[Mlir-commits] [mlir] [MLIR][NVVM] Add nvvm.fadd and nvvm.fsub Ops (PR #179162)

[Guray Ozen]

================
@@ -3072,6 +3072,83 @@ LogicalResult NVVM::TensormapReplaceOp::verify() {
   return success();
 }
 
+LogicalResult NVVM::FloatAdditionOp::verify() {
+  auto resFType = getRes().getType();
+  auto lhsFType = getLhs().getType();
+  auto rhsFType = getRhs().getType();
+  auto rndMode = getRnd();
+  auto satMode = getSat();
----------------
grypp wrote:

LLVM does not prefer using `auto` keyword when the type is not obvious. 

https://github.com/llvm/llvm-project/pull/179162