 _sk_colorburn_sse41 LABEL PROC DB 68,15,40,192 ; movaps %xmm0,%xmm8 - DB 68,15,40,21,152,53,0,0 ; movaps 0x3598(%rip),%xmm10 # 3b70 <_sk_callback_sse41+0x18e> + DB 68,15,40,21,216,52,0,0 ; movaps 0x34d8(%rip),%xmm10 # 3ab0 <_sk_callback_sse41+0x18d> DB 69,15,40,218 ; movaps %xmm10,%xmm11 DB 68,15,92,223 ; subps %xmm7,%xmm11 DB 69,15,40,203 ; movaps %xmm11,%xmm9 @@ -10316,7 +10263,7 @@ _sk_colorburn_sse41 LABEL PROC PUBLIC _sk_colordodge_sse41 _sk_colordodge_sse41 LABEL PROC DB 68,15,40,192 ; movaps %xmm0,%xmm8 - DB 68,15,40,21,118,52,0,0 ; movaps 0x3476(%rip),%xmm10 # 3b80 <_sk_callback_sse41+0x19e> + DB 68,15,40,21,182,51,0,0 ; movaps 0x33b6(%rip),%xmm10 # 3ac0 <_sk_callback_sse41+0x19d> DB 69,15,40,218 ; movaps %xmm10,%xmm11 DB 68,15,92,223 ; subps %xmm7,%xmm11 DB 69,15,40,227 ; movaps %xmm11,%xmm12 @@ -10397,7 +10344,7 @@ _sk_hardlight_sse41 LABEL PROC DB 15,40,244 ; movaps %xmm4,%xmm6 DB 15,40,227 ; movaps %xmm3,%xmm4 DB 68,15,40,200 ; movaps %xmm0,%xmm9 - DB 68,15,40,21,76,51,0,0 ; movaps 0x334c(%rip),%xmm10 # 3b90 <_sk_callback_sse41+0x1ae> + DB 68,15,40,21,140,50,0,0 ; movaps 0x328c(%rip),%xmm10 # 3ad0 <_sk_callback_sse41+0x1ad> DB 65,15,40,234 ; movaps %xmm10,%xmm5 DB 15,92,239 ; subps %xmm7,%xmm5 DB 15,40,197 ; movaps %xmm5,%xmm0 @@ -10479,7 +10426,7 @@ PUBLIC _sk_overlay_sse41 _sk_overlay_sse41 LABEL PROC DB 68,15,40,201 ; movaps %xmm1,%xmm9 DB 68,15,40,240 ; movaps %xmm0,%xmm14 - DB 68,15,40,21,46,50,0,0 ; movaps 0x322e(%rip),%xmm10 # 3ba0 <_sk_callback_sse41+0x1be> + DB 68,15,40,21,110,49,0,0 ; movaps 0x316e(%rip),%xmm10 # 3ae0 <_sk_callback_sse41+0x1bd> DB 69,15,40,218 ; movaps %xmm10,%xmm11 DB 68,15,92,223 ; subps %xmm7,%xmm11 DB 65,15,40,195 ; movaps %xmm11,%xmm0 @@ -10563,7 +10510,7 @@ _sk_softlight_sse41 LABEL PROC DB 15,40,198 ; movaps %xmm6,%xmm0 DB 15,94,199 ; divps %xmm7,%xmm0 DB 65,15,84,193 ; andps %xmm9,%xmm0 - DB 15,40,13,1,49,0,0 ; movaps 0x3101(%rip),%xmm1 # 3bb0 <_sk_callback_sse41+0x1ce> + DB 15,40,13,65,48,0,0 ; movaps 0x3041(%rip),%xmm1 # 3af0 <_sk_callback_sse41+0x1cd> DB 68,15,40,209 ; movaps %xmm1,%xmm10 DB 68,15,92,208 ; subps %xmm0,%xmm10 DB 68,15,40,240 ; movaps %xmm0,%xmm14 @@ -10576,10 +10523,10 @@ _sk_softlight_sse41 LABEL PROC DB 15,40,208 ; movaps %xmm0,%xmm2 DB 15,89,210 ; mulps %xmm2,%xmm2 DB 15,88,208 ; addps %xmm0,%xmm2 - DB 68,15,40,45,223,48,0,0 ; movaps 0x30df(%rip),%xmm13 # 3bc0 <_sk_callback_sse41+0x1de> + DB 68,15,40,45,31,48,0,0 ; movaps 0x301f(%rip),%xmm13 # 3b00 <_sk_callback_sse41+0x1dd> DB 69,15,88,245 ; addps %xmm13,%xmm14 DB 68,15,89,242 ; mulps %xmm2,%xmm14 - DB 68,15,40,37,223,48,0,0 ; movaps 0x30df(%rip),%xmm12 # 3bd0 <_sk_callback_sse41+0x1ee> + DB 68,15,40,37,31,48,0,0 ; movaps 0x301f(%rip),%xmm12 # 3b10 <_sk_callback_sse41+0x1ed> DB 69,15,89,252 ; mulps %xmm12,%xmm15 DB 69,15,88,254 ; addps %xmm14,%xmm15 DB 15,40,198 ; movaps %xmm6,%xmm0 @@ -10724,7 +10671,7 @@ _sk_clamp_0_sse41 LABEL PROC PUBLIC _sk_clamp_1_sse41 _sk_clamp_1_sse41 LABEL PROC - DB 68,15,40,5,239,46,0,0 ; movaps 0x2eef(%rip),%xmm8 # 3be0 <_sk_callback_sse41+0x1fe> + DB 68,15,40,5,47,46,0,0 ; movaps 0x2e2f(%rip),%xmm8 # 3b20 <_sk_callback_sse41+0x1fd> DB 65,15,93,192 ; minps %xmm8,%xmm0 DB 65,15,93,200 ; minps %xmm8,%xmm1 DB 65,15,93,208 ; minps %xmm8,%xmm2 @@ -10734,7 +10681,7 @@ _sk_clamp_1_sse41 LABEL PROC PUBLIC _sk_clamp_a_sse41 _sk_clamp_a_sse41 LABEL PROC - DB 15,93,29,228,46,0,0 ; minps 0x2ee4(%rip),%xmm3 # 3bf0 <_sk_callback_sse41+0x20e> + DB 15,93,29,36,46,0,0 ; minps 0x2e24(%rip),%xmm3 # 3b30 <_sk_callback_sse41+0x20d> DB 15,93,195 ; minps %xmm3,%xmm0 DB 15,93,203 ; minps %xmm3,%xmm1 DB 15,93,211 ; minps %xmm3,%xmm2 @@ -10807,7 +10754,7 @@ _sk_premul_sse41 LABEL PROC PUBLIC _sk_unpremul_sse41 _sk_unpremul_sse41 LABEL PROC DB 69,15,87,192 ; xorps %xmm8,%xmm8 - DB 68,15,40,13,79,46,0,0 ; movaps 0x2e4f(%rip),%xmm9 # 3c00 <_sk_callback_sse41+0x21e> + DB 68,15,40,13,143,45,0,0 ; movaps 0x2d8f(%rip),%xmm9 # 3b40 <_sk_callback_sse41+0x21d> DB 68,15,94,203 ; divps %xmm3,%xmm9 DB 68,15,194,195,4 ; cmpneqps %xmm3,%xmm8 DB 69,15,84,193 ; andps %xmm9,%xmm8 @@ -10819,20 +10766,20 @@ _sk_unpremul_sse41 LABEL PROC PUBLIC _sk_from_srgb_sse41 _sk_from_srgb_sse41 LABEL PROC - DB 68,15,40,29,58,46,0,0 ; movaps 0x2e3a(%rip),%xmm11 # 3c10 <_sk_callback_sse41+0x22e> + DB 68,15,40,29,122,45,0,0 ; movaps 0x2d7a(%rip),%xmm11 # 3b50 <_sk_callback_sse41+0x22d> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 DB 68,15,40,208 ; movaps %xmm0,%xmm10 DB 69,15,89,210 ; mulps %xmm10,%xmm10 - DB 68,15,40,37,50,46,0,0 ; movaps 0x2e32(%rip),%xmm12 # 3c20 <_sk_callback_sse41+0x23e> + DB 68,15,40,37,114,45,0,0 ; movaps 0x2d72(%rip),%xmm12 # 3b60 <_sk_callback_sse41+0x23d> DB 68,15,40,192 ; movaps %xmm0,%xmm8 DB 69,15,89,196 ; mulps %xmm12,%xmm8 - DB 68,15,40,45,50,46,0,0 ; movaps 0x2e32(%rip),%xmm13 # 3c30 <_sk_callback_sse41+0x24e> + DB 68,15,40,45,114,45,0,0 ; movaps 0x2d72(%rip),%xmm13 # 3b70 <_sk_callback_sse41+0x24d> DB 69,15,88,197 ; addps %xmm13,%xmm8 DB 69,15,89,194 ; mulps %xmm10,%xmm8 - DB 68,15,40,53,50,46,0,0 ; movaps 0x2e32(%rip),%xmm14 # 3c40 <_sk_callback_sse41+0x25e> + DB 68,15,40,53,114,45,0,0 ; movaps 0x2d72(%rip),%xmm14 # 3b80 <_sk_callback_sse41+0x25d> DB 69,15,88,198 ; addps %xmm14,%xmm8 - DB 68,15,40,61,54,46,0,0 ; movaps 0x2e36(%rip),%xmm15 # 3c50 <_sk_callback_sse41+0x26e> + DB 68,15,40,61,118,45,0,0 ; movaps 0x2d76(%rip),%xmm15 # 3b90 <_sk_callback_sse41+0x26d> DB 65,15,194,199,1 ; cmpltps %xmm15,%xmm0 DB 102,69,15,56,20,193 ; blendvps %xmm0,%xmm9,%xmm8 DB 68,15,40,209 ; movaps %xmm1,%xmm10 @@ -10876,20 +10823,20 @@ _sk_to_srgb_sse41 LABEL PROC DB 68,15,82,192 ; rsqrtps %xmm0,%xmm8 DB 69,15,83,200 ; rcpps %xmm8,%xmm9 DB 69,15,82,208 ; rsqrtps %xmm8,%xmm10 - DB 68,15,40,29,163,45,0,0 ; movaps 0x2da3(%rip),%xmm11 # 3c60 <_sk_callback_sse41+0x27e> + DB 68,15,40,29,227,44,0,0 ; movaps 0x2ce3(%rip),%xmm11 # 3ba0 <_sk_callback_sse41+0x27d> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 65,15,89,203 ; mulps %xmm11,%xmm1 - DB 68,15,40,37,164,45,0,0 ; movaps 0x2da4(%rip),%xmm12 # 3c70 <_sk_callback_sse41+0x28e> + DB 68,15,40,37,228,44,0,0 ; movaps 0x2ce4(%rip),%xmm12 # 3bb0 <_sk_callback_sse41+0x28d> DB 69,15,89,204 ; mulps %xmm12,%xmm9 - DB 68,15,40,45,168,45,0,0 ; movaps 0x2da8(%rip),%xmm13 # 3c80 <_sk_callback_sse41+0x29e> + DB 68,15,40,45,232,44,0,0 ; movaps 0x2ce8(%rip),%xmm13 # 3bc0 <_sk_callback_sse41+0x29d> DB 69,15,88,205 ; addps %xmm13,%xmm9 - DB 68,15,40,53,172,45,0,0 ; movaps 0x2dac(%rip),%xmm14 # 3c90 <_sk_callback_sse41+0x2ae> + DB 68,15,40,53,236,44,0,0 ; movaps 0x2cec(%rip),%xmm14 # 3bd0 <_sk_callback_sse41+0x2ad> DB 69,15,89,214 ; mulps %xmm14,%xmm10 DB 69,15,88,209 ; addps %xmm9,%xmm10 - DB 68,15,40,5,172,45,0,0 ; movaps 0x2dac(%rip),%xmm8 # 3ca0 <_sk_callback_sse41+0x2be> + DB 68,15,40,5,236,44,0,0 ; movaps 0x2cec(%rip),%xmm8 # 3be0 <_sk_callback_sse41+0x2bd> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,93,202 ; minps %xmm10,%xmm9 - DB 68,15,40,61,172,45,0,0 ; movaps 0x2dac(%rip),%xmm15 # 3cb0 <_sk_callback_sse41+0x2ce> + DB 68,15,40,61,236,44,0,0 ; movaps 0x2cec(%rip),%xmm15 # 3bf0 <_sk_callback_sse41+0x2cd> DB 65,15,194,199,1 ; cmpltps %xmm15,%xmm0 DB 102,68,15,56,20,201 ; blendvps %xmm0,%xmm1,%xmm9 DB 15,82,194 ; rsqrtps %xmm2,%xmm0 @@ -10942,7 +10889,7 @@ _sk_rgb_to_hsl_sse41 LABEL PROC DB 68,15,93,226 ; minps %xmm2,%xmm12 DB 65,15,40,203 ; movaps %xmm11,%xmm1 DB 65,15,92,204 ; subps %xmm12,%xmm1 - DB 68,15,40,53,250,44,0,0 ; movaps 0x2cfa(%rip),%xmm14 # 3cc0 <_sk_callback_sse41+0x2de> + DB 68,15,40,53,58,44,0,0 ; movaps 0x2c3a(%rip),%xmm14 # 3c00 <_sk_callback_sse41+0x2dd> DB 68,15,94,241 ; divps %xmm1,%xmm14 DB 69,15,40,211 ; movaps %xmm11,%xmm10 DB 69,15,194,208,0 ; cmpeqps %xmm8,%xmm10 @@ -10951,27 +10898,27 @@ _sk_rgb_to_hsl_sse41 LABEL PROC DB 65,15,89,198 ; mulps %xmm14,%xmm0 DB 69,15,40,249 ; movaps %xmm9,%xmm15 DB 68,15,194,250,1 ; cmpltps %xmm2,%xmm15 - DB 68,15,84,61,225,44,0,0 ; andps 0x2ce1(%rip),%xmm15 # 3cd0 <_sk_callback_sse41+0x2ee> + DB 68,15,84,61,33,44,0,0 ; andps 0x2c21(%rip),%xmm15 # 3c10 <_sk_callback_sse41+0x2ed> DB 68,15,88,248 ; addps %xmm0,%xmm15 DB 65,15,40,195 ; movaps %xmm11,%xmm0 DB 65,15,194,193,0 ; cmpeqps %xmm9,%xmm0 DB 65,15,92,208 ; subps %xmm8,%xmm2 DB 65,15,89,214 ; mulps %xmm14,%xmm2 - DB 68,15,40,45,212,44,0,0 ; movaps 0x2cd4(%rip),%xmm13 # 3ce0 <_sk_callback_sse41+0x2fe> + DB 68,15,40,45,20,44,0,0 ; movaps 0x2c14(%rip),%xmm13 # 3c20 <_sk_callback_sse41+0x2fd> DB 65,15,88,213 ; addps %xmm13,%xmm2 DB 69,15,92,193 ; subps %xmm9,%xmm8 DB 69,15,89,198 ; mulps %xmm14,%xmm8 - DB 68,15,88,5,208,44,0,0 ; addps 0x2cd0(%rip),%xmm8 # 3cf0 <_sk_callback_sse41+0x30e> + DB 68,15,88,5,16,44,0,0 ; addps 0x2c10(%rip),%xmm8 # 3c30 <_sk_callback_sse41+0x30d> DB 102,68,15,56,20,194 ; blendvps %xmm0,%xmm2,%xmm8 DB 65,15,40,194 ; movaps %xmm10,%xmm0 DB 102,69,15,56,20,199 ; blendvps %xmm0,%xmm15,%xmm8 - DB 68,15,89,5,200,44,0,0 ; mulps 0x2cc8(%rip),%xmm8 # 3d00 <_sk_callback_sse41+0x31e> + DB 68,15,89,5,8,44,0,0 ; mulps 0x2c08(%rip),%xmm8 # 3c40 <_sk_callback_sse41+0x31d> DB 69,15,40,203 ; movaps %xmm11,%xmm9 DB 69,15,194,204,4 ; cmpneqps %xmm12,%xmm9 DB 69,15,84,193 ; andps %xmm9,%xmm8 DB 69,15,92,235 ; subps %xmm11,%xmm13 DB 69,15,88,220 ; addps %xmm12,%xmm11 - DB 15,40,5,188,44,0,0 ; movaps 0x2cbc(%rip),%xmm0 # 3d10 <_sk_callback_sse41+0x32e> + DB 15,40,5,252,43,0,0 ; movaps 0x2bfc(%rip),%xmm0 # 3c50 <_sk_callback_sse41+0x32d> DB 65,15,40,211 ; movaps %xmm11,%xmm2 DB 15,89,208 ; mulps %xmm0,%xmm2 DB 15,194,194,1 ; cmpltps %xmm2,%xmm0 @@ -10985,163 +10932,126 @@ _sk_rgb_to_hsl_sse41 LABEL PROC PUBLIC _sk_hsl_to_rgb_sse41 _sk_hsl_to_rgb_sse41 LABEL PROC - DB 72,129,236,152,0,0,0 ; sub $0x98,%rsp - DB 15,41,188,36,128,0,0,0 ; movaps %xmm7,0x80(%rsp) - DB 15,41,116,36,112 ; movaps %xmm6,0x70(%rsp) - DB 15,41,108,36,96 ; movaps %xmm5,0x60(%rsp) - DB 15,41,100,36,80 ; movaps %xmm4,0x50(%rsp) - DB 15,41,92,36,64 ; movaps %xmm3,0x40(%rsp) - DB 68,15,40,216 ; movaps %xmm0,%xmm11 + DB 72,129,236,136,0,0,0 ; sub $0x88,%rsp + DB 15,41,124,36,112 ; movaps %xmm7,0x70(%rsp) + DB 15,41,116,36,96 ; movaps %xmm6,0x60(%rsp) + DB 15,41,108,36,80 ; movaps %xmm5,0x50(%rsp) + DB 15,41,100,36,64 ; movaps %xmm4,0x40(%rsp) + DB 15,41,92,36,48 ; movaps %xmm3,0x30(%rsp) + DB 15,40,233 ; movaps %xmm1,%xmm5 + DB 68,15,40,208 ; movaps %xmm0,%xmm10 DB 184,0,0,0,63 ; mov $0x3f000000,%eax - DB 102,15,110,216 ; movd %eax,%xmm3 - DB 15,198,219,0 ; shufps $0x0,%xmm3,%xmm3 - DB 15,41,28,36 ; movaps %xmm3,(%rsp) - DB 15,40,194 ; movaps %xmm2,%xmm0 - DB 15,194,195,1 ; cmpltps %xmm3,%xmm0 - DB 15,40,45,97,44,0,0 ; movaps 0x2c61(%rip),%xmm5 # 3d20 <_sk_callback_sse41+0x33e> - DB 15,40,249 ; movaps %xmm1,%xmm7 - DB 15,40,225 ; movaps %xmm1,%xmm4 - DB 15,40,217 ; movaps %xmm1,%xmm3 - DB 15,88,221 ; addps %xmm5,%xmm3 - DB 15,40,245 ; movaps %xmm5,%xmm6 - DB 15,89,218 ; mulps %xmm2,%xmm3 - DB 15,88,250 ; addps %xmm2,%xmm7 - DB 15,89,226 ; mulps %xmm2,%xmm4 - DB 15,40,234 ; movaps %xmm2,%xmm5 - DB 15,92,252 ; subps %xmm4,%xmm7 - DB 102,15,56,20,251 ; blendvps %xmm0,%xmm3,%xmm7 - DB 68,15,40,37,70,44,0,0 ; movaps 0x2c46(%rip),%xmm12 # 3d30 <_sk_callback_sse41+0x34e> - DB 69,15,88,227 ; addps %xmm11,%xmm12 - DB 184,0,0,0,0 ; mov $0x0,%eax - DB 185,0,0,128,63 ; mov $0x3f800000,%ecx - DB 102,68,15,110,201 ; movd %ecx,%xmm9 - DB 69,15,198,201,0 ; shufps $0x0,%xmm9,%xmm9 - DB 65,15,40,193 ; movaps %xmm9,%xmm0 - DB 65,15,194,196,1 ; cmpltps %xmm12,%xmm0 - DB 65,15,40,212 ; movaps %xmm12,%xmm2 - DB 15,88,21,42,44,0,0 ; addps 0x2c2a(%rip),%xmm2 # 3d40 <_sk_callback_sse41+0x35e> - DB 69,15,40,196 ; movaps %xmm12,%xmm8 - DB 65,15,40,220 ; movaps %xmm12,%xmm3 - DB 102,68,15,56,20,226 ; blendvps %xmm0,%xmm2,%xmm12 - DB 102,15,110,192 ; movd %eax,%xmm0 - DB 15,198,192,0 ; shufps $0x0,%xmm0,%xmm0 - DB 15,41,68,36,32 ; movaps %xmm0,0x20(%rsp) - DB 68,15,194,192,1 ; cmpltps %xmm0,%xmm8 - DB 15,88,222 ; addps %xmm6,%xmm3 - DB 65,15,40,192 ; movaps %xmm8,%xmm0 - DB 102,68,15,56,20,227 ; blendvps %xmm0,%xmm3,%xmm12 - DB 15,40,213 ; movaps %xmm5,%xmm2 - DB 15,41,84,36,48 ; movaps %xmm2,0x30(%rsp) - DB 68,15,40,194 ; movaps %xmm2,%xmm8 - DB 69,15,88,192 ; addps %xmm8,%xmm8 - DB 68,15,92,199 ; subps %xmm7,%xmm8 + DB 102,15,110,200 ; movd %eax,%xmm1 DB 184,171,170,42,62 ; mov $0x3e2aaaab,%eax - DB 15,40,247 ; movaps %xmm7,%xmm6 - DB 65,15,92,240 ; subps %xmm8,%xmm6 - DB 15,89,53,230,43,0,0 ; mulps 0x2be6(%rip),%xmm6 # 3d50 <_sk_callback_sse41+0x36e> DB 185,171,170,42,63 ; mov $0x3f2aaaab,%ecx - DB 102,15,110,193 ; movd %ecx,%xmm0 - DB 15,198,192,0 ; shufps $0x0,%xmm0,%xmm0 - DB 15,41,68,36,16 ; movaps %xmm0,0x10(%rsp) - DB 15,40,37,221,43,0,0 ; movaps 0x2bdd(%rip),%xmm4 # 3d60 <_sk_callback_sse41+0x37e> + DB 102,68,15,110,241 ; movd %ecx,%xmm14 + DB 15,198,201,0 ; shufps $0x0,%xmm1,%xmm1 + DB 15,40,218 ; movaps %xmm2,%xmm3 + DB 15,40,195 ; movaps %xmm3,%xmm0 + DB 15,194,193,1 ; cmpltps %xmm1,%xmm0 + DB 15,41,76,36,32 ; movaps %xmm1,0x20(%rsp) + DB 15,41,44,36 ; movaps %xmm5,(%rsp) + DB 68,15,40,253 ; movaps %xmm5,%xmm15 + DB 15,89,235 ; mulps %xmm3,%xmm5 + DB 68,15,92,253 ; subps %xmm5,%xmm15 + DB 102,68,15,56,20,253 ; blendvps %xmm0,%xmm5,%xmm15 + DB 68,15,88,251 ; addps %xmm3,%xmm15 + DB 68,15,40,195 ; movaps %xmm3,%xmm8 + DB 15,41,92,36,16 ; movaps %xmm3,0x10(%rsp) + DB 69,15,88,192 ; addps %xmm8,%xmm8 + DB 69,15,92,199 ; subps %xmm15,%xmm8 + DB 15,40,5,100,43,0,0 ; movaps 0x2b64(%rip),%xmm0 # 3c60 <_sk_callback_sse41+0x33d> + DB 65,15,88,194 ; addps %xmm10,%xmm0 + DB 102,15,58,8,208,1 ; roundps $0x1,%xmm0,%xmm2 + DB 15,92,194 ; subps %xmm2,%xmm0 + DB 65,15,40,255 ; movaps %xmm15,%xmm7 + DB 65,15,92,248 ; subps %xmm8,%xmm7 + DB 15,40,53,88,43,0,0 ; movaps 0x2b58(%rip),%xmm6 # 3c70 <_sk_callback_sse41+0x34d> + DB 68,15,40,232 ; movaps %xmm0,%xmm13 + DB 68,15,89,238 ; mulps %xmm6,%xmm13 + DB 69,15,198,246,0 ; shufps $0x0,%xmm14,%xmm14 + DB 68,15,40,216 ; movaps %xmm0,%xmm11 + DB 68,15,40,224 ; movaps %xmm0,%xmm12 + DB 65,15,194,198,1 ; cmpltps %xmm14,%xmm0 + DB 15,40,37,71,43,0,0 ; movaps 0x2b47(%rip),%xmm4 # 3c80 <_sk_callback_sse41+0x35d> DB 15,40,236 ; movaps %xmm4,%xmm5 - DB 65,15,92,236 ; subps %xmm12,%xmm5 - DB 69,15,40,236 ; movaps %xmm12,%xmm13 - DB 69,15,40,252 ; movaps %xmm12,%xmm15 - DB 69,15,40,244 ; movaps %xmm12,%xmm14 - DB 68,15,194,224,1 ; cmpltps %xmm0,%xmm12 - DB 15,89,238 ; mulps %xmm6,%xmm5 + DB 65,15,92,237 ; subps %xmm13,%xmm5 + DB 15,89,239 ; mulps %xmm7,%xmm5 DB 65,15,88,232 ; addps %xmm8,%xmm5 - DB 69,15,40,208 ; movaps %xmm8,%xmm10 + DB 69,15,40,200 ; movaps %xmm8,%xmm9 + DB 102,68,15,56,20,205 ; blendvps %xmm0,%xmm5,%xmm9 + DB 68,15,194,225,1 ; cmpltps %xmm1,%xmm12 DB 65,15,40,196 ; movaps %xmm12,%xmm0 - DB 102,68,15,56,20,213 ; blendvps %xmm0,%xmm5,%xmm10 - DB 68,15,194,52,36,1 ; cmpltps (%rsp),%xmm14 - DB 65,15,40,198 ; movaps %xmm14,%xmm0 - DB 102,68,15,56,20,215 ; blendvps %xmm0,%xmm7,%xmm10 + DB 102,69,15,56,20,207 ; blendvps %xmm0,%xmm15,%xmm9 DB 102,15,110,232 ; movd %eax,%xmm5 DB 15,198,237,0 ; shufps $0x0,%xmm5,%xmm5 - DB 68,15,194,237,1 ; cmpltps %xmm5,%xmm13 - DB 68,15,89,254 ; mulps %xmm6,%xmm15 - DB 69,15,88,248 ; addps %xmm8,%xmm15 - DB 65,15,40,197 ; movaps %xmm13,%xmm0 - DB 102,69,15,56,20,215 ; blendvps %xmm0,%xmm15,%xmm10 - DB 69,15,87,228 ; xorps %xmm12,%xmm12 - DB 68,15,194,225,0 ; cmpeqps %xmm1,%xmm12 - DB 65,15,40,196 ; movaps %xmm12,%xmm0 - DB 102,68,15,56,20,210 ; blendvps %xmm0,%xmm2,%xmm10 - DB 65,15,40,193 ; movaps %xmm9,%xmm0 - DB 65,15,194,195,1 ; cmpltps %xmm11,%xmm0 - DB 65,15,40,203 ; movaps %xmm11,%xmm1 - DB 15,88,13,58,43,0,0 ; addps 0x2b3a(%rip),%xmm1 # 3d40 <_sk_callback_sse41+0x35e> - DB 69,15,40,235 ; movaps %xmm11,%xmm13 - DB 102,68,15,56,20,233 ; blendvps %xmm0,%xmm1,%xmm13 + DB 68,15,194,221,1 ; cmpltps %xmm5,%xmm11 + DB 68,15,89,239 ; mulps %xmm7,%xmm13 + DB 69,15,88,232 ; addps %xmm8,%xmm13 DB 65,15,40,195 ; movaps %xmm11,%xmm0 - DB 15,194,68,36,32,1 ; cmpltps 0x20(%rsp),%xmm0 - DB 65,15,40,203 ; movaps %xmm11,%xmm1 - DB 15,88,13,251,42,0,0 ; addps 0x2afb(%rip),%xmm1 # 3d20 <_sk_callback_sse41+0x33e> - DB 102,68,15,56,20,233 ; blendvps %xmm0,%xmm1,%xmm13 + DB 102,69,15,56,20,205 ; blendvps %xmm0,%xmm13,%xmm9 + DB 69,15,87,219 ; xorps %xmm11,%xmm11 + DB 68,15,194,28,36,0 ; cmpeqps (%rsp),%xmm11 + DB 65,15,40,195 ; movaps %xmm11,%xmm0 + DB 102,68,15,56,20,203 ; blendvps %xmm0,%xmm3,%xmm9 + DB 102,65,15,58,8,202,1 ; roundps $0x1,%xmm10,%xmm1 + DB 65,15,40,194 ; movaps %xmm10,%xmm0 + DB 15,92,193 ; subps %xmm1,%xmm0 + DB 15,40,200 ; movaps %xmm0,%xmm1 + DB 15,89,206 ; mulps %xmm6,%xmm1 DB 15,40,220 ; movaps %xmm4,%xmm3 - DB 65,15,92,221 ; subps %xmm13,%xmm3 - DB 65,15,40,213 ; movaps %xmm13,%xmm2 - DB 69,15,40,245 ; movaps %xmm13,%xmm14 - DB 69,15,40,253 ; movaps %xmm13,%xmm15 - DB 68,15,194,108,36,16,1 ; cmpltps 0x10(%rsp),%xmm13 - DB 15,89,222 ; mulps %xmm6,%xmm3 + DB 15,92,217 ; subps %xmm1,%xmm3 + DB 68,15,40,224 ; movaps %xmm0,%xmm12 + DB 68,15,40,232 ; movaps %xmm0,%xmm13 + DB 65,15,194,198,1 ; cmpltps %xmm14,%xmm0 + DB 15,89,223 ; mulps %xmm7,%xmm3 DB 65,15,88,216 ; addps %xmm8,%xmm3 - DB 65,15,40,200 ; movaps %xmm8,%xmm1 + DB 65,15,40,208 ; movaps %xmm8,%xmm2 + DB 102,15,56,20,211 ; blendvps %xmm0,%xmm3,%xmm2 + DB 15,40,92,36,32 ; movaps 0x20(%rsp),%xmm3 + DB 68,15,194,235,1 ; cmpltps %xmm3,%xmm13 DB 65,15,40,197 ; movaps %xmm13,%xmm0 - DB 102,15,56,20,203 ; blendvps %xmm0,%xmm3,%xmm1 - DB 68,15,194,60,36,1 ; cmpltps (%rsp),%xmm15 - DB 65,15,40,199 ; movaps %xmm15,%xmm0 - DB 102,15,56,20,207 ; blendvps %xmm0,%xmm7,%xmm1 - DB 15,194,213,1 ; cmpltps %xmm5,%xmm2 - DB 68,15,89,246 ; mulps %xmm6,%xmm14 - DB 69,15,88,240 ; addps %xmm8,%xmm14 - DB 15,40,194 ; movaps %xmm2,%xmm0 - DB 102,65,15,56,20,206 ; blendvps %xmm0,%xmm14,%xmm1 + DB 102,65,15,56,20,215 ; blendvps %xmm0,%xmm15,%xmm2 + DB 68,15,194,229,1 ; cmpltps %xmm5,%xmm12 + DB 15,89,207 ; mulps %xmm7,%xmm1 + DB 65,15,88,200 ; addps %xmm8,%xmm1 DB 65,15,40,196 ; movaps %xmm12,%xmm0 - DB 68,15,40,116,36,48 ; movaps 0x30(%rsp),%xmm14 - DB 102,65,15,56,20,206 ; blendvps %xmm0,%xmm14,%xmm1 - DB 68,15,88,29,219,42,0,0 ; addps 0x2adb(%rip),%xmm11 # 3d70 <_sk_callback_sse41+0x38e> - DB 15,40,21,132,42,0,0 ; movaps 0x2a84(%rip),%xmm2 # 3d20 <_sk_callback_sse41+0x33e> - DB 65,15,88,211 ; addps %xmm11,%xmm2 - DB 69,15,194,203,1 ; cmpltps %xmm11,%xmm9 - DB 15,40,29,148,42,0,0 ; movaps 0x2a94(%rip),%xmm3 # 3d40 <_sk_callback_sse41+0x35e> - DB 65,15,88,219 ; addps %xmm11,%xmm3 - DB 69,15,40,235 ; movaps %xmm11,%xmm13 - DB 65,15,40,193 ; movaps %xmm9,%xmm0 - DB 102,68,15,56,20,219 ; blendvps %xmm0,%xmm3,%xmm11 - DB 68,15,194,108,36,32,1 ; cmpltps 0x20(%rsp),%xmm13 - DB 65,15,40,197 ; movaps %xmm13,%xmm0 - DB 102,68,15,56,20,218 ; blendvps %xmm0,%xmm2,%xmm11 - DB 65,15,92,227 ; subps %xmm11,%xmm4 - DB 69,15,40,203 ; movaps %xmm11,%xmm9 - DB 65,15,40,211 ; movaps %xmm11,%xmm2 - DB 69,15,40,235 ; movaps %xmm11,%xmm13 - DB 68,15,194,92,36,16,1 ; cmpltps 0x10(%rsp),%xmm11 - DB 15,89,214 ; mulps %xmm6,%xmm2 - DB 15,89,230 ; mulps %xmm6,%xmm4 - DB 65,15,88,208 ; addps %xmm8,%xmm2 - DB 65,15,88,224 ; addps %xmm8,%xmm4 + DB 102,15,56,20,209 ; blendvps %xmm0,%xmm1,%xmm2 DB 65,15,40,195 ; movaps %xmm11,%xmm0 + DB 15,40,76,36,16 ; movaps 0x10(%rsp),%xmm1 + DB 102,15,56,20,209 ; blendvps %xmm0,%xmm1,%xmm2 + DB 68,15,88,21,135,42,0,0 ; addps 0x2a87(%rip),%xmm10 # 3c90 <_sk_callback_sse41+0x36d> + DB 102,65,15,58,8,194,1 ; roundps $0x1,%xmm10,%xmm0 + DB 68,15,92,208 ; subps %xmm0,%xmm10 + DB 65,15,89,242 ; mulps %xmm10,%xmm6 + DB 69,15,40,226 ; movaps %xmm10,%xmm12 + DB 69,15,40,234 ; movaps %xmm10,%xmm13 + DB 69,15,194,214,1 ; cmpltps %xmm14,%xmm10 + DB 15,92,230 ; subps %xmm6,%xmm4 + DB 15,89,247 ; mulps %xmm7,%xmm6 + DB 15,89,231 ; mulps %xmm7,%xmm4 + DB 65,15,88,240 ; addps %xmm8,%xmm6 + DB 65,15,88,224 ; addps %xmm8,%xmm4 + DB 65,15,40,194 ; movaps %xmm10,%xmm0 DB 102,68,15,56,20,196 ; blendvps %xmm0,%xmm4,%xmm8 - DB 68,15,194,44,36,1 ; cmpltps (%rsp),%xmm13 + DB 68,15,194,235,1 ; cmpltps %xmm3,%xmm13 DB 65,15,40,197 ; movaps %xmm13,%xmm0 - DB 102,68,15,56,20,199 ; blendvps %xmm0,%xmm7,%xmm8 - DB 68,15,194,205,1 ; cmpltps %xmm5,%xmm9 - DB 65,15,40,193 ; movaps %xmm9,%xmm0 - DB 102,68,15,56,20,194 ; blendvps %xmm0,%xmm2,%xmm8 + DB 102,69,15,56,20,199 ; blendvps %xmm0,%xmm15,%xmm8 + DB 68,15,194,229,1 ; cmpltps %xmm5,%xmm12 DB 65,15,40,196 ; movaps %xmm12,%xmm0 - DB 102,69,15,56,20,198 ; blendvps %xmm0,%xmm14,%xmm8 + DB 102,68,15,56,20,198 ; blendvps %xmm0,%xmm6,%xmm8 + DB 65,15,40,195 ; movaps %xmm11,%xmm0 + DB 102,68,15,56,20,193 ; blendvps %xmm0,%xmm1,%xmm8 DB 72,173 ; lods %ds:(%rsi),%rax - DB 65,15,40,194 ; movaps %xmm10,%xmm0 + DB 65,15,40,193 ; movaps %xmm9,%xmm0 + DB 15,40,202 ; movaps %xmm2,%xmm1 DB 65,15,40,208 ; movaps %xmm8,%xmm2 - DB 15,40,92,36,64 ; movaps 0x40(%rsp),%xmm3 - DB 15,40,100,36,80 ; movaps 0x50(%rsp),%xmm4 - DB 15,40,108,36,96 ; movaps 0x60(%rsp),%xmm5 - DB 15,40,116,36,112 ; movaps 0x70(%rsp),%xmm6 - DB 15,40,188,36,128,0,0,0 ; movaps 0x80(%rsp),%xmm7 - DB 72,129,196,152,0,0,0 ; add $0x98,%rsp + DB 15,40,92,36,48 ; movaps 0x30(%rsp),%xmm3 + DB 15,40,100,36,64 ; movaps 0x40(%rsp),%xmm4 + DB 15,40,108,36,80 ; movaps 0x50(%rsp),%xmm5 + DB 15,40,116,36,96 ; movaps 0x60(%rsp),%xmm6 + DB 15,40,124,36,112 ; movaps 0x70(%rsp),%xmm7 + DB 72,129,196,136,0,0,0 ; add $0x88,%rsp DB 255,224 ; jmpq *%rax PUBLIC _sk_scale_1_float_sse41 @@ -11162,7 +11072,7 @@ _sk_scale_u8_sse41 LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 102,68,15,56,49,4,56 ; pmovzxbd (%rax,%rdi,1),%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,242,41,0,0 ; mulps 0x29f2(%rip),%xmm8 # 3d80 <_sk_callback_sse41+0x39e> + DB 68,15,89,5,209,41,0,0 ; mulps 0x29d1(%rip),%xmm8 # 3ca0 <_sk_callback_sse41+0x37d> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 65,15,89,208 ; mulps %xmm8,%xmm2 @@ -11196,7 +11106,7 @@ _sk_lerp_u8_sse41 LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 102,68,15,56,49,4,56 ; pmovzxbd (%rax,%rdi,1),%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,158,41,0,0 ; mulps 0x299e(%rip),%xmm8 # 3d90 <_sk_callback_sse41+0x3ae> + DB 68,15,89,5,125,41,0,0 ; mulps 0x297d(%rip),%xmm8 # 3cb0 <_sk_callback_sse41+0x38d> DB 15,92,196 ; subps %xmm4,%xmm0 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -11217,17 +11127,17 @@ _sk_lerp_565_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 102,68,15,56,51,4,120 ; pmovzxwd (%rax,%rdi,2),%xmm8 - DB 102,15,111,29,110,41,0,0 ; movdqa 0x296e(%rip),%xmm3 # 3da0 <_sk_callback_sse41+0x3be> + DB 102,15,111,29,77,41,0,0 ; movdqa 0x294d(%rip),%xmm3 # 3cc0 <_sk_callback_sse41+0x39d> DB 102,65,15,219,216 ; pand %xmm8,%xmm3 DB 68,15,91,203 ; cvtdq2ps %xmm3,%xmm9 - DB 68,15,89,13,109,41,0,0 ; mulps 0x296d(%rip),%xmm9 # 3db0 <_sk_callback_sse41+0x3ce> - DB 102,15,111,29,117,41,0,0 ; movdqa 0x2975(%rip),%xmm3 # 3dc0 <_sk_callback_sse41+0x3de> + DB 68,15,89,13,76,41,0,0 ; mulps 0x294c(%rip),%xmm9 # 3cd0 <_sk_callback_sse41+0x3ad> + DB 102,15,111,29,84,41,0,0 ; movdqa 0x2954(%rip),%xmm3 # 3ce0 <_sk_callback_sse41+0x3bd> DB 102,65,15,219,216 ; pand %xmm8,%xmm3 DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,118,41,0,0 ; mulps 0x2976(%rip),%xmm3 # 3dd0 <_sk_callback_sse41+0x3ee> - DB 102,68,15,219,5,125,41,0,0 ; pand 0x297d(%rip),%xmm8 # 3de0 <_sk_callback_sse41+0x3fe> + DB 15,89,29,85,41,0,0 ; mulps 0x2955(%rip),%xmm3 # 3cf0 <_sk_callback_sse41+0x3cd> + DB 102,68,15,219,5,92,41,0,0 ; pand 0x295c(%rip),%xmm8 # 3d00 <_sk_callback_sse41+0x3dd> DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,129,41,0,0 ; mulps 0x2981(%rip),%xmm8 # 3df0 <_sk_callback_sse41+0x40e> + DB 68,15,89,5,96,41,0,0 ; mulps 0x2960(%rip),%xmm8 # 3d10 <_sk_callback_sse41+0x3ed> DB 15,92,196 ; subps %xmm4,%xmm0 DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -11238,7 +11148,7 @@ _sk_lerp_565_sse41 LABEL PROC DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 15,88,214 ; addps %xmm6,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,107,41,0,0 ; movaps 0x296b(%rip),%xmm3 # 3e00 <_sk_callback_sse41+0x41e> + DB 15,40,29,74,41,0,0 ; movaps 0x294a(%rip),%xmm3 # 3d20 <_sk_callback_sse41+0x3fd> DB 255,224 ; jmpq *%rax PUBLIC _sk_load_tables_sse41 @@ -11247,7 +11157,7 @@ _sk_load_tables_sse41 LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 76,139,72,8 ; mov 0x8(%rax),%r9 DB 243,69,15,111,4,184 ; movdqu (%r8,%rdi,4),%xmm8 - DB 102,15,111,5,98,41,0,0 ; movdqa 0x2962(%rip),%xmm0 # 3e10 <_sk_callback_sse41+0x42e> + DB 102,15,111,5,65,41,0,0 ; movdqa 0x2941(%rip),%xmm0 # 3d30 <_sk_callback_sse41+0x40d> DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,73,15,58,22,192,1 ; pextrq $0x1,%xmm0,%r8 DB 102,72,15,126,193 ; movq %xmm0,%rcx @@ -11262,7 +11172,7 @@ _sk_load_tables_sse41 LABEL PROC DB 102,15,58,33,193,48 ; insertps $0x30,%xmm1,%xmm0 DB 76,139,64,16 ; mov 0x10(%rax),%r8 DB 102,65,15,111,200 ; movdqa %xmm8,%xmm1 - DB 102,15,56,0,13,29,41,0,0 ; pshufb 0x291d(%rip),%xmm1 # 3e20 <_sk_callback_sse41+0x43e> + DB 102,15,56,0,13,252,40,0,0 ; pshufb 0x28fc(%rip),%xmm1 # 3d40 <_sk_callback_sse41+0x41d> DB 102,73,15,58,22,201,1 ; pextrq $0x1,%xmm1,%r9 DB 102,72,15,126,201 ; movq %xmm1,%rcx DB 68,15,182,209 ; movzbl %cl,%r10d @@ -11277,7 +11187,7 @@ _sk_load_tables_sse41 LABEL PROC DB 102,15,58,33,202,48 ; insertps $0x30,%xmm2,%xmm1 DB 76,139,64,24 ; mov 0x18(%rax),%r8 DB 102,65,15,111,208 ; movdqa %xmm8,%xmm2 - DB 102,15,56,0,21,217,40,0,0 ; pshufb 0x28d9(%rip),%xmm2 # 3e30 <_sk_callback_sse41+0x44e> + DB 102,15,56,0,21,184,40,0,0 ; pshufb 0x28b8(%rip),%xmm2 # 3d50 <_sk_callback_sse41+0x42d> DB 102,72,15,58,22,209,1 ; pextrq $0x1,%xmm2,%rcx DB 102,72,15,126,208 ; movq %xmm2,%rax DB 68,15,182,200 ; movzbl %al,%r9d @@ -11292,7 +11202,7 @@ _sk_load_tables_sse41 LABEL PROC DB 102,15,58,33,211,48 ; insertps $0x30,%xmm3,%xmm2 DB 102,65,15,114,208,24 ; psrld $0x18,%xmm8 DB 65,15,91,216 ; cvtdq2ps %xmm8,%xmm3 - DB 15,89,29,150,40,0,0 ; mulps 0x2896(%rip),%xmm3 # 3e40 <_sk_callback_sse41+0x45e> + DB 15,89,29,117,40,0,0 ; mulps 0x2875(%rip),%xmm3 # 3d60 <_sk_callback_sse41+0x43d> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -11309,7 +11219,7 @@ _sk_load_tables_u16_be_sse41 LABEL PROC DB 102,65,15,111,201 ; movdqa %xmm9,%xmm1 DB 102,15,97,200 ; punpcklwd %xmm0,%xmm1 DB 102,68,15,105,200 ; punpckhwd %xmm0,%xmm9 - DB 102,68,15,111,5,105,40,0,0 ; movdqa 0x2869(%rip),%xmm8 # 3e50 <_sk_callback_sse41+0x46e> + DB 102,68,15,111,5,72,40,0,0 ; movdqa 0x2848(%rip),%xmm8 # 3d70 <_sk_callback_sse41+0x44d> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,15,56,51,192 ; pmovzxwd %xmm0,%xmm0 @@ -11326,7 +11236,7 @@ _sk_load_tables_u16_be_sse41 LABEL PROC DB 243,67,15,16,20,8 ; movss (%r8,%r9,1),%xmm2 DB 102,15,58,33,194,48 ; insertps $0x30,%xmm2,%xmm0 DB 76,139,64,16 ; mov 0x10(%rax),%r8 - DB 102,15,56,0,13,28,40,0,0 ; pshufb 0x281c(%rip),%xmm1 # 3e60 <_sk_callback_sse41+0x47e> + DB 102,15,56,0,13,251,39,0,0 ; pshufb 0x27fb(%rip),%xmm1 # 3d80 <_sk_callback_sse41+0x45d> DB 102,15,56,51,201 ; pmovzxwd %xmm1,%xmm1 DB 102,73,15,58,22,201,1 ; pextrq $0x1,%xmm1,%r9 DB 102,72,15,126,201 ; movq %xmm1,%rcx @@ -11362,7 +11272,7 @@ _sk_load_tables_u16_be_sse41 LABEL PROC DB 102,65,15,235,216 ; por %xmm8,%xmm3 DB 102,15,56,51,219 ; pmovzxwd %xmm3,%xmm3 DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,106,39,0,0 ; mulps 0x276a(%rip),%xmm3 # 3e70 <_sk_callback_sse41+0x48e> + DB 15,89,29,73,39,0,0 ; mulps 0x2749(%rip),%xmm3 # 3d90 <_sk_callback_sse41+0x46d> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -11382,7 +11292,7 @@ _sk_load_tables_rgb_u16_be_sse41 LABEL PROC DB 102,68,15,97,200 ; punpcklwd %xmm0,%xmm9 DB 102,15,111,202 ; movdqa %xmm2,%xmm1 DB 102,65,15,97,201 ; punpcklwd %xmm9,%xmm1 - DB 102,68,15,111,5,44,39,0,0 ; movdqa 0x272c(%rip),%xmm8 # 3e80 <_sk_callback_sse41+0x49e> + DB 102,68,15,111,5,11,39,0,0 ; movdqa 0x270b(%rip),%xmm8 # 3da0 <_sk_callback_sse41+0x47d> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,15,56,51,192 ; pmovzxwd %xmm0,%xmm0 @@ -11399,7 +11309,7 @@ _sk_load_tables_rgb_u16_be_sse41 LABEL PROC DB 243,67,15,16,28,8 ; movss (%r8,%r9,1),%xmm3 DB 102,15,58,33,195,48 ; insertps $0x30,%xmm3,%xmm0 DB 76,139,64,16 ; mov 0x10(%rax),%r8 - DB 102,15,56,0,13,223,38,0,0 ; pshufb 0x26df(%rip),%xmm1 # 3e90 <_sk_callback_sse41+0x4ae> + DB 102,15,56,0,13,190,38,0,0 ; pshufb 0x26be(%rip),%xmm1 # 3db0 <_sk_callback_sse41+0x48d> DB 102,15,56,51,201 ; pmovzxwd %xmm1,%xmm1 DB 102,73,15,58,22,201,1 ; pextrq $0x1,%xmm1,%r9 DB 102,72,15,126,201 ; movq %xmm1,%rcx @@ -11430,7 +11340,7 @@ _sk_load_tables_rgb_u16_be_sse41 LABEL PROC DB 243,65,15,16,28,8 ; movss (%r8,%rcx,1),%xmm3 DB 102,15,58,33,211,48 ; insertps $0x30,%xmm3,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,74,38,0,0 ; movaps 0x264a(%rip),%xmm3 # 3ea0 <_sk_callback_sse41+0x4be> + DB 15,40,29,41,38,0,0 ; movaps 0x2629(%rip),%xmm3 # 3dc0 <_sk_callback_sse41+0x49d> DB 255,224 ; jmpq *%rax PUBLIC _sk_byte_tables_sse41 @@ -11438,7 +11348,7 @@ _sk_byte_tables_sse41 LABEL PROC DB 65,86 ; push %r14 DB 83 ; push %rbx DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,75,38,0,0 ; movaps 0x264b(%rip),%xmm8 # 3eb0 <_sk_callback_sse41+0x4ce> + DB 68,15,40,5,42,38,0,0 ; movaps 0x262a(%rip),%xmm8 # 3dd0 <_sk_callback_sse41+0x4ad> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,91,192 ; cvtps2dq %xmm0,%xmm0 DB 102,72,15,58,22,193,1 ; pextrq $0x1,%xmm0,%rcx @@ -11457,7 +11367,7 @@ _sk_byte_tables_sse41 LABEL PROC DB 102,15,58,32,193,3 ; pinsrb $0x3,%ecx,%xmm0 DB 102,15,56,49,192 ; pmovzxbd %xmm0,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,13,252,37,0,0 ; movaps 0x25fc(%rip),%xmm9 # 3ec0 <_sk_callback_sse41+0x4de> + DB 68,15,40,13,219,37,0,0 ; movaps 0x25db(%rip),%xmm9 # 3de0 <_sk_callback_sse41+0x4bd> DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,91,201 ; cvtps2dq %xmm1,%xmm1 @@ -11546,7 +11456,7 @@ _sk_byte_tables_rgb_sse41 LABEL PROC DB 102,15,58,32,193,3 ; pinsrb $0x3,%ecx,%xmm0 DB 102,15,56,49,192 ; pmovzxbd %xmm0,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,13,132,36,0,0 ; movaps 0x2484(%rip),%xmm9 # 3ed0 <_sk_callback_sse41+0x4ee> + DB 68,15,40,13,99,36,0,0 ; movaps 0x2463(%rip),%xmm9 # 3df0 <_sk_callback_sse41+0x4cd> DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,91,201 ; cvtps2dq %xmm1,%xmm1 @@ -11713,31 +11623,31 @@ _sk_parametric_r_sse41 LABEL PROC DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,194 ; cvtdq2ps %xmm10,%xmm8 - DB 68,15,89,5,219,33,0,0 ; mulps 0x21db(%rip),%xmm8 # 3ee0 <_sk_callback_sse41+0x4fe> - DB 68,15,84,21,227,33,0,0 ; andps 0x21e3(%rip),%xmm10 # 3ef0 <_sk_callback_sse41+0x50e> - DB 68,15,86,21,235,33,0,0 ; orps 0x21eb(%rip),%xmm10 # 3f00 <_sk_callback_sse41+0x51e> - DB 68,15,88,5,243,33,0,0 ; addps 0x21f3(%rip),%xmm8 # 3f10 <_sk_callback_sse41+0x52e> - DB 68,15,40,37,251,33,0,0 ; movaps 0x21fb(%rip),%xmm12 # 3f20 <_sk_callback_sse41+0x53e> + DB 68,15,89,5,186,33,0,0 ; mulps 0x21ba(%rip),%xmm8 # 3e00 <_sk_callback_sse41+0x4dd> + DB 68,15,84,21,194,33,0,0 ; andps 0x21c2(%rip),%xmm10 # 3e10 <_sk_callback_sse41+0x4ed> + DB 68,15,86,21,202,33,0,0 ; orps 0x21ca(%rip),%xmm10 # 3e20 <_sk_callback_sse41+0x4fd> + DB 68,15,88,5,210,33,0,0 ; addps 0x21d2(%rip),%xmm8 # 3e30 <_sk_callback_sse41+0x50d> + DB 68,15,40,37,218,33,0,0 ; movaps 0x21da(%rip),%xmm12 # 3e40 <_sk_callback_sse41+0x51d> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,196 ; subps %xmm12,%xmm8 - DB 68,15,88,21,251,33,0,0 ; addps 0x21fb(%rip),%xmm10 # 3f30 <_sk_callback_sse41+0x54e> - DB 68,15,40,37,3,34,0,0 ; movaps 0x2203(%rip),%xmm12 # 3f40 <_sk_callback_sse41+0x55e> + DB 68,15,88,21,218,33,0,0 ; addps 0x21da(%rip),%xmm10 # 3e50 <_sk_callback_sse41+0x52d> + DB 68,15,40,37,226,33,0,0 ; movaps 0x21e2(%rip),%xmm12 # 3e60 <_sk_callback_sse41+0x53d> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,196 ; subps %xmm12,%xmm8 DB 69,15,89,195 ; mulps %xmm11,%xmm8 DB 102,69,15,58,8,208,1 ; roundps $0x1,%xmm8,%xmm10 DB 69,15,40,216 ; movaps %xmm8,%xmm11 DB 69,15,92,218 ; subps %xmm10,%xmm11 - DB 68,15,88,5,240,33,0,0 ; addps 0x21f0(%rip),%xmm8 # 3f50 <_sk_callback_sse41+0x56e> - DB 68,15,40,21,248,33,0,0 ; movaps 0x21f8(%rip),%xmm10 # 3f60 <_sk_callback_sse41+0x57e> + DB 68,15,88,5,207,33,0,0 ; addps 0x21cf(%rip),%xmm8 # 3e70 <_sk_callback_sse41+0x54d> + DB 68,15,40,21,215,33,0,0 ; movaps 0x21d7(%rip),%xmm10 # 3e80 <_sk_callback_sse41+0x55d> DB 69,15,89,211 ; mulps %xmm11,%xmm10 DB 69,15,92,194 ; subps %xmm10,%xmm8 - DB 68,15,40,21,248,33,0,0 ; movaps 0x21f8(%rip),%xmm10 # 3f70 <_sk_callback_sse41+0x58e> + DB 68,15,40,21,215,33,0,0 ; movaps 0x21d7(%rip),%xmm10 # 3e90 <_sk_callback_sse41+0x56d> DB 69,15,92,211 ; subps %xmm11,%xmm10 - DB 68,15,40,29,252,33,0,0 ; movaps 0x21fc(%rip),%xmm11 # 3f80 <_sk_callback_sse41+0x59e> + DB 68,15,40,29,219,33,0,0 ; movaps 0x21db(%rip),%xmm11 # 3ea0 <_sk_callback_sse41+0x57d> DB 69,15,94,218 ; divps %xmm10,%xmm11 DB 69,15,88,216 ; addps %xmm8,%xmm11 - DB 68,15,89,29,252,33,0,0 ; mulps 0x21fc(%rip),%xmm11 # 3f90 <_sk_callback_sse41+0x5ae> + DB 68,15,89,29,219,33,0,0 ; mulps 0x21db(%rip),%xmm11 # 3eb0 <_sk_callback_sse41+0x58d> DB 102,69,15,91,211 ; cvtps2dq %xmm11,%xmm10 DB 243,68,15,16,64,20 ; movss 0x14(%rax),%xmm8 DB 69,15,198,192,0 ; shufps $0x0,%xmm8,%xmm8 @@ -11745,7 +11655,7 @@ _sk_parametric_r_sse41 LABEL PROC DB 102,69,15,56,20,193 ; blendvps %xmm0,%xmm9,%xmm8 DB 15,87,192 ; xorps %xmm0,%xmm0 DB 68,15,95,192 ; maxps %xmm0,%xmm8 - DB 68,15,93,5,227,33,0,0 ; minps 0x21e3(%rip),%xmm8 # 3fa0 <_sk_callback_sse41+0x5be> + DB 68,15,93,5,194,33,0,0 ; minps 0x21c2(%rip),%xmm8 # 3ec0 <_sk_callback_sse41+0x59d> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -11773,31 +11683,31 @@ _sk_parametric_g_sse41 LABEL PROC DB 68,15,88,217 ; addps %xmm1,%xmm11 DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 DB 69,15,91,227 ; cvtdq2ps %xmm11,%xmm12 - DB 68,15,89,37,132,33,0,0 ; mulps 0x2184(%rip),%xmm12 # 3fb0 <_sk_callback_sse41+0x5ce> - DB 68,15,84,29,140,33,0,0 ; andps 0x218c(%rip),%xmm11 # 3fc0 <_sk_callback_sse41+0x5de> - DB 68,15,86,29,148,33,0,0 ; orps 0x2194(%rip),%xmm11 # 3fd0 <_sk_callback_sse41+0x5ee> - DB 68,15,88,37,156,33,0,0 ; addps 0x219c(%rip),%xmm12 # 3fe0 <_sk_callback_sse41+0x5fe> - DB 15,40,13,165,33,0,0 ; movaps 0x21a5(%rip),%xmm1 # 3ff0 <_sk_callback_sse41+0x60e> + DB 68,15,89,37,99,33,0,0 ; mulps 0x2163(%rip),%xmm12 # 3ed0 <_sk_callback_sse41+0x5ad> + DB 68,15,84,29,107,33,0,0 ; andps 0x216b(%rip),%xmm11 # 3ee0 <_sk_callback_sse41+0x5bd> + DB 68,15,86,29,115,33,0,0 ; orps 0x2173(%rip),%xmm11 # 3ef0 <_sk_callback_sse41+0x5cd> + DB 68,15,88,37,123,33,0,0 ; addps 0x217b(%rip),%xmm12 # 3f00 <_sk_callback_sse41+0x5dd> + DB 15,40,13,132,33,0,0 ; movaps 0x2184(%rip),%xmm1 # 3f10 <_sk_callback_sse41+0x5ed> DB 65,15,89,203 ; mulps %xmm11,%xmm1 DB 68,15,92,225 ; subps %xmm1,%xmm12 - DB 68,15,88,29,165,33,0,0 ; addps 0x21a5(%rip),%xmm11 # 4000 <_sk_callback_sse41+0x61e> - DB 15,40,13,174,33,0,0 ; movaps 0x21ae(%rip),%xmm1 # 4010 <_sk_callback_sse41+0x62e> + DB 68,15,88,29,132,33,0,0 ; addps 0x2184(%rip),%xmm11 # 3f20 <_sk_callback_sse41+0x5fd> + DB 15,40,13,141,33,0,0 ; movaps 0x218d(%rip),%xmm1 # 3f30 <_sk_callback_sse41+0x60d> DB 65,15,94,203 ; divps %xmm11,%xmm1 DB 68,15,92,225 ; subps %xmm1,%xmm12 DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 102,69,15,58,8,212,1 ; roundps $0x1,%xmm12,%xmm10 DB 69,15,40,220 ; movaps %xmm12,%xmm11 DB 69,15,92,218 ; subps %xmm10,%xmm11 - DB 68,15,88,37,155,33,0,0 ; addps 0x219b(%rip),%xmm12 # 4020 <_sk_callback_sse41+0x63e> - DB 15,40,13,164,33,0,0 ; movaps 0x21a4(%rip),%xmm1 # 4030 <_sk_callback_sse41+0x64e> + DB 68,15,88,37,122,33,0,0 ; addps 0x217a(%rip),%xmm12 # 3f40 <_sk_callback_sse41+0x61d> + DB 15,40,13,131,33,0,0 ; movaps 0x2183(%rip),%xmm1 # 3f50 <_sk_callback_sse41+0x62d> DB 65,15,89,203 ; mulps %xmm11,%xmm1 DB 68,15,92,225 ; subps %xmm1,%xmm12 - DB 68,15,40,21,164,33,0,0 ; movaps 0x21a4(%rip),%xmm10 # 4040 <_sk_callback_sse41+0x65e> + DB 68,15,40,21,131,33,0,0 ; movaps 0x2183(%rip),%xmm10 # 3f60 <_sk_callback_sse41+0x63d> DB 69,15,92,211 ; subps %xmm11,%xmm10 - DB 15,40,13,169,33,0,0 ; movaps 0x21a9(%rip),%xmm1 # 4050 <_sk_callback_sse41+0x66e> + DB 15,40,13,136,33,0,0 ; movaps 0x2188(%rip),%xmm1 # 3f70 <_sk_callback_sse41+0x64d> DB 65,15,94,202 ; divps %xmm10,%xmm1 DB 65,15,88,204 ; addps %xmm12,%xmm1 - DB 15,89,13,170,33,0,0 ; mulps 0x21aa(%rip),%xmm1 # 4060 <_sk_callback_sse41+0x67e> + DB 15,89,13,137,33,0,0 ; mulps 0x2189(%rip),%xmm1 # 3f80 <_sk_callback_sse41+0x65d> DB 102,68,15,91,209 ; cvtps2dq %xmm1,%xmm10 DB 243,15,16,72,20 ; movss 0x14(%rax),%xmm1 DB 15,198,201,0 ; shufps $0x0,%xmm1,%xmm1 @@ -11805,7 +11715,7 @@ _sk_parametric_g_sse41 LABEL PROC DB 102,65,15,56,20,201 ; blendvps %xmm0,%xmm9,%xmm1 DB 15,87,192 ; xorps %xmm0,%xmm0 DB 15,95,200 ; maxps %xmm0,%xmm1 - DB 15,93,13,149,33,0,0 ; minps 0x2195(%rip),%xmm1 # 4070 <_sk_callback_sse41+0x68e> + DB 15,93,13,116,33,0,0 ; minps 0x2174(%rip),%xmm1 # 3f90 <_sk_callback_sse41+0x66d> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -11833,31 +11743,31 @@ _sk_parametric_b_sse41 LABEL PROC DB 68,15,88,218 ; addps %xmm2,%xmm11 DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 DB 69,15,91,227 ; cvtdq2ps %xmm11,%xmm12 - DB 68,15,89,37,54,33,0,0 ; mulps 0x2136(%rip),%xmm12 # 4080 <_sk_callback_sse41+0x69e> - DB 68,15,84,29,62,33,0,0 ; andps 0x213e(%rip),%xmm11 # 4090 <_sk_callback_sse41+0x6ae> - DB 68,15,86,29,70,33,0,0 ; orps 0x2146(%rip),%xmm11 # 40a0 <_sk_callback_sse41+0x6be> - DB 68,15,88,37,78,33,0,0 ; addps 0x214e(%rip),%xmm12 # 40b0 <_sk_callback_sse41+0x6ce> - DB 15,40,21,87,33,0,0 ; movaps 0x2157(%rip),%xmm2 # 40c0 <_sk_callback_sse41+0x6de> + DB 68,15,89,37,21,33,0,0 ; mulps 0x2115(%rip),%xmm12 # 3fa0 <_sk_callback_sse41+0x67d> + DB 68,15,84,29,29,33,0,0 ; andps 0x211d(%rip),%xmm11 # 3fb0 <_sk_callback_sse41+0x68d> + DB 68,15,86,29,37,33,0,0 ; orps 0x2125(%rip),%xmm11 # 3fc0 <_sk_callback_sse41+0x69d> + DB 68,15,88,37,45,33,0,0 ; addps 0x212d(%rip),%xmm12 # 3fd0 <_sk_callback_sse41+0x6ad> + DB 15,40,21,54,33,0,0 ; movaps 0x2136(%rip),%xmm2 # 3fe0 <_sk_callback_sse41+0x6bd> DB 65,15,89,211 ; mulps %xmm11,%xmm2 DB 68,15,92,226 ; subps %xmm2,%xmm12 - DB 68,15,88,29,87,33,0,0 ; addps 0x2157(%rip),%xmm11 # 40d0 <_sk_callback_sse41+0x6ee> - DB 15,40,21,96,33,0,0 ; movaps 0x2160(%rip),%xmm2 # 40e0 <_sk_callback_sse41+0x6fe> + DB 68,15,88,29,54,33,0,0 ; addps 0x2136(%rip),%xmm11 # 3ff0 <_sk_callback_sse41+0x6cd> + DB 15,40,21,63,33,0,0 ; movaps 0x213f(%rip),%xmm2 # 4000 <_sk_callback_sse41+0x6dd> DB 65,15,94,211 ; divps %xmm11,%xmm2 DB 68,15,92,226 ; subps %xmm2,%xmm12 DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 102,69,15,58,8,212,1 ; roundps $0x1,%xmm12,%xmm10 DB 69,15,40,220 ; movaps %xmm12,%xmm11 DB 69,15,92,218 ; subps %xmm10,%xmm11 - DB 68,15,88,37,77,33,0,0 ; addps 0x214d(%rip),%xmm12 # 40f0 <_sk_callback_sse41+0x70e> - DB 15,40,21,86,33,0,0 ; movaps 0x2156(%rip),%xmm2 # 4100 <_sk_callback_sse41+0x71e> + DB 68,15,88,37,44,33,0,0 ; addps 0x212c(%rip),%xmm12 # 4010 <_sk_callback_sse41+0x6ed> + DB 15,40,21,53,33,0,0 ; movaps 0x2135(%rip),%xmm2 # 4020 <_sk_callback_sse41+0x6fd> DB 65,15,89,211 ; mulps %xmm11,%xmm2 DB 68,15,92,226 ; subps %xmm2,%xmm12 - DB 68,15,40,21,86,33,0,0 ; movaps 0x2156(%rip),%xmm10 # 4110 <_sk_callback_sse41+0x72e> + DB 68,15,40,21,53,33,0,0 ; movaps 0x2135(%rip),%xmm10 # 4030 <_sk_callback_sse41+0x70d> DB 69,15,92,211 ; subps %xmm11,%xmm10 - DB 15,40,21,91,33,0,0 ; movaps 0x215b(%rip),%xmm2 # 4120 <_sk_callback_sse41+0x73e> + DB 15,40,21,58,33,0,0 ; movaps 0x213a(%rip),%xmm2 # 4040 <_sk_callback_sse41+0x71d> DB 65,15,94,210 ; divps %xmm10,%xmm2 DB 65,15,88,212 ; addps %xmm12,%xmm2 - DB 15,89,21,92,33,0,0 ; mulps 0x215c(%rip),%xmm2 # 4130 <_sk_callback_sse41+0x74e> + DB 15,89,21,59,33,0,0 ; mulps 0x213b(%rip),%xmm2 # 4050 <_sk_callback_sse41+0x72d> DB 102,68,15,91,210 ; cvtps2dq %xmm2,%xmm10 DB 243,15,16,80,20 ; movss 0x14(%rax),%xmm2 DB 15,198,210,0 ; shufps $0x0,%xmm2,%xmm2 @@ -11865,7 +11775,7 @@ _sk_parametric_b_sse41 LABEL PROC DB 102,65,15,56,20,209 ; blendvps %xmm0,%xmm9,%xmm2 DB 15,87,192 ; xorps %xmm0,%xmm0 DB 15,95,208 ; maxps %xmm0,%xmm2 - DB 15,93,21,71,33,0,0 ; minps 0x2147(%rip),%xmm2 # 4140 <_sk_callback_sse41+0x75e> + DB 15,93,21,38,33,0,0 ; minps 0x2126(%rip),%xmm2 # 4060 <_sk_callback_sse41+0x73d> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -11893,31 +11803,31 @@ _sk_parametric_a_sse41 LABEL PROC DB 68,15,88,219 ; addps %xmm3,%xmm11 DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 DB 69,15,91,227 ; cvtdq2ps %xmm11,%xmm12 - DB 68,15,89,37,232,32,0,0 ; mulps 0x20e8(%rip),%xmm12 # 4150 <_sk_callback_sse41+0x76e> - DB 68,15,84,29,240,32,0,0 ; andps 0x20f0(%rip),%xmm11 # 4160 <_sk_callback_sse41+0x77e> - DB 68,15,86,29,248,32,0,0 ; orps 0x20f8(%rip),%xmm11 # 4170 <_sk_callback_sse41+0x78e> - DB 68,15,88,37,0,33,0,0 ; addps 0x2100(%rip),%xmm12 # 4180 <_sk_callback_sse41+0x79e> - DB 15,40,29,9,33,0,0 ; movaps 0x2109(%rip),%xmm3 # 4190 <_sk_callback_sse41+0x7ae> + DB 68,15,89,37,199,32,0,0 ; mulps 0x20c7(%rip),%xmm12 # 4070 <_sk_callback_sse41+0x74d> + DB 68,15,84,29,207,32,0,0 ; andps 0x20cf(%rip),%xmm11 # 4080 <_sk_callback_sse41+0x75d> + DB 68,15,86,29,215,32,0,0 ; orps 0x20d7(%rip),%xmm11 # 4090 <_sk_callback_sse41+0x76d> + DB 68,15,88,37,223,32,0,0 ; addps 0x20df(%rip),%xmm12 # 40a0 <_sk_callback_sse41+0x77d> + DB 15,40,29,232,32,0,0 ; movaps 0x20e8(%rip),%xmm3 # 40b0 <_sk_callback_sse41+0x78d> DB 65,15,89,219 ; mulps %xmm11,%xmm3 DB 68,15,92,227 ; subps %xmm3,%xmm12 - DB 68,15,88,29,9,33,0,0 ; addps 0x2109(%rip),%xmm11 # 41a0 <_sk_callback_sse41+0x7be> - DB 15,40,29,18,33,0,0 ; movaps 0x2112(%rip),%xmm3 # 41b0 <_sk_callback_sse41+0x7ce> + DB 68,15,88,29,232,32,0,0 ; addps 0x20e8(%rip),%xmm11 # 40c0 <_sk_callback_sse41+0x79d> + DB 15,40,29,241,32,0,0 ; movaps 0x20f1(%rip),%xmm3 # 40d0 <_sk_callback_sse41+0x7ad> DB 65,15,94,219 ; divps %xmm11,%xmm3 DB 68,15,92,227 ; subps %xmm3,%xmm12 DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 102,69,15,58,8,212,1 ; roundps $0x1,%xmm12,%xmm10 DB 69,15,40,220 ; movaps %xmm12,%xmm11 DB 69,15,92,218 ; subps %xmm10,%xmm11 - DB 68,15,88,37,255,32,0,0 ; addps 0x20ff(%rip),%xmm12 # 41c0 <_sk_callback_sse41+0x7de> - DB 15,40,29,8,33,0,0 ; movaps 0x2108(%rip),%xmm3 # 41d0 <_sk_callback_sse41+0x7ee> + DB 68,15,88,37,222,32,0,0 ; addps 0x20de(%rip),%xmm12 # 40e0 <_sk_callback_sse41+0x7bd> + DB 15,40,29,231,32,0,0 ; movaps 0x20e7(%rip),%xmm3 # 40f0 <_sk_callback_sse41+0x7cd> DB 65,15,89,219 ; mulps %xmm11,%xmm3 DB 68,15,92,227 ; subps %xmm3,%xmm12 - DB 68,15,40,21,8,33,0,0 ; movaps 0x2108(%rip),%xmm10 # 41e0 <_sk_callback_sse41+0x7fe> + DB 68,15,40,21,231,32,0,0 ; movaps 0x20e7(%rip),%xmm10 # 4100 <_sk_callback_sse41+0x7dd> DB 69,15,92,211 ; subps %xmm11,%xmm10 - DB 15,40,29,13,33,0,0 ; movaps 0x210d(%rip),%xmm3 # 41f0 <_sk_callback_sse41+0x80e> + DB 15,40,29,236,32,0,0 ; movaps 0x20ec(%rip),%xmm3 # 4110 <_sk_callback_sse41+0x7ed> DB 65,15,94,218 ; divps %xmm10,%xmm3 DB 65,15,88,220 ; addps %xmm12,%xmm3 - DB 15,89,29,14,33,0,0 ; mulps 0x210e(%rip),%xmm3 # 4200 <_sk_callback_sse41+0x81e> + DB 15,89,29,237,32,0,0 ; mulps 0x20ed(%rip),%xmm3 # 4120 <_sk_callback_sse41+0x7fd> DB 102,68,15,91,211 ; cvtps2dq %xmm3,%xmm10 DB 243,15,16,88,20 ; movss 0x14(%rax),%xmm3 DB 15,198,219,0 ; shufps $0x0,%xmm3,%xmm3 @@ -11925,7 +11835,7 @@ _sk_parametric_a_sse41 LABEL PROC DB 102,65,15,56,20,217 ; blendvps %xmm0,%xmm9,%xmm3 DB 15,87,192 ; xorps %xmm0,%xmm0 DB 15,95,216 ; maxps %xmm0,%xmm3 - DB 15,93,29,249,32,0,0 ; minps 0x20f9(%rip),%xmm3 # 4210 <_sk_callback_sse41+0x82e> + DB 15,93,29,216,32,0,0 ; minps 0x20d8(%rip),%xmm3 # 4130 <_sk_callback_sse41+0x80d> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -11933,29 +11843,29 @@ _sk_parametric_a_sse41 LABEL PROC PUBLIC _sk_lab_to_xyz_sse41 _sk_lab_to_xyz_sse41 LABEL PROC DB 68,15,40,192 ; movaps %xmm0,%xmm8 - DB 68,15,89,5,245,32,0,0 ; mulps 0x20f5(%rip),%xmm8 # 4220 <_sk_callback_sse41+0x83e> - DB 68,15,40,13,253,32,0,0 ; movaps 0x20fd(%rip),%xmm9 # 4230 <_sk_callback_sse41+0x84e> + DB 68,15,89,5,212,32,0,0 ; mulps 0x20d4(%rip),%xmm8 # 4140 <_sk_callback_sse41+0x81d> + DB 68,15,40,13,220,32,0,0 ; movaps 0x20dc(%rip),%xmm9 # 4150 <_sk_callback_sse41+0x82d> DB 65,15,89,201 ; mulps %xmm9,%xmm1 - DB 15,40,5,2,33,0,0 ; movaps 0x2102(%rip),%xmm0 # 4240 <_sk_callback_sse41+0x85e> + DB 15,40,5,225,32,0,0 ; movaps 0x20e1(%rip),%xmm0 # 4160 <_sk_callback_sse41+0x83d> DB 15,88,200 ; addps %xmm0,%xmm1 DB 65,15,89,209 ; mulps %xmm9,%xmm2 DB 15,88,208 ; addps %xmm0,%xmm2 - DB 68,15,88,5,0,33,0,0 ; addps 0x2100(%rip),%xmm8 # 4250 <_sk_callback_sse41+0x86e> - DB 68,15,89,5,8,33,0,0 ; mulps 0x2108(%rip),%xmm8 # 4260 <_sk_callback_sse41+0x87e> - DB 15,89,13,17,33,0,0 ; mulps 0x2111(%rip),%xmm1 # 4270 <_sk_callback_sse41+0x88e> + DB 68,15,88,5,223,32,0,0 ; addps 0x20df(%rip),%xmm8 # 4170 <_sk_callback_sse41+0x84d> + DB 68,15,89,5,231,32,0,0 ; mulps 0x20e7(%rip),%xmm8 # 4180 <_sk_callback_sse41+0x85d> + DB 15,89,13,240,32,0,0 ; mulps 0x20f0(%rip),%xmm1 # 4190 <_sk_callback_sse41+0x86d> DB 65,15,88,200 ; addps %xmm8,%xmm1 - DB 15,89,21,22,33,0,0 ; mulps 0x2116(%rip),%xmm2 # 4280 <_sk_callback_sse41+0x89e> + DB 15,89,21,245,32,0,0 ; mulps 0x20f5(%rip),%xmm2 # 41a0 <_sk_callback_sse41+0x87d> DB 69,15,40,208 ; movaps %xmm8,%xmm10 DB 68,15,92,210 ; subps %xmm2,%xmm10 DB 68,15,40,217 ; movaps %xmm1,%xmm11 DB 69,15,89,219 ; mulps %xmm11,%xmm11 DB 68,15,89,217 ; mulps %xmm1,%xmm11 - DB 68,15,40,13,10,33,0,0 ; movaps 0x210a(%rip),%xmm9 # 4290 <_sk_callback_sse41+0x8ae> + DB 68,15,40,13,233,32,0,0 ; movaps 0x20e9(%rip),%xmm9 # 41b0 <_sk_callback_sse41+0x88d> DB 65,15,40,193 ; movaps %xmm9,%xmm0 DB 65,15,194,195,1 ; cmpltps %xmm11,%xmm0 - DB 15,40,21,10,33,0,0 ; movaps 0x210a(%rip),%xmm2 # 42a0 <_sk_callback_sse41+0x8be> + DB 15,40,21,233,32,0,0 ; movaps 0x20e9(%rip),%xmm2 # 41c0 <_sk_callback_sse41+0x89d> DB 15,88,202 ; addps %xmm2,%xmm1 - DB 68,15,40,37,15,33,0,0 ; movaps 0x210f(%rip),%xmm12 # 42b0 <_sk_callback_sse41+0x8ce> + DB 68,15,40,37,238,32,0,0 ; movaps 0x20ee(%rip),%xmm12 # 41d0 <_sk_callback_sse41+0x8ad> DB 65,15,89,204 ; mulps %xmm12,%xmm1 DB 102,65,15,56,20,203 ; blendvps %xmm0,%xmm11,%xmm1 DB 69,15,40,216 ; movaps %xmm8,%xmm11 @@ -11974,8 +11884,8 @@ _sk_lab_to_xyz_sse41 LABEL PROC DB 65,15,89,212 ; mulps %xmm12,%xmm2 DB 65,15,40,193 ; movaps %xmm9,%xmm0 DB 102,65,15,56,20,211 ; blendvps %xmm0,%xmm11,%xmm2 - DB 15,89,13,200,32,0,0 ; mulps 0x20c8(%rip),%xmm1 # 42c0 <_sk_callback_sse41+0x8de> - DB 15,89,21,209,32,0,0 ; mulps 0x20d1(%rip),%xmm2 # 42d0 <_sk_callback_sse41+0x8ee> + DB 15,89,13,167,32,0,0 ; mulps 0x20a7(%rip),%xmm1 # 41e0 <_sk_callback_sse41+0x8bd> + DB 15,89,21,176,32,0,0 ; mulps 0x20b0(%rip),%xmm2 # 41f0 <_sk_callback_sse41+0x8cd> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,40,193 ; movaps %xmm1,%xmm0 DB 65,15,40,200 ; movaps %xmm8,%xmm1 @@ -11987,7 +11897,7 @@ _sk_load_a8_sse41 LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 102,15,56,49,4,56 ; pmovzxbd (%rax,%rdi,1),%xmm0 DB 15,91,216 ; cvtdq2ps %xmm0,%xmm3 - DB 15,89,29,193,32,0,0 ; mulps 0x20c1(%rip),%xmm3 # 42e0 <_sk_callback_sse41+0x8fe> + DB 15,89,29,160,32,0,0 ; mulps 0x20a0(%rip),%xmm3 # 4200 <_sk_callback_sse41+0x8dd> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 DB 15,87,201 ; xorps %xmm1,%xmm1 @@ -12018,7 +11928,7 @@ _sk_gather_a8_sse41 LABEL PROC DB 102,15,58,32,192,3 ; pinsrb $0x3,%eax,%xmm0 DB 102,15,56,49,192 ; pmovzxbd %xmm0,%xmm0 DB 15,91,216 ; cvtdq2ps %xmm0,%xmm3 - DB 15,89,29,85,32,0,0 ; mulps 0x2055(%rip),%xmm3 # 42f0 <_sk_callback_sse41+0x90e> + DB 15,89,29,52,32,0,0 ; mulps 0x2034(%rip),%xmm3 # 4210 <_sk_callback_sse41+0x8ed> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 DB 102,15,239,201 ; pxor %xmm1,%xmm1 @@ -12029,7 +11939,7 @@ PUBLIC _sk_store_a8_sse41 _sk_store_a8_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,73,32,0,0 ; movaps 0x2049(%rip),%xmm8 # 4300 <_sk_callback_sse41+0x91e> + DB 68,15,40,5,40,32,0,0 ; movaps 0x2028(%rip),%xmm8 # 4220 <_sk_callback_sse41+0x8fd> DB 68,15,89,195 ; mulps %xmm3,%xmm8 DB 102,69,15,91,192 ; cvtps2dq %xmm8,%xmm8 DB 102,69,15,56,43,192 ; packusdw %xmm8,%xmm8 @@ -12044,9 +11954,9 @@ _sk_load_g8_sse41 LABEL PROC DB 72,139,0 ; mov (%rax),%rax DB 102,15,56,49,4,56 ; pmovzxbd (%rax,%rdi,1),%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,38,32,0,0 ; mulps 0x2026(%rip),%xmm0 # 4310 <_sk_callback_sse41+0x92e> + DB 15,89,5,5,32,0,0 ; mulps 0x2005(%rip),%xmm0 # 4230 <_sk_callback_sse41+0x90d> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,45,32,0,0 ; movaps 0x202d(%rip),%xmm3 # 4320 <_sk_callback_sse41+0x93e> + DB 15,40,29,12,32,0,0 ; movaps 0x200c(%rip),%xmm3 # 4240 <_sk_callback_sse41+0x91d> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 15,40,208 ; movaps %xmm0,%xmm2 DB 255,224 ; jmpq *%rax @@ -12075,9 +11985,9 @@ _sk_gather_g8_sse41 LABEL PROC DB 102,15,58,32,192,3 ; pinsrb $0x3,%eax,%xmm0 DB 102,15,56,49,192 ; pmovzxbd %xmm0,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,198,31,0,0 ; mulps 0x1fc6(%rip),%xmm0 # 4330 <_sk_callback_sse41+0x94e> + DB 15,89,5,165,31,0,0 ; mulps 0x1fa5(%rip),%xmm0 # 4250 <_sk_callback_sse41+0x92d> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,205,31,0,0 ; movaps 0x1fcd(%rip),%xmm3 # 4340 <_sk_callback_sse41+0x95e> + DB 15,40,29,172,31,0,0 ; movaps 0x1fac(%rip),%xmm3 # 4260 <_sk_callback_sse41+0x93d> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 15,40,208 ; movaps %xmm0,%xmm2 DB 255,224 ; jmpq *%rax @@ -12087,9 +11997,9 @@ _sk_gather_i8_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 73,137,192 ; mov %rax,%r8 DB 77,133,192 ; test %r8,%r8 - DB 116,5 ; je 238a <_sk_gather_i8_sse41+0xf> + DB 116,5 ; je 22cb <_sk_gather_i8_sse41+0xf> DB 76,137,192 ; mov %r8,%rax - DB 235,2 ; jmp 238c <_sk_gather_i8_sse41+0x11> + DB 235,2 ; jmp 22cd <_sk_gather_i8_sse41+0x11> DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 DB 243,15,91,201 ; cvttps2dq %xmm1,%xmm1 @@ -12120,17 +12030,17 @@ _sk_gather_i8_sse41 LABEL PROC DB 102,15,58,34,28,8,1 ; pinsrd $0x1,(%rax,%rcx,1),%xmm3 DB 102,66,15,58,34,28,144,2 ; pinsrd $0x2,(%rax,%r10,4),%xmm3 DB 102,66,15,58,34,28,8,3 ; pinsrd $0x3,(%rax,%r9,1),%xmm3 - DB 102,15,111,5,36,31,0,0 ; movdqa 0x1f24(%rip),%xmm0 # 4350 <_sk_callback_sse41+0x96e> + DB 102,15,111,5,3,31,0,0 ; movdqa 0x1f03(%rip),%xmm0 # 4270 <_sk_callback_sse41+0x94d> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,37,31,0,0 ; movaps 0x1f25(%rip),%xmm8 # 4360 <_sk_callback_sse41+0x97e> + DB 68,15,40,5,4,31,0,0 ; movaps 0x1f04(%rip),%xmm8 # 4280 <_sk_callback_sse41+0x95d> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 - DB 102,15,56,0,13,36,31,0,0 ; pshufb 0x1f24(%rip),%xmm1 # 4370 <_sk_callback_sse41+0x98e> + DB 102,15,56,0,13,3,31,0,0 ; pshufb 0x1f03(%rip),%xmm1 # 4290 <_sk_callback_sse41+0x96d> DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,111,211 ; movdqa %xmm3,%xmm2 - DB 102,15,56,0,21,32,31,0,0 ; pshufb 0x1f20(%rip),%xmm2 # 4380 <_sk_callback_sse41+0x99e> + DB 102,15,56,0,21,255,30,0,0 ; pshufb 0x1eff(%rip),%xmm2 # 42a0 <_sk_callback_sse41+0x97d> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 102,15,114,211,24 ; psrld $0x18,%xmm3 @@ -12144,19 +12054,19 @@ _sk_load_565_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 102,15,56,51,20,120 ; pmovzxwd (%rax,%rdi,2),%xmm2 - DB 102,15,111,5,6,31,0,0 ; movdqa 0x1f06(%rip),%xmm0 # 4390 <_sk_callback_sse41+0x9ae> + DB 102,15,111,5,229,30,0,0 ; movdqa 0x1ee5(%rip),%xmm0 # 42b0 <_sk_callback_sse41+0x98d> DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,8,31,0,0 ; mulps 0x1f08(%rip),%xmm0 # 43a0 <_sk_callback_sse41+0x9be> - DB 102,15,111,13,16,31,0,0 ; movdqa 0x1f10(%rip),%xmm1 # 43b0 <_sk_callback_sse41+0x9ce> + DB 15,89,5,231,30,0,0 ; mulps 0x1ee7(%rip),%xmm0 # 42c0 <_sk_callback_sse41+0x99d> + DB 102,15,111,13,239,30,0,0 ; movdqa 0x1eef(%rip),%xmm1 # 42d0 <_sk_callback_sse41+0x9ad> DB 102,15,219,202 ; pand %xmm2,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,18,31,0,0 ; mulps 0x1f12(%rip),%xmm1 # 43c0 <_sk_callback_sse41+0x9de> - DB 102,15,219,21,26,31,0,0 ; pand 0x1f1a(%rip),%xmm2 # 43d0 <_sk_callback_sse41+0x9ee> + DB 15,89,13,241,30,0,0 ; mulps 0x1ef1(%rip),%xmm1 # 42e0 <_sk_callback_sse41+0x9bd> + DB 102,15,219,21,249,30,0,0 ; pand 0x1ef9(%rip),%xmm2 # 42f0 <_sk_callback_sse41+0x9cd> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,32,31,0,0 ; mulps 0x1f20(%rip),%xmm2 # 43e0 <_sk_callback_sse41+0x9fe> + DB 15,89,21,255,30,0,0 ; mulps 0x1eff(%rip),%xmm2 # 4300 <_sk_callback_sse41+0x9dd> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,39,31,0,0 ; movaps 0x1f27(%rip),%xmm3 # 43f0 <_sk_callback_sse41+0xa0e> + DB 15,40,29,6,31,0,0 ; movaps 0x1f06(%rip),%xmm3 # 4310 <_sk_callback_sse41+0x9ed> DB 255,224 ; jmpq *%rax PUBLIC _sk_gather_565_sse41 @@ -12182,31 +12092,31 @@ _sk_gather_565_sse41 LABEL PROC DB 65,15,183,4,65 ; movzwl (%r9,%rax,2),%eax DB 102,15,196,192,3 ; pinsrw $0x3,%eax,%xmm0 DB 102,15,56,51,208 ; pmovzxwd %xmm0,%xmm2 - DB 102,15,111,5,204,30,0,0 ; movdqa 0x1ecc(%rip),%xmm0 # 4400 <_sk_callback_sse41+0xa1e> + DB 102,15,111,5,171,30,0,0 ; movdqa 0x1eab(%rip),%xmm0 # 4320 <_sk_callback_sse41+0x9fd> DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,206,30,0,0 ; mulps 0x1ece(%rip),%xmm0 # 4410 <_sk_callback_sse41+0xa2e> - DB 102,15,111,13,214,30,0,0 ; movdqa 0x1ed6(%rip),%xmm1 # 4420 <_sk_callback_sse41+0xa3e> + DB 15,89,5,173,30,0,0 ; mulps 0x1ead(%rip),%xmm0 # 4330 <_sk_callback_sse41+0xa0d> + DB 102,15,111,13,181,30,0,0 ; movdqa 0x1eb5(%rip),%xmm1 # 4340 <_sk_callback_sse41+0xa1d> DB 102,15,219,202 ; pand %xmm2,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,216,30,0,0 ; mulps 0x1ed8(%rip),%xmm1 # 4430 <_sk_callback_sse41+0xa4e> - DB 102,15,219,21,224,30,0,0 ; pand 0x1ee0(%rip),%xmm2 # 4440 <_sk_callback_sse41+0xa5e> + DB 15,89,13,183,30,0,0 ; mulps 0x1eb7(%rip),%xmm1 # 4350 <_sk_callback_sse41+0xa2d> + DB 102,15,219,21,191,30,0,0 ; pand 0x1ebf(%rip),%xmm2 # 4360 <_sk_callback_sse41+0xa3d> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,230,30,0,0 ; mulps 0x1ee6(%rip),%xmm2 # 4450 <_sk_callback_sse41+0xa6e> + DB 15,89,21,197,30,0,0 ; mulps 0x1ec5(%rip),%xmm2 # 4370 <_sk_callback_sse41+0xa4d> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,237,30,0,0 ; movaps 0x1eed(%rip),%xmm3 # 4460 <_sk_callback_sse41+0xa7e> + DB 15,40,29,204,30,0,0 ; movaps 0x1ecc(%rip),%xmm3 # 4380 <_sk_callback_sse41+0xa5d> DB 255,224 ; jmpq *%rax PUBLIC _sk_store_565_sse41 _sk_store_565_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,238,30,0,0 ; movaps 0x1eee(%rip),%xmm8 # 4470 <_sk_callback_sse41+0xa8e> + DB 68,15,40,5,205,30,0,0 ; movaps 0x1ecd(%rip),%xmm8 # 4390 <_sk_callback_sse41+0xa6d> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 DB 102,65,15,114,241,11 ; pslld $0xb,%xmm9 - DB 68,15,40,21,227,30,0,0 ; movaps 0x1ee3(%rip),%xmm10 # 4480 <_sk_callback_sse41+0xa9e> + DB 68,15,40,21,194,30,0,0 ; movaps 0x1ec2(%rip),%xmm10 # 43a0 <_sk_callback_sse41+0xa7d> DB 68,15,89,209 ; mulps %xmm1,%xmm10 DB 102,69,15,91,210 ; cvtps2dq %xmm10,%xmm10 DB 102,65,15,114,242,5 ; pslld $0x5,%xmm10 @@ -12224,21 +12134,21 @@ _sk_load_4444_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 102,15,56,51,28,120 ; pmovzxwd (%rax,%rdi,2),%xmm3 - DB 102,15,111,5,174,30,0,0 ; movdqa 0x1eae(%rip),%xmm0 # 4490 <_sk_callback_sse41+0xaae> + DB 102,15,111,5,141,30,0,0 ; movdqa 0x1e8d(%rip),%xmm0 # 43b0 <_sk_callback_sse41+0xa8d> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,176,30,0,0 ; mulps 0x1eb0(%rip),%xmm0 # 44a0 <_sk_callback_sse41+0xabe> - DB 102,15,111,13,184,30,0,0 ; movdqa 0x1eb8(%rip),%xmm1 # 44b0 <_sk_callback_sse41+0xace> + DB 15,89,5,143,30,0,0 ; mulps 0x1e8f(%rip),%xmm0 # 43c0 <_sk_callback_sse41+0xa9d> + DB 102,15,111,13,151,30,0,0 ; movdqa 0x1e97(%rip),%xmm1 # 43d0 <_sk_callback_sse41+0xaad> DB 102,15,219,203 ; pand %xmm3,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,186,30,0,0 ; mulps 0x1eba(%rip),%xmm1 # 44c0 <_sk_callback_sse41+0xade> - DB 102,15,111,21,194,30,0,0 ; movdqa 0x1ec2(%rip),%xmm2 # 44d0 <_sk_callback_sse41+0xaee> + DB 15,89,13,153,30,0,0 ; mulps 0x1e99(%rip),%xmm1 # 43e0 <_sk_callback_sse41+0xabd> + DB 102,15,111,21,161,30,0,0 ; movdqa 0x1ea1(%rip),%xmm2 # 43f0 <_sk_callback_sse41+0xacd> DB 102,15,219,211 ; pand %xmm3,%xmm2 DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,196,30,0,0 ; mulps 0x1ec4(%rip),%xmm2 # 44e0 <_sk_callback_sse41+0xafe> - DB 102,15,219,29,204,30,0,0 ; pand 0x1ecc(%rip),%xmm3 # 44f0 <_sk_callback_sse41+0xb0e> + DB 15,89,21,163,30,0,0 ; mulps 0x1ea3(%rip),%xmm2 # 4400 <_sk_callback_sse41+0xadd> + DB 102,15,219,29,171,30,0,0 ; pand 0x1eab(%rip),%xmm3 # 4410 <_sk_callback_sse41+0xaed> DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,210,30,0,0 ; mulps 0x1ed2(%rip),%xmm3 # 4500 <_sk_callback_sse41+0xb1e> + DB 15,89,29,177,30,0,0 ; mulps 0x1eb1(%rip),%xmm3 # 4420 <_sk_callback_sse41+0xafd> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -12265,21 +12175,21 @@ _sk_gather_4444_sse41 LABEL PROC DB 65,15,183,4,65 ; movzwl (%r9,%rax,2),%eax DB 102,15,196,192,3 ; pinsrw $0x3,%eax,%xmm0 DB 102,15,56,51,216 ; pmovzxwd %xmm0,%xmm3 - DB 102,15,111,5,117,30,0,0 ; movdqa 0x1e75(%rip),%xmm0 # 4510 <_sk_callback_sse41+0xb2e> + DB 102,15,111,5,84,30,0,0 ; movdqa 0x1e54(%rip),%xmm0 # 4430 <_sk_callback_sse41+0xb0d> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,119,30,0,0 ; mulps 0x1e77(%rip),%xmm0 # 4520 <_sk_callback_sse41+0xb3e> - DB 102,15,111,13,127,30,0,0 ; movdqa 0x1e7f(%rip),%xmm1 # 4530 <_sk_callback_sse41+0xb4e> + DB 15,89,5,86,30,0,0 ; mulps 0x1e56(%rip),%xmm0 # 4440 <_sk_callback_sse41+0xb1d> + DB 102,15,111,13,94,30,0,0 ; movdqa 0x1e5e(%rip),%xmm1 # 4450 <_sk_callback_sse41+0xb2d> DB 102,15,219,203 ; pand %xmm3,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,129,30,0,0 ; mulps 0x1e81(%rip),%xmm1 # 4540 <_sk_callback_sse41+0xb5e> - DB 102,15,111,21,137,30,0,0 ; movdqa 0x1e89(%rip),%xmm2 # 4550 <_sk_callback_sse41+0xb6e> + DB 15,89,13,96,30,0,0 ; mulps 0x1e60(%rip),%xmm1 # 4460 <_sk_callback_sse41+0xb3d> + DB 102,15,111,21,104,30,0,0 ; movdqa 0x1e68(%rip),%xmm2 # 4470 <_sk_callback_sse41+0xb4d> DB 102,15,219,211 ; pand %xmm3,%xmm2 DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,139,30,0,0 ; mulps 0x1e8b(%rip),%xmm2 # 4560 <_sk_callback_sse41+0xb7e> - DB 102,15,219,29,147,30,0,0 ; pand 0x1e93(%rip),%xmm3 # 4570 <_sk_callback_sse41+0xb8e> + DB 15,89,21,106,30,0,0 ; mulps 0x1e6a(%rip),%xmm2 # 4480 <_sk_callback_sse41+0xb5d> + DB 102,15,219,29,114,30,0,0 ; pand 0x1e72(%rip),%xmm3 # 4490 <_sk_callback_sse41+0xb6d> DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,153,30,0,0 ; mulps 0x1e99(%rip),%xmm3 # 4580 <_sk_callback_sse41+0xb9e> + DB 15,89,29,120,30,0,0 ; mulps 0x1e78(%rip),%xmm3 # 44a0 <_sk_callback_sse41+0xb7d> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -12287,7 +12197,7 @@ PUBLIC _sk_store_4444_sse41 _sk_store_4444_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,152,30,0,0 ; movaps 0x1e98(%rip),%xmm8 # 4590 <_sk_callback_sse41+0xbae> + DB 68,15,40,5,119,30,0,0 ; movaps 0x1e77(%rip),%xmm8 # 44b0 <_sk_callback_sse41+0xb8d> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 @@ -12315,17 +12225,17 @@ _sk_load_8888_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 15,16,28,184 ; movups (%rax,%rdi,4),%xmm3 - DB 15,40,5,55,30,0,0 ; movaps 0x1e37(%rip),%xmm0 # 45a0 <_sk_callback_sse41+0xbbe> + DB 15,40,5,22,30,0,0 ; movaps 0x1e16(%rip),%xmm0 # 44c0 <_sk_callback_sse41+0xb9d> DB 15,84,195 ; andps %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,57,30,0,0 ; movaps 0x1e39(%rip),%xmm8 # 45b0 <_sk_callback_sse41+0xbce> + DB 68,15,40,5,24,30,0,0 ; movaps 0x1e18(%rip),%xmm8 # 44d0 <_sk_callback_sse41+0xbad> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,40,203 ; movaps %xmm3,%xmm1 - DB 102,15,56,0,13,57,30,0,0 ; pshufb 0x1e39(%rip),%xmm1 # 45c0 <_sk_callback_sse41+0xbde> + DB 102,15,56,0,13,24,30,0,0 ; pshufb 0x1e18(%rip),%xmm1 # 44e0 <_sk_callback_sse41+0xbbd> DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 15,40,211 ; movaps %xmm3,%xmm2 - DB 102,15,56,0,21,54,30,0,0 ; pshufb 0x1e36(%rip),%xmm2 # 45d0 <_sk_callback_sse41+0xbee> + DB 102,15,56,0,21,21,30,0,0 ; pshufb 0x1e15(%rip),%xmm2 # 44f0 <_sk_callback_sse41+0xbcd> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 102,15,114,211,24 ; psrld $0x18,%xmm3 @@ -12354,17 +12264,17 @@ _sk_gather_8888_sse41 LABEL PROC DB 102,65,15,58,34,28,129,1 ; pinsrd $0x1,(%r9,%rax,4),%xmm3 DB 102,67,15,58,34,28,145,2 ; pinsrd $0x2,(%r9,%r10,4),%xmm3 DB 102,65,15,58,34,28,137,3 ; pinsrd $0x3,(%r9,%rcx,4),%xmm3 - DB 102,15,111,5,207,29,0,0 ; movdqa 0x1dcf(%rip),%xmm0 # 45e0 <_sk_callback_sse41+0xbfe> + DB 102,15,111,5,174,29,0,0 ; movdqa 0x1dae(%rip),%xmm0 # 4500 <_sk_callback_sse41+0xbdd> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,208,29,0,0 ; movaps 0x1dd0(%rip),%xmm8 # 45f0 <_sk_callback_sse41+0xc0e> + DB 68,15,40,5,175,29,0,0 ; movaps 0x1daf(%rip),%xmm8 # 4510 <_sk_callback_sse41+0xbed> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 - DB 102,15,56,0,13,207,29,0,0 ; pshufb 0x1dcf(%rip),%xmm1 # 4600 <_sk_callback_sse41+0xc1e> + DB 102,15,56,0,13,174,29,0,0 ; pshufb 0x1dae(%rip),%xmm1 # 4520 <_sk_callback_sse41+0xbfd> DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,111,211 ; movdqa %xmm3,%xmm2 - DB 102,15,56,0,21,203,29,0,0 ; pshufb 0x1dcb(%rip),%xmm2 # 4610 <_sk_callback_sse41+0xc2e> + DB 102,15,56,0,21,170,29,0,0 ; pshufb 0x1daa(%rip),%xmm2 # 4530 <_sk_callback_sse41+0xc0d> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 102,15,114,211,24 ; psrld $0x18,%xmm3 @@ -12377,7 +12287,7 @@ PUBLIC _sk_store_8888_sse41 _sk_store_8888_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,183,29,0,0 ; movaps 0x1db7(%rip),%xmm8 # 4620 <_sk_callback_sse41+0xc3e> + DB 68,15,40,5,150,29,0,0 ; movaps 0x1d96(%rip),%xmm8 # 4540 <_sk_callback_sse41+0xc1d> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 @@ -12412,18 +12322,18 @@ _sk_load_f16_sse41 LABEL PROC DB 102,68,15,97,216 ; punpcklwd %xmm0,%xmm11 DB 102,68,15,105,200 ; punpckhwd %xmm0,%xmm9 DB 102,65,15,56,51,203 ; pmovzxwd %xmm11,%xmm1 - DB 102,68,15,111,5,48,29,0,0 ; movdqa 0x1d30(%rip),%xmm8 # 4630 <_sk_callback_sse41+0xc4e> + DB 102,68,15,111,5,15,29,0,0 ; movdqa 0x1d0f(%rip),%xmm8 # 4550 <_sk_callback_sse41+0xc2d> DB 102,15,111,209 ; movdqa %xmm1,%xmm2 DB 102,65,15,219,208 ; pand %xmm8,%xmm2 DB 102,15,239,202 ; pxor %xmm2,%xmm1 - DB 102,15,111,29,43,29,0,0 ; movdqa 0x1d2b(%rip),%xmm3 # 4640 <_sk_callback_sse41+0xc5e> + DB 102,15,111,29,10,29,0,0 ; movdqa 0x1d0a(%rip),%xmm3 # 4560 <_sk_callback_sse41+0xc3d> DB 102,15,114,242,16 ; pslld $0x10,%xmm2 DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,15,56,63,195 ; pmaxud %xmm3,%xmm0 DB 102,15,118,193 ; pcmpeqd %xmm1,%xmm0 DB 102,15,114,241,13 ; pslld $0xd,%xmm1 DB 102,15,235,202 ; por %xmm2,%xmm1 - DB 102,68,15,111,21,23,29,0,0 ; movdqa 0x1d17(%rip),%xmm10 # 4650 <_sk_callback_sse41+0xc6e> + DB 102,68,15,111,21,246,28,0,0 ; movdqa 0x1cf6(%rip),%xmm10 # 4570 <_sk_callback_sse41+0xc4d> DB 102,65,15,254,202 ; paddd %xmm10,%xmm1 DB 102,15,219,193 ; pand %xmm1,%xmm0 DB 102,65,15,115,219,8 ; psrldq $0x8,%xmm11 @@ -12494,18 +12404,18 @@ _sk_gather_f16_sse41 LABEL PROC DB 102,68,15,97,218 ; punpcklwd %xmm2,%xmm11 DB 102,68,15,105,202 ; punpckhwd %xmm2,%xmm9 DB 102,65,15,56,51,203 ; pmovzxwd %xmm11,%xmm1 - DB 102,68,15,111,5,213,27,0,0 ; movdqa 0x1bd5(%rip),%xmm8 # 4660 <_sk_callback_sse41+0xc7e> + DB 102,68,15,111,5,180,27,0,0 ; movdqa 0x1bb4(%rip),%xmm8 # 4580 <_sk_callback_sse41+0xc5d> DB 102,15,111,209 ; movdqa %xmm1,%xmm2 DB 102,65,15,219,208 ; pand %xmm8,%xmm2 DB 102,15,239,202 ; pxor %xmm2,%xmm1 - DB 102,15,111,29,208,27,0,0 ; movdqa 0x1bd0(%rip),%xmm3 # 4670 <_sk_callback_sse41+0xc8e> + DB 102,15,111,29,175,27,0,0 ; movdqa 0x1baf(%rip),%xmm3 # 4590 <_sk_callback_sse41+0xc6d> DB 102,15,114,242,16 ; pslld $0x10,%xmm2 DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,15,56,63,195 ; pmaxud %xmm3,%xmm0 DB 102,15,118,193 ; pcmpeqd %xmm1,%xmm0 DB 102,15,114,241,13 ; pslld $0xd,%xmm1 DB 102,15,235,202 ; por %xmm2,%xmm1 - DB 102,68,15,111,21,188,27,0,0 ; movdqa 0x1bbc(%rip),%xmm10 # 4680 <_sk_callback_sse41+0xc9e> + DB 102,68,15,111,21,155,27,0,0 ; movdqa 0x1b9b(%rip),%xmm10 # 45a0 <_sk_callback_sse41+0xc7d> DB 102,65,15,254,202 ; paddd %xmm10,%xmm1 DB 102,15,219,193 ; pand %xmm1,%xmm0 DB 102,65,15,115,219,8 ; psrldq $0x8,%xmm11 @@ -12551,17 +12461,17 @@ PUBLIC _sk_store_f16_sse41 _sk_store_f16_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 102,68,15,111,21,242,26,0,0 ; movdqa 0x1af2(%rip),%xmm10 # 4690 <_sk_callback_sse41+0xcae> + DB 102,68,15,111,21,209,26,0,0 ; movdqa 0x1ad1(%rip),%xmm10 # 45b0 <_sk_callback_sse41+0xc8d> DB 102,68,15,111,224 ; movdqa %xmm0,%xmm12 DB 102,68,15,111,232 ; movdqa %xmm0,%xmm13 DB 102,69,15,219,234 ; pand %xmm10,%xmm13 DB 102,69,15,239,229 ; pxor %xmm13,%xmm12 - DB 102,68,15,111,13,229,26,0,0 ; movdqa 0x1ae5(%rip),%xmm9 # 46a0 <_sk_callback_sse41+0xcbe> + DB 102,68,15,111,13,196,26,0,0 ; movdqa 0x1ac4(%rip),%xmm9 # 45c0 <_sk_callback_sse41+0xc9d> DB 102,65,15,114,213,16 ; psrld $0x10,%xmm13 DB 102,69,15,111,193 ; movdqa %xmm9,%xmm8 DB 102,69,15,102,196 ; pcmpgtd %xmm12,%xmm8 DB 102,65,15,114,212,13 ; psrld $0xd,%xmm12 - DB 102,68,15,111,29,214,26,0,0 ; movdqa 0x1ad6(%rip),%xmm11 # 46b0 <_sk_callback_sse41+0xcce> + DB 102,68,15,111,29,181,26,0,0 ; movdqa 0x1ab5(%rip),%xmm11 # 45d0 <_sk_callback_sse41+0xcad> DB 102,69,15,235,235 ; por %xmm11,%xmm13 DB 102,69,15,254,236 ; paddd %xmm12,%xmm13 DB 102,69,15,223,197 ; pandn %xmm13,%xmm8 @@ -12629,7 +12539,7 @@ _sk_load_u16_be_sse41 LABEL PROC DB 102,15,235,200 ; por %xmm0,%xmm1 DB 102,15,56,51,193 ; pmovzxwd %xmm1,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,165,25,0,0 ; movaps 0x19a5(%rip),%xmm8 # 46c0 <_sk_callback_sse41+0xcde> + DB 68,15,40,5,132,25,0,0 ; movaps 0x1984(%rip),%xmm8 # 45e0 <_sk_callback_sse41+0xcbd> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 DB 102,15,113,241,8 ; psllw $0x8,%xmm1 @@ -12679,7 +12589,7 @@ _sk_load_rgb_u16_be_sse41 LABEL PROC DB 102,15,235,193 ; por %xmm1,%xmm0 DB 102,15,56,51,192 ; pmovzxwd %xmm0,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,230,24,0,0 ; movaps 0x18e6(%rip),%xmm8 # 46d0 <_sk_callback_sse41+0xcee> + DB 68,15,40,5,197,24,0,0 ; movaps 0x18c5(%rip),%xmm8 # 45f0 <_sk_callback_sse41+0xccd> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 DB 102,15,113,241,8 ; psllw $0x8,%xmm1 @@ -12696,14 +12606,14 @@ _sk_load_rgb_u16_be_sse41 LABEL PROC DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,173,24,0,0 ; movaps 0x18ad(%rip),%xmm3 # 46e0 <_sk_callback_sse41+0xcfe> + DB 15,40,29,140,24,0,0 ; movaps 0x188c(%rip),%xmm3 # 4600 <_sk_callback_sse41+0xcdd> DB 255,224 ; jmpq *%rax PUBLIC _sk_store_u16_be_sse41 _sk_store_u16_be_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,13,174,24,0,0 ; movaps 0x18ae(%rip),%xmm9 # 46f0 <_sk_callback_sse41+0xd0e> + DB 68,15,40,13,141,24,0,0 ; movaps 0x188d(%rip),%xmm9 # 4610 <_sk_callback_sse41+0xced> DB 68,15,40,192 ; movaps %xmm0,%xmm8 DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 102,69,15,91,192 ; cvtps2dq %xmm8,%xmm8 @@ -12908,10 +12818,10 @@ _sk_mirror_y_sse41 LABEL PROC PUBLIC _sk_luminance_to_alpha_sse41 _sk_luminance_to_alpha_sse41 LABEL PROC DB 15,40,218 ; movaps %xmm2,%xmm3 - DB 15,89,5,204,21,0,0 ; mulps 0x15cc(%rip),%xmm0 # 4700 <_sk_callback_sse41+0xd1e> - DB 15,89,13,213,21,0,0 ; mulps 0x15d5(%rip),%xmm1 # 4710 <_sk_callback_sse41+0xd2e> + DB 15,89,5,171,21,0,0 ; mulps 0x15ab(%rip),%xmm0 # 4620 <_sk_callback_sse41+0xcfd> + DB 15,89,13,180,21,0,0 ; mulps 0x15b4(%rip),%xmm1 # 4630 <_sk_callback_sse41+0xd0d> DB 15,88,200 ; addps %xmm0,%xmm1 - DB 15,89,29,219,21,0,0 ; mulps 0x15db(%rip),%xmm3 # 4720 <_sk_callback_sse41+0xd3e> + DB 15,89,29,186,21,0,0 ; mulps 0x15ba(%rip),%xmm3 # 4640 <_sk_callback_sse41+0xd1d> DB 15,88,217 ; addps %xmm1,%xmm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 @@ -13134,7 +13044,7 @@ _sk_linear_gradient_sse41 LABEL PROC DB 69,15,198,237,0 ; shufps $0x0,%xmm13,%xmm13 DB 72,139,8 ; mov (%rax),%rcx DB 72,133,201 ; test %rcx,%rcx - DB 15,132,4,1,0,0 ; je 35ed <_sk_linear_gradient_sse41+0x13e> + DB 15,132,4,1,0,0 ; je 352e <_sk_linear_gradient_sse41+0x13e> DB 72,131,236,88 ; sub $0x58,%rsp DB 15,41,36,36 ; movaps %xmm4,(%rsp) DB 15,41,108,36,16 ; movaps %xmm5,0x10(%rsp) @@ -13185,13 +13095,13 @@ _sk_linear_gradient_sse41 LABEL PROC DB 15,40,196 ; movaps %xmm4,%xmm0 DB 72,131,192,36 ; add $0x24,%rax DB 72,255,201 ; dec %rcx - DB 15,133,65,255,255,255 ; jne 3515 <_sk_linear_gradient_sse41+0x66> + DB 15,133,65,255,255,255 ; jne 3456 <_sk_linear_gradient_sse41+0x66> DB 15,40,124,36,48 ; movaps 0x30(%rsp),%xmm7 DB 15,40,116,36,32 ; movaps 0x20(%rsp),%xmm6 DB 15,40,108,36,16 ; movaps 0x10(%rsp),%xmm5 DB 15,40,36,36 ; movaps (%rsp),%xmm4 DB 72,131,196,88 ; add $0x58,%rsp - DB 235,13 ; jmp 35fa <_sk_linear_gradient_sse41+0x14b> + DB 235,13 ; jmp 353b <_sk_linear_gradient_sse41+0x14b> DB 15,87,201 ; xorps %xmm1,%xmm1 DB 15,87,210 ; xorps %xmm2,%xmm2 DB 15,87,219 ; xorps %xmm3,%xmm3 @@ -13242,7 +13152,7 @@ _sk_linear_gradient_2stops_sse41 LABEL PROC PUBLIC _sk_save_xy_sse41 _sk_save_xy_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,151,16,0,0 ; movaps 0x1097(%rip),%xmm8 # 4730 <_sk_callback_sse41+0xd4e> + DB 68,15,40,5,118,16,0,0 ; movaps 0x1076(%rip),%xmm8 # 4650 <_sk_callback_sse41+0xd2d> DB 15,17,0 ; movups %xmm0,(%rax) DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,88,200 ; addps %xmm8,%xmm9 @@ -13282,8 +13192,8 @@ _sk_bilinear_nx_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,25,16,0,0 ; addps 0x1019(%rip),%xmm0 # 4740 <_sk_callback_sse41+0xd5e> - DB 68,15,40,13,33,16,0,0 ; movaps 0x1021(%rip),%xmm9 # 4750 <_sk_callback_sse41+0xd6e> + DB 15,88,5,248,15,0,0 ; addps 0xff8(%rip),%xmm0 # 4660 <_sk_callback_sse41+0xd3d> + DB 68,15,40,13,0,16,0,0 ; movaps 0x1000(%rip),%xmm9 # 4670 <_sk_callback_sse41+0xd4d> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 68,15,17,136,128,0,0,0 ; movups %xmm9,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -13294,7 +13204,7 @@ _sk_bilinear_px_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,16,16,0,0 ; addps 0x1010(%rip),%xmm0 # 4760 <_sk_callback_sse41+0xd7e> + DB 15,88,5,239,15,0,0 ; addps 0xfef(%rip),%xmm0 # 4680 <_sk_callback_sse41+0xd5d> DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -13304,8 +13214,8 @@ _sk_bilinear_ny_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,2,16,0,0 ; addps 0x1002(%rip),%xmm1 # 4770 <_sk_callback_sse41+0xd8e> - DB 68,15,40,13,10,16,0,0 ; movaps 0x100a(%rip),%xmm9 # 4780 <_sk_callback_sse41+0xd9e> + DB 15,88,13,225,15,0,0 ; addps 0xfe1(%rip),%xmm1 # 4690 <_sk_callback_sse41+0xd6d> + DB 68,15,40,13,233,15,0,0 ; movaps 0xfe9(%rip),%xmm9 # 46a0 <_sk_callback_sse41+0xd7d> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 68,15,17,136,160,0,0,0 ; movups %xmm9,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -13316,7 +13226,7 @@ _sk_bilinear_py_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,248,15,0,0 ; addps 0xff8(%rip),%xmm1 # 4790 <_sk_callback_sse41+0xdae> + DB 15,88,13,215,15,0,0 ; addps 0xfd7(%rip),%xmm1 # 46b0 <_sk_callback_sse41+0xd8d> DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -13326,13 +13236,13 @@ _sk_bicubic_n3x_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,235,15,0,0 ; addps 0xfeb(%rip),%xmm0 # 47a0 <_sk_callback_sse41+0xdbe> - DB 68,15,40,13,243,15,0,0 ; movaps 0xff3(%rip),%xmm9 # 47b0 <_sk_callback_sse41+0xdce> + DB 15,88,5,202,15,0,0 ; addps 0xfca(%rip),%xmm0 # 46c0 <_sk_callback_sse41+0xd9d> + DB 68,15,40,13,210,15,0,0 ; movaps 0xfd2(%rip),%xmm9 # 46d0 <_sk_callback_sse41+0xdad> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 69,15,40,193 ; movaps %xmm9,%xmm8 DB 69,15,89,192 ; mulps %xmm8,%xmm8 - DB 68,15,89,13,239,15,0,0 ; mulps 0xfef(%rip),%xmm9 # 47c0 <_sk_callback_sse41+0xdde> - DB 68,15,88,13,247,15,0,0 ; addps 0xff7(%rip),%xmm9 # 47d0 <_sk_callback_sse41+0xdee> + DB 68,15,89,13,206,15,0,0 ; mulps 0xfce(%rip),%xmm9 # 46e0 <_sk_callback_sse41+0xdbd> + DB 68,15,88,13,214,15,0,0 ; addps 0xfd6(%rip),%xmm9 # 46f0 <_sk_callback_sse41+0xdcd> DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 68,15,17,136,128,0,0,0 ; movups %xmm9,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -13343,16 +13253,16 @@ _sk_bicubic_n1x_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,230,15,0,0 ; addps 0xfe6(%rip),%xmm0 # 47e0 <_sk_callback_sse41+0xdfe> - DB 68,15,40,13,238,15,0,0 ; movaps 0xfee(%rip),%xmm9 # 47f0 <_sk_callback_sse41+0xe0e> + DB 15,88,5,197,15,0,0 ; addps 0xfc5(%rip),%xmm0 # 4700 <_sk_callback_sse41+0xddd> + DB 68,15,40,13,205,15,0,0 ; movaps 0xfcd(%rip),%xmm9 # 4710 <_sk_callback_sse41+0xded> DB 69,15,92,200 ; subps %xmm8,%xmm9 - DB 68,15,40,5,242,15,0,0 ; movaps 0xff2(%rip),%xmm8 # 4800 <_sk_callback_sse41+0xe1e> + DB 68,15,40,5,209,15,0,0 ; movaps 0xfd1(%rip),%xmm8 # 4720 <_sk_callback_sse41+0xdfd> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,246,15,0,0 ; addps 0xff6(%rip),%xmm8 # 4810 <_sk_callback_sse41+0xe2e> + DB 68,15,88,5,213,15,0,0 ; addps 0xfd5(%rip),%xmm8 # 4730 <_sk_callback_sse41+0xe0d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,250,15,0,0 ; addps 0xffa(%rip),%xmm8 # 4820 <_sk_callback_sse41+0xe3e> + DB 68,15,88,5,217,15,0,0 ; addps 0xfd9(%rip),%xmm8 # 4740 <_sk_callback_sse41+0xe1d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,254,15,0,0 ; addps 0xffe(%rip),%xmm8 # 4830 <_sk_callback_sse41+0xe4e> + DB 68,15,88,5,221,15,0,0 ; addps 0xfdd(%rip),%xmm8 # 4750 <_sk_callback_sse41+0xe2d> DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -13360,17 +13270,17 @@ _sk_bicubic_n1x_sse41 LABEL PROC PUBLIC _sk_bicubic_p1x_sse41 _sk_bicubic_p1x_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,248,15,0,0 ; movaps 0xff8(%rip),%xmm8 # 4840 <_sk_callback_sse41+0xe5e> + DB 68,15,40,5,215,15,0,0 ; movaps 0xfd7(%rip),%xmm8 # 4760 <_sk_callback_sse41+0xe3d> DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,72,64 ; movups 0x40(%rax),%xmm9 DB 65,15,88,192 ; addps %xmm8,%xmm0 - DB 68,15,40,21,244,15,0,0 ; movaps 0xff4(%rip),%xmm10 # 4850 <_sk_callback_sse41+0xe6e> + DB 68,15,40,21,211,15,0,0 ; movaps 0xfd3(%rip),%xmm10 # 4770 <_sk_callback_sse41+0xe4d> DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,248,15,0,0 ; addps 0xff8(%rip),%xmm10 # 4860 <_sk_callback_sse41+0xe7e> + DB 68,15,88,21,215,15,0,0 ; addps 0xfd7(%rip),%xmm10 # 4780 <_sk_callback_sse41+0xe5d> DB 69,15,89,209 ; mulps %xmm9,%xmm10 DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,244,15,0,0 ; addps 0xff4(%rip),%xmm10 # 4870 <_sk_callback_sse41+0xe8e> + DB 68,15,88,21,211,15,0,0 ; addps 0xfd3(%rip),%xmm10 # 4790 <_sk_callback_sse41+0xe6d> DB 68,15,17,144,128,0,0,0 ; movups %xmm10,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -13380,11 +13290,11 @@ _sk_bicubic_p3x_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,231,15,0,0 ; addps 0xfe7(%rip),%xmm0 # 4880 <_sk_callback_sse41+0xe9e> + DB 15,88,5,198,15,0,0 ; addps 0xfc6(%rip),%xmm0 # 47a0 <_sk_callback_sse41+0xe7d> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,89,201 ; mulps %xmm9,%xmm9 - DB 68,15,89,5,231,15,0,0 ; mulps 0xfe7(%rip),%xmm8 # 4890 <_sk_callback_sse41+0xeae> - DB 68,15,88,5,239,15,0,0 ; addps 0xfef(%rip),%xmm8 # 48a0 <_sk_callback_sse41+0xebe> + DB 68,15,89,5,198,15,0,0 ; mulps 0xfc6(%rip),%xmm8 # 47b0 <_sk_callback_sse41+0xe8d> + DB 68,15,88,5,206,15,0,0 ; addps 0xfce(%rip),%xmm8 # 47c0 <_sk_callback_sse41+0xe9d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -13395,13 +13305,13 @@ _sk_bicubic_n3y_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,221,15,0,0 ; addps 0xfdd(%rip),%xmm1 # 48b0 <_sk_callback_sse41+0xece> - DB 68,15,40,13,229,15,0,0 ; movaps 0xfe5(%rip),%xmm9 # 48c0 <_sk_callback_sse41+0xede> + DB 15,88,13,188,15,0,0 ; addps 0xfbc(%rip),%xmm1 # 47d0 <_sk_callback_sse41+0xead> + DB 68,15,40,13,196,15,0,0 ; movaps 0xfc4(%rip),%xmm9 # 47e0 <_sk_callback_sse41+0xebd> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 69,15,40,193 ; movaps %xmm9,%xmm8 DB 69,15,89,192 ; mulps %xmm8,%xmm8 - DB 68,15,89,13,225,15,0,0 ; mulps 0xfe1(%rip),%xmm9 # 48d0 <_sk_callback_sse41+0xeee> - DB 68,15,88,13,233,15,0,0 ; addps 0xfe9(%rip),%xmm9 # 48e0 <_sk_callback_sse41+0xefe> + DB 68,15,89,13,192,15,0,0 ; mulps 0xfc0(%rip),%xmm9 # 47f0 <_sk_callback_sse41+0xecd> + DB 68,15,88,13,200,15,0,0 ; addps 0xfc8(%rip),%xmm9 # 4800 <_sk_callback_sse41+0xedd> DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 68,15,17,136,160,0,0,0 ; movups %xmm9,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -13412,16 +13322,16 @@ _sk_bicubic_n1y_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,215,15,0,0 ; addps 0xfd7(%rip),%xmm1 # 48f0 <_sk_callback_sse41+0xf0e> - DB 68,15,40,13,223,15,0,0 ; movaps 0xfdf(%rip),%xmm9 # 4900 <_sk_callback_sse41+0xf1e> + DB 15,88,13,182,15,0,0 ; addps 0xfb6(%rip),%xmm1 # 4810 <_sk_callback_sse41+0xeed> + DB 68,15,40,13,190,15,0,0 ; movaps 0xfbe(%rip),%xmm9 # 4820 <_sk_callback_sse41+0xefd> DB 69,15,92,200 ; subps %xmm8,%xmm9 - DB 68,15,40,5,227,15,0,0 ; movaps 0xfe3(%rip),%xmm8 # 4910 <_sk_callback_sse41+0xf2e> + DB 68,15,40,5,194,15,0,0 ; movaps 0xfc2(%rip),%xmm8 # 4830 <_sk_callback_sse41+0xf0d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,231,15,0,0 ; addps 0xfe7(%rip),%xmm8 # 4920 <_sk_callback_sse41+0xf3e> + DB 68,15,88,5,198,15,0,0 ; addps 0xfc6(%rip),%xmm8 # 4840 <_sk_callback_sse41+0xf1d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,235,15,0,0 ; addps 0xfeb(%rip),%xmm8 # 4930 <_sk_callback_sse41+0xf4e> + DB 68,15,88,5,202,15,0,0 ; addps 0xfca(%rip),%xmm8 # 4850 <_sk_callback_sse41+0xf2d> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,239,15,0,0 ; addps 0xfef(%rip),%xmm8 # 4940 <_sk_callback_sse41+0xf5e> + DB 68,15,88,5,206,15,0,0 ; addps 0xfce(%rip),%xmm8 # 4860 <_sk_callback_sse41+0xf3d> DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -13429,17 +13339,17 @@ _sk_bicubic_n1y_sse41 LABEL PROC PUBLIC _sk_bicubic_p1y_sse41 _sk_bicubic_p1y_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,233,15,0,0 ; movaps 0xfe9(%rip),%xmm8 # 4950 <_sk_callback_sse41+0xf6e> + DB 68,15,40,5,200,15,0,0 ; movaps 0xfc8(%rip),%xmm8 # 4870 <_sk_callback_sse41+0xf4d> DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,72,96 ; movups 0x60(%rax),%xmm9 DB 65,15,88,200 ; addps %xmm8,%xmm1 - DB 68,15,40,21,228,15,0,0 ; movaps 0xfe4(%rip),%xmm10 # 4960 <_sk_callback_sse41+0xf7e> + DB 68,15,40,21,195,15,0,0 ; movaps 0xfc3(%rip),%xmm10 # 4880 <_sk_callback_sse41+0xf5d> DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,232,15,0,0 ; addps 0xfe8(%rip),%xmm10 # 4970 <_sk_callback_sse41+0xf8e> + DB 68,15,88,21,199,15,0,0 ; addps 0xfc7(%rip),%xmm10 # 4890 <_sk_callback_sse41+0xf6d> DB 69,15,89,209 ; mulps %xmm9,%xmm10 DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,228,15,0,0 ; addps 0xfe4(%rip),%xmm10 # 4980 <_sk_callback_sse41+0xf9e> + DB 68,15,88,21,195,15,0,0 ; addps 0xfc3(%rip),%xmm10 # 48a0 <_sk_callback_sse41+0xf7d> DB 68,15,17,144,160,0,0,0 ; movups %xmm10,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -13449,11 +13359,11 @@ _sk_bicubic_p3y_sse41 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,214,15,0,0 ; addps 0xfd6(%rip),%xmm1 # 4990 <_sk_callback_sse41+0xfae> + DB 15,88,13,181,15,0,0 ; addps 0xfb5(%rip),%xmm1 # 48b0 <_sk_callback_sse41+0xf8d> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,89,201 ; mulps %xmm9,%xmm9 - DB 68,15,89,5,214,15,0,0 ; mulps 0xfd6(%rip),%xmm8 # 49a0 <_sk_callback_sse41+0xfbe> - DB 68,15,88,5,222,15,0,0 ; addps 0xfde(%rip),%xmm8 # 49b0 <_sk_callback_sse41+0xfce> + DB 68,15,89,5,181,15,0,0 ; mulps 0xfb5(%rip),%xmm8 # 48c0 <_sk_callback_sse41+0xf9d> + DB 68,15,88,5,189,15,0,0 ; addps 0xfbd(%rip),%xmm8 # 48d0 <_sk_callback_sse41+0xfad> DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -13624,11 +13534,11 @@ ALIGN 16 DB 0,128,191,0,0,128 ; add %al,-0x7fffff41(%rax) DB 191,0,0,224,64 ; mov $0x40e00000,%edi DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 3c18 <.literal16+0x188> + DB 224,64 ; loopne 3b58 <.literal16+0x188> DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 3c1c <.literal16+0x18c> + DB 224,64 ; loopne 3b5c <.literal16+0x18c> DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 3c20 <.literal16+0x190> + DB 224,64 ; loopne 3b60 <.literal16+0x190> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -13767,12 +13677,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 0,0 ; add %al,(%rax) - DB 128,63,0 ; cmpb $0x0,(%rdi) - DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) - DB 63 ; (bad) - DB 0,0 ; add %al,(%rax) - DB 128,63,171 ; cmpb $0xab,(%rdi) + DB 171 ; stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) DB 62,171 ; ds stos %eax,%es:(%rdi) @@ -13785,25 +13690,14 @@ ALIGN 16 DB 170 ; stos %al,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) DB 62,0,0 ; add %al,%ds:(%rax) - DB 128,191,0,0,128,191,0 ; cmpb $0x0,-0x40800000(%rdi) - DB 0,128,191,0,0,128 ; add %al,-0x7fffff41(%rax) - DB 191,0,0,192,64 ; mov $0x40c00000,%edi - DB 0,0 ; add %al,(%rax) DB 192,64,0,0 ; rolb $0x0,0x0(%rax) DB 192,64,0,0 ; rolb $0x0,0x0(%rax) - DB 192,64,171,170 ; rolb $0xaa,-0x55(%rax) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) + DB 192,64,0,0 ; rolb $0x0,0x0(%rax) + DB 192,64,0,0 ; rolb $0x0,0x0(%rax) + DB 128,64,0,0 ; addb $0x0,0x0(%rax) + DB 128,64,0,0 ; addb $0x0,0x0(%rax) + DB 128,64,0,0 ; addb $0x0,0x0(%rax) + DB 128,64,171,170 ; addb $0xaa,-0x55(%rax) DB 170 ; stos %al,%es:(%rdi) DB 190,171,170,170,190 ; mov $0xbeaaaaab,%esi DB 171 ; stos %eax,%es:(%rdi) @@ -13831,13 +13725,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 3dc9 <.literal16+0x339> + DB 224,7 ; loopne 3ce9 <.literal16+0x319> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 3dcd <.literal16+0x33d> + DB 224,7 ; loopne 3ced <.literal16+0x31d> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 3dd1 <.literal16+0x341> + DB 224,7 ; loopne 3cf1 <.literal16+0x321> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 3dd5 <.literal16+0x345> + DB 224,7 ; loopne 3cf5 <.literal16+0x325> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -13877,10 +13771,10 @@ ALIGN 16 DB 0,1 ; add %al,(%rcx) DB 255 ; (bad) DB 255 ; (bad) - DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a003e28 <_sk_callback_sse41+0xa000446> + DB 255,5,255,255,255,9 ; incl 0x9ffffff(%rip) # a003d48 <_sk_callback_sse41+0xa000425> DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3003e30 <_sk_callback_sse41+0x300044e> + DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3003d50 <_sk_callback_sse41+0x300042d> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -13935,11 +13829,11 @@ ALIGN 16 DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 3efb <.literal16+0x46b> + DB 127,67 ; jg 3e1b <.literal16+0x44b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 3eff <.literal16+0x46f> + DB 127,67 ; jg 3e1f <.literal16+0x44f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 3f03 <.literal16+0x473> + DB 127,67 ; jg 3e23 <.literal16+0x453> DB 129,128,128,59,129,128,128,59,129,128; addl $0x80813b80,-0x7f7ec480(%rax) DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,129,128,128,59 ; addb $0x3b,-0x7f7f7ec5(%rax) @@ -13954,16 +13848,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 3ef4 <.literal16+0x464> + DB 127,0 ; jg 3e14 <.literal16+0x444> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 3ef8 <.literal16+0x468> + DB 127,0 ; jg 3e18 <.literal16+0x448> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 3efc <.literal16+0x46c> + DB 127,0 ; jg 3e1c <.literal16+0x44c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 3f00 <.literal16+0x470> + DB 127,0 ; jg 3e20 <.literal16+0x450> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -13972,7 +13866,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 3f85 <.literal16+0x4f5> + DB 119,115 ; ja 3ea5 <.literal16+0x4d5> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -13983,7 +13877,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 3ee9 <.literal16+0x459> + DB 117,191 ; jne 3e09 <.literal16+0x439> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -13995,7 +13889,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a37f2a <_sk_callback_sse41+0xffffffffe9a34548> + DB 233,220,63,163,233 ; jmpq ffffffffe9a37e4a <_sk_callback_sse41+0xffffffffe9a34527> DB 220,63 ; fdivrl (%rdi) DB 81 ; push %rcx DB 140,242 ; mov %?,%edx @@ -14050,16 +13944,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 3fc4 <.literal16+0x534> + DB 127,0 ; jg 3ee4 <.literal16+0x514> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 3fc8 <.literal16+0x538> + DB 127,0 ; jg 3ee8 <.literal16+0x518> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 3fcc <.literal16+0x53c> + DB 127,0 ; jg 3eec <.literal16+0x51c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 3fd0 <.literal16+0x540> + DB 127,0 ; jg 3ef0 <.literal16+0x520> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -14068,7 +13962,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4055 <.literal16+0x5c5> + DB 119,115 ; ja 3f75 <.literal16+0x5a5> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -14079,7 +13973,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 3fb9 <.literal16+0x529> + DB 117,191 ; jne 3ed9 <.literal16+0x509> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -14091,7 +13985,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a37ffa <_sk_callback_sse41+0xffffffffe9a34618> + DB 233,220,63,163,233 ; jmpq ffffffffe9a37f1a <_sk_callback_sse41+0xffffffffe9a345f7> DB 220,63 ; fdivrl (%rdi) DB 81 ; push %rcx DB 140,242 ; mov %?,%edx @@ -14146,16 +14040,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4094 <.literal16+0x604> + DB 127,0 ; jg 3fb4 <.literal16+0x5e4> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4098 <.literal16+0x608> + DB 127,0 ; jg 3fb8 <.literal16+0x5e8> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 409c <.literal16+0x60c> + DB 127,0 ; jg 3fbc <.literal16+0x5ec> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 40a0 <.literal16+0x610> + DB 127,0 ; jg 3fc0 <.literal16+0x5f0> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -14164,7 +14058,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4125 <.literal16+0x695> + DB 119,115 ; ja 4045 <.literal16+0x675> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -14175,7 +14069,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4089 <.literal16+0x5f9> + DB 117,191 ; jne 3fa9 <.literal16+0x5d9> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -14187,7 +14081,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a380ca <_sk_callback_sse41+0xffffffffe9a346e8> + DB 233,220,63,163,233 ; jmpq ffffffffe9a37fea <_sk_callback_sse41+0xffffffffe9a346c7> DB 220,63 ; fdivrl (%rdi) DB 81 ; push %rcx DB 140,242 ; mov %?,%edx @@ -14242,16 +14136,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4164 <.literal16+0x6d4> + DB 127,0 ; jg 4084 <.literal16+0x6b4> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4168 <.literal16+0x6d8> + DB 127,0 ; jg 4088 <.literal16+0x6b8> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 416c <.literal16+0x6dc> + DB 127,0 ; jg 408c <.literal16+0x6bc> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4170 <.literal16+0x6e0> + DB 127,0 ; jg 4090 <.literal16+0x6c0> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -14260,7 +14154,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 41f5 <.literal16+0x765> + DB 119,115 ; ja 4115 <.literal16+0x745> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -14271,7 +14165,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4159 <.literal16+0x6c9> + DB 117,191 ; jne 4079 <.literal16+0x6a9> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -14283,7 +14177,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a3819a <_sk_callback_sse41+0xffffffffe9a347b8> + DB 233,220,63,163,233 ; jmpq ffffffffe9a380ba <_sk_callback_sse41+0xffffffffe9a34797> DB 220,63 ; fdivrl (%rdi) DB 81 ; push %rcx DB 140,242 ; mov %?,%edx @@ -14334,13 +14228,13 @@ ALIGN 16 DB 200,66,0,0 ; enterq $0x42,$0x0 DB 200,66,0,0 ; enterq $0x42,$0x0 DB 200,66,0,0 ; enterq $0x42,$0x0 - DB 127,67 ; jg 4277 <.literal16+0x7e7> + DB 127,67 ; jg 4197 <.literal16+0x7c7> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 427b <.literal16+0x7eb> + DB 127,67 ; jg 419b <.literal16+0x7cb> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 427f <.literal16+0x7ef> + DB 127,67 ; jg 419f <.literal16+0x7cf> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4283 <.literal16+0x7f3> + DB 127,67 ; jg 41a3 <.literal16+0x7d3> DB 0,0 ; add %al,(%rax) DB 0,195 ; add %al,%bl DB 0,0 ; add %al,(%rax) @@ -14387,16 +14281,16 @@ ALIGN 16 DB 128,3,62 ; addb $0x3e,(%rbx) DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 4303 <.literal16+0x873> + DB 118,63 ; jbe 4223 <.literal16+0x853> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 4307 <.literal16+0x877> + DB 118,63 ; jbe 4227 <.literal16+0x857> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 430b <.literal16+0x87b> + DB 118,63 ; jbe 422b <.literal16+0x85b> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 430f <.literal16+0x87f> + DB 118,63 ; jbe 422f <.literal16+0x85f> DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 246,64,83,63 ; testb $0x3f,0x53(%rax) @@ -14408,11 +14302,11 @@ ALIGN 16 DB 128,59,0 ; cmpb $0x0,(%rbx) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 434b <.literal16+0x8bb> + DB 127,67 ; jg 426b <.literal16+0x89b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 434f <.literal16+0x8bf> + DB 127,67 ; jg 426f <.literal16+0x89f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4353 <.literal16+0x8c3> + DB 127,67 ; jg 4273 <.literal16+0x8a3> DB 129,128,128,59,129,128,128,59,129,128; addl $0x80813b80,-0x7f7ec480(%rax) DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,0,0,128,63 ; addb $0x3f,-0x7fffffc5(%rax) @@ -14441,7 +14335,7 @@ ALIGN 16 DB 5,255,255,255,9 ; add $0x9ffffff,%eax DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3004380 <_sk_callback_sse41+0x300099e> + DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 30042a0 <_sk_callback_sse41+0x300097d> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -14470,13 +14364,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 43b9 <.literal16+0x929> + DB 224,7 ; loopne 42d9 <.literal16+0x909> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 43bd <.literal16+0x92d> + DB 224,7 ; loopne 42dd <.literal16+0x90d> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 43c1 <.literal16+0x931> + DB 224,7 ; loopne 42e1 <.literal16+0x911> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 43c5 <.literal16+0x935> + DB 224,7 ; loopne 42e5 <.literal16+0x915> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -14522,13 +14416,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 4429 <.literal16+0x999> + DB 224,7 ; loopne 4349 <.literal16+0x979> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 442d <.literal16+0x99d> + DB 224,7 ; loopne 434d <.literal16+0x97d> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4431 <.literal16+0x9a1> + DB 224,7 ; loopne 4351 <.literal16+0x981> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4435 <.literal16+0x9a5> + DB 224,7 ; loopne 4355 <.literal16+0x985> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -14566,13 +14460,13 @@ ALIGN 16 DB 65,0,0 ; add %al,(%r8) DB 248 ; clc DB 65,0,0 ; add %al,(%r8) - DB 124,66 ; jl 44c6 <.literal16+0xa36> + DB 124,66 ; jl 43e6 <.literal16+0xa16> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 44ca <.literal16+0xa3a> + DB 124,66 ; jl 43ea <.literal16+0xa1a> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 44ce <.literal16+0xa3e> + DB 124,66 ; jl 43ee <.literal16+0xa1e> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 44d2 <.literal16+0xa42> + DB 124,66 ; jl 43f2 <.literal16+0xa22> DB 0,240 ; add %dh,%al DB 0,0 ; add %al,(%rax) DB 0,240 ; add %dh,%al @@ -14662,13 +14556,13 @@ ALIGN 16 DB 136,136,61,137,136,136 ; mov %cl,-0x777776c3(%rax) DB 61,137,136,136,61 ; cmp $0x3d888889,%eax DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 45d5 <.literal16+0xb45> + DB 112,65 ; jo 44f5 <.literal16+0xb25> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 45d9 <.literal16+0xb49> + DB 112,65 ; jo 44f9 <.literal16+0xb29> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 45dd <.literal16+0xb4d> + DB 112,65 ; jo 44fd <.literal16+0xb2d> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 45e1 <.literal16+0xb51> + DB 112,65 ; jo 4501 <.literal16+0xb31> DB 255,0 ; incl (%rax) DB 0,0 ; add %al,(%rax) DB 255,0 ; incl (%rax) @@ -14683,7 +14577,7 @@ ALIGN 16 DB 5,255,255,255,9 ; add $0x9ffffff,%eax DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 30045d0 <_sk_callback_sse41+0x3000bee> + DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 30044f0 <_sk_callback_sse41+0x3000bcd> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -14710,7 +14604,7 @@ ALIGN 16 DB 5,255,255,255,9 ; add $0x9ffffff,%eax DB 255 ; (bad) DB 255 ; (bad) - DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3004610 <_sk_callback_sse41+0x3000c2e> + DB 255,13,255,255,255,2 ; decl 0x2ffffff(%rip) # 3004530 <_sk_callback_sse41+0x3000c0d> DB 255 ; (bad) DB 255 ; (bad) DB 255,6 ; incl (%rsi) @@ -14725,11 +14619,11 @@ ALIGN 16 DB 255,0 ; incl (%rax) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 466b <.literal16+0xbdb> + DB 127,67 ; jg 458b <.literal16+0xbbb> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 466f <.literal16+0xbdf> + DB 127,67 ; jg 458f <.literal16+0xbbf> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4673 <.literal16+0xbe3> + DB 127,67 ; jg 4593 <.literal16+0xbc3> DB 0,128,0,0,0,128 ; add %al,-0x80000000(%rax) DB 0,0 ; add %al,(%rax) DB 0,128,0,0,0,128 ; add %al,-0x80000000(%rax) @@ -14805,13 +14699,13 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 255 ; (bad) - DB 127,71 ; jg 473b <.literal16+0xcab> + DB 127,71 ; jg 465b <.literal16+0xc8b> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 473f <.literal16+0xcaf> + DB 127,71 ; jg 465f <.literal16+0xc8f> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 4743 <.literal16+0xcb3> + DB 127,71 ; jg 4663 <.literal16+0xc93> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 4747 <.literal16+0xcb7> + DB 127,71 ; jg 4667 <.literal16+0xc97> DB 208 ; (bad) DB 179,89 ; mov $0x59,%bl DB 62,208 ; ds (bad) @@ -14895,11 +14789,11 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,114 ; cmpb $0x72,(%rdi) DB 28,199 ; sbb $0xc7,%al - DB 62,114,28 ; jb,pt 47e2 <.literal16+0xd52> + DB 62,114,28 ; jb,pt 4702 <.literal16+0xd32> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 47e6 <.literal16+0xd56> + DB 62,114,28 ; jb,pt 4706 <.literal16+0xd36> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 47ea <.literal16+0xd5a> + DB 62,114,28 ; jb,pt 470a <.literal16+0xd3a> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -14943,7 +14837,7 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d675 <_sk_callback_sse41+0x3d639c93> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d595 <_sk_callback_sse41+0x3d639c72> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -14969,7 +14863,7 @@ ALIGN 16 DB 0,192 ; add %al,%al DB 63 ; (bad) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d6b5 <_sk_callback_sse41+0x3d639cd3> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d5d5 <_sk_callback_sse41+0x3d639cb2> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al @@ -14978,13 +14872,13 @@ ALIGN 16 DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al DB 63 ; (bad) - DB 114,28 ; jb 48ae <.literal16+0xe1e> + DB 114,28 ; jb 47ce <.literal16+0xdfe> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 48b2 <.literal16+0xe22> + DB 62,114,28 ; jb,pt 47d2 <.literal16+0xe02> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 48b6 <.literal16+0xe26> + DB 62,114,28 ; jb,pt 47d6 <.literal16+0xe06> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 48ba <.literal16+0xe2a> + DB 62,114,28 ; jb,pt 47da <.literal16+0xe0a> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -15005,11 +14899,11 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,114 ; cmpb $0x72,(%rdi) DB 28,199 ; sbb $0xc7,%al - DB 62,114,28 ; jb,pt 48f2 <.literal16+0xe62> + DB 62,114,28 ; jb,pt 4812 <.literal16+0xe42> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 48f6 <.literal16+0xe66> + DB 62,114,28 ; jb,pt 4816 <.literal16+0xe46> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 48fa <.literal16+0xe6a> + DB 62,114,28 ; jb,pt 481a <.literal16+0xe4a> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -15053,7 +14947,7 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d785 <_sk_callback_sse41+0x3d639da3> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d6a5 <_sk_callback_sse41+0x3d639d82> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -15079,7 +14973,7 @@ ALIGN 16 DB 0,192 ; add %al,%al DB 63 ; (bad) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d7c5 <_sk_callback_sse41+0x3d639de3> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d6e5 <_sk_callback_sse41+0x3d639dc2> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al @@ -15088,13 +14982,13 @@ ALIGN 16 DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al DB 63 ; (bad) - DB 114,28 ; jb 49be <.literal16+0xf2e> + DB 114,28 ; jb 48de <.literal16+0xf0e> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 49c2 <_sk_callback_sse41+0xfe0> + DB 62,114,28 ; jb,pt 48e2 <_sk_callback_sse41+0xfbf> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 49c6 <_sk_callback_sse41+0xfe4> + DB 62,114,28 ; jb,pt 48e6 <_sk_callback_sse41+0xfc3> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 49ca <_sk_callback_sse41+0xfe8> + DB 62,114,28 ; jb,pt 48ea <_sk_callback_sse41+0xfc7> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -15185,7 +15079,7 @@ _sk_seed_shader_sse2 LABEL PROC DB 102,15,110,199 ; movd %edi,%xmm0 DB 102,15,112,192,0 ; pshufd $0x0,%xmm0,%xmm0 DB 15,91,200 ; cvtdq2ps %xmm0,%xmm1 - DB 15,40,21,129,61,0,0 ; movaps 0x3d81(%rip),%xmm2 # 3e90 <_sk_callback_sse2+0xb9> + DB 15,40,21,241,60,0,0 ; movaps 0x3cf1(%rip),%xmm2 # 3e00 <_sk_callback_sse2+0xaf> DB 15,88,202 ; addps %xmm2,%xmm1 DB 15,16,2 ; movups (%rdx),%xmm0 DB 15,88,193 ; addps %xmm1,%xmm0 @@ -15194,7 +15088,7 @@ _sk_seed_shader_sse2 LABEL PROC DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 DB 15,88,202 ; addps %xmm2,%xmm1 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,21,112,61,0,0 ; movaps 0x3d70(%rip),%xmm2 # 3ea0 <_sk_callback_sse2+0xc9> + DB 15,40,21,224,60,0,0 ; movaps 0x3ce0(%rip),%xmm2 # 3e10 <_sk_callback_sse2+0xbf> DB 15,87,219 ; xorps %xmm3,%xmm3 DB 15,87,228 ; xorps %xmm4,%xmm4 DB 15,87,237 ; xorps %xmm5,%xmm5 @@ -15228,7 +15122,7 @@ _sk_clear_sse2 LABEL PROC PUBLIC _sk_srcatop_sse2 _sk_srcatop_sse2 LABEL PROC DB 15,89,199 ; mulps %xmm7,%xmm0 - DB 68,15,40,5,43,61,0,0 ; movaps 0x3d2b(%rip),%xmm8 # 3eb0 <_sk_callback_sse2+0xd9> + DB 68,15,40,5,155,60,0,0 ; movaps 0x3c9b(%rip),%xmm8 # 3e20 <_sk_callback_sse2+0xcf> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,89,204 ; mulps %xmm4,%xmm9 @@ -15251,7 +15145,7 @@ PUBLIC _sk_dstatop_sse2 _sk_dstatop_sse2 LABEL PROC DB 68,15,40,195 ; movaps %xmm3,%xmm8 DB 68,15,89,196 ; mulps %xmm4,%xmm8 - DB 68,15,40,13,238,60,0,0 ; movaps 0x3cee(%rip),%xmm9 # 3ec0 <_sk_callback_sse2+0xe9> + DB 68,15,40,13,94,60,0,0 ; movaps 0x3c5e(%rip),%xmm9 # 3e30 <_sk_callback_sse2+0xdf> DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 65,15,88,192 ; addps %xmm8,%xmm0 @@ -15292,7 +15186,7 @@ _sk_dstin_sse2 LABEL PROC PUBLIC _sk_srcout_sse2 _sk_srcout_sse2 LABEL PROC - DB 68,15,40,5,146,60,0,0 ; movaps 0x3c92(%rip),%xmm8 # 3ed0 <_sk_callback_sse2+0xf9> + DB 68,15,40,5,2,60,0,0 ; movaps 0x3c02(%rip),%xmm8 # 3e40 <_sk_callback_sse2+0xef> DB 68,15,92,199 ; subps %xmm7,%xmm8 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 @@ -15303,7 +15197,7 @@ _sk_srcout_sse2 LABEL PROC PUBLIC _sk_dstout_sse2 _sk_dstout_sse2 LABEL PROC - DB 68,15,40,5,130,60,0,0 ; movaps 0x3c82(%rip),%xmm8 # 3ee0 <_sk_callback_sse2+0x109> + DB 68,15,40,5,242,59,0,0 ; movaps 0x3bf2(%rip),%xmm8 # 3e50 <_sk_callback_sse2+0xff> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 15,89,196 ; mulps %xmm4,%xmm0 @@ -15318,7 +15212,7 @@ _sk_dstout_sse2 LABEL PROC PUBLIC _sk_srcover_sse2 _sk_srcover_sse2 LABEL PROC - DB 68,15,40,5,101,60,0,0 ; movaps 0x3c65(%rip),%xmm8 # 3ef0 <_sk_callback_sse2+0x119> + DB 68,15,40,5,213,59,0,0 ; movaps 0x3bd5(%rip),%xmm8 # 3e60 <_sk_callback_sse2+0x10f> DB 68,15,92,195 ; subps %xmm3,%xmm8 DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,89,204 ; mulps %xmm4,%xmm9 @@ -15336,7 +15230,7 @@ _sk_srcover_sse2 LABEL PROC PUBLIC _sk_dstover_sse2 _sk_dstover_sse2 LABEL PROC - DB 68,15,40,5,57,60,0,0 ; movaps 0x3c39(%rip),%xmm8 # 3f00 <_sk_callback_sse2+0x129> + DB 68,15,40,5,169,59,0,0 ; movaps 0x3ba9(%rip),%xmm8 # 3e70 <_sk_callback_sse2+0x11f> DB 68,15,92,199 ; subps %xmm7,%xmm8 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -15360,7 +15254,7 @@ _sk_modulate_sse2 LABEL PROC PUBLIC _sk_multiply_sse2 _sk_multiply_sse2 LABEL PROC - DB 68,15,40,5,13,60,0,0 ; movaps 0x3c0d(%rip),%xmm8 # 3f10 <_sk_callback_sse2+0x139> + DB 68,15,40,5,125,59,0,0 ; movaps 0x3b7d(%rip),%xmm8 # 3e80 <_sk_callback_sse2+0x12f> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 69,15,40,209 ; movaps %xmm9,%xmm10 @@ -15430,7 +15324,7 @@ _sk_screen_sse2 LABEL PROC PUBLIC _sk_xor__sse2 _sk_xor__sse2 LABEL PROC DB 68,15,40,195 ; movaps %xmm3,%xmm8 - DB 15,40,29,62,59,0,0 ; movaps 0x3b3e(%rip),%xmm3 # 3f20 <_sk_callback_sse2+0x149> + DB 15,40,29,174,58,0,0 ; movaps 0x3aae(%rip),%xmm3 # 3e90 <_sk_callback_sse2+0x13f> DB 68,15,40,203 ; movaps %xmm3,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 65,15,89,193 ; mulps %xmm9,%xmm0 @@ -15476,7 +15370,7 @@ _sk_darken_sse2 LABEL PROC DB 68,15,89,206 ; mulps %xmm6,%xmm9 DB 65,15,95,209 ; maxps %xmm9,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,169,58,0,0 ; movaps 0x3aa9(%rip),%xmm2 # 3f30 <_sk_callback_sse2+0x159> + DB 15,40,21,25,58,0,0 ; movaps 0x3a19(%rip),%xmm2 # 3ea0 <_sk_callback_sse2+0x14f> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -15508,7 +15402,7 @@ _sk_lighten_sse2 LABEL PROC DB 68,15,89,206 ; mulps %xmm6,%xmm9 DB 65,15,93,209 ; minps %xmm9,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,78,58,0,0 ; movaps 0x3a4e(%rip),%xmm2 # 3f40 <_sk_callback_sse2+0x169> + DB 15,40,21,190,57,0,0 ; movaps 0x39be(%rip),%xmm2 # 3eb0 <_sk_callback_sse2+0x15f> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -15543,7 +15437,7 @@ _sk_difference_sse2 LABEL PROC DB 65,15,93,209 ; minps %xmm9,%xmm2 DB 15,88,210 ; addps %xmm2,%xmm2 DB 68,15,92,194 ; subps %xmm2,%xmm8 - DB 15,40,21,232,57,0,0 ; movaps 0x39e8(%rip),%xmm2 # 3f50 <_sk_callback_sse2+0x179> + DB 15,40,21,88,57,0,0 ; movaps 0x3958(%rip),%xmm2 # 3ec0 <_sk_callback_sse2+0x16f> DB 15,92,211 ; subps %xmm3,%xmm2 DB 15,89,215 ; mulps %xmm7,%xmm2 DB 15,88,218 ; addps %xmm2,%xmm3 @@ -15568,7 +15462,7 @@ _sk_exclusion_sse2 LABEL PROC DB 15,89,214 ; mulps %xmm6,%xmm2 DB 15,88,210 ; addps %xmm2,%xmm2 DB 68,15,92,202 ; subps %xmm2,%xmm9 - DB 15,40,13,169,57,0,0 ; movaps 0x39a9(%rip),%xmm1 # 3f60 <_sk_callback_sse2+0x189> + DB 15,40,13,25,57,0,0 ; movaps 0x3919(%rip),%xmm1 # 3ed0 <_sk_callback_sse2+0x17f> DB 15,92,203 ; subps %xmm3,%xmm1 DB 15,89,207 ; mulps %xmm7,%xmm1 DB 15,88,217 ; addps %xmm1,%xmm3 @@ -15580,7 +15474,7 @@ _sk_exclusion_sse2 LABEL PROC PUBLIC _sk_colorburn_sse2 _sk_colorburn_sse2 LABEL PROC DB 68,15,40,192 ; movaps %xmm0,%xmm8 - DB 68,15,40,21,152,57,0,0 ; movaps 0x3998(%rip),%xmm10 # 3f70 <_sk_callback_sse2+0x199> + DB 68,15,40,21,8,57,0,0 ; movaps 0x3908(%rip),%xmm10 # 3ee0 <_sk_callback_sse2+0x18f> DB 69,15,40,202 ; movaps %xmm10,%xmm9 DB 68,15,92,207 ; subps %xmm7,%xmm9 DB 69,15,40,217 ; movaps %xmm9,%xmm11 @@ -15672,7 +15566,7 @@ _sk_colorburn_sse2 LABEL PROC PUBLIC _sk_colordodge_sse2 _sk_colordodge_sse2 LABEL PROC DB 68,15,40,200 ; movaps %xmm0,%xmm9 - DB 68,15,40,21,78,56,0,0 ; movaps 0x384e(%rip),%xmm10 # 3f80 <_sk_callback_sse2+0x1a9> + DB 68,15,40,21,190,55,0,0 ; movaps 0x37be(%rip),%xmm10 # 3ef0 <_sk_callback_sse2+0x19f> DB 69,15,40,218 ; movaps %xmm10,%xmm11 DB 68,15,92,223 ; subps %xmm7,%xmm11 DB 69,15,40,227 ; movaps %xmm11,%xmm12 @@ -15765,7 +15659,7 @@ _sk_hardlight_sse2 LABEL PROC DB 15,41,52,36 ; movaps %xmm6,(%rsp) DB 15,40,245 ; movaps %xmm5,%xmm6 DB 15,40,236 ; movaps %xmm4,%xmm5 - DB 68,15,40,29,0,55,0,0 ; movaps 0x3700(%rip),%xmm11 # 3f90 <_sk_callback_sse2+0x1b9> + DB 68,15,40,29,112,54,0,0 ; movaps 0x3670(%rip),%xmm11 # 3f00 <_sk_callback_sse2+0x1af> DB 69,15,40,211 ; movaps %xmm11,%xmm10 DB 68,15,92,215 ; subps %xmm7,%xmm10 DB 69,15,40,194 ; movaps %xmm10,%xmm8 @@ -15852,7 +15746,7 @@ PUBLIC _sk_overlay_sse2 _sk_overlay_sse2 LABEL PROC DB 68,15,40,193 ; movaps %xmm1,%xmm8 DB 68,15,40,232 ; movaps %xmm0,%xmm13 - DB 68,15,40,13,203,53,0,0 ; movaps 0x35cb(%rip),%xmm9 # 3fa0 <_sk_callback_sse2+0x1c9> + DB 68,15,40,13,59,53,0,0 ; movaps 0x353b(%rip),%xmm9 # 3f10 <_sk_callback_sse2+0x1bf> DB 69,15,40,209 ; movaps %xmm9,%xmm10 DB 68,15,92,215 ; subps %xmm7,%xmm10 DB 69,15,40,218 ; movaps %xmm10,%xmm11 @@ -15942,7 +15836,7 @@ _sk_softlight_sse2 LABEL PROC DB 68,15,40,213 ; movaps %xmm5,%xmm10 DB 68,15,94,215 ; divps %xmm7,%xmm10 DB 69,15,84,212 ; andps %xmm12,%xmm10 - DB 68,15,40,13,133,52,0,0 ; movaps 0x3485(%rip),%xmm9 # 3fb0 <_sk_callback_sse2+0x1d9> + DB 68,15,40,13,245,51,0,0 ; movaps 0x33f5(%rip),%xmm9 # 3f20 <_sk_callback_sse2+0x1cf> DB 69,15,40,249 ; movaps %xmm9,%xmm15 DB 69,15,92,250 ; subps %xmm10,%xmm15 DB 69,15,40,218 ; movaps %xmm10,%xmm11 @@ -15955,10 +15849,10 @@ _sk_softlight_sse2 LABEL PROC DB 65,15,40,194 ; movaps %xmm10,%xmm0 DB 15,89,192 ; mulps %xmm0,%xmm0 DB 65,15,88,194 ; addps %xmm10,%xmm0 - DB 68,15,40,53,95,52,0,0 ; movaps 0x345f(%rip),%xmm14 # 3fc0 <_sk_callback_sse2+0x1e9> + DB 68,15,40,53,207,51,0,0 ; movaps 0x33cf(%rip),%xmm14 # 3f30 <_sk_callback_sse2+0x1df> DB 69,15,88,222 ; addps %xmm14,%xmm11 DB 68,15,89,216 ; mulps %xmm0,%xmm11 - DB 68,15,40,21,95,52,0,0 ; movaps 0x345f(%rip),%xmm10 # 3fd0 <_sk_callback_sse2+0x1f9> + DB 68,15,40,21,207,51,0,0 ; movaps 0x33cf(%rip),%xmm10 # 3f40 <_sk_callback_sse2+0x1ef> DB 69,15,89,234 ; mulps %xmm10,%xmm13 DB 69,15,88,235 ; addps %xmm11,%xmm13 DB 15,88,228 ; addps %xmm4,%xmm4 @@ -16107,7 +16001,7 @@ _sk_clamp_0_sse2 LABEL PROC PUBLIC _sk_clamp_1_sse2 _sk_clamp_1_sse2 LABEL PROC - DB 68,15,40,5,107,50,0,0 ; movaps 0x326b(%rip),%xmm8 # 3fe0 <_sk_callback_sse2+0x209> + DB 68,15,40,5,219,49,0,0 ; movaps 0x31db(%rip),%xmm8 # 3f50 <_sk_callback_sse2+0x1ff> DB 65,15,93,192 ; minps %xmm8,%xmm0 DB 65,15,93,200 ; minps %xmm8,%xmm1 DB 65,15,93,208 ; minps %xmm8,%xmm2 @@ -16117,7 +16011,7 @@ _sk_clamp_1_sse2 LABEL PROC PUBLIC _sk_clamp_a_sse2 _sk_clamp_a_sse2 LABEL PROC - DB 15,93,29,96,50,0,0 ; minps 0x3260(%rip),%xmm3 # 3ff0 <_sk_callback_sse2+0x219> + DB 15,93,29,208,49,0,0 ; minps 0x31d0(%rip),%xmm3 # 3f60 <_sk_callback_sse2+0x20f> DB 15,93,195 ; minps %xmm3,%xmm0 DB 15,93,203 ; minps %xmm3,%xmm1 DB 15,93,211 ; minps %xmm3,%xmm2 @@ -16190,7 +16084,7 @@ _sk_premul_sse2 LABEL PROC PUBLIC _sk_unpremul_sse2 _sk_unpremul_sse2 LABEL PROC DB 69,15,87,192 ; xorps %xmm8,%xmm8 - DB 68,15,40,13,203,49,0,0 ; movaps 0x31cb(%rip),%xmm9 # 4000 <_sk_callback_sse2+0x229> + DB 68,15,40,13,59,49,0,0 ; movaps 0x313b(%rip),%xmm9 # 3f70 <_sk_callback_sse2+0x21f> DB 68,15,94,203 ; divps %xmm3,%xmm9 DB 68,15,194,195,4 ; cmpneqps %xmm3,%xmm8 DB 69,15,84,193 ; andps %xmm9,%xmm8 @@ -16202,20 +16096,20 @@ _sk_unpremul_sse2 LABEL PROC PUBLIC _sk_from_srgb_sse2 _sk_from_srgb_sse2 LABEL PROC - DB 68,15,40,5,182,49,0,0 ; movaps 0x31b6(%rip),%xmm8 # 4010 <_sk_callback_sse2+0x239> + DB 68,15,40,5,38,49,0,0 ; movaps 0x3126(%rip),%xmm8 # 3f80 <_sk_callback_sse2+0x22f> DB 68,15,40,232 ; movaps %xmm0,%xmm13 DB 69,15,89,232 ; mulps %xmm8,%xmm13 DB 68,15,40,216 ; movaps %xmm0,%xmm11 DB 69,15,89,219 ; mulps %xmm11,%xmm11 - DB 68,15,40,13,174,49,0,0 ; movaps 0x31ae(%rip),%xmm9 # 4020 <_sk_callback_sse2+0x249> + DB 68,15,40,13,30,49,0,0 ; movaps 0x311e(%rip),%xmm9 # 3f90 <_sk_callback_sse2+0x23f> DB 68,15,40,240 ; movaps %xmm0,%xmm14 DB 69,15,89,241 ; mulps %xmm9,%xmm14 - DB 68,15,40,21,174,49,0,0 ; movaps 0x31ae(%rip),%xmm10 # 4030 <_sk_callback_sse2+0x259> + DB 68,15,40,21,30,49,0,0 ; movaps 0x311e(%rip),%xmm10 # 3fa0 <_sk_callback_sse2+0x24f> DB 69,15,88,242 ; addps %xmm10,%xmm14 DB 69,15,89,243 ; mulps %xmm11,%xmm14 - DB 68,15,40,29,174,49,0,0 ; movaps 0x31ae(%rip),%xmm11 # 4040 <_sk_callback_sse2+0x269> + DB 68,15,40,29,30,49,0,0 ; movaps 0x311e(%rip),%xmm11 # 3fb0 <_sk_callback_sse2+0x25f> DB 69,15,88,243 ; addps %xmm11,%xmm14 - DB 68,15,40,37,178,49,0,0 ; movaps 0x31b2(%rip),%xmm12 # 4050 <_sk_callback_sse2+0x279> + DB 68,15,40,37,34,49,0,0 ; movaps 0x3122(%rip),%xmm12 # 3fc0 <_sk_callback_sse2+0x26f> DB 65,15,194,196,1 ; cmpltps %xmm12,%xmm0 DB 68,15,84,232 ; andps %xmm0,%xmm13 DB 65,15,85,198 ; andnps %xmm14,%xmm0 @@ -16252,20 +16146,20 @@ _sk_to_srgb_sse2 LABEL PROC DB 68,15,82,192 ; rsqrtps %xmm0,%xmm8 DB 69,15,83,200 ; rcpps %xmm8,%xmm9 DB 69,15,82,232 ; rsqrtps %xmm8,%xmm13 - DB 68,15,40,5,55,49,0,0 ; movaps 0x3137(%rip),%xmm8 # 4060 <_sk_callback_sse2+0x289> + DB 68,15,40,5,167,48,0,0 ; movaps 0x30a7(%rip),%xmm8 # 3fd0 <_sk_callback_sse2+0x27f> DB 68,15,40,240 ; movaps %xmm0,%xmm14 DB 69,15,89,240 ; mulps %xmm8,%xmm14 - DB 68,15,40,21,55,49,0,0 ; movaps 0x3137(%rip),%xmm10 # 4070 <_sk_callback_sse2+0x299> + DB 68,15,40,21,167,48,0,0 ; movaps 0x30a7(%rip),%xmm10 # 3fe0 <_sk_callback_sse2+0x28f> DB 69,15,89,202 ; mulps %xmm10,%xmm9 - DB 68,15,40,29,59,49,0,0 ; movaps 0x313b(%rip),%xmm11 # 4080 <_sk_callback_sse2+0x2a9> + DB 68,15,40,29,171,48,0,0 ; movaps 0x30ab(%rip),%xmm11 # 3ff0 <_sk_callback_sse2+0x29f> DB 69,15,88,203 ; addps %xmm11,%xmm9 - DB 68,15,40,37,63,49,0,0 ; movaps 0x313f(%rip),%xmm12 # 4090 <_sk_callback_sse2+0x2b9> + DB 68,15,40,37,175,48,0,0 ; movaps 0x30af(%rip),%xmm12 # 4000 <_sk_callback_sse2+0x2af> DB 69,15,89,236 ; mulps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,40,13,63,49,0,0 ; movaps 0x313f(%rip),%xmm9 # 40a0 <_sk_callback_sse2+0x2c9> + DB 68,15,40,13,175,48,0,0 ; movaps 0x30af(%rip),%xmm9 # 4010 <_sk_callback_sse2+0x2bf> DB 69,15,40,249 ; movaps %xmm9,%xmm15 DB 69,15,93,253 ; minps %xmm13,%xmm15 - DB 68,15,40,45,63,49,0,0 ; movaps 0x313f(%rip),%xmm13 # 40b0 <_sk_callback_sse2+0x2d9> + DB 68,15,40,45,175,48,0,0 ; movaps 0x30af(%rip),%xmm13 # 4020 <_sk_callback_sse2+0x2cf> DB 65,15,194,197,1 ; cmpltps %xmm13,%xmm0 DB 68,15,84,240 ; andps %xmm0,%xmm14 DB 65,15,85,199 ; andnps %xmm15,%xmm0 @@ -16313,7 +16207,7 @@ _sk_rgb_to_hsl_sse2 LABEL PROC DB 68,15,93,218 ; minps %xmm2,%xmm11 DB 65,15,40,202 ; movaps %xmm10,%xmm1 DB 65,15,92,203 ; subps %xmm11,%xmm1 - DB 68,15,40,45,152,48,0,0 ; movaps 0x3098(%rip),%xmm13 # 40c0 <_sk_callback_sse2+0x2e9> + DB 68,15,40,45,8,48,0,0 ; movaps 0x3008(%rip),%xmm13 # 4030 <_sk_callback_sse2+0x2df> DB 68,15,94,233 ; divps %xmm1,%xmm13 DB 65,15,40,194 ; movaps %xmm10,%xmm0 DB 65,15,194,192,0 ; cmpeqps %xmm8,%xmm0 @@ -16322,30 +16216,30 @@ _sk_rgb_to_hsl_sse2 LABEL PROC DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,40,241 ; movaps %xmm9,%xmm14 DB 68,15,194,242,1 ; cmpltps %xmm2,%xmm14 - DB 68,15,84,53,126,48,0,0 ; andps 0x307e(%rip),%xmm14 # 40d0 <_sk_callback_sse2+0x2f9> + DB 68,15,84,53,238,47,0,0 ; andps 0x2fee(%rip),%xmm14 # 4040 <_sk_callback_sse2+0x2ef> DB 69,15,88,244 ; addps %xmm12,%xmm14 DB 69,15,40,250 ; movaps %xmm10,%xmm15 DB 69,15,194,249,0 ; cmpeqps %xmm9,%xmm15 DB 65,15,92,208 ; subps %xmm8,%xmm2 DB 65,15,89,213 ; mulps %xmm13,%xmm2 - DB 68,15,40,37,113,48,0,0 ; movaps 0x3071(%rip),%xmm12 # 40e0 <_sk_callback_sse2+0x309> + DB 68,15,40,37,225,47,0,0 ; movaps 0x2fe1(%rip),%xmm12 # 4050 <_sk_callback_sse2+0x2ff> DB 65,15,88,212 ; addps %xmm12,%xmm2 DB 69,15,92,193 ; subps %xmm9,%xmm8 DB 69,15,89,197 ; mulps %xmm13,%xmm8 - DB 68,15,88,5,109,48,0,0 ; addps 0x306d(%rip),%xmm8 # 40f0 <_sk_callback_sse2+0x319> + DB 68,15,88,5,221,47,0,0 ; addps 0x2fdd(%rip),%xmm8 # 4060 <_sk_callback_sse2+0x30f> DB 65,15,84,215 ; andps %xmm15,%xmm2 DB 69,15,85,248 ; andnps %xmm8,%xmm15 DB 68,15,86,250 ; orps %xmm2,%xmm15 DB 68,15,84,240 ; andps %xmm0,%xmm14 DB 65,15,85,199 ; andnps %xmm15,%xmm0 DB 65,15,86,198 ; orps %xmm14,%xmm0 - DB 15,89,5,94,48,0,0 ; mulps 0x305e(%rip),%xmm0 # 4100 <_sk_callback_sse2+0x329> + DB 15,89,5,206,47,0,0 ; mulps 0x2fce(%rip),%xmm0 # 4070 <_sk_callback_sse2+0x31f> DB 69,15,40,194 ; movaps %xmm10,%xmm8 DB 69,15,194,195,4 ; cmpneqps %xmm11,%xmm8 DB 65,15,84,192 ; andps %xmm8,%xmm0 DB 69,15,92,226 ; subps %xmm10,%xmm12 DB 69,15,88,211 ; addps %xmm11,%xmm10 - DB 68,15,40,13,81,48,0,0 ; movaps 0x3051(%rip),%xmm9 # 4110 <_sk_callback_sse2+0x339> + DB 68,15,40,13,193,47,0,0 ; movaps 0x2fc1(%rip),%xmm9 # 4080 <_sk_callback_sse2+0x32f> DB 65,15,40,210 ; movaps %xmm10,%xmm2 DB 65,15,89,209 ; mulps %xmm9,%xmm2 DB 68,15,194,202,1 ; cmpltps %xmm2,%xmm9 @@ -16360,184 +16254,153 @@ _sk_rgb_to_hsl_sse2 LABEL PROC PUBLIC _sk_hsl_to_rgb_sse2 _sk_hsl_to_rgb_sse2 LABEL PROC - DB 72,129,236,168,0,0,0 ; sub $0xa8,%rsp - DB 15,41,188,36,144,0,0,0 ; movaps %xmm7,0x90(%rsp) - DB 15,41,180,36,128,0,0,0 ; movaps %xmm6,0x80(%rsp) - DB 15,41,108,36,112 ; movaps %xmm5,0x70(%rsp) - DB 15,41,100,36,96 ; movaps %xmm4,0x60(%rsp) - DB 15,41,92,36,80 ; movaps %xmm3,0x50(%rsp) - DB 68,15,40,226 ; movaps %xmm2,%xmm12 - DB 15,40,240 ; movaps %xmm0,%xmm6 + DB 72,131,236,120 ; sub $0x78,%rsp + DB 15,41,124,36,96 ; movaps %xmm7,0x60(%rsp) + DB 15,41,116,36,80 ; movaps %xmm6,0x50(%rsp) + DB 15,41,108,36,64 ; movaps %xmm5,0x40(%rsp) + DB 15,41,100,36,48 ; movaps %xmm4,0x30(%rsp) + DB 15,41,92,36,32 ; movaps %xmm3,0x20(%rsp) + DB 68,15,40,210 ; movaps %xmm2,%xmm10 + DB 15,40,224 ; movaps %xmm0,%xmm4 DB 184,0,0,0,63 ; mov $0x3f000000,%eax - DB 102,15,110,192 ; movd %eax,%xmm0 - DB 15,198,192,0 ; shufps $0x0,%xmm0,%xmm0 - DB 69,15,40,196 ; movaps %xmm12,%xmm8 - DB 68,15,194,192,1 ; cmpltps %xmm0,%xmm8 - DB 68,15,40,208 ; movaps %xmm0,%xmm10 - DB 68,15,41,84,36,48 ; movaps %xmm10,0x30(%rsp) - DB 15,40,61,228,47,0,0 ; movaps 0x2fe4(%rip),%xmm7 # 4120 <_sk_callback_sse2+0x349> - DB 15,40,193 ; movaps %xmm1,%xmm0 - DB 15,40,225 ; movaps %xmm1,%xmm4 - DB 15,87,210 ; xorps %xmm2,%xmm2 - DB 15,194,209,0 ; cmpeqps %xmm1,%xmm2 - DB 15,41,84,36,32 ; movaps %xmm2,0x20(%rsp) - DB 15,88,207 ; addps %xmm7,%xmm1 - DB 65,15,89,204 ; mulps %xmm12,%xmm1 - DB 65,15,88,196 ; addps %xmm12,%xmm0 - DB 65,15,89,228 ; mulps %xmm12,%xmm4 - DB 15,92,196 ; subps %xmm4,%xmm0 - DB 65,15,84,200 ; andps %xmm8,%xmm1 - DB 68,15,85,192 ; andnps %xmm0,%xmm8 - DB 68,15,86,193 ; orps %xmm1,%xmm8 - DB 15,40,13,189,47,0,0 ; movaps 0x2fbd(%rip),%xmm1 # 4130 <_sk_callback_sse2+0x359> - DB 15,88,206 ; addps %xmm6,%xmm1 - DB 184,0,0,0,0 ; mov $0x0,%eax - DB 185,0,0,128,63 ; mov $0x3f800000,%ecx - DB 102,68,15,110,241 ; movd %ecx,%xmm14 - DB 69,15,198,246,0 ; shufps $0x0,%xmm14,%xmm14 - DB 65,15,40,198 ; movaps %xmm14,%xmm0 - DB 15,194,193,1 ; cmpltps %xmm1,%xmm0 - DB 68,15,40,61,166,47,0,0 ; movaps 0x2fa6(%rip),%xmm15 # 4140 <_sk_callback_sse2+0x369> - DB 15,40,225 ; movaps %xmm1,%xmm4 - DB 65,15,88,231 ; addps %xmm15,%xmm4 - DB 15,84,224 ; andps %xmm0,%xmm4 - DB 15,85,193 ; andnps %xmm1,%xmm0 - DB 15,86,196 ; orps %xmm4,%xmm0 - DB 102,15,110,208 ; movd %eax,%xmm2 - DB 15,198,210,0 ; shufps $0x0,%xmm2,%xmm2 - DB 15,41,84,36,16 ; movaps %xmm2,0x10(%rsp) - DB 15,40,225 ; movaps %xmm1,%xmm4 - DB 15,194,202,1 ; cmpltps %xmm2,%xmm1 - DB 15,88,231 ; addps %xmm7,%xmm4 - DB 15,84,225 ; andps %xmm1,%xmm4 - DB 15,85,200 ; andnps %xmm0,%xmm1 - DB 15,86,204 ; orps %xmm4,%xmm1 - DB 69,15,40,236 ; movaps %xmm12,%xmm13 - DB 69,15,88,237 ; addps %xmm13,%xmm13 - DB 69,15,92,232 ; subps %xmm8,%xmm13 + DB 102,68,15,110,248 ; movd %eax,%xmm15 + DB 69,15,198,255,0 ; shufps $0x0,%xmm15,%xmm15 + DB 69,15,40,202 ; movaps %xmm10,%xmm9 + DB 69,15,194,207,1 ; cmpltps %xmm15,%xmm9 + DB 15,40,209 ; movaps %xmm1,%xmm2 + DB 69,15,87,219 ; xorps %xmm11,%xmm11 + DB 68,15,194,217,0 ; cmpeqps %xmm1,%xmm11 + DB 65,15,89,202 ; mulps %xmm10,%xmm1 + DB 15,92,209 ; subps %xmm1,%xmm2 + DB 65,15,84,201 ; andps %xmm9,%xmm1 + DB 68,15,85,202 ; andnps %xmm2,%xmm9 + DB 68,15,86,201 ; orps %xmm1,%xmm9 + DB 69,15,88,202 ; addps %xmm10,%xmm9 + DB 69,15,40,226 ; movaps %xmm10,%xmm12 + DB 69,15,88,228 ; addps %xmm12,%xmm12 + DB 69,15,92,225 ; subps %xmm9,%xmm12 + DB 15,40,21,54,47,0,0 ; movaps 0x2f36(%rip),%xmm2 # 4090 <_sk_callback_sse2+0x33f> + DB 15,88,212 ; addps %xmm4,%xmm2 + DB 243,15,91,202 ; cvttps2dq %xmm2,%xmm1 + DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 + DB 15,40,218 ; movaps %xmm2,%xmm3 + DB 15,194,217,1 ; cmpltps %xmm1,%xmm3 + DB 15,84,29,46,47,0,0 ; andps 0x2f2e(%rip),%xmm3 # 40a0 <_sk_callback_sse2+0x34f> + DB 15,92,203 ; subps %xmm3,%xmm1 + DB 15,92,209 ; subps %xmm1,%xmm2 DB 184,171,170,42,62 ; mov $0x3e2aaaab,%eax - DB 69,15,40,200 ; movaps %xmm8,%xmm9 - DB 69,15,92,205 ; subps %xmm13,%xmm9 - DB 68,15,89,13,101,47,0,0 ; mulps 0x2f65(%rip),%xmm9 # 4150 <_sk_callback_sse2+0x379> + DB 65,15,40,249 ; movaps %xmm9,%xmm7 + DB 65,15,92,252 ; subps %xmm12,%xmm7 + DB 68,15,40,53,35,47,0,0 ; movaps 0x2f23(%rip),%xmm14 # 40b0 <_sk_callback_sse2+0x35f> + DB 68,15,40,194 ; movaps %xmm2,%xmm8 + DB 69,15,89,198 ; mulps %xmm14,%xmm8 DB 185,171,170,42,63 ; mov $0x3f2aaaab,%ecx DB 102,15,110,217 ; movd %ecx,%xmm3 DB 15,198,219,0 ; shufps $0x0,%xmm3,%xmm3 DB 15,41,28,36 ; movaps %xmm3,(%rsp) - DB 15,40,45,93,47,0,0 ; movaps 0x2f5d(%rip),%xmm5 # 4160 <_sk_callback_sse2+0x389> - DB 15,40,229 ; movaps %xmm5,%xmm4 - DB 15,92,225 ; subps %xmm1,%xmm4 - DB 15,40,209 ; movaps %xmm1,%xmm2 - DB 68,15,40,217 ; movaps %xmm1,%xmm11 - DB 15,40,193 ; movaps %xmm1,%xmm0 - DB 15,194,203,1 ; cmpltps %xmm3,%xmm1 - DB 65,15,89,225 ; mulps %xmm9,%xmm4 - DB 65,15,88,229 ; addps %xmm13,%xmm4 - DB 15,84,225 ; andps %xmm1,%xmm4 - DB 65,15,85,205 ; andnps %xmm13,%xmm1 - DB 15,86,204 ; orps %xmm4,%xmm1 - DB 65,15,194,194,1 ; cmpltps %xmm10,%xmm0 - DB 65,15,40,224 ; movaps %xmm8,%xmm4 - DB 15,84,224 ; andps %xmm0,%xmm4 - DB 15,85,193 ; andnps %xmm1,%xmm0 - DB 15,86,196 ; orps %xmm4,%xmm0 - DB 102,68,15,110,208 ; movd %eax,%xmm10 - DB 69,15,198,210,0 ; shufps $0x0,%xmm10,%xmm10 - DB 65,15,194,210,1 ; cmpltps %xmm10,%xmm2 - DB 69,15,89,217 ; mulps %xmm9,%xmm11 - DB 69,15,88,221 ; addps %xmm13,%xmm11 - DB 68,15,84,218 ; andps %xmm2,%xmm11 - DB 15,85,208 ; andnps %xmm0,%xmm2 - DB 65,15,86,211 ; orps %xmm11,%xmm2 - DB 15,40,68,36,32 ; movaps 0x20(%rsp),%xmm0 + DB 15,40,202 ; movaps %xmm2,%xmm1 + DB 15,40,194 ; movaps %xmm2,%xmm0 + DB 15,194,211,1 ; cmpltps %xmm3,%xmm2 + DB 15,40,53,9,47,0,0 ; movaps 0x2f09(%rip),%xmm6 # 40c0 <_sk_callback_sse2+0x36f> + DB 15,40,238 ; movaps %xmm6,%xmm5 + DB 65,15,92,232 ; subps %xmm8,%xmm5 + DB 15,89,239 ; mulps %xmm7,%xmm5 + DB 65,15,88,236 ; addps %xmm12,%xmm5 + DB 15,84,234 ; andps %xmm2,%xmm5 + DB 65,15,85,212 ; andnps %xmm12,%xmm2 + DB 15,86,213 ; orps %xmm5,%xmm2 + DB 65,15,194,199,1 ; cmpltps %xmm15,%xmm0 + DB 68,15,41,124,36,16 ; movaps %xmm15,0x10(%rsp) + DB 65,15,40,233 ; movaps %xmm9,%xmm5 + DB 15,84,232 ; andps %xmm0,%xmm5 DB 15,85,194 ; andnps %xmm2,%xmm0 - DB 15,41,68,36,64 ; movaps %xmm0,0x40(%rsp) - DB 65,15,40,198 ; movaps %xmm14,%xmm0 - DB 15,194,198,1 ; cmpltps %xmm6,%xmm0 - DB 15,40,206 ; movaps %xmm6,%xmm1 - DB 65,15,88,207 ; addps %xmm15,%xmm1 - DB 15,84,200 ; andps %xmm0,%xmm1 - DB 15,85,198 ; andnps %xmm6,%xmm0 - DB 15,86,193 ; orps %xmm1,%xmm0 - DB 15,40,206 ; movaps %xmm6,%xmm1 - DB 15,194,76,36,16,1 ; cmpltps 0x10(%rsp),%xmm1 - DB 15,40,214 ; movaps %xmm6,%xmm2 - DB 15,88,215 ; addps %xmm7,%xmm2 - DB 15,84,209 ; andps %xmm1,%xmm2 + DB 15,86,197 ; orps %xmm5,%xmm0 + DB 102,15,110,232 ; movd %eax,%xmm5 + DB 15,198,237,0 ; shufps $0x0,%xmm5,%xmm5 + DB 15,194,205,1 ; cmpltps %xmm5,%xmm1 + DB 68,15,89,199 ; mulps %xmm7,%xmm8 + DB 69,15,88,196 ; addps %xmm12,%xmm8 + DB 68,15,84,193 ; andps %xmm1,%xmm8 DB 15,85,200 ; andnps %xmm0,%xmm1 - DB 15,86,202 ; orps %xmm2,%xmm1 - DB 15,40,197 ; movaps %xmm5,%xmm0 + DB 65,15,86,200 ; orps %xmm8,%xmm1 + DB 69,15,40,195 ; movaps %xmm11,%xmm8 + DB 68,15,85,193 ; andnps %xmm1,%xmm8 + DB 243,15,91,196 ; cvttps2dq %xmm4,%xmm0 + DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 + DB 15,40,204 ; movaps %xmm4,%xmm1 + DB 15,194,200,1 ; cmpltps %xmm0,%xmm1 + DB 15,84,13,125,46,0,0 ; andps 0x2e7d(%rip),%xmm1 # 40a0 <_sk_callback_sse2+0x34f> DB 15,92,193 ; subps %xmm1,%xmm0 - DB 15,40,217 ; movaps %xmm1,%xmm3 - DB 15,40,225 ; movaps %xmm1,%xmm4 - DB 15,40,209 ; movaps %xmm1,%xmm2 - DB 15,194,12,36,1 ; cmpltps (%rsp),%xmm1 - DB 65,15,89,193 ; mulps %xmm9,%xmm0 - DB 65,15,88,197 ; addps %xmm13,%xmm0 - DB 15,84,193 ; andps %xmm1,%xmm0 - DB 65,15,85,205 ; andnps %xmm13,%xmm1 - DB 15,86,200 ; orps %xmm0,%xmm1 - DB 68,15,40,92,36,48 ; movaps 0x30(%rsp),%xmm11 - DB 65,15,194,211,1 ; cmpltps %xmm11,%xmm2 - DB 65,15,40,192 ; movaps %xmm8,%xmm0 - DB 15,84,194 ; andps %xmm2,%xmm0 - DB 15,85,209 ; andnps %xmm1,%xmm2 - DB 15,86,208 ; orps %xmm0,%xmm2 - DB 65,15,194,218,1 ; cmpltps %xmm10,%xmm3 - DB 65,15,89,225 ; mulps %xmm9,%xmm4 - DB 65,15,88,229 ; addps %xmm13,%xmm4 - DB 15,84,227 ; andps %xmm3,%xmm4 - DB 15,85,218 ; andnps %xmm2,%xmm3 - DB 15,86,220 ; orps %xmm4,%xmm3 - DB 15,40,100,36,32 ; movaps 0x20(%rsp),%xmm4 DB 15,40,204 ; movaps %xmm4,%xmm1 - DB 15,85,203 ; andnps %xmm3,%xmm1 - DB 15,88,53,112,46,0,0 ; addps 0x2e70(%rip),%xmm6 # 4170 <_sk_callback_sse2+0x399> - DB 15,88,254 ; addps %xmm6,%xmm7 - DB 68,15,194,246,1 ; cmpltps %xmm6,%xmm14 - DB 68,15,88,254 ; addps %xmm6,%xmm15 - DB 69,15,84,254 ; andps %xmm14,%xmm15 - DB 68,15,85,246 ; andnps %xmm6,%xmm14 - DB 15,194,116,36,16,1 ; cmpltps 0x10(%rsp),%xmm6 - DB 69,15,86,247 ; orps %xmm15,%xmm14 - DB 15,84,254 ; andps %xmm6,%xmm7 - DB 65,15,85,246 ; andnps %xmm14,%xmm6 - DB 15,86,247 ; orps %xmm7,%xmm6 - DB 15,40,254 ; movaps %xmm6,%xmm7 - DB 65,15,194,250,1 ; cmpltps %xmm10,%xmm7 - DB 15,40,198 ; movaps %xmm6,%xmm0 - DB 65,15,194,195,1 ; cmpltps %xmm11,%xmm0 - DB 15,92,238 ; subps %xmm6,%xmm5 + DB 15,92,200 ; subps %xmm0,%xmm1 + DB 15,40,193 ; movaps %xmm1,%xmm0 + DB 65,15,89,198 ; mulps %xmm14,%xmm0 + DB 68,15,40,239 ; movaps %xmm7,%xmm13 + DB 68,15,89,232 ; mulps %xmm0,%xmm13 DB 15,40,222 ; movaps %xmm6,%xmm3 - DB 15,194,52,36,1 ; cmpltps (%rsp),%xmm6 - DB 65,15,89,217 ; mulps %xmm9,%xmm3 - DB 65,15,89,233 ; mulps %xmm9,%xmm5 - DB 65,15,88,221 ; addps %xmm13,%xmm3 - DB 65,15,88,237 ; addps %xmm13,%xmm5 - DB 15,84,238 ; andps %xmm6,%xmm5 - DB 65,15,85,245 ; andnps %xmm13,%xmm6 - DB 15,86,245 ; orps %xmm5,%xmm6 - DB 68,15,84,192 ; andps %xmm0,%xmm8 - DB 15,85,198 ; andnps %xmm6,%xmm0 - DB 65,15,86,192 ; orps %xmm8,%xmm0 - DB 15,84,223 ; andps %xmm7,%xmm3 - DB 15,85,248 ; andnps %xmm0,%xmm7 - DB 15,86,251 ; orps %xmm3,%xmm7 + DB 15,92,216 ; subps %xmm0,%xmm3 + DB 15,89,223 ; mulps %xmm7,%xmm3 + DB 15,40,209 ; movaps %xmm1,%xmm2 + DB 15,40,193 ; movaps %xmm1,%xmm0 + DB 15,194,12,36,1 ; cmpltps (%rsp),%xmm1 + DB 65,15,88,220 ; addps %xmm12,%xmm3 + DB 15,84,217 ; andps %xmm1,%xmm3 + DB 65,15,85,204 ; andnps %xmm12,%xmm1 + DB 15,86,203 ; orps %xmm3,%xmm1 + DB 65,15,194,199,1 ; cmpltps %xmm15,%xmm0 + DB 65,15,40,217 ; movaps %xmm9,%xmm3 + DB 15,84,216 ; andps %xmm0,%xmm3 + DB 15,85,193 ; andnps %xmm1,%xmm0 + DB 15,86,195 ; orps %xmm3,%xmm0 + DB 15,194,213,1 ; cmpltps %xmm5,%xmm2 + DB 69,15,88,236 ; addps %xmm12,%xmm13 + DB 68,15,84,234 ; andps %xmm2,%xmm13 + DB 15,85,208 ; andnps %xmm0,%xmm2 + DB 65,15,86,213 ; orps %xmm13,%xmm2 + DB 65,15,40,203 ; movaps %xmm11,%xmm1 + DB 15,85,202 ; andnps %xmm2,%xmm1 + DB 15,88,37,64,46,0,0 ; addps 0x2e40(%rip),%xmm4 # 40d0 <_sk_callback_sse2+0x37f> + DB 243,15,91,196 ; cvttps2dq %xmm4,%xmm0 + DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 + DB 15,40,212 ; movaps %xmm4,%xmm2 + DB 15,194,208,1 ; cmpltps %xmm0,%xmm2 + DB 15,84,21,251,45,0,0 ; andps 0x2dfb(%rip),%xmm2 # 40a0 <_sk_callback_sse2+0x34f> + DB 15,92,194 ; subps %xmm2,%xmm0 + DB 15,92,224 ; subps %xmm0,%xmm4 + DB 68,15,40,252 ; movaps %xmm4,%xmm15 + DB 68,15,194,253,1 ; cmpltps %xmm5,%xmm15 + DB 68,15,89,244 ; mulps %xmm4,%xmm14 + DB 65,15,92,246 ; subps %xmm14,%xmm6 + DB 15,89,247 ; mulps %xmm7,%xmm6 + DB 65,15,89,254 ; mulps %xmm14,%xmm7 DB 15,40,196 ; movaps %xmm4,%xmm0 - DB 68,15,84,224 ; andps %xmm0,%xmm12 - DB 15,85,199 ; andnps %xmm7,%xmm0 - DB 15,40,84,36,64 ; movaps 0x40(%rsp),%xmm2 - DB 65,15,86,212 ; orps %xmm12,%xmm2 - DB 65,15,86,204 ; orps %xmm12,%xmm1 - DB 68,15,86,224 ; orps %xmm0,%xmm12 + DB 15,194,68,36,16,1 ; cmpltps 0x10(%rsp),%xmm0 + DB 15,194,36,36,1 ; cmpltps (%rsp),%xmm4 + DB 65,15,88,252 ; addps %xmm12,%xmm7 + DB 65,15,88,244 ; addps %xmm12,%xmm6 + DB 15,84,244 ; andps %xmm4,%xmm6 + DB 65,15,85,228 ; andnps %xmm12,%xmm4 + DB 15,86,230 ; orps %xmm6,%xmm4 + DB 68,15,84,200 ; andps %xmm0,%xmm9 + DB 15,85,196 ; andnps %xmm4,%xmm0 + DB 65,15,86,193 ; orps %xmm9,%xmm0 + DB 65,15,84,255 ; andps %xmm15,%xmm7 + DB 68,15,85,248 ; andnps %xmm0,%xmm15 + DB 68,15,86,255 ; orps %xmm7,%xmm15 + DB 69,15,84,211 ; andps %xmm11,%xmm10 + DB 69,15,85,223 ; andnps %xmm15,%xmm11 + DB 69,15,86,194 ; orps %xmm10,%xmm8 + DB 65,15,86,202 ; orps %xmm10,%xmm1 + DB 69,15,86,211 ; orps %xmm11,%xmm10 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,194 ; movaps %xmm2,%xmm0 - DB 65,15,40,212 ; movaps %xmm12,%xmm2 - DB 15,40,92,36,80 ; movaps 0x50(%rsp),%xmm3 - DB 15,40,100,36,96 ; movaps 0x60(%rsp),%xmm4 - DB 15,40,108,36,112 ; movaps 0x70(%rsp),%xmm5 - DB 15,40,180,36,128,0,0,0 ; movaps 0x80(%rsp),%xmm6 - DB 15,40,188,36,144,0,0,0 ; movaps 0x90(%rsp),%xmm7 - DB 72,129,196,168,0,0,0 ; add $0xa8,%rsp + DB 65,15,40,192 ; movaps %xmm8,%xmm0 + DB 65,15,40,210 ; movaps %xmm10,%xmm2 + DB 15,40,92,36,32 ; movaps 0x20(%rsp),%xmm3 + DB 15,40,100,36,48 ; movaps 0x30(%rsp),%xmm4 + DB 15,40,108,36,64 ; movaps 0x40(%rsp),%xmm5 + DB 15,40,116,36,80 ; movaps 0x50(%rsp),%xmm6 + DB 15,40,124,36,96 ; movaps 0x60(%rsp),%xmm7 + DB 72,131,196,120 ; add $0x78,%rsp DB 255,224 ; jmpq *%rax PUBLIC _sk_scale_1_float_sse2 @@ -16561,7 +16424,7 @@ _sk_scale_u8_sse2 LABEL PROC DB 102,69,15,96,193 ; punpcklbw %xmm9,%xmm8 DB 102,69,15,97,193 ; punpcklwd %xmm9,%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,125,45,0,0 ; mulps 0x2d7d(%rip),%xmm8 # 4180 <_sk_callback_sse2+0x3a9> + DB 68,15,89,5,99,45,0,0 ; mulps 0x2d63(%rip),%xmm8 # 40e0 <_sk_callback_sse2+0x38f> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 65,15,89,208 ; mulps %xmm8,%xmm2 @@ -16598,7 +16461,7 @@ _sk_lerp_u8_sse2 LABEL PROC DB 102,69,15,96,193 ; punpcklbw %xmm9,%xmm8 DB 102,69,15,97,193 ; punpcklwd %xmm9,%xmm8 DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,27,45,0,0 ; mulps 0x2d1b(%rip),%xmm8 # 4190 <_sk_callback_sse2+0x3b9> + DB 68,15,89,5,1,45,0,0 ; mulps 0x2d01(%rip),%xmm8 # 40f0 <_sk_callback_sse2+0x39f> DB 15,92,196 ; subps %xmm4,%xmm0 DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -16621,17 +16484,17 @@ _sk_lerp_565_sse2 LABEL PROC DB 243,68,15,126,4,120 ; movq (%rax,%rdi,2),%xmm8 DB 102,15,239,219 ; pxor %xmm3,%xmm3 DB 102,68,15,97,195 ; punpcklwd %xmm3,%xmm8 - DB 102,15,111,29,227,44,0,0 ; movdqa 0x2ce3(%rip),%xmm3 # 41a0 <_sk_callback_sse2+0x3c9> + DB 102,15,111,29,201,44,0,0 ; movdqa 0x2cc9(%rip),%xmm3 # 4100 <_sk_callback_sse2+0x3af> DB 102,65,15,219,216 ; pand %xmm8,%xmm3 DB 68,15,91,203 ; cvtdq2ps %xmm3,%xmm9 - DB 68,15,89,13,226,44,0,0 ; mulps 0x2ce2(%rip),%xmm9 # 41b0 <_sk_callback_sse2+0x3d9> - DB 102,15,111,29,234,44,0,0 ; movdqa 0x2cea(%rip),%xmm3 # 41c0 <_sk_callback_sse2+0x3e9> + DB 68,15,89,13,200,44,0,0 ; mulps 0x2cc8(%rip),%xmm9 # 4110 <_sk_callback_sse2+0x3bf> + DB 102,15,111,29,208,44,0,0 ; movdqa 0x2cd0(%rip),%xmm3 # 4120 <_sk_callback_sse2+0x3cf> DB 102,65,15,219,216 ; pand %xmm8,%xmm3 DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,235,44,0,0 ; mulps 0x2ceb(%rip),%xmm3 # 41d0 <_sk_callback_sse2+0x3f9> - DB 102,68,15,219,5,242,44,0,0 ; pand 0x2cf2(%rip),%xmm8 # 41e0 <_sk_callback_sse2+0x409> + DB 15,89,29,209,44,0,0 ; mulps 0x2cd1(%rip),%xmm3 # 4130 <_sk_callback_sse2+0x3df> + DB 102,68,15,219,5,216,44,0,0 ; pand 0x2cd8(%rip),%xmm8 # 4140 <_sk_callback_sse2+0x3ef> DB 69,15,91,192 ; cvtdq2ps %xmm8,%xmm8 - DB 68,15,89,5,246,44,0,0 ; mulps 0x2cf6(%rip),%xmm8 # 41f0 <_sk_callback_sse2+0x419> + DB 68,15,89,5,220,44,0,0 ; mulps 0x2cdc(%rip),%xmm8 # 4150 <_sk_callback_sse2+0x3ff> DB 15,92,196 ; subps %xmm4,%xmm0 DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 15,88,196 ; addps %xmm4,%xmm0 @@ -16642,7 +16505,7 @@ _sk_lerp_565_sse2 LABEL PROC DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 15,88,214 ; addps %xmm6,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,224,44,0,0 ; movaps 0x2ce0(%rip),%xmm3 # 4200 <_sk_callback_sse2+0x429> + DB 15,40,29,198,44,0,0 ; movaps 0x2cc6(%rip),%xmm3 # 4160 <_sk_callback_sse2+0x40f> DB 255,224 ; jmpq *%rax PUBLIC _sk_load_tables_sse2 @@ -16651,7 +16514,7 @@ _sk_load_tables_sse2 LABEL PROC DB 76,139,0 ; mov (%rax),%r8 DB 76,139,72,8 ; mov 0x8(%rax),%r9 DB 243,69,15,111,12,184 ; movdqu (%r8,%rdi,4),%xmm9 - DB 102,68,15,111,5,214,44,0,0 ; movdqa 0x2cd6(%rip),%xmm8 # 4210 <_sk_callback_sse2+0x439> + DB 102,68,15,111,5,188,44,0,0 ; movdqa 0x2cbc(%rip),%xmm8 # 4170 <_sk_callback_sse2+0x41f> DB 102,65,15,111,193 ; movdqa %xmm9,%xmm0 DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,15,112,200,78 ; pshufd $0x4e,%xmm0,%xmm1 @@ -16706,7 +16569,7 @@ _sk_load_tables_sse2 LABEL PROC DB 65,15,20,208 ; unpcklps %xmm8,%xmm2 DB 102,65,15,114,209,24 ; psrld $0x18,%xmm9 DB 65,15,91,217 ; cvtdq2ps %xmm9,%xmm3 - DB 15,89,29,227,43,0,0 ; mulps 0x2be3(%rip),%xmm3 # 4220 <_sk_callback_sse2+0x449> + DB 15,89,29,201,43,0,0 ; mulps 0x2bc9(%rip),%xmm3 # 4180 <_sk_callback_sse2+0x42f> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -16723,7 +16586,7 @@ _sk_load_tables_u16_be_sse2 LABEL PROC DB 102,65,15,111,201 ; movdqa %xmm9,%xmm1 DB 102,15,97,200 ; punpcklwd %xmm0,%xmm1 DB 102,68,15,105,200 ; punpckhwd %xmm0,%xmm9 - DB 102,68,15,111,21,182,43,0,0 ; movdqa 0x2bb6(%rip),%xmm10 # 4230 <_sk_callback_sse2+0x459> + DB 102,68,15,111,21,156,43,0,0 ; movdqa 0x2b9c(%rip),%xmm10 # 4190 <_sk_callback_sse2+0x43f> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,194 ; pand %xmm10,%xmm0 DB 102,69,15,239,192 ; pxor %xmm8,%xmm8 @@ -16784,7 +16647,7 @@ _sk_load_tables_u16_be_sse2 LABEL PROC DB 102,65,15,235,217 ; por %xmm9,%xmm3 DB 102,65,15,97,216 ; punpcklwd %xmm8,%xmm3 DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,165,42,0,0 ; mulps 0x2aa5(%rip),%xmm3 # 4240 <_sk_callback_sse2+0x469> + DB 15,89,29,139,42,0,0 ; mulps 0x2a8b(%rip),%xmm3 # 41a0 <_sk_callback_sse2+0x44f> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -16804,7 +16667,7 @@ _sk_load_tables_rgb_u16_be_sse2 LABEL PROC DB 102,68,15,97,208 ; punpcklwd %xmm0,%xmm10 DB 102,65,15,111,195 ; movdqa %xmm11,%xmm0 DB 102,65,15,97,194 ; punpcklwd %xmm10,%xmm0 - DB 102,68,15,111,5,101,42,0,0 ; movdqa 0x2a65(%rip),%xmm8 # 4250 <_sk_callback_sse2+0x479> + DB 102,68,15,111,5,75,42,0,0 ; movdqa 0x2a4b(%rip),%xmm8 # 41b0 <_sk_callback_sse2+0x45f> DB 102,15,112,200,78 ; pshufd $0x4e,%xmm0,%xmm1 DB 102,65,15,219,192 ; pand %xmm8,%xmm0 DB 102,69,15,239,201 ; pxor %xmm9,%xmm9 @@ -16859,7 +16722,7 @@ _sk_load_tables_rgb_u16_be_sse2 LABEL PROC DB 15,20,211 ; unpcklps %xmm3,%xmm2 DB 65,15,20,208 ; unpcklps %xmm8,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,116,41,0,0 ; movaps 0x2974(%rip),%xmm3 # 4260 <_sk_callback_sse2+0x489> + DB 15,40,29,90,41,0,0 ; movaps 0x295a(%rip),%xmm3 # 41c0 <_sk_callback_sse2+0x46f> DB 255,224 ; jmpq *%rax PUBLIC _sk_byte_tables_sse2 @@ -16867,7 +16730,7 @@ _sk_byte_tables_sse2 LABEL PROC DB 65,86 ; push %r14 DB 83 ; push %rbx DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,117,41,0,0 ; movaps 0x2975(%rip),%xmm8 # 4270 <_sk_callback_sse2+0x499> + DB 68,15,40,5,91,41,0,0 ; movaps 0x295b(%rip),%xmm8 # 41d0 <_sk_callback_sse2+0x47f> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,91,192 ; cvtps2dq %xmm0,%xmm0 DB 102,72,15,126,193 ; movq %xmm0,%rcx @@ -16894,7 +16757,7 @@ _sk_byte_tables_sse2 LABEL PROC DB 102,65,15,96,193 ; punpcklbw %xmm9,%xmm0 DB 102,65,15,97,193 ; punpcklwd %xmm9,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,21,18,41,0,0 ; movaps 0x2912(%rip),%xmm10 # 4280 <_sk_callback_sse2+0x4a9> + DB 68,15,40,21,248,40,0,0 ; movaps 0x28f8(%rip),%xmm10 # 41e0 <_sk_callback_sse2+0x48f> DB 65,15,89,194 ; mulps %xmm10,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,91,201 ; cvtps2dq %xmm1,%xmm1 @@ -17008,7 +16871,7 @@ _sk_byte_tables_rgb_sse2 LABEL PROC DB 102,65,15,96,193 ; punpcklbw %xmm9,%xmm0 DB 102,65,15,97,193 ; punpcklwd %xmm9,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,21,101,39,0,0 ; movaps 0x2765(%rip),%xmm10 # 4290 <_sk_callback_sse2+0x4b9> + DB 68,15,40,21,75,39,0,0 ; movaps 0x274b(%rip),%xmm10 # 41f0 <_sk_callback_sse2+0x49f> DB 65,15,89,194 ; mulps %xmm10,%xmm0 DB 65,15,89,200 ; mulps %xmm8,%xmm1 DB 102,15,91,201 ; cvtps2dq %xmm1,%xmm1 @@ -17195,15 +17058,15 @@ _sk_parametric_r_sse2 LABEL PROC DB 69,15,88,209 ; addps %xmm9,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,202 ; cvtdq2ps %xmm10,%xmm9 - DB 68,15,89,13,164,36,0,0 ; mulps 0x24a4(%rip),%xmm9 # 42a0 <_sk_callback_sse2+0x4c9> - DB 68,15,84,21,172,36,0,0 ; andps 0x24ac(%rip),%xmm10 # 42b0 <_sk_callback_sse2+0x4d9> - DB 68,15,86,21,180,36,0,0 ; orps 0x24b4(%rip),%xmm10 # 42c0 <_sk_callback_sse2+0x4e9> - DB 68,15,88,13,188,36,0,0 ; addps 0x24bc(%rip),%xmm9 # 42d0 <_sk_callback_sse2+0x4f9> - DB 68,15,40,37,196,36,0,0 ; movaps 0x24c4(%rip),%xmm12 # 42e0 <_sk_callback_sse2+0x509> + DB 68,15,89,13,138,36,0,0 ; mulps 0x248a(%rip),%xmm9 # 4200 <_sk_callback_sse2+0x4af> + DB 68,15,84,21,146,36,0,0 ; andps 0x2492(%rip),%xmm10 # 4210 <_sk_callback_sse2+0x4bf> + DB 68,15,86,21,154,36,0,0 ; orps 0x249a(%rip),%xmm10 # 4220 <_sk_callback_sse2+0x4cf> + DB 68,15,88,13,162,36,0,0 ; addps 0x24a2(%rip),%xmm9 # 4230 <_sk_callback_sse2+0x4df> + DB 68,15,40,37,170,36,0,0 ; movaps 0x24aa(%rip),%xmm12 # 4240 <_sk_callback_sse2+0x4ef> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,88,21,196,36,0,0 ; addps 0x24c4(%rip),%xmm10 # 42f0 <_sk_callback_sse2+0x519> - DB 68,15,40,37,204,36,0,0 ; movaps 0x24cc(%rip),%xmm12 # 4300 <_sk_callback_sse2+0x529> + DB 68,15,88,21,170,36,0,0 ; addps 0x24aa(%rip),%xmm10 # 4250 <_sk_callback_sse2+0x4ff> + DB 68,15,40,37,178,36,0,0 ; movaps 0x24b2(%rip),%xmm12 # 4260 <_sk_callback_sse2+0x50f> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 @@ -17211,22 +17074,22 @@ _sk_parametric_r_sse2 LABEL PROC DB 69,15,91,226 ; cvtdq2ps %xmm10,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,194,236,1 ; cmpltps %xmm12,%xmm13 - DB 68,15,40,21,182,36,0,0 ; movaps 0x24b6(%rip),%xmm10 # 4310 <_sk_callback_sse2+0x539> + DB 68,15,40,21,156,36,0,0 ; movaps 0x249c(%rip),%xmm10 # 4270 <_sk_callback_sse2+0x51f> DB 69,15,84,234 ; andps %xmm10,%xmm13 DB 69,15,87,219 ; xorps %xmm11,%xmm11 DB 69,15,92,229 ; subps %xmm13,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,92,236 ; subps %xmm12,%xmm13 - DB 68,15,88,13,170,36,0,0 ; addps 0x24aa(%rip),%xmm9 # 4320 <_sk_callback_sse2+0x549> - DB 68,15,40,37,178,36,0,0 ; movaps 0x24b2(%rip),%xmm12 # 4330 <_sk_callback_sse2+0x559> + DB 68,15,88,13,144,36,0,0 ; addps 0x2490(%rip),%xmm9 # 4280 <_sk_callback_sse2+0x52f> + DB 68,15,40,37,152,36,0,0 ; movaps 0x2498(%rip),%xmm12 # 4290 <_sk_callback_sse2+0x53f> DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,40,37,178,36,0,0 ; movaps 0x24b2(%rip),%xmm12 # 4340 <_sk_callback_sse2+0x569> + DB 68,15,40,37,152,36,0,0 ; movaps 0x2498(%rip),%xmm12 # 42a0 <_sk_callback_sse2+0x54f> DB 69,15,92,229 ; subps %xmm13,%xmm12 - DB 68,15,40,45,182,36,0,0 ; movaps 0x24b6(%rip),%xmm13 # 4350 <_sk_callback_sse2+0x579> + DB 68,15,40,45,156,36,0,0 ; movaps 0x249c(%rip),%xmm13 # 42b0 <_sk_callback_sse2+0x55f> DB 69,15,94,236 ; divps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,89,45,182,36,0,0 ; mulps 0x24b6(%rip),%xmm13 # 4360 <_sk_callback_sse2+0x589> + DB 68,15,89,45,156,36,0,0 ; mulps 0x249c(%rip),%xmm13 # 42c0 <_sk_callback_sse2+0x56f> DB 102,69,15,91,205 ; cvtps2dq %xmm13,%xmm9 DB 243,68,15,16,96,20 ; movss 0x14(%rax),%xmm12 DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 @@ -17260,15 +17123,15 @@ _sk_parametric_g_sse2 LABEL PROC DB 69,15,88,209 ; addps %xmm9,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,202 ; cvtdq2ps %xmm10,%xmm9 - DB 68,15,89,13,54,36,0,0 ; mulps 0x2436(%rip),%xmm9 # 4370 <_sk_callback_sse2+0x599> - DB 68,15,84,21,62,36,0,0 ; andps 0x243e(%rip),%xmm10 # 4380 <_sk_callback_sse2+0x5a9> - DB 68,15,86,21,70,36,0,0 ; orps 0x2446(%rip),%xmm10 # 4390 <_sk_callback_sse2+0x5b9> - DB 68,15,88,13,78,36,0,0 ; addps 0x244e(%rip),%xmm9 # 43a0 <_sk_callback_sse2+0x5c9> - DB 68,15,40,37,86,36,0,0 ; movaps 0x2456(%rip),%xmm12 # 43b0 <_sk_callback_sse2+0x5d9> + DB 68,15,89,13,28,36,0,0 ; mulps 0x241c(%rip),%xmm9 # 42d0 <_sk_callback_sse2+0x57f> + DB 68,15,84,21,36,36,0,0 ; andps 0x2424(%rip),%xmm10 # 42e0 <_sk_callback_sse2+0x58f> + DB 68,15,86,21,44,36,0,0 ; orps 0x242c(%rip),%xmm10 # 42f0 <_sk_callback_sse2+0x59f> + DB 68,15,88,13,52,36,0,0 ; addps 0x2434(%rip),%xmm9 # 4300 <_sk_callback_sse2+0x5af> + DB 68,15,40,37,60,36,0,0 ; movaps 0x243c(%rip),%xmm12 # 4310 <_sk_callback_sse2+0x5bf> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,88,21,86,36,0,0 ; addps 0x2456(%rip),%xmm10 # 43c0 <_sk_callback_sse2+0x5e9> - DB 68,15,40,37,94,36,0,0 ; movaps 0x245e(%rip),%xmm12 # 43d0 <_sk_callback_sse2+0x5f9> + DB 68,15,88,21,60,36,0,0 ; addps 0x243c(%rip),%xmm10 # 4320 <_sk_callback_sse2+0x5cf> + DB 68,15,40,37,68,36,0,0 ; movaps 0x2444(%rip),%xmm12 # 4330 <_sk_callback_sse2+0x5df> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 @@ -17276,22 +17139,22 @@ _sk_parametric_g_sse2 LABEL PROC DB 69,15,91,226 ; cvtdq2ps %xmm10,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,194,236,1 ; cmpltps %xmm12,%xmm13 - DB 68,15,40,21,72,36,0,0 ; movaps 0x2448(%rip),%xmm10 # 43e0 <_sk_callback_sse2+0x609> + DB 68,15,40,21,46,36,0,0 ; movaps 0x242e(%rip),%xmm10 # 4340 <_sk_callback_sse2+0x5ef> DB 69,15,84,234 ; andps %xmm10,%xmm13 DB 69,15,87,219 ; xorps %xmm11,%xmm11 DB 69,15,92,229 ; subps %xmm13,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,92,236 ; subps %xmm12,%xmm13 - DB 68,15,88,13,60,36,0,0 ; addps 0x243c(%rip),%xmm9 # 43f0 <_sk_callback_sse2+0x619> - DB 68,15,40,37,68,36,0,0 ; movaps 0x2444(%rip),%xmm12 # 4400 <_sk_callback_sse2+0x629> + DB 68,15,88,13,34,36,0,0 ; addps 0x2422(%rip),%xmm9 # 4350 <_sk_callback_sse2+0x5ff> + DB 68,15,40,37,42,36,0,0 ; movaps 0x242a(%rip),%xmm12 # 4360 <_sk_callback_sse2+0x60f> DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,40,37,68,36,0,0 ; movaps 0x2444(%rip),%xmm12 # 4410 <_sk_callback_sse2+0x639> + DB 68,15,40,37,42,36,0,0 ; movaps 0x242a(%rip),%xmm12 # 4370 <_sk_callback_sse2+0x61f> DB 69,15,92,229 ; subps %xmm13,%xmm12 - DB 68,15,40,45,72,36,0,0 ; movaps 0x2448(%rip),%xmm13 # 4420 <_sk_callback_sse2+0x649> + DB 68,15,40,45,46,36,0,0 ; movaps 0x242e(%rip),%xmm13 # 4380 <_sk_callback_sse2+0x62f> DB 69,15,94,236 ; divps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,89,45,72,36,0,0 ; mulps 0x2448(%rip),%xmm13 # 4430 <_sk_callback_sse2+0x659> + DB 68,15,89,45,46,36,0,0 ; mulps 0x242e(%rip),%xmm13 # 4390 <_sk_callback_sse2+0x63f> DB 102,69,15,91,205 ; cvtps2dq %xmm13,%xmm9 DB 243,68,15,16,96,20 ; movss 0x14(%rax),%xmm12 DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 @@ -17325,15 +17188,15 @@ _sk_parametric_b_sse2 LABEL PROC DB 69,15,88,209 ; addps %xmm9,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,202 ; cvtdq2ps %xmm10,%xmm9 - DB 68,15,89,13,200,35,0,0 ; mulps 0x23c8(%rip),%xmm9 # 4440 <_sk_callback_sse2+0x669> - DB 68,15,84,21,208,35,0,0 ; andps 0x23d0(%rip),%xmm10 # 4450 <_sk_callback_sse2+0x679> - DB 68,15,86,21,216,35,0,0 ; orps 0x23d8(%rip),%xmm10 # 4460 <_sk_callback_sse2+0x689> - DB 68,15,88,13,224,35,0,0 ; addps 0x23e0(%rip),%xmm9 # 4470 <_sk_callback_sse2+0x699> - DB 68,15,40,37,232,35,0,0 ; movaps 0x23e8(%rip),%xmm12 # 4480 <_sk_callback_sse2+0x6a9> + DB 68,15,89,13,174,35,0,0 ; mulps 0x23ae(%rip),%xmm9 # 43a0 <_sk_callback_sse2+0x64f> + DB 68,15,84,21,182,35,0,0 ; andps 0x23b6(%rip),%xmm10 # 43b0 <_sk_callback_sse2+0x65f> + DB 68,15,86,21,190,35,0,0 ; orps 0x23be(%rip),%xmm10 # 43c0 <_sk_callback_sse2+0x66f> + DB 68,15,88,13,198,35,0,0 ; addps 0x23c6(%rip),%xmm9 # 43d0 <_sk_callback_sse2+0x67f> + DB 68,15,40,37,206,35,0,0 ; movaps 0x23ce(%rip),%xmm12 # 43e0 <_sk_callback_sse2+0x68f> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,88,21,232,35,0,0 ; addps 0x23e8(%rip),%xmm10 # 4490 <_sk_callback_sse2+0x6b9> - DB 68,15,40,37,240,35,0,0 ; movaps 0x23f0(%rip),%xmm12 # 44a0 <_sk_callback_sse2+0x6c9> + DB 68,15,88,21,206,35,0,0 ; addps 0x23ce(%rip),%xmm10 # 43f0 <_sk_callback_sse2+0x69f> + DB 68,15,40,37,214,35,0,0 ; movaps 0x23d6(%rip),%xmm12 # 4400 <_sk_callback_sse2+0x6af> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 @@ -17341,22 +17204,22 @@ _sk_parametric_b_sse2 LABEL PROC DB 69,15,91,226 ; cvtdq2ps %xmm10,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,194,236,1 ; cmpltps %xmm12,%xmm13 - DB 68,15,40,21,218,35,0,0 ; movaps 0x23da(%rip),%xmm10 # 44b0 <_sk_callback_sse2+0x6d9> + DB 68,15,40,21,192,35,0,0 ; movaps 0x23c0(%rip),%xmm10 # 4410 <_sk_callback_sse2+0x6bf> DB 69,15,84,234 ; andps %xmm10,%xmm13 DB 69,15,87,219 ; xorps %xmm11,%xmm11 DB 69,15,92,229 ; subps %xmm13,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,92,236 ; subps %xmm12,%xmm13 - DB 68,15,88,13,206,35,0,0 ; addps 0x23ce(%rip),%xmm9 # 44c0 <_sk_callback_sse2+0x6e9> - DB 68,15,40,37,214,35,0,0 ; movaps 0x23d6(%rip),%xmm12 # 44d0 <_sk_callback_sse2+0x6f9> + DB 68,15,88,13,180,35,0,0 ; addps 0x23b4(%rip),%xmm9 # 4420 <_sk_callback_sse2+0x6cf> + DB 68,15,40,37,188,35,0,0 ; movaps 0x23bc(%rip),%xmm12 # 4430 <_sk_callback_sse2+0x6df> DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,40,37,214,35,0,0 ; movaps 0x23d6(%rip),%xmm12 # 44e0 <_sk_callback_sse2+0x709> + DB 68,15,40,37,188,35,0,0 ; movaps 0x23bc(%rip),%xmm12 # 4440 <_sk_callback_sse2+0x6ef> DB 69,15,92,229 ; subps %xmm13,%xmm12 - DB 68,15,40,45,218,35,0,0 ; movaps 0x23da(%rip),%xmm13 # 44f0 <_sk_callback_sse2+0x719> + DB 68,15,40,45,192,35,0,0 ; movaps 0x23c0(%rip),%xmm13 # 4450 <_sk_callback_sse2+0x6ff> DB 69,15,94,236 ; divps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,89,45,218,35,0,0 ; mulps 0x23da(%rip),%xmm13 # 4500 <_sk_callback_sse2+0x729> + DB 68,15,89,45,192,35,0,0 ; mulps 0x23c0(%rip),%xmm13 # 4460 <_sk_callback_sse2+0x70f> DB 102,69,15,91,205 ; cvtps2dq %xmm13,%xmm9 DB 243,68,15,16,96,20 ; movss 0x14(%rax),%xmm12 DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 @@ -17390,15 +17253,15 @@ _sk_parametric_a_sse2 LABEL PROC DB 69,15,88,209 ; addps %xmm9,%xmm10 DB 69,15,198,219,0 ; shufps $0x0,%xmm11,%xmm11 DB 69,15,91,202 ; cvtdq2ps %xmm10,%xmm9 - DB 68,15,89,13,90,35,0,0 ; mulps 0x235a(%rip),%xmm9 # 4510 <_sk_callback_sse2+0x739> - DB 68,15,84,21,98,35,0,0 ; andps 0x2362(%rip),%xmm10 # 4520 <_sk_callback_sse2+0x749> - DB 68,15,86,21,106,35,0,0 ; orps 0x236a(%rip),%xmm10 # 4530 <_sk_callback_sse2+0x759> - DB 68,15,88,13,114,35,0,0 ; addps 0x2372(%rip),%xmm9 # 4540 <_sk_callback_sse2+0x769> - DB 68,15,40,37,122,35,0,0 ; movaps 0x237a(%rip),%xmm12 # 4550 <_sk_callback_sse2+0x779> + DB 68,15,89,13,64,35,0,0 ; mulps 0x2340(%rip),%xmm9 # 4470 <_sk_callback_sse2+0x71f> + DB 68,15,84,21,72,35,0,0 ; andps 0x2348(%rip),%xmm10 # 4480 <_sk_callback_sse2+0x72f> + DB 68,15,86,21,80,35,0,0 ; orps 0x2350(%rip),%xmm10 # 4490 <_sk_callback_sse2+0x73f> + DB 68,15,88,13,88,35,0,0 ; addps 0x2358(%rip),%xmm9 # 44a0 <_sk_callback_sse2+0x74f> + DB 68,15,40,37,96,35,0,0 ; movaps 0x2360(%rip),%xmm12 # 44b0 <_sk_callback_sse2+0x75f> DB 69,15,89,226 ; mulps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,88,21,122,35,0,0 ; addps 0x237a(%rip),%xmm10 # 4560 <_sk_callback_sse2+0x789> - DB 68,15,40,37,130,35,0,0 ; movaps 0x2382(%rip),%xmm12 # 4570 <_sk_callback_sse2+0x799> + DB 68,15,88,21,96,35,0,0 ; addps 0x2360(%rip),%xmm10 # 44c0 <_sk_callback_sse2+0x76f> + DB 68,15,40,37,104,35,0,0 ; movaps 0x2368(%rip),%xmm12 # 44d0 <_sk_callback_sse2+0x77f> DB 69,15,94,226 ; divps %xmm10,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 DB 69,15,89,203 ; mulps %xmm11,%xmm9 @@ -17406,22 +17269,22 @@ _sk_parametric_a_sse2 LABEL PROC DB 69,15,91,226 ; cvtdq2ps %xmm10,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,194,236,1 ; cmpltps %xmm12,%xmm13 - DB 68,15,40,21,108,35,0,0 ; movaps 0x236c(%rip),%xmm10 # 4580 <_sk_callback_sse2+0x7a9> + DB 68,15,40,21,82,35,0,0 ; movaps 0x2352(%rip),%xmm10 # 44e0 <_sk_callback_sse2+0x78f> DB 69,15,84,234 ; andps %xmm10,%xmm13 DB 69,15,87,219 ; xorps %xmm11,%xmm11 DB 69,15,92,229 ; subps %xmm13,%xmm12 DB 69,15,40,233 ; movaps %xmm9,%xmm13 DB 69,15,92,236 ; subps %xmm12,%xmm13 - DB 68,15,88,13,96,35,0,0 ; addps 0x2360(%rip),%xmm9 # 4590 <_sk_callback_sse2+0x7b9> - DB 68,15,40,37,104,35,0,0 ; movaps 0x2368(%rip),%xmm12 # 45a0 <_sk_callback_sse2+0x7c9> + DB 68,15,88,13,70,35,0,0 ; addps 0x2346(%rip),%xmm9 # 44f0 <_sk_callback_sse2+0x79f> + DB 68,15,40,37,78,35,0,0 ; movaps 0x234e(%rip),%xmm12 # 4500 <_sk_callback_sse2+0x7af> DB 69,15,89,229 ; mulps %xmm13,%xmm12 DB 69,15,92,204 ; subps %xmm12,%xmm9 - DB 68,15,40,37,104,35,0,0 ; movaps 0x2368(%rip),%xmm12 # 45b0 <_sk_callback_sse2+0x7d9> + DB 68,15,40,37,78,35,0,0 ; movaps 0x234e(%rip),%xmm12 # 4510 <_sk_callback_sse2+0x7bf> DB 69,15,92,229 ; subps %xmm13,%xmm12 - DB 68,15,40,45,108,35,0,0 ; movaps 0x236c(%rip),%xmm13 # 45c0 <_sk_callback_sse2+0x7e9> + DB 68,15,40,45,82,35,0,0 ; movaps 0x2352(%rip),%xmm13 # 4520 <_sk_callback_sse2+0x7cf> DB 69,15,94,236 ; divps %xmm12,%xmm13 DB 69,15,88,233 ; addps %xmm9,%xmm13 - DB 68,15,89,45,108,35,0,0 ; mulps 0x236c(%rip),%xmm13 # 45d0 <_sk_callback_sse2+0x7f9> + DB 68,15,89,45,82,35,0,0 ; mulps 0x2352(%rip),%xmm13 # 4530 <_sk_callback_sse2+0x7df> DB 102,69,15,91,205 ; cvtps2dq %xmm13,%xmm9 DB 243,68,15,16,96,20 ; movss 0x14(%rax),%xmm12 DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 @@ -17436,29 +17299,29 @@ _sk_parametric_a_sse2 LABEL PROC PUBLIC _sk_lab_to_xyz_sse2 _sk_lab_to_xyz_sse2 LABEL PROC - DB 15,89,5,73,35,0,0 ; mulps 0x2349(%rip),%xmm0 # 45e0 <_sk_callback_sse2+0x809> - DB 68,15,40,5,81,35,0,0 ; movaps 0x2351(%rip),%xmm8 # 45f0 <_sk_callback_sse2+0x819> + DB 15,89,5,47,35,0,0 ; mulps 0x232f(%rip),%xmm0 # 4540 <_sk_callback_sse2+0x7ef> + DB 68,15,40,5,55,35,0,0 ; movaps 0x2337(%rip),%xmm8 # 4550 <_sk_callback_sse2+0x7ff> DB 65,15,89,200 ; mulps %xmm8,%xmm1 - DB 68,15,40,13,85,35,0,0 ; movaps 0x2355(%rip),%xmm9 # 4600 <_sk_callback_sse2+0x829> + DB 68,15,40,13,59,35,0,0 ; movaps 0x233b(%rip),%xmm9 # 4560 <_sk_callback_sse2+0x80f> DB 65,15,88,201 ; addps %xmm9,%xmm1 DB 65,15,89,208 ; mulps %xmm8,%xmm2 DB 65,15,88,209 ; addps %xmm9,%xmm2 - DB 15,88,5,82,35,0,0 ; addps 0x2352(%rip),%xmm0 # 4610 <_sk_callback_sse2+0x839> - DB 15,89,5,91,35,0,0 ; mulps 0x235b(%rip),%xmm0 # 4620 <_sk_callback_sse2+0x849> - DB 15,89,13,100,35,0,0 ; mulps 0x2364(%rip),%xmm1 # 4630 <_sk_callback_sse2+0x859> + DB 15,88,5,56,35,0,0 ; addps 0x2338(%rip),%xmm0 # 4570 <_sk_callback_sse2+0x81f> + DB 15,89,5,65,35,0,0 ; mulps 0x2341(%rip),%xmm0 # 4580 <_sk_callback_sse2+0x82f> + DB 15,89,13,74,35,0,0 ; mulps 0x234a(%rip),%xmm1 # 4590 <_sk_callback_sse2+0x83f> DB 15,88,200 ; addps %xmm0,%xmm1 - DB 15,89,21,106,35,0,0 ; mulps 0x236a(%rip),%xmm2 # 4640 <_sk_callback_sse2+0x869> + DB 15,89,21,80,35,0,0 ; mulps 0x2350(%rip),%xmm2 # 45a0 <_sk_callback_sse2+0x84f> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 68,15,92,202 ; subps %xmm2,%xmm9 DB 68,15,40,225 ; movaps %xmm1,%xmm12 DB 69,15,89,228 ; mulps %xmm12,%xmm12 DB 68,15,89,225 ; mulps %xmm1,%xmm12 - DB 15,40,21,95,35,0,0 ; movaps 0x235f(%rip),%xmm2 # 4650 <_sk_callback_sse2+0x879> + DB 15,40,21,69,35,0,0 ; movaps 0x2345(%rip),%xmm2 # 45b0 <_sk_callback_sse2+0x85f> DB 68,15,40,194 ; movaps %xmm2,%xmm8 DB 69,15,194,196,1 ; cmpltps %xmm12,%xmm8 - DB 68,15,40,21,94,35,0,0 ; movaps 0x235e(%rip),%xmm10 # 4660 <_sk_callback_sse2+0x889> + DB 68,15,40,21,68,35,0,0 ; movaps 0x2344(%rip),%xmm10 # 45c0 <_sk_callback_sse2+0x86f> DB 65,15,88,202 ; addps %xmm10,%xmm1 - DB 68,15,40,29,98,35,0,0 ; movaps 0x2362(%rip),%xmm11 # 4670 <_sk_callback_sse2+0x899> + DB 68,15,40,29,72,35,0,0 ; movaps 0x2348(%rip),%xmm11 # 45d0 <_sk_callback_sse2+0x87f> DB 65,15,89,203 ; mulps %xmm11,%xmm1 DB 69,15,84,224 ; andps %xmm8,%xmm12 DB 68,15,85,193 ; andnps %xmm1,%xmm8 @@ -17482,8 +17345,8 @@ _sk_lab_to_xyz_sse2 LABEL PROC DB 15,84,194 ; andps %xmm2,%xmm0 DB 65,15,85,209 ; andnps %xmm9,%xmm2 DB 15,86,208 ; orps %xmm0,%xmm2 - DB 68,15,89,5,18,35,0,0 ; mulps 0x2312(%rip),%xmm8 # 4680 <_sk_callback_sse2+0x8a9> - DB 15,89,21,27,35,0,0 ; mulps 0x231b(%rip),%xmm2 # 4690 <_sk_callback_sse2+0x8b9> + DB 68,15,89,5,248,34,0,0 ; mulps 0x22f8(%rip),%xmm8 # 45e0 <_sk_callback_sse2+0x88f> + DB 15,89,21,1,35,0,0 ; mulps 0x2301(%rip),%xmm2 # 45f0 <_sk_callback_sse2+0x89f> DB 72,173 ; lods %ds:(%rsi),%rax DB 65,15,40,192 ; movaps %xmm8,%xmm0 DB 255,224 ; jmpq *%rax @@ -17497,7 +17360,7 @@ _sk_load_a8_sse2 LABEL PROC DB 102,15,96,193 ; punpcklbw %xmm1,%xmm0 DB 102,15,97,193 ; punpcklwd %xmm1,%xmm0 DB 15,91,216 ; cvtdq2ps %xmm0,%xmm3 - DB 15,89,29,3,35,0,0 ; mulps 0x2303(%rip),%xmm3 # 46a0 <_sk_callback_sse2+0x8c9> + DB 15,89,29,233,34,0,0 ; mulps 0x22e9(%rip),%xmm3 # 4600 <_sk_callback_sse2+0x8af> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 DB 102,15,239,201 ; pxor %xmm1,%xmm1 @@ -17540,7 +17403,7 @@ _sk_gather_a8_sse2 LABEL PROC DB 102,15,96,193 ; punpcklbw %xmm1,%xmm0 DB 102,15,97,193 ; punpcklwd %xmm1,%xmm0 DB 15,91,216 ; cvtdq2ps %xmm0,%xmm3 - DB 15,89,29,114,34,0,0 ; mulps 0x2272(%rip),%xmm3 # 46b0 <_sk_callback_sse2+0x8d9> + DB 15,89,29,88,34,0,0 ; mulps 0x2258(%rip),%xmm3 # 4610 <_sk_callback_sse2+0x8bf> DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 DB 102,15,239,201 ; pxor %xmm1,%xmm1 @@ -17551,7 +17414,7 @@ PUBLIC _sk_store_a8_sse2 _sk_store_a8_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,102,34,0,0 ; movaps 0x2266(%rip),%xmm8 # 46c0 <_sk_callback_sse2+0x8e9> + DB 68,15,40,5,76,34,0,0 ; movaps 0x224c(%rip),%xmm8 # 4620 <_sk_callback_sse2+0x8cf> DB 68,15,89,195 ; mulps %xmm3,%xmm8 DB 102,69,15,91,192 ; cvtps2dq %xmm8,%xmm8 DB 102,65,15,114,240,16 ; pslld $0x10,%xmm8 @@ -17571,9 +17434,9 @@ _sk_load_g8_sse2 LABEL PROC DB 102,15,96,193 ; punpcklbw %xmm1,%xmm0 DB 102,15,97,193 ; punpcklwd %xmm1,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,45,34,0,0 ; mulps 0x222d(%rip),%xmm0 # 46d0 <_sk_callback_sse2+0x8f9> + DB 15,89,5,19,34,0,0 ; mulps 0x2213(%rip),%xmm0 # 4630 <_sk_callback_sse2+0x8df> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,52,34,0,0 ; movaps 0x2234(%rip),%xmm3 # 46e0 <_sk_callback_sse2+0x909> + DB 15,40,29,26,34,0,0 ; movaps 0x221a(%rip),%xmm3 # 4640 <_sk_callback_sse2+0x8ef> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 15,40,208 ; movaps %xmm0,%xmm2 DB 255,224 ; jmpq *%rax @@ -17614,9 +17477,9 @@ _sk_gather_g8_sse2 LABEL PROC DB 102,15,96,193 ; punpcklbw %xmm1,%xmm0 DB 102,15,97,193 ; punpcklwd %xmm1,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,169,33,0,0 ; mulps 0x21a9(%rip),%xmm0 # 46f0 <_sk_callback_sse2+0x919> + DB 15,89,5,143,33,0,0 ; mulps 0x218f(%rip),%xmm0 # 4650 <_sk_callback_sse2+0x8ff> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,176,33,0,0 ; movaps 0x21b0(%rip),%xmm3 # 4700 <_sk_callback_sse2+0x929> + DB 15,40,29,150,33,0,0 ; movaps 0x2196(%rip),%xmm3 # 4660 <_sk_callback_sse2+0x90f> DB 15,40,200 ; movaps %xmm0,%xmm1 DB 15,40,208 ; movaps %xmm0,%xmm2 DB 255,224 ; jmpq *%rax @@ -17626,9 +17489,9 @@ _sk_gather_i8_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 73,137,192 ; mov %rax,%r8 DB 77,133,192 ; test %r8,%r8 - DB 116,5 ; je 2567 <_sk_gather_i8_sse2+0xf> + DB 116,5 ; je 24e1 <_sk_gather_i8_sse2+0xf> DB 76,137,192 ; mov %r8,%rax - DB 235,2 ; jmp 2569 <_sk_gather_i8_sse2+0x11> + DB 235,2 ; jmp 24e3 <_sk_gather_i8_sse2+0x11> DB 72,173 ; lods %ds:(%rsi),%rax DB 76,139,16 ; mov (%rax),%r10 DB 243,15,91,201 ; cvttps2dq %xmm1,%xmm1 @@ -17677,11 +17540,11 @@ _sk_gather_i8_sse2 LABEL PROC DB 102,67,15,110,12,136 ; movd (%r8,%r9,4),%xmm1 DB 102,68,15,98,201 ; punpckldq %xmm1,%xmm9 DB 102,68,15,98,200 ; punpckldq %xmm0,%xmm9 - DB 102,15,111,21,207,32,0,0 ; movdqa 0x20cf(%rip),%xmm2 # 4710 <_sk_callback_sse2+0x939> + DB 102,15,111,21,181,32,0,0 ; movdqa 0x20b5(%rip),%xmm2 # 4670 <_sk_callback_sse2+0x91f> DB 102,65,15,111,193 ; movdqa %xmm9,%xmm0 DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,203,32,0,0 ; movaps 0x20cb(%rip),%xmm8 # 4720 <_sk_callback_sse2+0x949> + DB 68,15,40,5,177,32,0,0 ; movaps 0x20b1(%rip),%xmm8 # 4680 <_sk_callback_sse2+0x92f> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,65,15,111,201 ; movdqa %xmm9,%xmm1 DB 102,15,114,209,8 ; psrld $0x8,%xmm1 @@ -17706,19 +17569,19 @@ _sk_load_565_sse2 LABEL PROC DB 243,15,126,20,120 ; movq (%rax,%rdi,2),%xmm2 DB 102,15,239,192 ; pxor %xmm0,%xmm0 DB 102,15,97,208 ; punpcklwd %xmm0,%xmm2 - DB 102,15,111,5,129,32,0,0 ; movdqa 0x2081(%rip),%xmm0 # 4730 <_sk_callback_sse2+0x959> + DB 102,15,111,5,103,32,0,0 ; movdqa 0x2067(%rip),%xmm0 # 4690 <_sk_callback_sse2+0x93f> DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,131,32,0,0 ; mulps 0x2083(%rip),%xmm0 # 4740 <_sk_callback_sse2+0x969> - DB 102,15,111,13,139,32,0,0 ; movdqa 0x208b(%rip),%xmm1 # 4750 <_sk_callback_sse2+0x979> + DB 15,89,5,105,32,0,0 ; mulps 0x2069(%rip),%xmm0 # 46a0 <_sk_callback_sse2+0x94f> + DB 102,15,111,13,113,32,0,0 ; movdqa 0x2071(%rip),%xmm1 # 46b0 <_sk_callback_sse2+0x95f> DB 102,15,219,202 ; pand %xmm2,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,141,32,0,0 ; mulps 0x208d(%rip),%xmm1 # 4760 <_sk_callback_sse2+0x989> - DB 102,15,219,21,149,32,0,0 ; pand 0x2095(%rip),%xmm2 # 4770 <_sk_callback_sse2+0x999> + DB 15,89,13,115,32,0,0 ; mulps 0x2073(%rip),%xmm1 # 46c0 <_sk_callback_sse2+0x96f> + DB 102,15,219,21,123,32,0,0 ; pand 0x207b(%rip),%xmm2 # 46d0 <_sk_callback_sse2+0x97f> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,155,32,0,0 ; mulps 0x209b(%rip),%xmm2 # 4780 <_sk_callback_sse2+0x9a9> + DB 15,89,21,129,32,0,0 ; mulps 0x2081(%rip),%xmm2 # 46e0 <_sk_callback_sse2+0x98f> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,162,32,0,0 ; movaps 0x20a2(%rip),%xmm3 # 4790 <_sk_callback_sse2+0x9b9> + DB 15,40,29,136,32,0,0 ; movaps 0x2088(%rip),%xmm3 # 46f0 <_sk_callback_sse2+0x99f> DB 255,224 ; jmpq *%rax PUBLIC _sk_gather_565_sse2 @@ -17751,31 +17614,31 @@ _sk_gather_565_sse2 LABEL PROC DB 102,15,196,208,3 ; pinsrw $0x3,%eax,%xmm2 DB 102,15,239,192 ; pxor %xmm0,%xmm0 DB 102,15,97,208 ; punpcklwd %xmm0,%xmm2 - DB 102,15,111,5,43,32,0,0 ; movdqa 0x202b(%rip),%xmm0 # 47a0 <_sk_callback_sse2+0x9c9> + DB 102,15,111,5,17,32,0,0 ; movdqa 0x2011(%rip),%xmm0 # 4700 <_sk_callback_sse2+0x9af> DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,45,32,0,0 ; mulps 0x202d(%rip),%xmm0 # 47b0 <_sk_callback_sse2+0x9d9> - DB 102,15,111,13,53,32,0,0 ; movdqa 0x2035(%rip),%xmm1 # 47c0 <_sk_callback_sse2+0x9e9> + DB 15,89,5,19,32,0,0 ; mulps 0x2013(%rip),%xmm0 # 4710 <_sk_callback_sse2+0x9bf> + DB 102,15,111,13,27,32,0,0 ; movdqa 0x201b(%rip),%xmm1 # 4720 <_sk_callback_sse2+0x9cf> DB 102,15,219,202 ; pand %xmm2,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,55,32,0,0 ; mulps 0x2037(%rip),%xmm1 # 47d0 <_sk_callback_sse2+0x9f9> - DB 102,15,219,21,63,32,0,0 ; pand 0x203f(%rip),%xmm2 # 47e0 <_sk_callback_sse2+0xa09> + DB 15,89,13,29,32,0,0 ; mulps 0x201d(%rip),%xmm1 # 4730 <_sk_callback_sse2+0x9df> + DB 102,15,219,21,37,32,0,0 ; pand 0x2025(%rip),%xmm2 # 4740 <_sk_callback_sse2+0x9ef> DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,69,32,0,0 ; mulps 0x2045(%rip),%xmm2 # 47f0 <_sk_callback_sse2+0xa19> + DB 15,89,21,43,32,0,0 ; mulps 0x202b(%rip),%xmm2 # 4750 <_sk_callback_sse2+0x9ff> DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,76,32,0,0 ; movaps 0x204c(%rip),%xmm3 # 4800 <_sk_callback_sse2+0xa29> + DB 15,40,29,50,32,0,0 ; movaps 0x2032(%rip),%xmm3 # 4760 <_sk_callback_sse2+0xa0f> DB 255,224 ; jmpq *%rax PUBLIC _sk_store_565_sse2 _sk_store_565_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,77,32,0,0 ; movaps 0x204d(%rip),%xmm8 # 4810 <_sk_callback_sse2+0xa39> + DB 68,15,40,5,51,32,0,0 ; movaps 0x2033(%rip),%xmm8 # 4770 <_sk_callback_sse2+0xa1f> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 DB 102,65,15,114,241,11 ; pslld $0xb,%xmm9 - DB 68,15,40,21,66,32,0,0 ; movaps 0x2042(%rip),%xmm10 # 4820 <_sk_callback_sse2+0xa49> + DB 68,15,40,21,40,32,0,0 ; movaps 0x2028(%rip),%xmm10 # 4780 <_sk_callback_sse2+0xa2f> DB 68,15,89,209 ; mulps %xmm1,%xmm10 DB 102,69,15,91,210 ; cvtps2dq %xmm10,%xmm10 DB 102,65,15,114,242,5 ; pslld $0x5,%xmm10 @@ -17797,21 +17660,21 @@ _sk_load_4444_sse2 LABEL PROC DB 243,15,126,28,120 ; movq (%rax,%rdi,2),%xmm3 DB 102,15,239,192 ; pxor %xmm0,%xmm0 DB 102,15,97,216 ; punpcklwd %xmm0,%xmm3 - DB 102,15,111,5,251,31,0,0 ; movdqa 0x1ffb(%rip),%xmm0 # 4830 <_sk_callback_sse2+0xa59> + DB 102,15,111,5,225,31,0,0 ; movdqa 0x1fe1(%rip),%xmm0 # 4790 <_sk_callback_sse2+0xa3f> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,253,31,0,0 ; mulps 0x1ffd(%rip),%xmm0 # 4840 <_sk_callback_sse2+0xa69> - DB 102,15,111,13,5,32,0,0 ; movdqa 0x2005(%rip),%xmm1 # 4850 <_sk_callback_sse2+0xa79> + DB 15,89,5,227,31,0,0 ; mulps 0x1fe3(%rip),%xmm0 # 47a0 <_sk_callback_sse2+0xa4f> + DB 102,15,111,13,235,31,0,0 ; movdqa 0x1feb(%rip),%xmm1 # 47b0 <_sk_callback_sse2+0xa5f> DB 102,15,219,203 ; pand %xmm3,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,7,32,0,0 ; mulps 0x2007(%rip),%xmm1 # 4860 <_sk_callback_sse2+0xa89> - DB 102,15,111,21,15,32,0,0 ; movdqa 0x200f(%rip),%xmm2 # 4870 <_sk_callback_sse2+0xa99> + DB 15,89,13,237,31,0,0 ; mulps 0x1fed(%rip),%xmm1 # 47c0 <_sk_callback_sse2+0xa6f> + DB 102,15,111,21,245,31,0,0 ; movdqa 0x1ff5(%rip),%xmm2 # 47d0 <_sk_callback_sse2+0xa7f> DB 102,15,219,211 ; pand %xmm3,%xmm2 DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,17,32,0,0 ; mulps 0x2011(%rip),%xmm2 # 4880 <_sk_callback_sse2+0xaa9> - DB 102,15,219,29,25,32,0,0 ; pand 0x2019(%rip),%xmm3 # 4890 <_sk_callback_sse2+0xab9> + DB 15,89,21,247,31,0,0 ; mulps 0x1ff7(%rip),%xmm2 # 47e0 <_sk_callback_sse2+0xa8f> + DB 102,15,219,29,255,31,0,0 ; pand 0x1fff(%rip),%xmm3 # 47f0 <_sk_callback_sse2+0xa9f> DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,31,32,0,0 ; mulps 0x201f(%rip),%xmm3 # 48a0 <_sk_callback_sse2+0xac9> + DB 15,89,29,5,32,0,0 ; mulps 0x2005(%rip),%xmm3 # 4800 <_sk_callback_sse2+0xaaf> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -17845,21 +17708,21 @@ _sk_gather_4444_sse2 LABEL PROC DB 102,15,196,216,3 ; pinsrw $0x3,%eax,%xmm3 DB 102,15,239,192 ; pxor %xmm0,%xmm0 DB 102,15,97,216 ; punpcklwd %xmm0,%xmm3 - DB 102,15,111,5,166,31,0,0 ; movdqa 0x1fa6(%rip),%xmm0 # 48b0 <_sk_callback_sse2+0xad9> + DB 102,15,111,5,140,31,0,0 ; movdqa 0x1f8c(%rip),%xmm0 # 4810 <_sk_callback_sse2+0xabf> DB 102,15,219,195 ; pand %xmm3,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 15,89,5,168,31,0,0 ; mulps 0x1fa8(%rip),%xmm0 # 48c0 <_sk_callback_sse2+0xae9> - DB 102,15,111,13,176,31,0,0 ; movdqa 0x1fb0(%rip),%xmm1 # 48d0 <_sk_callback_sse2+0xaf9> + DB 15,89,5,142,31,0,0 ; mulps 0x1f8e(%rip),%xmm0 # 4820 <_sk_callback_sse2+0xacf> + DB 102,15,111,13,150,31,0,0 ; movdqa 0x1f96(%rip),%xmm1 # 4830 <_sk_callback_sse2+0xadf> DB 102,15,219,203 ; pand %xmm3,%xmm1 DB 15,91,201 ; cvtdq2ps %xmm1,%xmm1 - DB 15,89,13,178,31,0,0 ; mulps 0x1fb2(%rip),%xmm1 # 48e0 <_sk_callback_sse2+0xb09> - DB 102,15,111,21,186,31,0,0 ; movdqa 0x1fba(%rip),%xmm2 # 48f0 <_sk_callback_sse2+0xb19> + DB 15,89,13,152,31,0,0 ; mulps 0x1f98(%rip),%xmm1 # 4840 <_sk_callback_sse2+0xaef> + DB 102,15,111,21,160,31,0,0 ; movdqa 0x1fa0(%rip),%xmm2 # 4850 <_sk_callback_sse2+0xaff> DB 102,15,219,211 ; pand %xmm3,%xmm2 DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 - DB 15,89,21,188,31,0,0 ; mulps 0x1fbc(%rip),%xmm2 # 4900 <_sk_callback_sse2+0xb29> - DB 102,15,219,29,196,31,0,0 ; pand 0x1fc4(%rip),%xmm3 # 4910 <_sk_callback_sse2+0xb39> + DB 15,89,21,162,31,0,0 ; mulps 0x1fa2(%rip),%xmm2 # 4860 <_sk_callback_sse2+0xb0f> + DB 102,15,219,29,170,31,0,0 ; pand 0x1faa(%rip),%xmm3 # 4870 <_sk_callback_sse2+0xb1f> DB 15,91,219 ; cvtdq2ps %xmm3,%xmm3 - DB 15,89,29,202,31,0,0 ; mulps 0x1fca(%rip),%xmm3 # 4920 <_sk_callback_sse2+0xb49> + DB 15,89,29,176,31,0,0 ; mulps 0x1fb0(%rip),%xmm3 # 4880 <_sk_callback_sse2+0xb2f> DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -17867,7 +17730,7 @@ PUBLIC _sk_store_4444_sse2 _sk_store_4444_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,201,31,0,0 ; movaps 0x1fc9(%rip),%xmm8 # 4930 <_sk_callback_sse2+0xb59> + DB 68,15,40,5,175,31,0,0 ; movaps 0x1faf(%rip),%xmm8 # 4890 <_sk_callback_sse2+0xb3f> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 @@ -17897,11 +17760,11 @@ _sk_load_8888_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax DB 68,15,16,12,184 ; movups (%rax,%rdi,4),%xmm9 - DB 15,40,21,92,31,0,0 ; movaps 0x1f5c(%rip),%xmm2 # 4940 <_sk_callback_sse2+0xb69> + DB 15,40,21,66,31,0,0 ; movaps 0x1f42(%rip),%xmm2 # 48a0 <_sk_callback_sse2+0xb4f> DB 65,15,40,193 ; movaps %xmm9,%xmm0 DB 15,84,194 ; andps %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,90,31,0,0 ; movaps 0x1f5a(%rip),%xmm8 # 4950 <_sk_callback_sse2+0xb79> + DB 68,15,40,5,64,31,0,0 ; movaps 0x1f40(%rip),%xmm8 # 48b0 <_sk_callback_sse2+0xb5f> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 65,15,40,201 ; movaps %xmm9,%xmm1 DB 102,15,114,209,8 ; psrld $0x8,%xmm1 @@ -17948,11 +17811,11 @@ _sk_gather_8888_sse2 LABEL PROC DB 102,67,15,110,12,129 ; movd (%r9,%r8,4),%xmm1 DB 102,68,15,98,201 ; punpckldq %xmm1,%xmm9 DB 102,68,15,98,200 ; punpckldq %xmm0,%xmm9 - DB 102,15,111,21,171,30,0,0 ; movdqa 0x1eab(%rip),%xmm2 # 4960 <_sk_callback_sse2+0xb89> + DB 102,15,111,21,145,30,0,0 ; movdqa 0x1e91(%rip),%xmm2 # 48c0 <_sk_callback_sse2+0xb6f> DB 102,65,15,111,193 ; movdqa %xmm9,%xmm0 DB 102,15,219,194 ; pand %xmm2,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,5,167,30,0,0 ; movaps 0x1ea7(%rip),%xmm8 # 4970 <_sk_callback_sse2+0xb99> + DB 68,15,40,5,141,30,0,0 ; movaps 0x1e8d(%rip),%xmm8 # 48d0 <_sk_callback_sse2+0xb7f> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,65,15,111,201 ; movdqa %xmm9,%xmm1 DB 102,15,114,209,8 ; psrld $0x8,%xmm1 @@ -17974,7 +17837,7 @@ PUBLIC _sk_store_8888_sse2 _sk_store_8888_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,5,106,30,0,0 ; movaps 0x1e6a(%rip),%xmm8 # 4980 <_sk_callback_sse2+0xba9> + DB 68,15,40,5,80,30,0,0 ; movaps 0x1e50(%rip),%xmm8 # 48e0 <_sk_callback_sse2+0xb8f> DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 102,69,15,91,201 ; cvtps2dq %xmm9,%xmm9 @@ -18011,7 +17874,7 @@ _sk_load_f16_sse2 LABEL PROC DB 102,69,15,239,210 ; pxor %xmm10,%xmm10 DB 102,65,15,111,206 ; movdqa %xmm14,%xmm1 DB 102,65,15,97,202 ; punpcklwd %xmm10,%xmm1 - DB 102,68,15,111,13,218,29,0,0 ; movdqa 0x1dda(%rip),%xmm9 # 4990 <_sk_callback_sse2+0xbb9> + DB 102,68,15,111,13,192,29,0,0 ; movdqa 0x1dc0(%rip),%xmm9 # 48f0 <_sk_callback_sse2+0xb9f> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,193 ; pand %xmm9,%xmm0 DB 102,15,239,200 ; pxor %xmm0,%xmm1 @@ -18019,11 +17882,11 @@ _sk_load_f16_sse2 LABEL PROC DB 102,68,15,111,233 ; movdqa %xmm1,%xmm13 DB 102,65,15,114,245,13 ; pslld $0xd,%xmm13 DB 102,68,15,235,232 ; por %xmm0,%xmm13 - DB 102,68,15,111,29,191,29,0,0 ; movdqa 0x1dbf(%rip),%xmm11 # 49a0 <_sk_callback_sse2+0xbc9> + DB 102,68,15,111,29,165,29,0,0 ; movdqa 0x1da5(%rip),%xmm11 # 4900 <_sk_callback_sse2+0xbaf> DB 102,69,15,254,235 ; paddd %xmm11,%xmm13 - DB 102,68,15,111,37,193,29,0,0 ; movdqa 0x1dc1(%rip),%xmm12 # 49b0 <_sk_callback_sse2+0xbd9> + DB 102,68,15,111,37,167,29,0,0 ; movdqa 0x1da7(%rip),%xmm12 # 4910 <_sk_callback_sse2+0xbbf> DB 102,65,15,239,204 ; pxor %xmm12,%xmm1 - DB 102,15,111,29,196,29,0,0 ; movdqa 0x1dc4(%rip),%xmm3 # 49c0 <_sk_callback_sse2+0xbe9> + DB 102,15,111,29,170,29,0,0 ; movdqa 0x1daa(%rip),%xmm3 # 4920 <_sk_callback_sse2+0xbcf> DB 102,15,111,195 ; movdqa %xmm3,%xmm0 DB 102,15,102,193 ; pcmpgtd %xmm1,%xmm0 DB 102,65,15,223,197 ; pandn %xmm13,%xmm0 @@ -18107,7 +17970,7 @@ _sk_gather_f16_sse2 LABEL PROC DB 102,69,15,239,210 ; pxor %xmm10,%xmm10 DB 102,65,15,111,206 ; movdqa %xmm14,%xmm1 DB 102,65,15,97,202 ; punpcklwd %xmm10,%xmm1 - DB 102,68,15,111,13,82,28,0,0 ; movdqa 0x1c52(%rip),%xmm9 # 49d0 <_sk_callback_sse2+0xbf9> + DB 102,68,15,111,13,56,28,0,0 ; movdqa 0x1c38(%rip),%xmm9 # 4930 <_sk_callback_sse2+0xbdf> DB 102,15,111,193 ; movdqa %xmm1,%xmm0 DB 102,65,15,219,193 ; pand %xmm9,%xmm0 DB 102,15,239,200 ; pxor %xmm0,%xmm1 @@ -18115,11 +17978,11 @@ _sk_gather_f16_sse2 LABEL PROC DB 102,68,15,111,233 ; movdqa %xmm1,%xmm13 DB 102,65,15,114,245,13 ; pslld $0xd,%xmm13 DB 102,68,15,235,232 ; por %xmm0,%xmm13 - DB 102,68,15,111,29,55,28,0,0 ; movdqa 0x1c37(%rip),%xmm11 # 49e0 <_sk_callback_sse2+0xc09> + DB 102,68,15,111,29,29,28,0,0 ; movdqa 0x1c1d(%rip),%xmm11 # 4940 <_sk_callback_sse2+0xbef> DB 102,69,15,254,235 ; paddd %xmm11,%xmm13 - DB 102,68,15,111,37,57,28,0,0 ; movdqa 0x1c39(%rip),%xmm12 # 49f0 <_sk_callback_sse2+0xc19> + DB 102,68,15,111,37,31,28,0,0 ; movdqa 0x1c1f(%rip),%xmm12 # 4950 <_sk_callback_sse2+0xbff> DB 102,65,15,239,204 ; pxor %xmm12,%xmm1 - DB 102,15,111,29,60,28,0,0 ; movdqa 0x1c3c(%rip),%xmm3 # 4a00 <_sk_callback_sse2+0xc29> + DB 102,15,111,29,34,28,0,0 ; movdqa 0x1c22(%rip),%xmm3 # 4960 <_sk_callback_sse2+0xc0f> DB 102,15,111,195 ; movdqa %xmm3,%xmm0 DB 102,15,102,193 ; pcmpgtd %xmm1,%xmm0 DB 102,65,15,223,197 ; pandn %xmm13,%xmm0 @@ -18170,17 +18033,17 @@ PUBLIC _sk_store_f16_sse2 _sk_store_f16_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 102,68,15,111,21,100,27,0,0 ; movdqa 0x1b64(%rip),%xmm10 # 4a10 <_sk_callback_sse2+0xc39> + DB 102,68,15,111,21,74,27,0,0 ; movdqa 0x1b4a(%rip),%xmm10 # 4970 <_sk_callback_sse2+0xc1f> DB 102,68,15,111,224 ; movdqa %xmm0,%xmm12 DB 102,68,15,111,232 ; movdqa %xmm0,%xmm13 DB 102,69,15,219,234 ; pand %xmm10,%xmm13 DB 102,69,15,239,229 ; pxor %xmm13,%xmm12 - DB 102,68,15,111,13,87,27,0,0 ; movdqa 0x1b57(%rip),%xmm9 # 4a20 <_sk_callback_sse2+0xc49> + DB 102,68,15,111,13,61,27,0,0 ; movdqa 0x1b3d(%rip),%xmm9 # 4980 <_sk_callback_sse2+0xc2f> DB 102,65,15,114,213,16 ; psrld $0x10,%xmm13 DB 102,69,15,111,193 ; movdqa %xmm9,%xmm8 DB 102,69,15,102,196 ; pcmpgtd %xmm12,%xmm8 DB 102,65,15,114,212,13 ; psrld $0xd,%xmm12 - DB 102,68,15,111,29,72,27,0,0 ; movdqa 0x1b48(%rip),%xmm11 # 4a30 <_sk_callback_sse2+0xc59> + DB 102,68,15,111,29,46,27,0,0 ; movdqa 0x1b2e(%rip),%xmm11 # 4990 <_sk_callback_sse2+0xc3f> DB 102,69,15,235,235 ; por %xmm11,%xmm13 DB 102,69,15,254,236 ; paddd %xmm12,%xmm13 DB 102,65,15,114,245,16 ; pslld $0x10,%xmm13 @@ -18257,7 +18120,7 @@ _sk_load_u16_be_sse2 LABEL PROC DB 102,69,15,239,201 ; pxor %xmm9,%xmm9 DB 102,65,15,97,201 ; punpcklwd %xmm9,%xmm1 DB 15,91,193 ; cvtdq2ps %xmm1,%xmm0 - DB 68,15,40,5,230,25,0,0 ; movaps 0x19e6(%rip),%xmm8 # 4a40 <_sk_callback_sse2+0xc69> + DB 68,15,40,5,204,25,0,0 ; movaps 0x19cc(%rip),%xmm8 # 49a0 <_sk_callback_sse2+0xc4f> DB 65,15,89,192 ; mulps %xmm8,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 DB 102,15,113,241,8 ; psllw $0x8,%xmm1 @@ -18308,7 +18171,7 @@ _sk_load_rgb_u16_be_sse2 LABEL PROC DB 102,69,15,239,192 ; pxor %xmm8,%xmm8 DB 102,65,15,97,192 ; punpcklwd %xmm8,%xmm0 DB 15,91,192 ; cvtdq2ps %xmm0,%xmm0 - DB 68,15,40,13,34,25,0,0 ; movaps 0x1922(%rip),%xmm9 # 4a50 <_sk_callback_sse2+0xc79> + DB 68,15,40,13,8,25,0,0 ; movaps 0x1908(%rip),%xmm9 # 49b0 <_sk_callback_sse2+0xc5f> DB 65,15,89,193 ; mulps %xmm9,%xmm0 DB 102,15,111,203 ; movdqa %xmm3,%xmm1 DB 102,15,113,241,8 ; psllw $0x8,%xmm1 @@ -18325,14 +18188,14 @@ _sk_load_rgb_u16_be_sse2 LABEL PROC DB 15,91,210 ; cvtdq2ps %xmm2,%xmm2 DB 65,15,89,209 ; mulps %xmm9,%xmm2 DB 72,173 ; lods %ds:(%rsi),%rax - DB 15,40,29,233,24,0,0 ; movaps 0x18e9(%rip),%xmm3 # 4a60 <_sk_callback_sse2+0xc89> + DB 15,40,29,207,24,0,0 ; movaps 0x18cf(%rip),%xmm3 # 49c0 <_sk_callback_sse2+0xc6f> DB 255,224 ; jmpq *%rax PUBLIC _sk_store_u16_be_sse2 _sk_store_u16_be_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 72,139,0 ; mov (%rax),%rax - DB 68,15,40,13,234,24,0,0 ; movaps 0x18ea(%rip),%xmm9 # 4a70 <_sk_callback_sse2+0xc99> + DB 68,15,40,13,208,24,0,0 ; movaps 0x18d0(%rip),%xmm9 # 49d0 <_sk_callback_sse2+0xc7f> DB 68,15,40,192 ; movaps %xmm0,%xmm8 DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 102,69,15,91,192 ; cvtps2dq %xmm8,%xmm8 @@ -18472,7 +18335,7 @@ _sk_repeat_x_sse2 LABEL PROC DB 243,69,15,91,209 ; cvttps2dq %xmm9,%xmm10 DB 69,15,91,210 ; cvtdq2ps %xmm10,%xmm10 DB 69,15,194,202,1 ; cmpltps %xmm10,%xmm9 - DB 68,15,84,13,212,22,0,0 ; andps 0x16d4(%rip),%xmm9 # 4a80 <_sk_callback_sse2+0xca9> + DB 68,15,84,13,186,22,0,0 ; andps 0x16ba(%rip),%xmm9 # 49e0 <_sk_callback_sse2+0xc8f> DB 69,15,92,209 ; subps %xmm9,%xmm10 DB 69,15,89,208 ; mulps %xmm8,%xmm10 DB 65,15,92,194 ; subps %xmm10,%xmm0 @@ -18492,7 +18355,7 @@ _sk_repeat_y_sse2 LABEL PROC DB 243,69,15,91,209 ; cvttps2dq %xmm9,%xmm10 DB 69,15,91,210 ; cvtdq2ps %xmm10,%xmm10 DB 69,15,194,202,1 ; cmpltps %xmm10,%xmm9 - DB 68,15,84,13,156,22,0,0 ; andps 0x169c(%rip),%xmm9 # 4a90 <_sk_callback_sse2+0xcb9> + DB 68,15,84,13,130,22,0,0 ; andps 0x1682(%rip),%xmm9 # 49f0 <_sk_callback_sse2+0xc9f> DB 69,15,92,209 ; subps %xmm9,%xmm10 DB 69,15,89,208 ; mulps %xmm8,%xmm10 DB 65,15,92,202 ; subps %xmm10,%xmm1 @@ -18516,7 +18379,7 @@ _sk_mirror_x_sse2 LABEL PROC DB 243,69,15,91,218 ; cvttps2dq %xmm10,%xmm11 DB 69,15,91,219 ; cvtdq2ps %xmm11,%xmm11 DB 69,15,194,211,1 ; cmpltps %xmm11,%xmm10 - DB 68,15,84,21,82,22,0,0 ; andps 0x1652(%rip),%xmm10 # 4aa0 <_sk_callback_sse2+0xcc9> + DB 68,15,84,21,56,22,0,0 ; andps 0x1638(%rip),%xmm10 # 4a00 <_sk_callback_sse2+0xcaf> DB 69,15,87,228 ; xorps %xmm12,%xmm12 DB 69,15,92,218 ; subps %xmm10,%xmm11 DB 69,15,89,216 ; mulps %xmm8,%xmm11 @@ -18544,7 +18407,7 @@ _sk_mirror_y_sse2 LABEL PROC DB 243,69,15,91,218 ; cvttps2dq %xmm10,%xmm11 DB 69,15,91,219 ; cvtdq2ps %xmm11,%xmm11 DB 69,15,194,211,1 ; cmpltps %xmm11,%xmm10 - DB 68,15,84,21,248,21,0,0 ; andps 0x15f8(%rip),%xmm10 # 4ab0 <_sk_callback_sse2+0xcd9> + DB 68,15,84,21,222,21,0,0 ; andps 0x15de(%rip),%xmm10 # 4a10 <_sk_callback_sse2+0xcbf> DB 69,15,87,228 ; xorps %xmm12,%xmm12 DB 69,15,92,218 ; subps %xmm10,%xmm11 DB 69,15,89,216 ; mulps %xmm8,%xmm11 @@ -18561,10 +18424,10 @@ _sk_mirror_y_sse2 LABEL PROC PUBLIC _sk_luminance_to_alpha_sse2 _sk_luminance_to_alpha_sse2 LABEL PROC DB 15,40,218 ; movaps %xmm2,%xmm3 - DB 15,89,5,208,21,0,0 ; mulps 0x15d0(%rip),%xmm0 # 4ac0 <_sk_callback_sse2+0xce9> - DB 15,89,13,217,21,0,0 ; mulps 0x15d9(%rip),%xmm1 # 4ad0 <_sk_callback_sse2+0xcf9> + DB 15,89,5,182,21,0,0 ; mulps 0x15b6(%rip),%xmm0 # 4a20 <_sk_callback_sse2+0xccf> + DB 15,89,13,191,21,0,0 ; mulps 0x15bf(%rip),%xmm1 # 4a30 <_sk_callback_sse2+0xcdf> DB 15,88,200 ; addps %xmm0,%xmm1 - DB 15,89,29,223,21,0,0 ; mulps 0x15df(%rip),%xmm3 # 4ae0 <_sk_callback_sse2+0xd09> + DB 15,89,29,197,21,0,0 ; mulps 0x15c5(%rip),%xmm3 # 4a40 <_sk_callback_sse2+0xcef> DB 15,88,217 ; addps %xmm1,%xmm3 DB 72,173 ; lods %ds:(%rsi),%rax DB 15,87,192 ; xorps %xmm0,%xmm0 @@ -18787,7 +18650,7 @@ _sk_linear_gradient_sse2 LABEL PROC DB 69,15,198,228,0 ; shufps $0x0,%xmm12,%xmm12 DB 72,139,8 ; mov (%rax),%rcx DB 72,133,201 ; test %rcx,%rcx - DB 15,132,15,1,0,0 ; je 39b4 <_sk_linear_gradient_sse2+0x149> + DB 15,132,15,1,0,0 ; je 392e <_sk_linear_gradient_sse2+0x149> DB 72,139,64,8 ; mov 0x8(%rax),%rax DB 72,131,192,32 ; add $0x20,%rax DB 69,15,87,192 ; xorps %xmm8,%xmm8 @@ -18848,8 +18711,8 @@ _sk_linear_gradient_sse2 LABEL PROC DB 69,15,86,231 ; orps %xmm15,%xmm12 DB 72,131,192,36 ; add $0x24,%rax DB 72,255,201 ; dec %rcx - DB 15,133,8,255,255,255 ; jne 38ba <_sk_linear_gradient_sse2+0x4f> - DB 235,13 ; jmp 39c1 <_sk_linear_gradient_sse2+0x156> + DB 15,133,8,255,255,255 ; jne 3834 <_sk_linear_gradient_sse2+0x4f> + DB 235,13 ; jmp 393b <_sk_linear_gradient_sse2+0x156> DB 15,87,201 ; xorps %xmm1,%xmm1 DB 15,87,210 ; xorps %xmm2,%xmm2 DB 15,87,219 ; xorps %xmm3,%xmm3 @@ -18900,7 +18763,7 @@ _sk_linear_gradient_2stops_sse2 LABEL PROC PUBLIC _sk_save_xy_sse2 _sk_save_xy_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,144,16,0,0 ; movaps 0x1090(%rip),%xmm8 # 4af0 <_sk_callback_sse2+0xd19> + DB 68,15,40,5,118,16,0,0 ; movaps 0x1076(%rip),%xmm8 # 4a50 <_sk_callback_sse2+0xcff> DB 15,17,0 ; movups %xmm0,(%rax) DB 68,15,40,200 ; movaps %xmm0,%xmm9 DB 69,15,88,200 ; addps %xmm8,%xmm9 @@ -18908,7 +18771,7 @@ _sk_save_xy_sse2 LABEL PROC DB 69,15,91,210 ; cvtdq2ps %xmm10,%xmm10 DB 69,15,40,217 ; movaps %xmm9,%xmm11 DB 69,15,194,218,1 ; cmpltps %xmm10,%xmm11 - DB 68,15,40,37,123,16,0,0 ; movaps 0x107b(%rip),%xmm12 # 4b00 <_sk_callback_sse2+0xd29> + DB 68,15,40,37,97,16,0,0 ; movaps 0x1061(%rip),%xmm12 # 4a60 <_sk_callback_sse2+0xd0f> DB 69,15,84,220 ; andps %xmm12,%xmm11 DB 69,15,92,211 ; subps %xmm11,%xmm10 DB 69,15,92,202 ; subps %xmm10,%xmm9 @@ -18951,8 +18814,8 @@ _sk_bilinear_nx_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,244,15,0,0 ; addps 0xff4(%rip),%xmm0 # 4b10 <_sk_callback_sse2+0xd39> - DB 68,15,40,13,252,15,0,0 ; movaps 0xffc(%rip),%xmm9 # 4b20 <_sk_callback_sse2+0xd49> + DB 15,88,5,218,15,0,0 ; addps 0xfda(%rip),%xmm0 # 4a70 <_sk_callback_sse2+0xd1f> + DB 68,15,40,13,226,15,0,0 ; movaps 0xfe2(%rip),%xmm9 # 4a80 <_sk_callback_sse2+0xd2f> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 68,15,17,136,128,0,0,0 ; movups %xmm9,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -18963,7 +18826,7 @@ _sk_bilinear_px_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,235,15,0,0 ; addps 0xfeb(%rip),%xmm0 # 4b30 <_sk_callback_sse2+0xd59> + DB 15,88,5,209,15,0,0 ; addps 0xfd1(%rip),%xmm0 # 4a90 <_sk_callback_sse2+0xd3f> DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -18973,8 +18836,8 @@ _sk_bilinear_ny_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,221,15,0,0 ; addps 0xfdd(%rip),%xmm1 # 4b40 <_sk_callback_sse2+0xd69> - DB 68,15,40,13,229,15,0,0 ; movaps 0xfe5(%rip),%xmm9 # 4b50 <_sk_callback_sse2+0xd79> + DB 15,88,13,195,15,0,0 ; addps 0xfc3(%rip),%xmm1 # 4aa0 <_sk_callback_sse2+0xd4f> + DB 68,15,40,13,203,15,0,0 ; movaps 0xfcb(%rip),%xmm9 # 4ab0 <_sk_callback_sse2+0xd5f> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 68,15,17,136,160,0,0,0 ; movups %xmm9,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -18985,7 +18848,7 @@ _sk_bilinear_py_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,211,15,0,0 ; addps 0xfd3(%rip),%xmm1 # 4b60 <_sk_callback_sse2+0xd89> + DB 15,88,13,185,15,0,0 ; addps 0xfb9(%rip),%xmm1 # 4ac0 <_sk_callback_sse2+0xd6f> DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -18995,13 +18858,13 @@ _sk_bicubic_n3x_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,198,15,0,0 ; addps 0xfc6(%rip),%xmm0 # 4b70 <_sk_callback_sse2+0xd99> - DB 68,15,40,13,206,15,0,0 ; movaps 0xfce(%rip),%xmm9 # 4b80 <_sk_callback_sse2+0xda9> + DB 15,88,5,172,15,0,0 ; addps 0xfac(%rip),%xmm0 # 4ad0 <_sk_callback_sse2+0xd7f> + DB 68,15,40,13,180,15,0,0 ; movaps 0xfb4(%rip),%xmm9 # 4ae0 <_sk_callback_sse2+0xd8f> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 69,15,40,193 ; movaps %xmm9,%xmm8 DB 69,15,89,192 ; mulps %xmm8,%xmm8 - DB 68,15,89,13,202,15,0,0 ; mulps 0xfca(%rip),%xmm9 # 4b90 <_sk_callback_sse2+0xdb9> - DB 68,15,88,13,210,15,0,0 ; addps 0xfd2(%rip),%xmm9 # 4ba0 <_sk_callback_sse2+0xdc9> + DB 68,15,89,13,176,15,0,0 ; mulps 0xfb0(%rip),%xmm9 # 4af0 <_sk_callback_sse2+0xd9f> + DB 68,15,88,13,184,15,0,0 ; addps 0xfb8(%rip),%xmm9 # 4b00 <_sk_callback_sse2+0xdaf> DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 68,15,17,136,128,0,0,0 ; movups %xmm9,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -19012,16 +18875,16 @@ _sk_bicubic_n1x_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,193,15,0,0 ; addps 0xfc1(%rip),%xmm0 # 4bb0 <_sk_callback_sse2+0xdd9> - DB 68,15,40,13,201,15,0,0 ; movaps 0xfc9(%rip),%xmm9 # 4bc0 <_sk_callback_sse2+0xde9> + DB 15,88,5,167,15,0,0 ; addps 0xfa7(%rip),%xmm0 # 4b10 <_sk_callback_sse2+0xdbf> + DB 68,15,40,13,175,15,0,0 ; movaps 0xfaf(%rip),%xmm9 # 4b20 <_sk_callback_sse2+0xdcf> DB 69,15,92,200 ; subps %xmm8,%xmm9 - DB 68,15,40,5,205,15,0,0 ; movaps 0xfcd(%rip),%xmm8 # 4bd0 <_sk_callback_sse2+0xdf9> + DB 68,15,40,5,179,15,0,0 ; movaps 0xfb3(%rip),%xmm8 # 4b30 <_sk_callback_sse2+0xddf> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,209,15,0,0 ; addps 0xfd1(%rip),%xmm8 # 4be0 <_sk_callback_sse2+0xe09> + DB 68,15,88,5,183,15,0,0 ; addps 0xfb7(%rip),%xmm8 # 4b40 <_sk_callback_sse2+0xdef> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,213,15,0,0 ; addps 0xfd5(%rip),%xmm8 # 4bf0 <_sk_callback_sse2+0xe19> + DB 68,15,88,5,187,15,0,0 ; addps 0xfbb(%rip),%xmm8 # 4b50 <_sk_callback_sse2+0xdff> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,217,15,0,0 ; addps 0xfd9(%rip),%xmm8 # 4c00 <_sk_callback_sse2+0xe29> + DB 68,15,88,5,191,15,0,0 ; addps 0xfbf(%rip),%xmm8 # 4b60 <_sk_callback_sse2+0xe0f> DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -19029,17 +18892,17 @@ _sk_bicubic_n1x_sse2 LABEL PROC PUBLIC _sk_bicubic_p1x_sse2 _sk_bicubic_p1x_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,211,15,0,0 ; movaps 0xfd3(%rip),%xmm8 # 4c10 <_sk_callback_sse2+0xe39> + DB 68,15,40,5,185,15,0,0 ; movaps 0xfb9(%rip),%xmm8 # 4b70 <_sk_callback_sse2+0xe1f> DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,72,64 ; movups 0x40(%rax),%xmm9 DB 65,15,88,192 ; addps %xmm8,%xmm0 - DB 68,15,40,21,207,15,0,0 ; movaps 0xfcf(%rip),%xmm10 # 4c20 <_sk_callback_sse2+0xe49> + DB 68,15,40,21,181,15,0,0 ; movaps 0xfb5(%rip),%xmm10 # 4b80 <_sk_callback_sse2+0xe2f> DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,211,15,0,0 ; addps 0xfd3(%rip),%xmm10 # 4c30 <_sk_callback_sse2+0xe59> + DB 68,15,88,21,185,15,0,0 ; addps 0xfb9(%rip),%xmm10 # 4b90 <_sk_callback_sse2+0xe3f> DB 69,15,89,209 ; mulps %xmm9,%xmm10 DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,207,15,0,0 ; addps 0xfcf(%rip),%xmm10 # 4c40 <_sk_callback_sse2+0xe69> + DB 68,15,88,21,181,15,0,0 ; addps 0xfb5(%rip),%xmm10 # 4ba0 <_sk_callback_sse2+0xe4f> DB 68,15,17,144,128,0,0,0 ; movups %xmm10,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -19049,11 +18912,11 @@ _sk_bicubic_p3x_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,0 ; movups (%rax),%xmm0 DB 68,15,16,64,64 ; movups 0x40(%rax),%xmm8 - DB 15,88,5,194,15,0,0 ; addps 0xfc2(%rip),%xmm0 # 4c50 <_sk_callback_sse2+0xe79> + DB 15,88,5,168,15,0,0 ; addps 0xfa8(%rip),%xmm0 # 4bb0 <_sk_callback_sse2+0xe5f> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,89,201 ; mulps %xmm9,%xmm9 - DB 68,15,89,5,194,15,0,0 ; mulps 0xfc2(%rip),%xmm8 # 4c60 <_sk_callback_sse2+0xe89> - DB 68,15,88,5,202,15,0,0 ; addps 0xfca(%rip),%xmm8 # 4c70 <_sk_callback_sse2+0xe99> + DB 68,15,89,5,168,15,0,0 ; mulps 0xfa8(%rip),%xmm8 # 4bc0 <_sk_callback_sse2+0xe6f> + DB 68,15,88,5,176,15,0,0 ; addps 0xfb0(%rip),%xmm8 # 4bd0 <_sk_callback_sse2+0xe7f> DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 68,15,17,128,128,0,0,0 ; movups %xmm8,0x80(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -19064,13 +18927,13 @@ _sk_bicubic_n3y_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,184,15,0,0 ; addps 0xfb8(%rip),%xmm1 # 4c80 <_sk_callback_sse2+0xea9> - DB 68,15,40,13,192,15,0,0 ; movaps 0xfc0(%rip),%xmm9 # 4c90 <_sk_callback_sse2+0xeb9> + DB 15,88,13,158,15,0,0 ; addps 0xf9e(%rip),%xmm1 # 4be0 <_sk_callback_sse2+0xe8f> + DB 68,15,40,13,166,15,0,0 ; movaps 0xfa6(%rip),%xmm9 # 4bf0 <_sk_callback_sse2+0xe9f> DB 69,15,92,200 ; subps %xmm8,%xmm9 DB 69,15,40,193 ; movaps %xmm9,%xmm8 DB 69,15,89,192 ; mulps %xmm8,%xmm8 - DB 68,15,89,13,188,15,0,0 ; mulps 0xfbc(%rip),%xmm9 # 4ca0 <_sk_callback_sse2+0xec9> - DB 68,15,88,13,196,15,0,0 ; addps 0xfc4(%rip),%xmm9 # 4cb0 <_sk_callback_sse2+0xed9> + DB 68,15,89,13,162,15,0,0 ; mulps 0xfa2(%rip),%xmm9 # 4c00 <_sk_callback_sse2+0xeaf> + DB 68,15,88,13,170,15,0,0 ; addps 0xfaa(%rip),%xmm9 # 4c10 <_sk_callback_sse2+0xebf> DB 69,15,89,200 ; mulps %xmm8,%xmm9 DB 68,15,17,136,160,0,0,0 ; movups %xmm9,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -19081,16 +18944,16 @@ _sk_bicubic_n1y_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,178,15,0,0 ; addps 0xfb2(%rip),%xmm1 # 4cc0 <_sk_callback_sse2+0xee9> - DB 68,15,40,13,186,15,0,0 ; movaps 0xfba(%rip),%xmm9 # 4cd0 <_sk_callback_sse2+0xef9> + DB 15,88,13,152,15,0,0 ; addps 0xf98(%rip),%xmm1 # 4c20 <_sk_callback_sse2+0xecf> + DB 68,15,40,13,160,15,0,0 ; movaps 0xfa0(%rip),%xmm9 # 4c30 <_sk_callback_sse2+0xedf> DB 69,15,92,200 ; subps %xmm8,%xmm9 - DB 68,15,40,5,190,15,0,0 ; movaps 0xfbe(%rip),%xmm8 # 4ce0 <_sk_callback_sse2+0xf09> + DB 68,15,40,5,164,15,0,0 ; movaps 0xfa4(%rip),%xmm8 # 4c40 <_sk_callback_sse2+0xeef> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,194,15,0,0 ; addps 0xfc2(%rip),%xmm8 # 4cf0 <_sk_callback_sse2+0xf19> + DB 68,15,88,5,168,15,0,0 ; addps 0xfa8(%rip),%xmm8 # 4c50 <_sk_callback_sse2+0xeff> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,198,15,0,0 ; addps 0xfc6(%rip),%xmm8 # 4d00 <_sk_callback_sse2+0xf29> + DB 68,15,88,5,172,15,0,0 ; addps 0xfac(%rip),%xmm8 # 4c60 <_sk_callback_sse2+0xf0f> DB 69,15,89,193 ; mulps %xmm9,%xmm8 - DB 68,15,88,5,202,15,0,0 ; addps 0xfca(%rip),%xmm8 # 4d10 <_sk_callback_sse2+0xf39> + DB 68,15,88,5,176,15,0,0 ; addps 0xfb0(%rip),%xmm8 # 4c70 <_sk_callback_sse2+0xf1f> DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -19098,17 +18961,17 @@ _sk_bicubic_n1y_sse2 LABEL PROC PUBLIC _sk_bicubic_p1y_sse2 _sk_bicubic_p1y_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax - DB 68,15,40,5,196,15,0,0 ; movaps 0xfc4(%rip),%xmm8 # 4d20 <_sk_callback_sse2+0xf49> + DB 68,15,40,5,170,15,0,0 ; movaps 0xfaa(%rip),%xmm8 # 4c80 <_sk_callback_sse2+0xf2f> DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,72,96 ; movups 0x60(%rax),%xmm9 DB 65,15,88,200 ; addps %xmm8,%xmm1 - DB 68,15,40,21,191,15,0,0 ; movaps 0xfbf(%rip),%xmm10 # 4d30 <_sk_callback_sse2+0xf59> + DB 68,15,40,21,165,15,0,0 ; movaps 0xfa5(%rip),%xmm10 # 4c90 <_sk_callback_sse2+0xf3f> DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,195,15,0,0 ; addps 0xfc3(%rip),%xmm10 # 4d40 <_sk_callback_sse2+0xf69> + DB 68,15,88,21,169,15,0,0 ; addps 0xfa9(%rip),%xmm10 # 4ca0 <_sk_callback_sse2+0xf4f> DB 69,15,89,209 ; mulps %xmm9,%xmm10 DB 69,15,88,208 ; addps %xmm8,%xmm10 DB 69,15,89,209 ; mulps %xmm9,%xmm10 - DB 68,15,88,21,191,15,0,0 ; addps 0xfbf(%rip),%xmm10 # 4d50 <_sk_callback_sse2+0xf79> + DB 68,15,88,21,165,15,0,0 ; addps 0xfa5(%rip),%xmm10 # 4cb0 <_sk_callback_sse2+0xf5f> DB 68,15,17,144,160,0,0,0 ; movups %xmm10,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax DB 255,224 ; jmpq *%rax @@ -19118,11 +18981,11 @@ _sk_bicubic_p3y_sse2 LABEL PROC DB 72,173 ; lods %ds:(%rsi),%rax DB 15,16,72,32 ; movups 0x20(%rax),%xmm1 DB 68,15,16,64,96 ; movups 0x60(%rax),%xmm8 - DB 15,88,13,177,15,0,0 ; addps 0xfb1(%rip),%xmm1 # 4d60 <_sk_callback_sse2+0xf89> + DB 15,88,13,151,15,0,0 ; addps 0xf97(%rip),%xmm1 # 4cc0 <_sk_callback_sse2+0xf6f> DB 69,15,40,200 ; movaps %xmm8,%xmm9 DB 69,15,89,201 ; mulps %xmm9,%xmm9 - DB 68,15,89,5,177,15,0,0 ; mulps 0xfb1(%rip),%xmm8 # 4d70 <_sk_callback_sse2+0xf99> - DB 68,15,88,5,185,15,0,0 ; addps 0xfb9(%rip),%xmm8 # 4d80 <_sk_callback_sse2+0xfa9> + DB 68,15,89,5,151,15,0,0 ; mulps 0xf97(%rip),%xmm8 # 4cd0 <_sk_callback_sse2+0xf7f> + DB 68,15,88,5,159,15,0,0 ; addps 0xf9f(%rip),%xmm8 # 4ce0 <_sk_callback_sse2+0xf8f> DB 69,15,89,193 ; mulps %xmm9,%xmm8 DB 68,15,17,128,160,0,0,0 ; movups %xmm8,0xa0(%rax) DB 72,173 ; lods %ds:(%rsi),%rax @@ -19293,11 +19156,11 @@ ALIGN 16 DB 0,128,191,0,0,128 ; add %al,-0x7fffff41(%rax) DB 191,0,0,224,64 ; mov $0x40e00000,%edi DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 4018 <.literal16+0x188> + DB 224,64 ; loopne 3f88 <.literal16+0x188> DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 401c <.literal16+0x18c> + DB 224,64 ; loopne 3f8c <.literal16+0x18c> DB 0,0 ; add %al,(%rax) - DB 224,64 ; loopne 4020 <.literal16+0x190> + DB 224,64 ; loopne 3f90 <.literal16+0x190> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -19436,12 +19299,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 0,0 ; add %al,(%rax) - DB 128,63,0 ; cmpb $0x0,(%rdi) - DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) - DB 63 ; (bad) - DB 0,0 ; add %al,(%rax) - DB 128,63,171 ; cmpb $0xab,(%rdi) + DB 171 ; stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) DB 62,171 ; ds stos %eax,%es:(%rdi) @@ -19454,25 +19312,20 @@ ALIGN 16 DB 170 ; stos %al,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) DB 62,0,0 ; add %al,%ds:(%rax) - DB 128,191,0,0,128,191,0 ; cmpb $0x0,-0x40800000(%rdi) - DB 0,128,191,0,0,128 ; add %al,-0x7fffff41(%rax) - DB 191,0,0,192,64 ; mov $0x40c00000,%edi + DB 128,63,0 ; cmpb $0x0,(%rdi) + DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) + DB 63 ; (bad) DB 0,0 ; add %al,(%rax) + DB 128,63,0 ; cmpb $0x0,(%rdi) + DB 0,192 ; add %al,%al + DB 64,0,0 ; add %al,(%rax) DB 192,64,0,0 ; rolb $0x0,0x0(%rax) DB 192,64,0,0 ; rolb $0x0,0x0(%rax) - DB 192,64,171,170 ; rolb $0xaa,-0x55(%rax) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) - DB 42,63 ; sub (%rdi),%bh - DB 171 ; stos %eax,%es:(%rdi) - DB 170 ; stos %al,%es:(%rdi) + DB 192,64,0,0 ; rolb $0x0,0x0(%rax) + DB 128,64,0,0 ; addb $0x0,0x0(%rax) + DB 128,64,0,0 ; addb $0x0,0x0(%rax) + DB 128,64,0,0 ; addb $0x0,0x0(%rax) + DB 128,64,171,170 ; addb $0xaa,-0x55(%rax) DB 170 ; stos %al,%es:(%rdi) DB 190,171,170,170,190 ; mov $0xbeaaaaab,%esi DB 171 ; stos %eax,%es:(%rdi) @@ -19500,13 +19353,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 41c9 <.literal16+0x339> + DB 224,7 ; loopne 4129 <.literal16+0x329> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 41cd <.literal16+0x33d> + DB 224,7 ; loopne 412d <.literal16+0x32d> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 41d1 <.literal16+0x341> + DB 224,7 ; loopne 4131 <.literal16+0x331> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 41d5 <.literal16+0x345> + DB 224,7 ; loopne 4135 <.literal16+0x335> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -19575,11 +19428,11 @@ ALIGN 16 DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 42bb <.literal16+0x42b> + DB 127,67 ; jg 421b <.literal16+0x41b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 42bf <.literal16+0x42f> + DB 127,67 ; jg 421f <.literal16+0x41f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 42c3 <.literal16+0x433> + DB 127,67 ; jg 4223 <.literal16+0x423> DB 129,128,128,59,129,128,128,59,129,128; addl $0x80813b80,-0x7f7ec480(%rax) DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,129,128,128,59 ; addb $0x3b,-0x7f7f7ec5(%rax) @@ -19594,16 +19447,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 42b4 <.literal16+0x424> + DB 127,0 ; jg 4214 <.literal16+0x414> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 42b8 <.literal16+0x428> + DB 127,0 ; jg 4218 <.literal16+0x418> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 42bc <.literal16+0x42c> + DB 127,0 ; jg 421c <.literal16+0x41c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 42c0 <.literal16+0x430> + DB 127,0 ; jg 4220 <.literal16+0x420> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -19612,7 +19465,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4345 <.literal16+0x4b5> + DB 119,115 ; ja 42a5 <.literal16+0x4a5> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -19623,7 +19476,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 42a9 <.literal16+0x419> + DB 117,191 ; jne 4209 <.literal16+0x409> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -19635,7 +19488,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a382ea <_sk_callback_sse2+0xffffffffe9a34513> + DB 233,220,63,163,233 ; jmpq ffffffffe9a3824a <_sk_callback_sse2+0xffffffffe9a344f9> DB 220,63 ; fdivrl (%rdi) DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) @@ -19689,16 +19542,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4384 <.literal16+0x4f4> + DB 127,0 ; jg 42e4 <.literal16+0x4e4> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4388 <.literal16+0x4f8> + DB 127,0 ; jg 42e8 <.literal16+0x4e8> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 438c <.literal16+0x4fc> + DB 127,0 ; jg 42ec <.literal16+0x4ec> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4390 <.literal16+0x500> + DB 127,0 ; jg 42f0 <.literal16+0x4f0> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -19707,7 +19560,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 4415 <.literal16+0x585> + DB 119,115 ; ja 4375 <.literal16+0x575> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -19718,7 +19571,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4379 <.literal16+0x4e9> + DB 117,191 ; jne 42d9 <.literal16+0x4d9> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -19730,7 +19583,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a383ba <_sk_callback_sse2+0xffffffffe9a345e3> + DB 233,220,63,163,233 ; jmpq ffffffffe9a3831a <_sk_callback_sse2+0xffffffffe9a345c9> DB 220,63 ; fdivrl (%rdi) DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) @@ -19784,16 +19637,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4454 <.literal16+0x5c4> + DB 127,0 ; jg 43b4 <.literal16+0x5b4> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4458 <.literal16+0x5c8> + DB 127,0 ; jg 43b8 <.literal16+0x5b8> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 445c <.literal16+0x5cc> + DB 127,0 ; jg 43bc <.literal16+0x5bc> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4460 <.literal16+0x5d0> + DB 127,0 ; jg 43c0 <.literal16+0x5c0> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -19802,7 +19655,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 44e5 <.literal16+0x655> + DB 119,115 ; ja 4445 <.literal16+0x645> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -19813,7 +19666,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4449 <.literal16+0x5b9> + DB 117,191 ; jne 43a9 <.literal16+0x5a9> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -19825,7 +19678,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a3848a <_sk_callback_sse2+0xffffffffe9a346b3> + DB 233,220,63,163,233 ; jmpq ffffffffe9a383ea <_sk_callback_sse2+0xffffffffe9a34699> DB 220,63 ; fdivrl (%rdi) DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) @@ -19879,16 +19732,16 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 52,255 ; xor $0xff,%al DB 255 ; (bad) - DB 127,0 ; jg 4524 <.literal16+0x694> + DB 127,0 ; jg 4484 <.literal16+0x684> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4528 <.literal16+0x698> + DB 127,0 ; jg 4488 <.literal16+0x688> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 452c <.literal16+0x69c> + DB 127,0 ; jg 448c <.literal16+0x68c> DB 255 ; (bad) DB 255 ; (bad) - DB 127,0 ; jg 4530 <.literal16+0x6a0> + DB 127,0 ; jg 4490 <.literal16+0x690> DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -19897,7 +19750,7 @@ ALIGN 16 DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) - DB 119,115 ; ja 45b5 <.literal16+0x725> + DB 119,115 ; ja 4515 <.literal16+0x715> DB 248 ; clc DB 194,119,115 ; retq $0x7377 DB 248 ; clc @@ -19908,7 +19761,7 @@ ALIGN 16 DB 194,117,191 ; retq $0xbf75 DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) - DB 117,191 ; jne 4519 <.literal16+0x689> + DB 117,191 ; jne 4479 <.literal16+0x679> DB 191,63,117,191,191 ; mov $0xbfbf753f,%edi DB 63 ; (bad) DB 249 ; stc @@ -19920,7 +19773,7 @@ ALIGN 16 DB 249 ; stc DB 68,180,62 ; rex.R mov $0x3e,%spl DB 163,233,220,63,163,233,220,63,163 ; movabs %eax,0xa33fdce9a33fdce9 - DB 233,220,63,163,233 ; jmpq ffffffffe9a3855a <_sk_callback_sse2+0xffffffffe9a34783> + DB 233,220,63,163,233 ; jmpq ffffffffe9a384ba <_sk_callback_sse2+0xffffffffe9a34769> DB 220,63 ; fdivrl (%rdi) DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) @@ -19970,13 +19823,13 @@ ALIGN 16 DB 200,66,0,0 ; enterq $0x42,$0x0 DB 200,66,0,0 ; enterq $0x42,$0x0 DB 200,66,0,0 ; enterq $0x42,$0x0 - DB 127,67 ; jg 4637 <.literal16+0x7a7> + DB 127,67 ; jg 4597 <.literal16+0x797> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 463b <.literal16+0x7ab> + DB 127,67 ; jg 459b <.literal16+0x79b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 463f <.literal16+0x7af> + DB 127,67 ; jg 459f <.literal16+0x79f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4643 <.literal16+0x7b3> + DB 127,67 ; jg 45a3 <.literal16+0x7a3> DB 0,0 ; add %al,(%rax) DB 0,195 ; add %al,%bl DB 0,0 ; add %al,(%rax) @@ -20023,16 +19876,16 @@ ALIGN 16 DB 128,3,62 ; addb $0x3e,(%rbx) DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 46c3 <.literal16+0x833> + DB 118,63 ; jbe 4623 <.literal16+0x823> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 46c7 <.literal16+0x837> + DB 118,63 ; jbe 4627 <.literal16+0x827> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 46cb <.literal16+0x83b> + DB 118,63 ; jbe 462b <.literal16+0x82b> DB 31 ; (bad) DB 215 ; xlat %ds:(%rbx) - DB 118,63 ; jbe 46cf <.literal16+0x83f> + DB 118,63 ; jbe 462f <.literal16+0x82f> DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 246,64,83,63 ; testb $0x3f,0x53(%rax) DB 246,64,83,63 ; testb $0x3f,0x53(%rax) @@ -20044,11 +19897,11 @@ ALIGN 16 DB 128,59,0 ; cmpb $0x0,(%rbx) DB 0,127,67 ; add %bh,0x43(%rdi) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 470b <.literal16+0x87b> + DB 127,67 ; jg 466b <.literal16+0x86b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 470f <.literal16+0x87f> + DB 127,67 ; jg 466f <.literal16+0x86f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 4713 <.literal16+0x883> + DB 127,67 ; jg 4673 <.literal16+0x873> DB 129,128,128,59,129,128,128,59,129,128; addl $0x80813b80,-0x7f7ec480(%rax) DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,0,0,128,63 ; addb $0x3f,-0x7fffffc5(%rax) @@ -20088,13 +19941,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 4759 <.literal16+0x8c9> + DB 224,7 ; loopne 46b9 <.literal16+0x8b9> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 475d <.literal16+0x8cd> + DB 224,7 ; loopne 46bd <.literal16+0x8bd> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4761 <.literal16+0x8d1> + DB 224,7 ; loopne 46c1 <.literal16+0x8c1> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 4765 <.literal16+0x8d5> + DB 224,7 ; loopne 46c5 <.literal16+0x8c5> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -20140,13 +19993,13 @@ ALIGN 16 DB 132,55 ; test %dh,(%rdi) DB 8,33 ; or %ah,(%rcx) DB 132,55 ; test %dh,(%rdi) - DB 224,7 ; loopne 47c9 <.literal16+0x939> + DB 224,7 ; loopne 4729 <.literal16+0x929> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 47cd <.literal16+0x93d> + DB 224,7 ; loopne 472d <.literal16+0x92d> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 47d1 <.literal16+0x941> + DB 224,7 ; loopne 4731 <.literal16+0x931> DB 0,0 ; add %al,(%rax) - DB 224,7 ; loopne 47d5 <.literal16+0x945> + DB 224,7 ; loopne 4735 <.literal16+0x935> DB 0,0 ; add %al,(%rax) DB 33,8 ; and %ecx,(%rax) DB 2,58 ; add (%rdx),%bh @@ -20184,13 +20037,13 @@ ALIGN 16 DB 65,0,0 ; add %al,(%r8) DB 248 ; clc DB 65,0,0 ; add %al,(%r8) - DB 124,66 ; jl 4866 <.literal16+0x9d6> + DB 124,66 ; jl 47c6 <.literal16+0x9c6> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 486a <.literal16+0x9da> + DB 124,66 ; jl 47ca <.literal16+0x9ca> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 486e <.literal16+0x9de> + DB 124,66 ; jl 47ce <.literal16+0x9ce> DB 0,0 ; add %al,(%rax) - DB 124,66 ; jl 4872 <.literal16+0x9e2> + DB 124,66 ; jl 47d2 <.literal16+0x9d2> DB 0,240 ; add %dh,%al DB 0,0 ; add %al,(%rax) DB 0,240 ; add %dh,%al @@ -20280,13 +20133,13 @@ ALIGN 16 DB 136,136,61,137,136,136 ; mov %cl,-0x777776c3(%rax) DB 61,137,136,136,61 ; cmp $0x3d888889,%eax DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 4975 <.literal16+0xae5> + DB 112,65 ; jo 48d5 <.literal16+0xad5> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 4979 <.literal16+0xae9> + DB 112,65 ; jo 48d9 <.literal16+0xad9> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 497d <.literal16+0xaed> + DB 112,65 ; jo 48dd <.literal16+0xadd> DB 0,0 ; add %al,(%rax) - DB 112,65 ; jo 4981 <.literal16+0xaf1> + DB 112,65 ; jo 48e1 <.literal16+0xae1> DB 255,0 ; incl (%rax) DB 0,0 ; add %al,(%rax) DB 255,0 ; incl (%rax) @@ -20308,11 +20161,11 @@ ALIGN 16 DB 128,59,129 ; cmpb $0x81,(%rbx) DB 128,128,59,0,0,127,67 ; addb $0x43,0x7f00003b(%rax) DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 49cb <.literal16+0xb3b> + DB 127,67 ; jg 492b <.literal16+0xb2b> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 49cf <.literal16+0xb3f> + DB 127,67 ; jg 492f <.literal16+0xb2f> DB 0,0 ; add %al,(%rax) - DB 127,67 ; jg 49d3 <.literal16+0xb43> + DB 127,67 ; jg 4933 <.literal16+0xb33> DB 0,128,0,0,0,128 ; add %al,-0x80000000(%rax) DB 0,0 ; add %al,(%rax) DB 0,128,0,0,0,128 ; add %al,-0x80000000(%rax) @@ -20388,13 +20241,13 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 255 ; (bad) - DB 127,71 ; jg 4abb <.literal16+0xc2b> + DB 127,71 ; jg 4a1b <.literal16+0xc1b> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 4abf <.literal16+0xc2f> + DB 127,71 ; jg 4a1f <.literal16+0xc1f> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 4ac3 <.literal16+0xc33> + DB 127,71 ; jg 4a23 <.literal16+0xc23> DB 0,255 ; add %bh,%bh - DB 127,71 ; jg 4ac7 <.literal16+0xc37> + DB 127,71 ; jg 4a27 <.literal16+0xc27> DB 0,0 ; add %al,(%rax) DB 128,63,0 ; cmpb $0x0,(%rdi) DB 0,128,63,0,0,128 ; add %al,-0x7fffffc1(%rax) @@ -20505,11 +20358,11 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,114 ; cmpb $0x72,(%rdi) DB 28,199 ; sbb $0xc7,%al - DB 62,114,28 ; jb,pt 4bb2 <.literal16+0xd22> + DB 62,114,28 ; jb,pt 4b12 <.literal16+0xd12> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4bb6 <.literal16+0xd26> + DB 62,114,28 ; jb,pt 4b16 <.literal16+0xd16> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4bba <.literal16+0xd2a> + DB 62,114,28 ; jb,pt 4b1a <.literal16+0xd1a> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -20553,7 +20406,7 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63da45 <_sk_callback_sse2+0x3d639c6e> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d9a5 <_sk_callback_sse2+0x3d639c54> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -20579,7 +20432,7 @@ ALIGN 16 DB 0,192 ; add %al,%al DB 63 ; (bad) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63da85 <_sk_callback_sse2+0x3d639cae> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63d9e5 <_sk_callback_sse2+0x3d639c94> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al @@ -20588,13 +20441,13 @@ ALIGN 16 DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al DB 63 ; (bad) - DB 114,28 ; jb 4c7e <.literal16+0xdee> + DB 114,28 ; jb 4bde <.literal16+0xdde> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4c82 <.literal16+0xdf2> + DB 62,114,28 ; jb,pt 4be2 <.literal16+0xde2> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4c86 <.literal16+0xdf6> + DB 62,114,28 ; jb,pt 4be6 <.literal16+0xde6> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4c8a <.literal16+0xdfa> + DB 62,114,28 ; jb,pt 4bea <.literal16+0xdea> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -20615,11 +20468,11 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 128,63,114 ; cmpb $0x72,(%rdi) DB 28,199 ; sbb $0xc7,%al - DB 62,114,28 ; jb,pt 4cc2 <.literal16+0xe32> + DB 62,114,28 ; jb,pt 4c22 <.literal16+0xe22> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4cc6 <.literal16+0xe36> + DB 62,114,28 ; jb,pt 4c26 <.literal16+0xe26> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4cca <.literal16+0xe3a> + DB 62,114,28 ; jb,pt 4c2a <.literal16+0xe2a> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) @@ -20663,7 +20516,7 @@ ALIGN 16 DB 0,0 ; add %al,(%rax) DB 0,63 ; add %bh,(%rdi) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63db55 <_sk_callback_sse2+0x3d639d7e> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63dab5 <_sk_callback_sse2+0x3d639d64> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 0,63 ; add %bh,(%rdi) DB 0,0 ; add %al,(%rax) @@ -20689,7 +20542,7 @@ ALIGN 16 DB 0,192 ; add %al,%al DB 63 ; (bad) DB 57,142,99,61,57,142 ; cmp %ecx,-0x71c6c29d(%rsi) - DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63db95 <_sk_callback_sse2+0x3d639dbe> + DB 99,61,57,142,99,61 ; movslq 0x3d638e39(%rip),%edi # 3d63daf5 <_sk_callback_sse2+0x3d639da4> DB 57,142,99,61,0,0 ; cmp %ecx,0x3d63(%rsi) DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al @@ -20698,13 +20551,13 @@ ALIGN 16 DB 192,63,0 ; sarb $0x0,(%rdi) DB 0,192 ; add %al,%al DB 63 ; (bad) - DB 114,28 ; jb 4d8e <.literal16+0xefe> + DB 114,28 ; jb 4cee <.literal16+0xeee> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4d92 <_sk_callback_sse2+0xfbb> + DB 62,114,28 ; jb,pt 4cf2 <_sk_callback_sse2+0xfa1> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4d96 <_sk_callback_sse2+0xfbf> + DB 62,114,28 ; jb,pt 4cf6 <_sk_callback_sse2+0xfa5> DB 199 ; (bad) - DB 62,114,28 ; jb,pt 4d9a <_sk_callback_sse2+0xfc3> + DB 62,114,28 ; jb,pt 4cfa <_sk_callback_sse2+0xfa9> DB 199 ; (bad) DB 62,171 ; ds stos %eax,%es:(%rdi) DB 170 ; stos %al,%es:(%rdi) diff --git a/src/jumper/SkJumper_stages.cpp b/src/jumper/SkJumper_stages.cpp index a74cb7badb..f926f187a4 100644 --- a/src/jumper/SkJumper_stages.cpp +++ b/src/jumper/SkJumper_stages.cpp @@ -504,17 +504,15 @@ STAGE(hsl_to_rgb) { s = g, l = b; - F q = if_then_else(l < 0.5_f, l*(1.0f + s), l + s - l*s), - p = 2.0f*l - q; + F q = l + if_then_else(l < 0.5_f, l*s + , s - l*s); + F p = 2.0f*l - q; auto hue_to_rgb = [&](F t) { - t = if_then_else(t < 0.0_f, t + 1.0f, - if_then_else(t > 1.0_f, t - 1.0f, - t)); - - return if_then_else(t < C(1/6.0f), p + (q-p)*6.0f*t, + t = fract(t); + return if_then_else(t < C(1/6.0f), p + (q-p)*( 6.0f*t), if_then_else(t < C(3/6.0f), q, - if_then_else(t < C(4/6.0f), p + (q-p)*6.0f*((4/6.0f) - t), + if_then_else(t < C(4/6.0f), p + (q-p)*(4.0f - 6.0f*t), p))); }; |