Commit 388e0d25 authored by Martin Storsjö's avatar Martin Storsjö

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.
Signed-off-by: 's avatarMartin Storsjö <martin@martin.st>
parent fea92a4b
......@@ -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
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment