https://gcc.gnu.org/bugzilla/show_bug.cgi?id=54939
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|ASSIGNED |RESOLVED
Resolution|--- |FIXED
CC| |crazylht at gmail dot com
--- Comment #14 from Richard Biener <rguenth at gcc dot gnu.org> ---
With SSE4.2 we now get
.L3:
movupd (%rdx,%rax), %xmm0
movupd (%rcx,%rax), %xmm4
movapd %xmm0, %xmm1
palignr $8, %xmm0, %xmm0
mulpd %xmm3, %xmm1
mulpd %xmm2, %xmm0
addpd %xmm4, %xmm1
addsubpd %xmm0, %xmm1
movups %xmm1, (%rcx,%rax)
addq $16, %rax
cmpq %rsi, %rax
jne .L3
with AVX and FMA
.L4:
vmovupd (%rdx,%rax), %ymm0
vmovapd %ymm4, %ymm1
vfmadd213pd (%rcx,%rax), %ymm0, %ymm1
vpermilpd $5, %ymm0, %ymm0
vmulpd %ymm3, %ymm0, %ymm0
vaddsubpd %ymm0, %ymm1, %ymm1
vmovupd %ymm1, (%rcx,%rax)
addq $32, %rax
cmpq %rsi, %rax
jne .L4
so I'd say fixed. But. With AVX512 we now get
.L4:
vmovupd (%rdi,%rax), %zmm0
vmovapd %zmm7, %zmm2
vmovapd %zmm4, %zmm6
vfmadd213pd (%rcx,%rax), %zmm0, %zmm2
vpermilpd $85, %zmm0, %zmm0
vfmadd132pd %zmm0, %zmm2, %zmm6
vfnmadd132pd %zmm4, %zmm2, %zmm0
vmovapd %zmm6, %zmm0{%k1}
vmovupd %zmm0, (%rcx,%rax)
addq $64, %rax
cmpq %rax, %rsi
jne .L4
it's odd that this only happens with -mprefer-vector-width=512 though. Do
we possibly miss vec_{fm,}{addsub,subadd} for those? Looks like so.
Tracking in PR110767. The vectorizer side is fixed.
