[Bug target/94962] Suboptimal AVX2 code for _mm256_zextsi128_si256(_mm_set1_epi8(-1))

[n...@self-evident.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94962

--- Comment #7 from Nemo <n...@self-evident.org> ---
(In reply to Hongtao.liu from comment #6)
>
> vmovdqa xmm0, xmm0 is not redundant here, it would clear up 128-256 bit
> which is the meaning of `zext`.

No, it is redundant because "vpcmpeqd xmm0, xmm0, xmm0" already zeroes out the
high lane of ymm0.