aarch64: vp9itxfm: Use the right lane sizes in 8x8 for improved readability
This is cherrypicked from libav commit 3dd7827258ddaa2e51085d0c677d6f3b1be3572f. Signed-off-by: Martin Storsjö <martin@martin.st>
This commit is contained in:
parent
19a0f9529c
commit
6752318c73
@ -385,10 +385,10 @@ function ff_vp9_\txfm1\()_\txfm2\()_8x8_add_neon, export=1
|
||||
.endif
|
||||
ld1 {v0.8h}, [x4]
|
||||
|
||||
movi v2.16b, #0
|
||||
movi v3.16b, #0
|
||||
movi v4.16b, #0
|
||||
movi v5.16b, #0
|
||||
movi v2.8h, #0
|
||||
movi v3.8h, #0
|
||||
movi v4.8h, #0
|
||||
movi v5.8h, #0
|
||||
|
||||
.ifc \txfm1\()_\txfm2,idct_idct
|
||||
cmp w3, #1
|
||||
@ -411,11 +411,11 @@ function ff_vp9_\txfm1\()_\txfm2\()_8x8_add_neon, export=1
|
||||
b 2f
|
||||
.endif
|
||||
1:
|
||||
ld1 {v16.16b,v17.16b,v18.16b,v19.16b}, [x2], #64
|
||||
ld1 {v20.16b,v21.16b,v22.16b,v23.16b}, [x2], #64
|
||||
ld1 {v16.8h,v17.8h,v18.8h,v19.8h}, [x2], #64
|
||||
ld1 {v20.8h,v21.8h,v22.8h,v23.8h}, [x2], #64
|
||||
sub x2, x2, #128
|
||||
st1 {v2.16b,v3.16b,v4.16b,v5.16b}, [x2], #64
|
||||
st1 {v2.16b,v3.16b,v4.16b,v5.16b}, [x2], #64
|
||||
st1 {v2.8h,v3.8h,v4.8h,v5.8h}, [x2], #64
|
||||
st1 {v2.8h,v3.8h,v4.8h,v5.8h}, [x2], #64
|
||||
|
||||
\txfm1\()8
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user