[clang] [llvm] [clang][NVPTX] Add overloaded fmul intrinsics (PR #224546)

[Durgadoss R via llvm-commits]

================
@@ -7261,9 +7257,9 @@ static bool isSupportedFAdd(EVT VT, const NVPTXSubtarget &STI,
   }
 }
 
-static SDValue diagnoseUnsupportedFAdd(SDNode *N, SelectionDAG &DAG,
-                                       Intrinsic::ID IID,
-                                       APFloat::roundingMode RoundingMode) {
+static SDValue diagnoseUnsupportedFPArith(SDNode *N, SelectionDAG &DAG,
----------------
durga4github wrote:

LGTM as is for now.
It feels like we will have a better place for this after PR #221751 (in IR verfier..). We can move these checks over there once those APIs/usages settle.

https://github.com/llvm/llvm-project/pull/224546