diff options
| author | James Almer <jamrial@gmail.com> | 2019-03-14 16:22:29 -0300 |
|---|---|---|
| committer | James Almer <jamrial@gmail.com> | 2019-03-14 16:22:29 -0300 |
| commit | 5c363d3e595a9e5b7c42897b7aab91b91b154ac1 (patch) | |
| tree | 297d1fdcc5f76f3d1016124b374a10bece268b44 | |
| parent | 409e684e79b6ee0c511292326f09b13fe230e58e (diff) | |
| parent | 7e42d5f0ab2aeac811fd01e122627c9198b13f01 (diff) | |
| download | ffmpeg-5c363d3e595a9e5b7c42897b7aab91b91b154ac1.tar.gz | |
Merge commit '7e42d5f0ab2aeac811fd01e122627c9198b13f01'
* commit '7e42d5f0ab2aeac811fd01e122627c9198b13f01':
aarch64: vp8: Optimize vp8_idct_add_neon for aarch64
Merged-by: James Almer <jamrial@gmail.com>
| -rw-r--r-- | libavcodec/aarch64/vp8dsp_neon.S | 49 |
1 files changed, 25 insertions, 24 deletions
diff --git a/libavcodec/aarch64/vp8dsp_neon.S b/libavcodec/aarch64/vp8dsp_neon.S index be4f26c481..4bbf16d1a4 100644 --- a/libavcodec/aarch64/vp8dsp_neon.S +++ b/libavcodec/aarch64/vp8dsp_neon.S @@ -125,36 +125,37 @@ function ff_vp8_idct_add_neon, export=1 sub v17.4h, v0.4h, v2.4h add v18.4h, v20.4h, v23.4h - ld1 {v24.d}[0], [x0], x2 - zip1 v16.2d, v16.2d, v17.2d - sub v19.4h, v21.4h, v22.4h - ld1 {v25.d}[0], [x0], x2 - zip1 v18.2d, v18.2d, v19.2d - add v0.8h, v16.8h, v18.8h - ld1 {v25.d}[1], [x0], x2 - sub v1.8h, v16.8h, v18.8h - ld1 {v24.d}[1], [x0], x2 - srshr v0.8h, v0.8h, #3 - trn1 v24.4s, v24.4s, v25.4s - srshr v1.8h, v1.8h, #3 + ld1 {v24.s}[0], [x0], x2 + sub v19.4h, v21.4h, v22.4h + ld1 {v25.s}[0], [x0], x2 + add v0.4h, v16.4h, v18.4h + add v1.4h, v17.4h, v19.4h + ld1 {v26.s}[0], [x0], x2 + sub v3.4h, v16.4h, v18.4h + sub v2.4h, v17.4h, v19.4h + ld1 {v27.s}[0], [x0], x2 + srshr v0.4h, v0.4h, #3 + srshr v1.4h, v1.4h, #3 + srshr v2.4h, v2.4h, #3 + srshr v3.4h, v3.4h, #3 + sub x0, x0, x2, lsl #2 - ext v1.16b, v1.16b, v1.16b, #8 - trn1 v3.2d, v0.2d, v1.2d - trn2 v0.2d, v0.2d, v1.2d - trn1 v1.8h, v3.8h, v0.8h - trn2 v3.8h, v3.8h, v0.8h - uzp1 v0.4s, v1.4s, v3.4s - uzp2 v1.4s, v3.4s, v1.4s + transpose_4x4H v0, v1, v2, v3, v5, v6, v7, v16 uaddw v0.8h, v0.8h, v24.8b - uaddw2 v1.8h, v1.8h, v24.16b + uaddw v1.8h, v1.8h, v25.8b + uaddw v2.8h, v2.8h, v26.8b + uaddw v3.8h, v3.8h, v27.8b sqxtun v0.8b, v0.8h - sqxtun2 v0.16b, v1.8h + sqxtun v1.8b, v1.8h + sqxtun v2.8b, v2.8h + sqxtun v3.8b, v3.8h + st1 {v0.s}[0], [x0], x2 - st1 {v0.s}[1], [x0], x2 - st1 {v0.s}[3], [x0], x2 - st1 {v0.s}[2], [x0], x2 + st1 {v1.s}[0], [x0], x2 + st1 {v2.s}[0], [x0], x2 + st1 {v3.s}[0], [x0], x2 ret endfunc |