[llvm] DAG: Improve fminimum/fmaximum vector expansion logic (PR #93579)

[Phoebe Wang via llvm-commits]

================
@@ -28,35 +28,17 @@ define half @test_fminimum(half %x, half %y) {
 define <8 x half> @test_fminimum_scalarize(<8 x half> %x, <8 x half> %y) "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" {
----------------
phoebewang wrote:

The `_scalarize` should be removed now.

@e-kud What's these tests testing for? If in a NNan, Nsz situation, we can generate VMIN/MAXPH directly. Or you actually wanted `"no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false"`?

https://github.com/llvm/llvm-project/pull/93579