diff options
| author | Frank Barchard <fbarchard@google.com> | 2023-02-20 02:21:22 -0800 |
|---|---|---|
| committer | libyuv LUCI CQ <libyuv-scoped@luci-project-accounts.iam.gserviceaccount.com> | 2023-02-22 21:19:08 +0000 |
| commit | 88b050f337cc0ca2a51800fe7bf4737222c87344 (patch) | |
| tree | a4ffa708c5e32fb6b0baffa42823098784bee677 /source/convert_from_argb.cc | |
| parent | 2bdc210be9eb11ded16bf3ef1f6cadb0d4dcb0c2 (diff) | |
| download | libyuv-88b050f337cc0ca2a51800fe7bf4737222c87344.tar.gz | |
MergeUV AVX512BW use assembly
- Convert MergeUVRow_AVX512BW to assembly
- Enable MergeUVRow_AVX512BW for Windows with clangcl
- MergeUVRow_AVX2 use vpmovzxbw and vpsllw
- MergeUVRow_16_AVX2 use vpmovzxbw and vpsllw with different shift for U and V
AMD Zen 4 640x360 100000 iterations
Was
AVX512 MergeUVPlane_Opt (884 ms)
AVX2 MergeUVPlane_Opt (945 ms)
AVX2 MergeUVPlane_16_Opt (2167 ms)
Now
AVX512 MergeUVPlane_Opt (865 ms)
AVX2 MergeUVPlane_Opt (943 ms)
SSE2 MergeUVPlane_Opt (973 ms)
AVX2 MergeUVPlane_16_Opt (2102 ms)
Bug: None
Change-Id: I658ada2a75d44c3f93be8bd3ed96f83d5fa2ab8d
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4271230
Reviewed-by: Fritz Koenig <frkoenig@chromium.org>
Commit-Queue: Frank Barchard <fbarchard@chromium.org>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Diffstat (limited to 'source/convert_from_argb.cc')
| -rw-r--r-- | source/convert_from_argb.cc | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/source/convert_from_argb.cc b/source/convert_from_argb.cc index 1b8572a0..55516cbd 100644 --- a/source/convert_from_argb.cc +++ b/source/convert_from_argb.cc @@ -384,7 +384,7 @@ int ARGBToNV12(const uint8_t* src_argb, #if defined(HAS_MERGEUVROW_AVX2) if (TestCpuFlag(kCpuHasAVX2)) { MergeUVRow_ = MergeUVRow_Any_AVX2; - if (IS_ALIGNED(halfwidth, 32)) { + if (IS_ALIGNED(halfwidth, 16)) { MergeUVRow_ = MergeUVRow_AVX2; } } @@ -562,7 +562,7 @@ int ARGBToNV21(const uint8_t* src_argb, #if defined(HAS_MERGEUVROW_AVX2) if (TestCpuFlag(kCpuHasAVX2)) { MergeUVRow_ = MergeUVRow_Any_AVX2; - if (IS_ALIGNED(halfwidth, 32)) { + if (IS_ALIGNED(halfwidth, 16)) { MergeUVRow_ = MergeUVRow_AVX2; } } @@ -737,7 +737,7 @@ int ABGRToNV12(const uint8_t* src_abgr, #if defined(HAS_MERGEUVROW_AVX2) if (TestCpuFlag(kCpuHasAVX2)) { MergeUVRow_ = MergeUVRow_Any_AVX2; - if (IS_ALIGNED(halfwidth, 32)) { + if (IS_ALIGNED(halfwidth, 16)) { MergeUVRow_ = MergeUVRow_AVX2; } } @@ -913,7 +913,7 @@ int ABGRToNV21(const uint8_t* src_abgr, #if defined(HAS_MERGEUVROW_AVX2) if (TestCpuFlag(kCpuHasAVX2)) { MergeUVRow_ = MergeUVRow_Any_AVX2; - if (IS_ALIGNED(halfwidth, 32)) { + if (IS_ALIGNED(halfwidth, 16)) { MergeUVRow_ = MergeUVRow_AVX2; } } @@ -2948,7 +2948,7 @@ int RAWToJNV21(const uint8_t* src_raw, #if defined(HAS_MERGEUVROW_AVX2) if (TestCpuFlag(kCpuHasAVX2)) { MergeUVRow_ = MergeUVRow_Any_AVX2; - if (IS_ALIGNED(halfwidth, 32)) { + if (IS_ALIGNED(halfwidth, 16)) { MergeUVRow_ = MergeUVRow_AVX2; } } |