Use 16-byte alignment (align=4) instead of 4-byte (align=2) in the function and
const macros. This improves instruction fetch and NEON load performance on
modern AArch64 CPUs.
---
libavutil/aarch64/asm.S | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/libavutil/aarch64/asm.S b/libavutil/aarch64/asm.S
index 50ce7d4dfd..2e4e451ec2 100644
--- a/libavutil/aarch64/asm.S
+++ b/libavutil/aarch64/asm.S
@@ -196,7 +196,7 @@ DISABLE_SVE2
.popsection
#endif
-.macro function name, export=0, align=2
+.macro function name, export=0, align=4
.macro endfunc
ELF .size \name, . - \name
FUNC .endfunc
@@ -217,7 +217,7 @@ FUNC .func \name
.endif
.endm
-.macro const name, align=2, relocate=0
+.macro const name, align=4, relocate=0
.macro endconst
ELF .size \name, . - \name
.purgem endconst
--
2.39.5
_______________________________________________
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".
