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, 29 insertions, 0 deletions

diff --git a/src/core/SkHalf.h b/src/core/SkHalf.h
index dd978a2347..e71cb8750a 100644
--- a/src/core/SkHalf.h
+++ b/src/core/SkHalf.h
@@ -11,6 +11,10 @@
 #include "SkNx.h"
 #include "SkTypes.h"
 
+#if !defined(_MSC_VER) && SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_AVX2
+    #include <x86intrin.h>
+#endif
+
 // 16-bit floating point value
 // format is 1 bit sign, 5 bits exponent, 10 bits mantissa
 // only used for storage
@@ -85,4 +89,29 @@ static inline Sk4h SkFloatToHalf_finite_ftz(const Sk4f& fs) {
 #endif
 }
 
+static inline Sk8f SkHalfToFloat_finite_ftz(const Sk8h& hs) {
+#if !defined(SKNX_NO_SIMD) && SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_AVX2
+    return _mm256_cvtph_ps(hs.fVec);
+
+#else
+    uint64_t parts[2];
+    hs.store(parts);
+    return SkNx_join(SkHalfToFloat_finite_ftz(parts[0]),
+                     SkHalfToFloat_finite_ftz(parts[1]));
+
+#endif
+}
+
+static inline Sk8h SkFloatToHalf_finite_ftz(const Sk8f& fs) {
+#if !defined(SKNX_NO_SIMD) && SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_AVX2
+    return _mm256_cvtps_ph(fs.fVec, _MM_FROUND_CUR_DIRECTION);
+
+#else
+    uint64_t parts[2];
+    SkFloatToHalf_finite_ftz(fs.fLo).store(parts+0);
+    SkFloatToHalf_finite_ftz(fs.fHi).store(parts+1);
+    return Sk8h::Load(parts);
+#endif
+}
+
 #endif