mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2025-01-24 13:56:33 +02:00
aarch64: hevc_idct: Fix overflows in idct_dc
This is marginally slower, but correct for all input values. The previous implementation failed with certain input seeds, e.g. "checkasm --test=hevc_idct 98". Signed-off-by: Martin Storsjö <martin@martin.st>
This commit is contained in:
parent
0fd7f14c75
commit
f27e3ccf06
@ -573,14 +573,13 @@ idct_16x16 10
|
||||
// void ff_hevc_idct_NxN_dc_DEPTH_neon(int16_t *coeffs)
|
||||
.macro idct_dc size, bitdepth
|
||||
function ff_hevc_idct_\size\()x\size\()_dc_\bitdepth\()_neon, export=1
|
||||
movi v1.8h, #((1 << (14 - \bitdepth))+1)
|
||||
ld1r {v4.8h}, [x0]
|
||||
add v4.8h, v4.8h, v1.8h
|
||||
sshr v0.8h, v4.8h, #(15 - \bitdepth)
|
||||
sshr v1.8h, v4.8h, #(15 - \bitdepth)
|
||||
srshr v4.8h, v4.8h, #1
|
||||
srshr v0.8h, v4.8h, #(14 - \bitdepth)
|
||||
srshr v1.8h, v4.8h, #(14 - \bitdepth)
|
||||
.if \size > 4
|
||||
sshr v2.8h, v4.8h, #(15 - \bitdepth)
|
||||
sshr v3.8h, v4.8h, #(15 - \bitdepth)
|
||||
srshr v2.8h, v4.8h, #(14 - \bitdepth)
|
||||
srshr v3.8h, v4.8h, #(14 - \bitdepth)
|
||||
.if \size > 16 /* dc 32x32 */
|
||||
mov x2, #4
|
||||
1:
|
||||
|
Loading…
x
Reference in New Issue
Block a user