[llvm] [X86] Lower `minimum`/`maximum`/`minimumnum`/`maximumnum` using bitwise operations (PR #170069)

[Phoebe Wang via llvm-commits]

================
@@ -402,9 +353,10 @@ define float @test_fmaximumnum_nsz(float %x, float %y) "no-signed-zeros-fp-math"
 ; X86:       # %bb.0:
 ; X86-NEXT:    pushl %eax
 ; X86-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; X86-NEXT:    vmaxss {{[0-9]+}}(%esp), %xmm0, %xmm1
-; X86-NEXT:    vcmpunordss %xmm1, %xmm1, %xmm2
-; X86-NEXT:    vblendvps %xmm2, %xmm0, %xmm1, %xmm0
+; X86-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
----------------
phoebewang wrote:

ditto.

https://github.com/llvm/llvm-project/pull/170069