diff options
author | commit-bot@chromium.org <commit-bot@chromium.org@2bbb7eff-a529-9590-31e7-b0007b416f81> | 2014-02-19 03:09:52 +0000 |
---|---|---|
committer | commit-bot@chromium.org <commit-bot@chromium.org@2bbb7eff-a529-9590-31e7-b0007b416f81> | 2014-02-19 03:09:52 +0000 |
commit | 475910750cdc7d14da3071d4052ba9ab98383be9 (patch) | |
tree | 3cf3f26d35a3a6375275a784a3ef0b2ed6f30a0d /src/opts/SkColor_opts_SSE2.h | |
parent | b45c56e4b7e3d51c808b0d8694e13ea3b403ec6f (diff) |
SSE2 implementation of S32A_D565_Opaque
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
Diffstat (limited to 'src/opts/SkColor_opts_SSE2.h')
-rw-r--r-- | src/opts/SkColor_opts_SSE2.h | 31 |
1 files changed, 31 insertions, 0 deletions
diff --git a/src/opts/SkColor_opts_SSE2.h b/src/opts/SkColor_opts_SSE2.h new file mode 100644 index 0000000000..13a5be5655 --- /dev/null +++ b/src/opts/SkColor_opts_SSE2.h @@ -0,0 +1,31 @@ +/* + * Copyright 2014 The Android Open Source Project + * + * Use of this source code is governed by a BSD-style license that can be + * found in the LICENSE file. + */ + +#ifndef SkColor_opts_SSE2_DEFINED +#define SkColor_opts_SSE2_DEFINED + +#include <emmintrin.h> + +static inline __m128i SkMul16ShiftRound_SSE(__m128i a, __m128i b, int shift) { + __m128i prod = _mm_mullo_epi16(a, b); + prod = _mm_add_epi16(prod, _mm_set1_epi16(1 << (shift - 1))); + prod = _mm_add_epi16(prod, _mm_srli_epi16(prod, shift)); + prod = _mm_srli_epi16(prod, shift); + + return prod; +} + +static inline __m128i SkPackRGB16_SSE(__m128i r, __m128i g, __m128i b) { + r = _mm_slli_epi16(r, SK_R16_SHIFT); + g = _mm_slli_epi16(g, SK_G16_SHIFT); + b = _mm_slli_epi16(b, SK_B16_SHIFT); + + __m128i c = _mm_or_si128(r, g); + return _mm_or_si128(c, b); +} + +#endif//SkColor_opts_SSE2_DEFINED |