diff options
| author | Frank Barchard <fbarchard@google.com> | 2023-02-13 10:52:58 -0800 |
|---|---|---|
| committer | libyuv LUCI CQ <libyuv-scoped@luci-project-accounts.iam.gserviceaccount.com> | 2023-02-13 20:14:57 +0000 |
| commit | 2bdc210be9eb11ded16bf3ef1f6cadb0d4dcb0c2 (patch) | |
| tree | c446d71538c965d0e5391ef77cd49b45ba51463d /source/row_neon64.cc | |
| parent | b2528b0be934de1918e20c85fc170d809eeb49ab (diff) | |
| download | libyuv-2bdc210be9eb11ded16bf3ef1f6cadb0d4dcb0c2.tar.gz | |
MergeUV_AVX512BW for I420ToNV12
On Skylake Xeon 640x360 100000 iterations
AVX512 MergeUVPlane_Opt (1196 ms)
AVX2 MergeUVPlane_Opt (1565 ms)
SSE2 MergeUVPlane_Opt (1780 ms)
Pixel 7 MergeUVPlane_Opt (1177 ms)
Bug: None
Change-Id: If47d4fa957cf27781bba5fd6a2f0bf554101a5c6
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4242247
Commit-Queue: Frank Barchard <fbarchard@chromium.org>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Diffstat (limited to 'source/row_neon64.cc')
| -rw-r--r-- | source/row_neon64.cc | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/source/row_neon64.cc b/source/row_neon64.cc index 7f04b606..df346ee0 100644 --- a/source/row_neon64.cc +++ b/source/row_neon64.cc @@ -820,6 +820,28 @@ void MergeUVRow_NEON(const uint8_t* src_u, : "cc", "memory", "v0", "v1" // Clobber List ); } +// Reads 16 U's and V's and writes out 16 pairs of UV. +void MergeUVRow_NEON1(const uint8_t* src_u, + const uint8_t* src_v, + uint8_t* dst_uv, + int width) { + asm volatile( + "1: \n" + "ld1 {v0.16b,v2.16b}, [%0], #32 \n" // load U + "ld1 {v1.16b,v3.16b}, [%1], #32 \n" // load V + "subs %w3, %w3, #32 \n" // 32 processed per loop + "prfm pldl1keep, [%0, 448] \n" + "prfm pldl1keep, [%1, 448] \n" + "st2 {v0.16b,v1.16b,v2.16b,v3.16b}, [%2], #64 \n" // store 32 UV + "b.gt 1b \n" + : "+r"(src_u), // %0 + "+r"(src_v), // %1 + "+r"(dst_uv), // %2 + "+r"(width) // %3 // Output registers + : // Input registers + : "cc", "memory", "v0", "v1" // Clobber List + ); +} void MergeUVRow_16_NEON(const uint16_t* src_u, const uint16_t* src_v, |