| Commit message (Collapse) | Author | Age |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Adds an SSE2 version of the Color32A_D565 function, to replace
the existing SSE4 version. Also does some minor cleanup.
Performance improvement in the following Skia benchmarks.
Measured on Atom Silvermont:
Xfermode_SrcOver - x3
luma_colorfilter_large - x4.6
luma_colorfilter_small - x2
tablebench - ~15%
chart_bw - ~10%
Measured on Corei7 Haswell:
luma_colorfilter_large running SSE2 - x2
luma_colorfilter_large running SSE4 - x2.3
Also improves performance in WPS Office application and 2D subtest of 0xbenchmark on Android.
Signed-off-by: Henrik Smiding <henrik.smiding@intel.com>
Review URL: https://codereview.chromium.org/923523002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Backport optimization from https://codereview.chromium.org/874863002/.
Microbenchmarks data compared to previous SSE2 implementation:
bitmap_BGRA_8888_A_source_stripes_three 7.52us -> 8.67us 1.15x
bitmap_BGRA_8888_A_source_stripes_two 7.48us -> 8.56us 1.15x
bitmap_BGRA_8888_update_scale_rotate_bilerp 63.4us -> 64us 1.01x
bitmap_BGRA_8888_update_volatile 3.31us -> 3.33us 1.01x
bitmap_BGRA_8888_scale 11.1us -> 11.2us 1x
bitmap_BGRA_8888_scale_bilerp 35.8us -> 35.9us 1x
bitmap_BGRA_8888 3.33us -> 3.33us 1x
bitmap_BGRA_8888_A_scale_rotate_bicubic 66.7us -> 66.5us 1x
bitmap_BGRA_8888_update_volatile_scale_rotate_bilerp 65.1us -> 64us 0.98x
bitmap_BGRA_8888_scale_rotate_bilerp 65.1us -> 64us 0.98x
bitmap_BGRA_8888_A_scale_bicubic 30.6us -> 29.9us 0.98x
bitmap_BGRA_8888_A_scale_bilerp 42.7us -> 41.4us 0.97x
bitmap_BGRA_8888_A_scale_rotate_bilerp 71us -> 67.7us 0.95x
bitmap_BGRA_8888_A 7.44us -> 5.7us 0.77x
bitmap_BGRA_8888_A_source_opaque 7.46us -> 3.72us 0.5x
bitmap_BGRA_8888_A_source_transparent 7.46us -> 1.96us 0.26x
BUG=skia:
Review URL: https://codereview.chromium.org/886403002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Related nanobench results:
before:
maxrss loops min median mean max stddev samples config bench
10M 2 31.9µs 32.4µs 33.3µs 38.7µs 6% █▄▂▂▂▁▂▁▁▁ 8888 bitmap_BGRA_8888_A_scale_bicubic
10M 13 43.8µs 51.8µs 49.6µs 57.9µs 11% ▁▁▁▁▂▆▇▆▅█ 8888 bitmap_BGRA_8888_A_scale_bilerp
10M 13 23.7µs 24.3µs 26µs 32.7µs 13% ▅█▆▁▁▁▁▂▁▁ 8888 bitmap_Index_8_A
10M 4 1.68µs 1.7µs 4.09µs 25.4µs 183% █▁▁▁▁▁▁▁▁▁ 8888 text_16_AA_88
10M 144 1.76µs 1.77µs 1.78µs 1.81µs 1% █▂▇▂▅▁▁▁▁▁ 8888 text_16_AA_FF
10M 10 4.7µs 5.34µs 5.61µs 8.63µs 21% █▂▂▃▂▁▁▁▁▄ 8888 rotated_rects_aa_alternating_transparent_and_opaque_src
10M 50 4.44µs 4.47µs 4.5µs 4.71µs 2% █▅▃▂▂▂▁▁▁▁ 8888 rotated_rects_aa_changing_opaque_src
10M 51 4.39µs 4.78µs 5.21µs 6.62µs 17% ▁▆▆▇▁▁█▁▂▂ 8888 rotated_rects_aa_same_opaque_src
10M 50 4.47µs 5.79µs 5.43µs 6.14µs 11% ▄▂▁▃▇▇▆▇▇█ 8888 rotated_rects_aa_alternating_transparent_and_opaque_srcover
10M 30 4.35µs 6.06µs 5.84µs 7.63µs 16% ▅▅▅▄▅▅▄█▁▁ 8888 rotated_rects_aa_changing_transparent_srcover
10M 44 4.31µs 4.51µs 4.76µs 6.25µs 13% ▄▂▂▁█▃▁▃▁▁ 8888 rotated_rects_aa_changing_opaque_srcover
10M 46 4.36µs 4.42µs 4.75µs 6.19µs 14% ▆█▃▁▁▁▁▁▁▁ 8888 rotated_rects_aa_same_transparent_srcover
10M 47 4.29µs 4.35µs 4.44µs 5.15µs 6% ▃▂▂▁▁█▁▁▁▁ 8888 rotated_rects_aa_same_opaque_srcover
10M 3 39.1µs 39.2µs 50.7µs 153µs 71% █▁▁▁▁▁▁▁▁▁ 8888 rectori
10M 1 2.3ms 2.31ms 2.35ms 2.74ms 6% ▁▁▁▁▁▁▁▁█▂ 8888 maskcolor
10M 1 2.33ms 2.34ms 2.53ms 3.14ms 11% ▁▁▁▁▁▁▅█▄▄ 8888 maskopaque
10M 11 15µs 15.3µs 15.7µs 18.3µs 7% ▅▃▂▂▁▁▁▁█▁ 8888 rrects_3_stroke_4
10M 46 3.99µs 4.07µs 4.14µs 4.54µs 4% █▅▅▃▂▂▁▁▁▁ 8888 rrects_3
10M 16 15.6µs 15.9µs 16.1µs 17.5µs 4% █▄▃▂▂▂▁▂▁▁ 8888 ovals_3_stroke_4
10M 40 5.09µs 5.18µs 5.23µs 5.67µs 3% █▅▃▂▂▁▃▁▁▁ 8888 ovals_3
10M 231 1.92µs 1.93µs 1.94µs 2µs 1% █▃▂▁▃▁▁▁▁▁ 8888 zeroradroundrect
10M 924 3.88µs 3.93µs 4.11µs 4.95µs 9% ▁█▆▃▁▁▁▁▁▁ 8888 arbroundrect
10M 8 8.11µs 8.47µs 8.48µs 8.85µs 3% █▅▇▄▄▂▁▄▄▆ 8888 merge_large
10M 14 6.71µs 6.92µs 6.96µs 7.46µs 3% ▃▆▁█▃▃▃▂▂▁ 8888 merge_small
11M 2 225µs 227µs 229µs 233µs 1% ███▃▇▂▃▁▃▂ 8888 displacement_full_large
16M 1 381µs 401µs 401µs 421µs 3% ▅▅▅█▆▄▄▃▃▁ 8888 displacement_alpha_large
19M 1 507µs 508µs 509µs 512µs 0% █▃▂▆▂▂▃▂▃▁ 8888 displacement_zero_large
19M 19 9µs 9.11µs 9.15µs 9.67µs 2% ▄▂▂▂█▂▁▁▁▂ 8888 displacement_full_small
19M 5 54.2µs 54.5µs 54.9µs 58µs 2% █▃▂▂▁▁▃▁▁▁ 8888 blurroundrect_WH[100x100]_cr[90]
20M 1 229µs 230µs 231µs 240µs 2% █▄▃▂▂▁▁▁▁▂ 8888 GM_varied_text_clipped_no_lcd
20M 1 267µs 269µs 270µs 279µs 1% █▄▃▂▂▂▂▂▁▁ 8888 GM_varied_text_ignorable_clip_no_lcd
22M 1 1.95ms 1.97ms 2.03ms 2.46ms 8% ▁▁▁▁▁▁▁▂█▃ 8888 GM_convex_poly_clip
after:
maxrss loops min median mean max stddev samples config bench
10M 2 31.5µs 32.3µs 32.8µs 37.2µs 5% █▄▃▂▂▂▁▁▁▁ 8888 bitmap_BGRA_8888_A_scale_bicubic
10M 13 43.9µs 44µs 44.1µs 44.9µs 1% █▂▁▁▁▆▁▁▁▂ 8888 bitmap_BGRA_8888_A_scale_bilerp
10M 19 22.7µs 23.3µs 25.6µs 32.4µs 14% ▁▁▁▁▁▅▆▁▅█ 8888 bitmap_Index_8_A
10M 5 1.79µs 1.97µs 3.85µs 21.1µs 158% █▁▁▁▁▁▁▁▁▁ 8888 text_16_AA_88
10M 141 1.83µs 1.83µs 1.85µs 1.93µs 2% ▅▁▁█▁▁▁▁▁▁ 8888 text_16_AA_FF
10M 10 4.65µs 4.92µs 5.06µs 6.56µs 11% █▃▃▂▂▂▁▁▁▁ 8888 rotated_rects_aa_alternating_transparent_and_opaque_src
10M 51 4.35µs 4.48µs 4.83µs 6.68µs 17% ▂▁▁▁▁▁▁▂▆█ 8888 rotated_rects_aa_changing_opaque_src
10M 51 4.38µs 4.79µs 4.85µs 5.84µs 11% ▁█▁▃▃▁▄▁▄▇ 8888 rotated_rects_aa_same_opaque_src
10M 32 5.58µs 6.24µs 6.1µs 6.39µs 5% █▂█▆▁▇▄▅▇▇ 8888 rotated_rects_aa_alternating_transparent_and_opaque_srcover
10M 42 4.28µs 5.59µs 5.11µs 6.01µs 15% ▂▂█▇█▂▁▆▁▇ 8888 rotated_rects_aa_changing_transparent_srcover
10M 48 4.24µs 4.33µs 4.58µs 6.46µs 15% ▁▁▁▁▁█▃▂▁▁ 8888 rotated_rects_aa_changing_opaque_srcover
10M 48 4.28µs 4.3µs 4.4µs 5.12µs 6% ▂▂▁▁▁▁▁▁▁█ 8888 rotated_rects_aa_same_transparent_srcover
10M 46 4.24µs 4.29µs 4.66µs 7.11µs 20% ▁▁▁▁▁▁▁▁▃█ 8888 rotated_rects_aa_same_opaque_srcover
10M 3 39.3µs 39.4µs 51.4µs 154µs 70% █▁▁▁▁▁▁▁▁▁ 8888 rectori
10M 1 2.32ms 2.43ms 2.53ms 3.14ms 11% ▁▁▁▁▂▄█▃▅▁ 8888 maskcolor
10M 1 2.33ms 2.37ms 2.54ms 3.21ms 12% ▁▁▁▁▁▂█▅▆▁ 8888 maskopaque
10M 10 15.3µs 15.6µs 15.8µs 17.2µs 4% █▅▃▂▂▂▁▁▁▁ 8888 rrects_3_stroke_4
10M 46 4.03µs 4.09µs 4.15µs 4.47µs 4% █▄▆▂▂▂▁▁▁▁ 8888 rrects_3
10M 15 15.9µs 16.2µs 16.3µs 17.8µs 4% █▄▃▂▂▂▁▁▁▁ 8888 ovals_3_stroke_4
10M 40 5.14µs 5.26µs 5.29µs 5.72µs 3% █▅▃▂▂▁▂▂▁▁ 8888 ovals_3
10M 222 1.91µs 1.99µs 2.21µs 2.91µs 19% ▂▁▁▁▁▁▂▇▇█ 8888 zeroradroundrect
10M 462 3.9µs 3.96µs 4.23µs 5.22µs 12% ▆▄█▁▂▁▁▁▁▁ 8888 arbroundrect
10M 8 8.2µs 8.59µs 8.62µs 8.97µs 3% ▆▄█▄▅▃▁▆▄█ 8888 merge_large
10M 14 6.73µs 6.88µs 6.86µs 7.08µs 2% ▄█▁▂▄▂▅▄▂▅ 8888 merge_small
11M 2 221µs 234µs 237µs 263µs 5% ▄▃▃▃▄▃▂▁▇█ 8888 displacement_full_large
16M 1 387µs 416µs 427µs 471µs 7% ▇█▁▃▃▁▃▃▇▆ 8888 displacement_alpha_large
19M 1 512µs 521µs 528µs 594µs 5% █▂▂▂▁▁▂▃▁▁ 8888 displacement_zero_large
19M 18 9.06µs 9.12µs 9.13µs 9.23µs 1% █▃▃▃▄▃▆▁▅▅ 8888 displacement_full_small
19M 5 55.6µs 55.9µs 56.5µs 59.5µs 2% █▃▂▁▁▁▁▁▅▁ 8888 blurroundrect_WH[100x100]_cr[90]
20M 1 229µs 233µs 235µs 254µs 3% █▄▃▂▂▁▁▂▁▁ 8888 GM_varied_text_clipped_no_lcd
20M 1 270µs 271µs 272µs 278µs 1% █▄▃▂▂▂▁▂▁▇ 8888 GM_varied_text_ignorable_clip_no_lcd
22M 1 1.96ms 2ms 2.06ms 2.45ms 7% ▂▂▁▁▁▁▁▃█▄ 8888 GM_convex_poly_clip
BUG=skia:
Review URL: https://codereview.chromium.org/754733002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Related nanobench results:
before:
10M 18 7.03µs 7.31µs 7.38µs 8.46µs 6% ▂▁▂▂▂▃▄▁█▁ 8888 bitmaprect_80_filter_identity
10M 43 6.96µs 6.97µs 6.99µs 7.19µs 1% ▁▂▁▁▁▁▁█▁▁ 8888 bitmaprect_80_nofilter_identity
10M 14 35.7µs 35.8µs 35.9µs 36.3µs 1% ▃▂▁▂▁█▂▁▁▁ 8888 bitmap_BGRA_8888_update_scale_bilerp
10M 16 35.5µs 35.6µs 35.7µs 36.3µs 1% █▅▂▁▁▁▃▂▁▁ 8888 bitmap_BGRA_8888_update_volatile_scale_bilerp
10M 16 35.4µs 35.4µs 35.5µs 36.8µs 1% ▂▁█▁▁▁▁▂▁▁ 8888 bitmap_BGRA_8888_scale_bilerp
10M 25 16.4µs 16.6µs 16.7µs 17.4µs 2% ▂▁▁▂▁▁▁▅▅█ 8888 bitmap_Index_8
10M 15 37.9µs 38µs 38µs 38.4µs 0% ▄▆▂▁▁▁█▂▁▁ 8888 bitmap_RGB_565
10M 33 11.1µs 11.1µs 11.1µs 11.2µs 0% ▆▂█▂▂▂▁▁▂▁ 8888 bitmap_BGRA_8888_scale
after:
10M 9 7.04µs 7.06µs 7.1µs 7.32µs 1% █▅▂▁▁▂▁▁▁▁ 8888 bitmaprect_80_filter_identity
10M 18 7.01µs 7.02µs 7.05µs 7.25µs 1% █▂▁▁▁▁▁▁▁▁ 8888 bitmaprect_80_nofilter_identity
10M 5 33.9µs 34µs 34.1µs 34.5µs 1% █▃▂▂▁▁▁▅▃▂ 8888 bitmap_BGRA_8888_update_scale_bilerp
10M 7 35.5µs 35.5µs 35.6µs 36.3µs 1% ▃▂▂▁▂▁▂▁█▂ 8888 bitmap_BGRA_8888_update_volatile_scale_bilerp
10M 7 35.5µs 35.5µs 35.7µs 36.8µs 1% ▂▁▁▁▁▁▁▁▁█ 8888 bitmap_BGRA_8888_scale_bilerp
10M 11 16.4µs 16.4µs 16.4µs 16.6µs 0% █▂▁▁▂▁▁▁▂▁ 8888 bitmap_Index_8
10M 7 37.3µs 37.4µs 38.4µs 47.8µs 9% ▁▁▁▁▁▁▁▁▁█ 8888 bitmap_RGB_565
10M 33 11µs 11µs 11.1µs 11.2µs 1% ▄█▅▃▂▁▁▁▁▁ 8888 bitmap_BGRA_8888_scale
BUG=skia:
Review URL: https://codereview.chromium.org/755573002
|
|
|
|
|
|
| |
BUG=skia:
Review URL: https://codereview.chromium.org/725693003
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
With clang this:
- movzbl -3(%rbx), %edx
- pxor %xmm5, %xmm5
- pinsrw $0, %edx, %xmm5
- pinsrw $1, %edx, %xmm5
- movzbl -2(%rbx), %edx
- pinsrw $2, %edx, %xmm5
- pinsrw $3, %edx, %xmm5
- movzbl -1(%rbx), %edx
- pinsrw $4, %edx, %xmm5
- pinsrw $5, %edx, %xmm5
- movzbl (%rbx), %edx
- pinsrw $6, %edx, %xmm5
- pinsrw $7, %edx, %xmm5
becomes:
+ movd (%rbx), %xmm4
+ punpcklbw %xmm9, %xmm4
+ punpcklwd %xmm4, %xmm4
And clang already does better codegen than msvc 2013 on this.
BUG=skia:
Review URL: https://codereview.chromium.org/609823003
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
General cleanup of optimization files for x86/SSEx.
Renamed the opts_check_SSE2.cpp file to _x86, since it's not specific
to SSE2. Commented out the ColorRect32 optimization, since it's
disabled anyway, to make it more visible.
Also fixed a lot of indentation, inclusion guards, spelling,
copyright headers, braces, whitespace, and sorting of includes.
Author: henrik.smiding@intel.com
Signed-off-by: Henrik Smiding <henrik.smiding@intel.com>
R=reed@google.com, mtklein@google.com, tomhudson@google.com, djsollen@google.com, joakim.landberg@intel.com
Author: henrik.smiding@intel.com
Review URL: https://codereview.chromium.org/264603002
git-svn-id: http://skia.googlecode.com/svn/trunk@14464 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch implements basics for Xfermode SSE optimization. Based on
these basics, SSE2 implementation of multiply_modeproc is provided. SSE2
implementation for other modes will come in future. With this patch
performance of Xfermode_Multiply will improve about 45%. Here are the
data on desktop i7-3770.
before:
Xfermode_Multiply 8888: cmsecs = 33.30 565: cmsecs = 45.65
after:
Xfermode_Multiply 8888: cmsecs = 17.18 565: cmsecs = 24.87
BUG=
Committed: http://code.google.com/p/skia/source/detail?r=14006
Committed: http://code.google.com/p/skia/source/detail?r=14050
R=mtklein@google.com, robertphillips@google.com
Author: qiankun.miao@intel.com
Review URL: https://codereview.chromium.org/202903004
git-svn-id: http://skia.googlecode.com/svn/trunk@14107 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(https://codereview.chromium.org/202903004/)
Reason for revert:
It looks like serialization is broken. The serialize and pipe-cross-process tests are failing and turning (at least the Ubuntu12 and Win7) bots red
Original issue's description:
> Xfermode: SSE2 implementation of multiply_modeproc
>
> This patch implements basics for Xfermode SSE optimization. Based on
> these basics, SSE2 implementation of multiply_modeproc is provided. SSE2
> implementation for other modes will come in future. With this patch
> performance of Xfermode_Multiply will improve about 45%. Here are the
> data on desktop i7-3770.
> before:
> Xfermode_Multiply 8888: cmsecs = 33.30 565: cmsecs = 45.65
> after:
> Xfermode_Multiply 8888: cmsecs = 17.18 565: cmsecs = 24.87
>
> BUG=
>
> Committed: http://code.google.com/p/skia/source/detail?r=14006
>
> Committed: http://code.google.com/p/skia/source/detail?r=14050
R=mtklein@google.com, qiankun.miao@intel.com
TBR=mtklein@google.com, qiankun.miao@intel.com
NOTREECHECKS=true
NOTRY=true
BUG=
Author: robertphillips@google.com
Review URL: https://codereview.chromium.org/224253003
git-svn-id: http://skia.googlecode.com/svn/trunk@14053 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch implements basics for Xfermode SSE optimization. Based on
these basics, SSE2 implementation of multiply_modeproc is provided. SSE2
implementation for other modes will come in future. With this patch
performance of Xfermode_Multiply will improve about 45%. Here are the
data on desktop i7-3770.
before:
Xfermode_Multiply 8888: cmsecs = 33.30 565: cmsecs = 45.65
after:
Xfermode_Multiply 8888: cmsecs = 17.18 565: cmsecs = 24.87
BUG=
Committed: http://code.google.com/p/skia/source/detail?r=14006
R=mtklein@google.com, robertphillips@google.com
Author: qiankun.miao@intel.com
Review URL: https://codereview.chromium.org/202903004
git-svn-id: http://skia.googlecode.com/svn/trunk@14050 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(https://codereview.chromium.org/202903004/)
Reason for revert:
Breaking builds
Original issue's description:
> Xfermode: SSE2 implementation of multiply_modeproc
>
> This patch implements basics for Xfermode SSE optimization. Based on
> these basics, SSE2 implementation of multiply_modeproc is provided. SSE2
> implementation for other modes will come in future. With this patch
> performance of Xfermode_Multiply will improve about 45%. Here are the
> data on desktop i7-3770.
> before:
> Xfermode_Multiply 8888: cmsecs = 33.30 565: cmsecs = 45.65
> after:
> Xfermode_Multiply 8888: cmsecs = 17.18 565: cmsecs = 24.87
>
> BUG=
>
> Committed: http://code.google.com/p/skia/source/detail?r=14006
R=mtklein@google.com, qiankun.miao@intel.com
TBR=mtklein@google.com, qiankun.miao@intel.com
NOTREECHECKS=true
NOTRY=true
BUG=
Author: robertphillips@google.com
Review URL: https://codereview.chromium.org/219243009
git-svn-id: http://skia.googlecode.com/svn/trunk@14007 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch implements basics for Xfermode SSE optimization. Based on
these basics, SSE2 implementation of multiply_modeproc is provided. SSE2
implementation for other modes will come in future. With this patch
performance of Xfermode_Multiply will improve about 45%. Here are the
data on desktop i7-3770.
before:
Xfermode_Multiply 8888: cmsecs = 33.30 565: cmsecs = 45.65
after:
Xfermode_Multiply 8888: cmsecs = 17.18 565: cmsecs = 24.87
BUG=
R=mtklein@google.com
Author: qiankun.miao@intel.com
Review URL: https://codereview.chromium.org/202903004
git-svn-id: http://skia.googlecode.com/svn/trunk@14006 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Run benchmarks with command line option "--forceDither true --forceBlend
1", almost all the benchmarks exercised S32A_D565_Opaque_Dither can get
about 20%-70% performance improvement.
Here are the data on i7-3770:
before after
verts 4314.81 3627.64 15.93%
constXTile_MM_filter_trans 1434.22 432.82 69.82%
constXTile_CC_filter_trans_scale 1440.17 437.00 69.66%
constXTile_RR_filter_trans 1436.96 431.93 69.94%
constXTile_MM_trans_scale 1436.33 435.77 69.66%
constXTile_CC_trans 1433.12 431.36 69.90%
constXTile_RR_trans_scale 1436.13 436.06 69.64%
constXTile_MM_filter 1411.55 408.06 71.09%
constXTile_CC_filter_scale 1416.68 414.18 70.76%
constXTile_RR_filter 1429.46 409.81 71.33%
constXTile_MM_scale 1415.00 412.56 70.84%
constXTile_CC 1410.32 408.36 71.04%
constXTile_RR_scale 1413.26 413.16 70.77%
repeatTile_4444_A 1922.01 879.03 54.27%
repeatTile_4444_A 1430.68 818.34 42.80%
repeatTile_4444_X 1817.43 816.63 55.07%
maskshader 5911.09 5895.46 0.26%
gradient_create_alpha 4.41 4.41 -0.15%
gradient_conical_clamp_3color 35298.71 27574.34 21.88%
gradient_conical_clamp_hicolor 35262.15 27538.99 21.90%
gradient_conical_clamp 35276.21 27599.80 21.76%
gradient_radial2_mirror 20846.74 12969.39 37.79%
gradient_radial2_clamp_hicolor 21848.12 13967.57 36.07%
gradient_radial2_clamp 21829.95 13978.57 35.97%
bitmap_4444_A_scale_rotate_bicubic 105.31 87.13 17.26%
bitmap_4444_A_scale_bicubic 73.69 47.76 35.20%
bitmap_4444_update_scale_rotate_bilerp 125.65 87.86 30.08%
bitmap_4444_update_volatile_scale_rotate_bilerp 125.50 87.65 30.16%
bitmap_4444_scale_rotate_bilerp 124.46 87.91 29.37%
bitmap_4444_A_scale_rotate_bilerp 105.09 87.27 16.96%
bitmap_4444_update_scale_bilerp 106.78 63.28 40.74%
bitmap_4444_update_volatile_scale_bilerp 106.66 63.66 40.32%
bitmap_4444_scale_bilerp 106.70 63.19 40.78%
bitmap_4444_A_scale_bilerp 83.05 62.25 25.04%
bitmap_a8 98.11 52.76 46.22%
bitmap_a8_A 98.24 52.85 46.20%
BUG=
R=mtklein@google.com
Author: qiankun.miao@intel.com
Review URL: https://codereview.chromium.org/179443003
git-svn-id: http://skia.googlecode.com/svn/trunk@13699 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Run benchmarks with command line option "--forceDither true". The result
shows that all benchmarks exercised S32_D565_Opaque_Dither benefit from
this SSE2 optimization. Here are the data on i7-3770:
before after
constXTile_MM_filter 900.93 217.75 75.83%
constXTile_CC_filter_scale 907.59 225.65 75.14%
constXTile_RR_filter 903.33 219.41 75.71%
constXTile_MM_scale 902.45 221.46 75.46%
constXTile_CC 898.55 218.37 75.70%
constXTile_RR_scale 902.69 222.35 75.37%
repeatTile_4444_X 938.53 240.49 74.38%
gradient_radial2_mirror 16999.49 11540.39 32.11%
gradient_radial2_clamp_hicolor 17943.38 12501.71 30.33%
gradient_radial2_clamp 17816.36 12492.04 29.88%
bitmaprect_FF_filter_trans 47.81 10.98 77.03%
bitmaprect_FF_nofilter_trans 47.79 10.91 77.18%
bitmaprect_FF_filter_identity 47.74 10.89 77.18%
bitmaprect_FF_nofilter_identity 47.83 10.89 77.24%
bitmap_4444_update_scale_rotate_bilerp 100.45 76.84 23.50%
bitmap_4444_update_volatile_scale_rotate_bilerp 100.80 76.70 23.91%
bitmap_4444_scale_rotate_bilerp 100.43 77.18 23.15%
bitmap_4444_update_scale_bilerp 79.00 49.03 37.93%
bitmap_4444_update_volatile_scale_bilerp 78.90 48.87 38.06%
bitmap_4444_scale_bilerp 78.92 48.81 38.16%
bitmap_4444_update 42.19 11.53 72.68%
bitmap_4444_update_volatile 42.28 11.49 72.82%
bitmap_a8 60.37 29.75 50.72%
bitmap_4444 42.19 11.52 72.69%
BUG=
R=mtklein@google.com
Author: qiankun.miao@intel.com
Review URL: https://codereview.chromium.org/181293002
git-svn-id: http://skia.googlecode.com/svn/trunk@13698 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Benchmarks hitting this path can benfit from this patch.
Here are the data:
before after
gradient_radial2_mirror 10885.52 10849.48 0.33%
gradient_radial2_clamp_hicolor 11819.69 11644.83 1.48%
gradient_radial2_clamp 11816.10 11649.91 1.41%
bitmaprect_FF_filter_trans 6.27 4.88 22.17%
bitmaprect_FF_nofilter_trans 6.27 4.88 22.17%
bitmaprect_FF_filter_identity 6.31 4.86 22.98%
bitmaprect_FF_nofilter_identity 6.25 4.86 22.24%
bitmap_4444_update 6.26 5.05 19.33%
bitmap_4444_update_volatile 6.21 5.06 18.52%
bitmap_4444 6.22 5.06 18.65%
BUG=
R=mtklein@google.com
Author: qiankun.miao@intel.com
Review URL: https://codereview.chromium.org/172083003
git-svn-id: http://skia.googlecode.com/svn/trunk@13556 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
microbenchmark of S32A_D565_Opaque() shows a 3x speedup after SSE optimization with various count on i7-3770.
BUG=
R=mtklein@google.com, reed@google.com
Author: qiankun.miao@intel.com
Review URL: https://codereview.chromium.org/138163013
git-svn-id: http://skia.googlecode.com/svn/trunk@13495 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
| |
R=senorblanco@chromium.org, alokp@chromium.org, reed@google.com, bungeman@google.com
Author: ernstm@chromium.org
Review URL: https://chromiumcodereview.appspot.com/17847010
git-svn-id: http://skia.googlecode.com/svn/trunk@9870 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
| |
https://codereview.appspot.com/6465078/)
This CL is part I of IV (I broke down the 1280 files into 4 CLs).
Review URL: https://codereview.appspot.com/6485054
git-svn-id: http://skia.googlecode.com/svn/trunk@5262 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
| |
https://codereview.appspot.com/6460123/
git-svn-id: http://skia.googlecode.com/svn/trunk@5218 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
| |
git-svn-id: http://skia.googlecode.com/svn/trunk@4803 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
| |
git-svn-id: http://skia.googlecode.com/svn/trunk@4801 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
| |
git-svn-id: http://skia.googlecode.com/svn/trunk@4800 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
| |
SSE optimization for 565 pixel format -- by Lei
git-svn-id: http://skia.googlecode.com/svn/trunk@4799 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
| |
http://codereview.appspot.com/6356062/
git-svn-id: http://skia.googlecode.com/svn/trunk@4481 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Fix these class of warnings:
- unused functions
- unused locals
- sign mismatch
- missing function prototypes
- missing newline at end of file
- 64 to 32 bit truncation
The changes prefer to link in dead code in the debug build
with 'if (false)' than to comment it out, but trivial cases
are commented out or sometimes deleted if it appears to be
a copy/paste error.
Review URL: https://codereview.appspot.com/6303045
git-svn-id: http://skia.googlecode.com/svn/trunk@4184 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
| |
Courtesy of Evan Nier.
http://codereview.appspot.com/5518045/
git-svn-id: http://skia.googlecode.com/svn/trunk@3273 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Yields 25-30% speedup on Windows (32b), 4-7% on Linux (64b, less register
pressure), not invoked on Mac (lcd text is 32b instead of 16b).
Followup: GDI system settings on Windows can suppress LCD text for small
fonts, interfering with our benchmarks.
(http://code.google.com/p/skia/issues/detail?id=483)
http://codereview.appspot.com/5617058/
git-svn-id: http://skia.googlecode.com/svn/trunk@3189 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
| |
git-svn-id: http://skia.googlecode.com/svn/trunk@2527 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
| |
git-svn-id: http://skia.googlecode.com/svn/trunk@2484 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
I have manually examined all of these diffs and restored a few files that
seem to require manual adjustment.
The following files still need to be modified manually, in a separate CL:
android_sample/SampleApp/AndroidManifest.xml
android_sample/SampleApp/res/layout/layout.xml
android_sample/SampleApp/res/menu/sample.xml
android_sample/SampleApp/res/values/strings.xml
android_sample/SampleApp/src/com/skia/sampleapp/SampleApp.java
android_sample/SampleApp/src/com/skia/sampleapp/SampleView.java
experimental/CiCarbonSampleMain.c
experimental/CocoaDebugger/main.m
experimental/FileReaderApp/main.m
experimental/SimpleCocoaApp/main.m
experimental/iOSSampleApp/Shared/SkAlertPrompt.h
experimental/iOSSampleApp/Shared/SkAlertPrompt.m
experimental/iOSSampleApp/SkiOSSampleApp-Base.xcconfig
experimental/iOSSampleApp/SkiOSSampleApp-Debug.xcconfig
experimental/iOSSampleApp/SkiOSSampleApp-Release.xcconfig
gpu/src/android/GrGLDefaultInterface_android.cpp
gyp/common.gypi
gyp_skia
include/ports/SkHarfBuzzFont.h
include/views/SkOSWindow_wxwidgets.h
make.bat
make.py
src/opts/memset.arm.S
src/opts/memset16_neon.S
src/opts/memset32_neon.S
src/opts/opts_check_arm.cpp
src/ports/SkDebug_brew.cpp
src/ports/SkMemory_brew.cpp
src/ports/SkOSFile_brew.cpp
src/ports/SkXMLParser_empty.cpp
src/utils/ios/SkImageDecoder_iOS.mm
src/utils/ios/SkOSFile_iOS.mm
src/utils/ios/SkStream_NSData.mm
tests/FillPathTest.cpp
Review URL: http://codereview.appspot.com/4816058
git-svn-id: http://skia.googlecode.com/svn/trunk@1982 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
| |
want a SkPMColor, they need to call SkPreMultiplyColor()
Add Opaque and Black optimizations for blitmask_d32
git-svn-id: http://skia.googlecode.com/svn/trunk@911 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
| |
Add blitmask procs (with optional platform acceleration)
patch by yaojie.yan
git-svn-id: http://skia.googlecode.com/svn/trunk@910 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
[Patch from weiwei.li@intel.com]
SSE2 optimization has been added by Stephen White before, this improves the skia
performance on SSE2-supporting platform. (please refer to below issues)
Issue 171055: More SSE2ification
Issue 157141: More SSE2ification
Issue 150060: minor tweaks to SSE2 code for -fPIC
Issue 144072: SSE2 optimizations for 32bit blending blitters
This CL implements SSE2 optimizations for the 32bit Color operation. Like above
issues, it uses CPUID to detect for SSE2 and changes the platform procs at
runtime as well. The 32bit Color operation is heavily used on Chrome HTML5
canvas operations. Take Microsoft IE test drives Pulsating Bubbles as example
(http://ie.microsoft.com/testdrive/Performance/PulsatingBubbles/Default.xhtml),
if running this cases on Chrome, the overhead of 32bit Color operation is about
40~50%. So this CL will make skia performance more better, and also make Chrome
HTML5 canvas performance more better.
Additional, this CL has passed the skia bench & tests validation, the result is
pretty good. We also apply this CL to the latest chromium, and re-run Microsoft
IE test drives Pulsating Bubbles, the performance is improved by almost 9~10%.
git-svn-id: http://skia.googlecode.com/svn/trunk@633 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
| |
cycles off the SSE2 blends.
Review URL: http://codereview.appspot.com/171055
git-svn-id: http://skia.googlecode.com/svn/trunk@456 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
|
|
| |
S32_bitmap_D32_filter_DX, and uses aligned loads and stores for dst, in all blending.
Review URL: http://codereview.appspot.com/157141
git-svn-id: http://skia.googlecode.com/svn/trunk@448 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
| |
Review URL: http://codereview.appspot.com/154163
git-svn-id: http://skia.googlecode.com/svn/trunk@428 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
| |
on some gccs).
git-svn-id: http://skia.googlecode.com/svn/trunk@425 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
|
|
|
|
|
|
| |
http://codereview.appspot.com/150060
git-svn-id: http://skia.googlecode.com/svn/trunk@421 2bbb7eff-a529-9590-31e7-b0007b416f81
|
|
This CL implements SSE2 optimizations for 3 of the 32bit blending blitters. It
uses CPUID to detect for SSE2 at runtime. In order to accomodate runtime
detection, it changes the platform procs from static arrays to static
functions.
It also includes an implementation of SkTime for Win32.
http://codereview.appspot.com/144072
git-svn-id: http://skia.googlecode.com/svn/trunk@418 2bbb7eff-a529-9590-31e7-b0007b416f81
|