diff options
| author | Martin Storsjö <martin@martin.st> | 2016-12-17 13:14:38 +0200 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2017-03-11 13:14:48 +0200 |
| commit | 045e33ae3fee74e39b1321dddf727eacb1ecf541 (patch) | |
| tree | 530a31cb2cdfd879770c015efa62525728b329bd /libavcodec | |
| parent | bff07715904cc02f04eb5c5e171b431eb00f0c3b (diff) | |
aarch64: vp9mc: Calculate less unused data in the 4 pixel wide horizontal filter
No measured speedup on a Cortex A53, but other cores might benefit.
This is cherrypicked from libav commit
388e0d2515bc6bbc9d0c9af1d230bd16cf945fe7.
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libavcodec')
| -rw-r--r-- | libavcodec/aarch64/vp9mc_neon.S | 15 |
1 files changed, 13 insertions, 2 deletions
diff --git a/libavcodec/aarch64/vp9mc_neon.S b/libavcodec/aarch64/vp9mc_neon.S index 94039114bd..82a0f53133 100644 --- a/libavcodec/aarch64/vp9mc_neon.S +++ b/libavcodec/aarch64/vp9mc_neon.S @@ -202,9 +202,12 @@ endfunc ext v23.16b, \src5\().16b, \src6\().16b, #(2*\offset) mla \dst2\().8h, v21.8h, v0.h[\offset] mla \dst4\().8h, v23.8h, v0.h[\offset] -.else +.elseif \size == 8 mla \dst1\().8h, v20.8h, v0.h[\offset] mla \dst3\().8h, v22.8h, v0.h[\offset] +.else + mla \dst1\().4h, v20.4h, v0.h[\offset] + mla \dst3\().4h, v22.4h, v0.h[\offset] .endif .endm // The same as above, but don't accumulate straight into the @@ -219,16 +222,24 @@ endfunc ext v23.16b, \src5\().16b, \src6\().16b, #(2*\offset) mul v21.8h, v21.8h, v0.h[\offset] mul v23.8h, v23.8h, v0.h[\offset] -.else +.elseif \size == 8 mul v20.8h, v20.8h, v0.h[\offset] mul v22.8h, v22.8h, v0.h[\offset] +.else + mul v20.4h, v20.4h, v0.h[\offset] + mul v22.4h, v22.4h, v0.h[\offset] .endif +.if \size == 4 + sqadd \dst1\().4h, \dst1\().4h, v20.4h + sqadd \dst3\().4h, \dst3\().4h, v22.4h +.else sqadd \dst1\().8h, \dst1\().8h, v20.8h sqadd \dst3\().8h, \dst3\().8h, v22.8h .if \size >= 16 sqadd \dst2\().8h, \dst2\().8h, v21.8h sqadd \dst4\().8h, \dst4\().8h, v23.8h .endif +.endif .endm |