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".
---
libavcodec/aarch64/hevcdsp_idct_neon.S | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_idct_neon.S
b/libavcodec/aarch64/hevcdsp_idct_neon.S
index 28c11e632c..0869431294 100644
--- a/libavcodec/aarch64/hevcdsp_idct_neon.S
+++ b/libavcodec/aarch64/hevcdsp_idct_neon.S
@@ -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:
--
2.25.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
