-
-
Save travisdowns/9216bffba33876ee578aa0bb74b3c8f2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
903: | |
vmovdqa ymm0,YMMWORD PTR [rax+0x20] | |
add rax,0x40 | |
vmovdqa ymm3,YMMWORD PTR [rax-0x40] | |
vperm2i128 ymm4,ymm3,ymm0,0x20 ; what | |
vperm2i128 ymm3,ymm3,ymm0,0x31 ; no | |
vpshufd ymm4,ymm4,0xd8 ; don't need | |
vpshufd ymm3,ymm3,0xd8 ; nope | |
vpunpcklqdq ymm7,ymm4,ymm3 ; I really don't understand | |
vpunpckhqdq ymm3,ymm4,ymm3 ; why it is doing this | |
vpsrld ymm4,ymm7,0x10 ; starting here it's fine | |
vpand ymm7,ymm6,ymm7 | |
vpsrld ymm0,ymm3,0x10 | |
vpand ymm3,ymm6,ymm3 | |
vpaddd ymm3,ymm3,ymm7 | |
vpaddd ymm0,ymm0,ymm4 | |
vpaddd ymm1,ymm1,ymm3 | |
vpaddd ymm2,ymm2,ymm0 | |
cmp rcx,rax | |
jne 903 <sum_halves_bench(unsigned long, void*)+0x53> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment