[Mlir-commits] [mlir] [MLIR][NVVM] Add nvvm.fma Op (PR #184776)

[Durgadoss R]

================
@@ -6368,6 +6368,37 @@ def NVVM_SubFOp : NVVM_FloatBinaryOp<"subf"> {
   let hasCanonicalizer = 1;
 }
 
+def NVVM_FmaOp : NVVM_Op<"fma", [Pure, SameOperandsAndResultType]> {
+  let summary = [{
+    Performs floating point fused multiply-add operation with support for mixed 
+    precision operands
+  }];
+  let description = [{
+    The `nvvm.fma` operation performs floating point fused multiply-add of three operands.
----------------
durga4github wrote:

Let us add actual description, mainly for `oob` behavior.

https://github.com/llvm/llvm-project/pull/184776