diff options
| author | Frank Barchard <fbarchard@google.com> | 2022-09-30 15:12:37 -0700 |
|---|---|---|
| committer | libyuv LUCI CQ <libyuv-scoped@luci-project-accounts.iam.gserviceaccount.com> | 2022-09-30 22:41:21 +0000 |
| commit | 00950840d1c9bcbb3eb6ebc5aac5793e71166c8b (patch) | |
| tree | a261be18062391f039e4e230ce5714f0059ae845 /source/row_neon64.cc | |
| parent | 9ba40a8f03673b79d3236e79707723fdf99f76b6 (diff) | |
| download | libyuv-00950840d1c9bcbb3eb6ebc5aac5793e71166c8b.tar.gz | |
YUY2ToNV12 using YUY2ToY and YUY2ToNVUV
- Optimized YUY2ToNV12 that reduces it from 3 steps to 2 steps
- Was SplitUV, memcpy Y, InterpolateUV
- Now YUY2ToY, YUY2ToNVUV
- rollback LIBYUV_UNLIMITED_DATA
3840x2160 1000 iterations:
Pixel 2 Cortex A73
Was YUY2ToNV12_Opt (6515 ms)
Now YUY2ToNV12_Opt (3350 ms)
AB7 Mediatek P35 Cortex A53
Was YUY2ToNV12_Opt (6435 ms)
Now YUY2ToNV12_Opt (3301 ms)
Skylake AVX2 x64
Was YUY2ToNV12_Opt (1872 ms)
Now YUY2ToNV12_Opt (1657 ms)
SSE2 x64
Was YUY2ToNV12_Opt (2008 ms)
Now YUY2ToNV12_Opt (1691 ms)
Windows Skylake AVX2 32 bit x86
Was YUY2ToNV12_Opt (2161 ms)
Now YUY2ToNV12_Opt (1628 ms)
Bug: libyuv:943
Change-Id: I6c2ba2ae765413426baf770b837de114f808f6d0
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3929843
Reviewed-by: Wan-Teh Chang <wtc@google.com>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@chromium.org>
Diffstat (limited to 'source/row_neon64.cc')
| -rw-r--r-- | source/row_neon64.cc | 23 |
1 files changed, 23 insertions, 0 deletions
diff --git a/source/row_neon64.cc b/source/row_neon64.cc index 3cbd9b79..880a5f06 100644 --- a/source/row_neon64.cc +++ b/source/row_neon64.cc @@ -1808,6 +1808,29 @@ void UYVYToUVRow_NEON(const uint8_t* src_uyvy, ); } +void YUY2ToNVUVRow_NEON(const uint8_t* src_yuy2, + int stride_yuy2, + uint8_t* dst_uv, + int width) { + const uint8_t* src_yuy2b = src_yuy2 + stride_yuy2; + asm volatile( + "1: \n" + "ld2 {v0.16b,v1.16b}, [%0], #32 \n" // load 16 pixels + "subs %w3, %w3, #16 \n" // 16 pixels = 8 UVs. + "ld2 {v2.16b,v3.16b}, [%1], #32 \n" // load next row + "urhadd v4.16b, v1.16b, v3.16b \n" // average rows of UV + "prfm pldl1keep, [%0, 448] \n" + "st1 {v4.16b}, [%2], #16 \n" // store 8 UV. + "b.gt 1b \n" + : "+r"(src_yuy2), // %0 + "+r"(src_yuy2b), // %1 + "+r"(dst_uv), // %2 + "+r"(width) // %3 + : + : "cc", "memory", "v0", "v1", "v2", "v3", "v4" // Clobber List + ); +} + // For BGRAToARGB, ABGRToARGB, RGBAToARGB, and ARGBToRGBA. void ARGBShuffleRow_NEON(const uint8_t* src_argb, uint8_t* dst_argb, |