MrBesen
/
ffmpeg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

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:
Martin Storsjö 2021-05-17 12:48:03 +03:00
parent 0fd7f14c75
commit f27e3ccf06
1 changed files with 5 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
libavcodec/aarch64/hevcdsp_idct_neon.S
View File

@ -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: