diff options
| author |  Mike Klein <mtklein@chromium.org> | 2018-06-12 12:11:28 -0400 |
|---|---|---|
| committer |  Skia Commit-Bot <skia-commit-bot@chromium.org> | 2018-06-12 18:24:33 +0000 |
| commit | 8ea971bfefb687a813f5b7cb62137b5d7b742dee (patch) | |
| tree | 8dae6feec1bbf6116fb9a79de24001662a4f363d /src/opts | |
| parent | 2107bd8ee0f17bfff35eb9d91b63f501cb57a50e (diff) | |
avoid immintrin.h in SkNx_sse.h
Including <immintrin.h> is an easy way to get all the supported
Intel intrinsics for the current build flags, and for intrinsics
since AVX, the only supported way.
But, including immintrin.h can pull in more headers than needed,
and for pieces of code like SkNx.h, that extra include cost is
measurable. Here we'll include only the intrisnics we'll use.
$ gn clean out && time ninja -C out
Before: 131.57 real 4207.95 user 249.18 sys
After: 125.60 real 3988.18 user 241.64 sys
Seems like a win.
Change-Id: I81543202d889be403ff0aa393c13c19ed89c5373
Reviewed-on: https://skia-review.googlesource.com/134325
Reviewed-by: Hal Canary <halcanary@google.com>
Commit-Queue: Hal Canary <halcanary@google.com>
Auto-Submit: Mike Klein <mtklein@chromium.org>
Diffstat (limited to 'src/opts')
| -rw-r--r-- | src/opts/SkNx_sse.h | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/src/opts/SkNx_sse.h b/src/opts/SkNx_sse.h index 1720f14fb8..335b70c1e9 100644 --- a/src/opts/SkNx_sse.h +++ b/src/opts/SkNx_sse.h @@ -8,7 +8,15 @@ #ifndef SkNx_sse_DEFINED #define SkNx_sse_DEFINED -#include <immintrin.h> +#include "SkTypes.h" + +#if SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE41 + #include <smmintrin.h> +#elif SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSSE3 + #include <tmmintrin.h> +#else + #include <emmintrin.h> +#endif // This file may assume <= SSE2, but must check SK_CPU_SSE_LEVEL for anything more recent. // If you do, make sure this is in a static inline function... anywhere else risks violating ODR. |