From: Henrik Gramner <hen...@gramner.com>
Most VEX-encoded instructions require an additional byte to encode when src2
is a high register (e.g. x|ymm8..15). If the instruction is commutative we
can swap src1 and src2 when doing so reduces the instruction length, e.g.
vpaddw xmm0, xmm0, xmm8 -> vpaddw xmm0, xmm8, xmm0
---
libavutil/x86/x86inc.asm | 35 +++++++++++++++++++++++++++++++++--
1 file changed, 33 insertions(+), 2 deletions(-)
diff --git a/libavutil/x86/x86inc.asm b/libavutil/x86/x86inc.asm
index bc370a6186..39cba5db09 100644
--- a/libavutil/x86/x86inc.asm
+++ b/libavutil/x86/x86inc.asm
@@ -1244,9 +1244,40 @@ INIT_XMM
%elif %0 >= 9
__instr %6, %7, %8, %9
%elif %0 == 8
- __instr %6, %7, %8
+ %if avx_enabled && %5
+ %xdefine __src1 %7
+ %xdefine __src2 %8
+ %ifnum regnumof%7
+ %ifnum regnumof%8
+ %if regnumof%7 < 8 && regnumof%8 >= 8 && regnumof%8 < 16
&& sizeof%8 <= 32
+ ; Most VEX-encoded instructions require an additional
byte to encode when
+ ; src2 is a high register (e.g. m8..15). If the
instruction is commutative
+ ; we can swap src1 and src2 when doing so reduces the
instruction length.
+ %xdefine __src1 %8
+ %xdefine __src2 %7
+ %endif
+ %endif
+ %endif
+ __instr %6, __src1, __src2
+ %else
+ __instr %6, %7, %8
+ %endif
%elif %0 == 7
- __instr %6, %7
+ %if avx_enabled && %5
+ %xdefine __src1 %6
+ %xdefine __src2 %7
+ %ifnum regnumof%6
+ %ifnum regnumof%7
+ %if regnumof%6 < 8 && regnumof%7 >= 8 && regnumof%7 < 16
&& sizeof%7 <= 32
+ %xdefine __src1 %7
+ %xdefine __src2 %6
+ %endif
+ %endif
+ %endif
+ __instr %6, __src1, __src2
+ %else
+ __instr %6, %7
+ %endif
%else
__instr %6
%endif
--
2.22.0
_______________________________________________
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".
