diff options
author | mtklein <mtklein@google.com> | 2015-09-20 15:02:54 -0700 |
---|---|---|
committer | Commit bot <commit-bot@chromium.org> | 2015-09-20 15:02:54 -0700 |
commit | b63d816683a8fe2d95e4ca7754034204c8bc10d5 (patch) | |
tree | 9f7212b5e8799c99366988210c5a06429dc33b7b /include | |
parent | b68fa409fc00ce2f38e2a0fd6f9dc2379b372481 (diff) |
Revert of update memset16/32 inlining heuristics (patchset #1 id:1 of https://codereview.chromium.org/1357193002/ )
Reason for revert:
Who wants to land forever?
Original issue's description:
> update memset16/32 inlining heuristics
>
> I spent some time looking at perf.skia.org and it looks like we can do better.
>
> It is weird, weird, weird that on x86, we see three completely different behaviors:
> - x86 Android: inlining better for small N, custom better for large N;
> - Windows: inlining better for large N, custom better for small N;
> - other x86: inlining generally better
>
> BUG=skia:4316,chromium:516426
>
> (Temporary, plan to revert.)
> TBR=reed@google.com
>
> Committed: https://skia.googlesource.com/skia/+/b68fa409fc00ce2f38e2a0fd6f9dc2379b372481
TBR=reed@google.com,jcgregorio@google.com,mtklein@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:4316,chromium:516426
Review URL: https://codereview.chromium.org/1358793002
Diffstat (limited to 'include')
-rw-r--r-- | include/core/SkUtils.h | 32 |
1 files changed, 15 insertions, 17 deletions
diff --git a/include/core/SkUtils.h b/include/core/SkUtils.h index 7dcc4d17e5..4e24bd0883 100644 --- a/include/core/SkUtils.h +++ b/include/core/SkUtils.h @@ -17,11 +17,13 @@ namespace SkOpts { /////////////////////////////////////////////////////////////////////////////// -// Inlining heuristics were determined by using perf.skia.org and bench/MemsetBench.cpp. -// When using MSVC, inline is better >= 1K and worse <= 100. The Nexus Player was the opposite. -// Otherwise, when NEON or SSE is available to GCC or Clang, they can handle it best. -// See https://code.google.com/p/chromium/issues/detail?id=516426#c15 for more details. -// See also skia:4316; it might be a good idea to use rep stosw/stosd here. +// The inlining heuristics below were determined using bench/MemsetBench.cpp +// on a x86 desktop, a Nexus 7 with and without NEON, and a Nexus 9: +// - on x86, inlining was never faster, +// - on ARMv7, inlining was faster for N<=10. Putting this check inside the NEON +// code was not helpful; it's got to be here outside. +// - NEON code generation for ARMv8 with GCC 4.9 is terrible, +// making the NEON code ~8x slower that just a serial loop. /** Similar to memset(), but it assigns a 16bit value into the buffer. @param buffer The memory to have value copied into it @@ -29,12 +31,10 @@ namespace SkOpts { @param count The number of times value should be copied into the buffer. */ static inline void sk_memset16(uint16_t buffer[], uint16_t value, int count) { -#if defined(_MSC_VER) - if (count > 300) { while (count --> 0) { *buffer++ = value; } return; } -#elif defined(SK_BUILD_FOR_ANDROID) && defined(SK_CPU_X86) - if (count < 300) { while (count --> 0) { *buffer++ = value; } return; } -#elif defined(SK_ARM_HAS_NEON) || SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE2 - { while (count --> 0) { *buffer++ = value; } return; } +#if defined(SK_CPU_ARM64) + while (count --> 0) { *buffer++ = value; } return; +#elif defined(SK_CPU_ARM32) + if (count <= 10) { while (count --> 0) { *buffer++ = value; } return; } #endif SkOpts::memset16(buffer, value, count); } @@ -45,12 +45,10 @@ static inline void sk_memset16(uint16_t buffer[], uint16_t value, int count) { @param count The number of times value should be copied into the buffer. */ static inline void sk_memset32(uint32_t buffer[], uint32_t value, int count) { -#if defined(_MSC_VER) - if (count > 300) { while (count --> 0) { *buffer++ = value; } return; } -#elif defined(SK_BUILD_FOR_ANDROID) && defined(SK_CPU_X86) - if (count < 300) { while (count --> 0) { *buffer++ = value; } return; } -#elif defined(SK_ARM_HAS_NEON) || SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE2 - { while (count --> 0) { *buffer++ = value; } return; } +#if defined(SK_CPU_ARM64) + while (count --> 0) { *buffer++ = value; } return; +#elif defined(SK_CPU_ARM32) + if (count <= 10) { while (count --> 0) { *buffer++ = value; } return; } #endif SkOpts::memset32(buffer, value, count); } |