[llvm] [AMDGPU] Fix v32f16 FMINIMUMNUM/FMAXIMUMNUM lowering in non-IEEE mode (PR #207896)

[Jay Foad via llvm-commits]

================
@@ -8730,7 +8730,7 @@ SITargetLowering::lowerFMINIMUMNUM_FMAXIMUMNUM(SDValue Op,
     return expandFMINIMUMNUM_FMAXIMUMNUM(Op.getNode(), DAG);
 
   if (VT == MVT::v4f16 || VT == MVT::v8f16 || VT == MVT::v16f16 ||
----------------
jayfoad wrote:

Do we need this "if" at all? It would be better to avoid yet another long list of vector types if possible.

https://github.com/llvm/llvm-project/pull/207896