[llvm] [X86] Try Folding icmp of v8i32 -> fcmp of v8f32 on AVX (PR #82290)

[Timothy Herchen via llvm-commits]

anematode wrote:

We should probably disable it regardless of the compiler settings because it'd be weird for FP flags to invalidate what looks like integer comparisons.... In my comment where I brought this up I posted a way to compare f32 for equality/inequality regardless of range, but it fails to generalize. I think your converting-to-float method is totally fine though.

https://github.com/llvm/llvm-project/pull/82290