[Bug target/87976] [i386] Sub-optimal code generation for _mm256_set1_epi64()

[glisse at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=87976

--- Comment #4 from Marc Glisse <glisse at gcc dot gnu.org> ---
(In reply to Andrew Pinski from comment #1)
> apinski@xeond:~/src/toolchain-o7$ gcc t6.c -mavx -O2 -S -o -  -march=native
>         .file   "t6.c"
>         .text
>         .p2align 4,,15
>         .globl  g
>         .type   g, @function
> g:
> .LFB4758:
>         .cfi_startproc
>         vpbroadcastq    %rdi, %ymm0
>         jmp     f@PLT
>         .cfi_endproc

This requires AVX512. Regular -march=skylake still goes through the stack. So
it seems at least a tiny bit different from bug 80820 where -march=haswell is
enough to avoid going through memory.