https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98172
--- Comment #9 from Hongtao.liu <crazylht at gmail dot com> ---
> .L3:
> vmovupd (%rcx,%rax), %xmm3
> vmovupd (%rsi,%rax), %xmm4
> vinsertf128 $0x1, 16(%rcx,%rax), %ymm3, %ymm0
> vinsertf128 $0x1, 16(%rsi,%rax), %ymm4, %ymm2
> vmovupd (%rdi,%rax), %xmm5
> vinsertf128 $0x1, 16(%rdi,%rax), %ymm5, %ymm1
> vfmadd132pd %ymm2, %ymm1, %ymm0
> vmovupd %xmm0, (%rdx,%rax)
> vextractf128 $0x1, %ymm0, 16(%rdx,%rax)
> addq $32, %rax
> cmpq $2048, %rax
> jne .L3
> vzeroupper
> ret
The kernel loop could be better as
.L3:
vmovupd (%rcx,%rax), %ymm0
vmovupd (%rdi,%rax), %ymm1
vfmadd132pd (%rsi,%rax), %ymm1, %ymm0
vmovupd %ymm0, (%rdx,%rax)
addq $32, %rax
cmpq $2048, %rax
jne .L3
