[Mlir-commits] [mlir] Define an amdgpu.scaling_mfma wrapper (PR #137498)

[Prashant Kumar]

================
@@ -833,6 +833,14 @@ mfmaOpToScaledIntrinsic(MFMAOp mfma, Chipset chipset) {
       mfma.getBlocks(), chipset);
 }
 
+static std::optional<std::tuple<StringRef, uint32_t, uint32_t>>
+mfmaOpToScaledIntrinsic(ScaledMFMAOp smfma, Chipset chipset) {
+  return mfmaOpToScaledIntrinsic(smfma.getSourceA().getType(),
----------------
pashu123 wrote:

Rather than creating an overloaded function, you can pass the operation* and then do the dyn_cast + if_else.

https://github.com/llvm/llvm-project/pull/137498