From: Martin Storsjö <mar...@martin.st>
This initializes things properly if this were to be called with
h < 4.
---
libavcodec/aarch64/me_cmp_neon.S | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index 3662419edf..cfba3eb33a 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -245,12 +245,12 @@ function ff_pix_abs8_xy2_neon, export=1
cmp w4, #4
add x6, x5, 1 // pix3 + stride + 1
- b.lt 2f
-
ld1 {v0.8b}, [x2], x3
ld1 {v1.8b}, [x0], x3
uaddl v2.8h, v0.8b, v1.8b
+ b.lt 2f
+
// make 4 iterations at once
1:
ld1 {v4.8b}, [x5], x3
--
2.37.1
_______________________________________________
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".
