[llvm] [X86] Try Folding icmp of v8i32 -> fcmp of v8f32 on AVX (PR #82290)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Feb 29 11:34:21 PST 2024
goldsteinn wrote:
> Reposting here. If the input bound checks fail, `vpcmpeqd` can be emulated with no restrictions on the input bounds:
>
> ```
> vpcmpeqd result, a, b
> =>
> vpxor ymm0, a, b
> vcvtdq2ps ymm1, ymm0
> vcmpps result, ymm1, zero, 0
> ```
Ah nice :)
Ill add todo for that.
https://github.com/llvm/llvm-project/pull/82290
More information about the llvm-commits
mailing list