SkRasterPipeline: 8x pipelines, attempt 2

Original review here: https://skia-review.googlesource.com/c/2990/

Changes since:
  - simpler implementations of load_tail() / store_tail(): slower, but more obviously correct to all compilers
  - fleshed out math ops on Sk8i and Sk8u to make unit tests happy on -Fast bot (where we always have AVX2)
  - now storing stage functions as void(*)() to avoid undefined behavior and/or linker problems.  This restores 32-bit Windows.
  - all AVX2 Sk8x methods are marked always-inline, to avoid linking the "wrong" version on Debug builds.

CQ_INCLUDE_TRYBOTS=master.client.skia:Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-ASAN-Trybot,Perf-Ubuntu-Clang-GCE-CPU-AVX2-x86_64-Debug-GN,Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot,Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-Fast-Trybot;master.client.skia.compile:Build-Win-MSVC-x86_64-Debug-Trybot

GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=3064

Change-Id: Id0ba250037e271a9475fe2f0989d64f0aa909bae
Reviewed-on: https://skia-review.googlesource.com/3064
Reviewed-by: Mike Klein <mtklein@chromium.org>
Commit-Queue: Mike Klein <mtklein@chromium.org>

1 files changed, 62 insertions, 1 deletions

diff --git a/src/opts/SkOpts_hsw.cpp b/src/opts/SkOpts_hsw.cpp
index 53e2e5acdd..9f724805a6 100644
--- a/src/opts/SkOpts_hsw.cpp
+++ b/src/opts/SkOpts_hsw.cpp
@@ -7,9 +7,70 @@
 
 #include "SkOpts.h"
 
+
 #define SK_OPTS_NS hsw
+#include "SkRasterPipeline_opts.h"
 
 namespace SkOpts {
-    void Init_hsw() { }
+    void Init_hsw() {
+
+        run_pipeline = SK_OPTS_NS::run_pipeline;
+
+    #define STAGE(stage)                                                       \
+        body[SkRasterPipeline::stage] = (SkOpts::VoidFn)SK_OPTS_NS::stage;      \
+        tail[SkRasterPipeline::stage] = (SkOpts::VoidFn)SK_OPTS_NS::stage##_tail
+
+        STAGE(store_565);
+        STAGE(store_srgb);
+        STAGE(store_f16);
+
+        STAGE(load_s_565);
+        STAGE(load_s_srgb);
+        STAGE(load_s_f16);
+
+        STAGE(load_d_565);
+        STAGE(load_d_srgb);
+        STAGE(load_d_f16);
+
+        STAGE(scale_u8);
+
+        STAGE(lerp_u8);
+        STAGE(lerp_565);
+    #undef STAGE
+
+    #define STAGE(stage) \
+        body[SkRasterPipeline::stage] = (SkOpts::VoidFn)SK_OPTS_NS::stage; \
+        tail[SkRasterPipeline::stage] = (SkOpts::VoidFn)SK_OPTS_NS::stage
+
+        STAGE(lerp_constant_float);
+        STAGE(constant_color);
+
+        STAGE(dst);
+        STAGE(dstatop);
+        STAGE(dstin);
+        STAGE(dstout);
+        STAGE(dstover);
+        STAGE(srcatop);
+        STAGE(srcin);
+        STAGE(srcout);
+        STAGE(srcover);
+        STAGE(clear);
+        STAGE(modulate);
+        STAGE(multiply);
+        STAGE(plus_);
+        STAGE(screen);
+        STAGE(xor_);
+        STAGE(colorburn);
+        STAGE(colordodge);
+        STAGE(darken);
+        STAGE(difference);
+        STAGE(exclusion);
+        STAGE(hardlight);
+        STAGE(lighten);
+        STAGE(overlay);
+        STAGE(softlight);
+    #undef STAGE
+
+    }
 }