diff options
| author | Hubert Mazur <hum@semihalf.com> | 2022-09-08 11:25:06 +0200 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2022-09-09 10:19:46 +0300 |
| commit | 908abe8032d2e56f9b94a7ae387e415de4c29115 (patch) | |
| tree | 39f211d7fdd25f6ee801416c80ab38204053cd9f /libavcodec/aarch64/me_cmp_neon.S | |
| parent | ce03ea3e796bdf9013da51d53e89759a92707c4a (diff) | |
| download | ffmpeg-908abe8032d2e56f9b94a7ae387e415de4c29115.tar.gz | |
lavc/aarch64: Add neon implementation for vsse_intra16
Provide optimized implementation for vsse_intra16 for arm64.
Performance tests are shown below.
- vsse_4_c: 155.2
- vsse_4_neon: 36.2
Benchmarks and tests are run with checkasm tool on AWS Graviton 3.
Signed-off-by: Hubert Mazur <hum@semihalf.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libavcodec/aarch64/me_cmp_neon.S')
| -rw-r--r-- | libavcodec/aarch64/me_cmp_neon.S | 63 |
1 files changed, 63 insertions, 0 deletions
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S index ce198ea227..cf2b8da425 100644 --- a/libavcodec/aarch64/me_cmp_neon.S +++ b/libavcodec/aarch64/me_cmp_neon.S @@ -784,3 +784,66 @@ function vsad_intra16_neon, export=1 ret endfunc + +function vsse_intra16_neon, export=1 + // x0 unused + // x1 uint8_t *pix1 + // x2 uint8_t *dummy + // x3 ptrdiff_t stride + // w4 int h + + ld1 {v0.16b}, [x1], x3 + movi v16.4s, #0 + movi v17.4s, #0 + + sub w4, w4, #1 // we need to make h-1 iterations + cmp w4, #3 + b.lt 2f + +1: + // v = abs( pix1[0] - pix1[0 + stride] ) + // score = sum( v * v ) + ld1 {v1.16b}, [x1], x3 + ld1 {v2.16b}, [x1], x3 + uabd v30.16b, v0.16b, v1.16b + ld1 {v3.16b}, [x1], x3 + umull v29.8h, v30.8b, v30.8b + umull2 v28.8h, v30.16b, v30.16b + uabd v27.16b, v1.16b, v2.16b + uadalp v16.4s, v29.8h + umull v26.8h, v27.8b, v27.8b + umull2 v27.8h, v27.16b, v27.16b + uadalp v17.4s, v28.8h + uabd v25.16b, v2.16b, v3.16b + uadalp v16.4s, v26.8h + umull v24.8h, v25.8b, v25.8b + umull2 v25.8h, v25.16b, v25.16b + uadalp v17.4s, v27.8h + sub w4, w4, #3 + uadalp v16.4s, v24.8h + cmp w4, #3 + uadalp v17.4s, v25.8h + mov v0.16b, v3.16b + + b.ge 1b + cbz w4, 3f + +// iterate by one +2: + ld1 {v1.16b}, [x1], x3 + subs w4, w4, #1 + uabd v30.16b, v0.16b, v1.16b + mov v0.16b, v1.16b + umull v29.8h, v30.8b, v30.8b + umull2 v30.8h, v30.16b, v30.16b + uadalp v16.4s, v29.8h + uadalp v17.4s, v30.8h + cbnz w4, 2b + +3: + add v16.4s, v16.4s, v17.4S + uaddlv d17, v16.4s + fmov w0, s17 + + ret +endfunc |