[llvm] [NVPTX] Constant fold NVVM fmin and fmax (PR #121966)

[Lewis Crawford via llvm-commits]

================
@@ -38,9 +38,8 @@ enum class TMAReductionOp : uint8_t {
   XOR = 7,
 };
 
-inline bool IntrinsicShouldFTZ(Intrinsic::ID IntrinsicID) {
+inline bool FloatToIntIntrinsicShouldFTZ(Intrinsic::ID IntrinsicID) {
----------------
LewisCrawford wrote:

Ah, I see what you mean now. I've changed it to `FPToInteger` now, which hopefully implies a broader range of both floating-point and integer types, rather than just specifically `float` and `int`.

https://github.com/llvm/llvm-project/pull/121966