[Mlir-commits] [mlir] [MLIR][NVVM] Add new narrow FP convert Ops (PR #184291)

[Durgadoss R]

================
@@ -1951,6 +1951,45 @@ def NVVM_ConvertF32x2ToF4x2Op : NVVM_Op<"convert.f32x2.to.f4x2"> {
   }];
 }
 
+class NVVM_ConvertFPx2ToF4x2Op<string srcType>
+    : NVVM_Op<"convert."#!tolower(srcType)#"x2.to.f4x2"> {
+  let summary = "Convert a pair of "#srcType#" inputs to F4x2";
+  let description = [{
+    This Op converts each of the given }]#srcType#[{ inputs to the specified 
+    F4x2 type.
+    The result `dst` is returned as an i8 type where the converted values are 
+    packed such that the value converted from `a` is stored in the upper 4 bits 
+    of `dst` and the value converted from `b` is stored in the lower 4 bits of 
+    `dst`.
+    The `relu` attribute, when set, lowers to the '.relu' variant of
+    the cvt instruction.
+    }];
+  let hasVerifier = 1;
+  let results = (outs I8:$dst);
+  let arguments = (ins
+      VectorOfLengthAndType<[2], [!cast<Type>(srcType)]>:$a,
----------------
durga4github wrote:

Also, instead of `a` can we name it `src` to align it better with `dst`?

https://github.com/llvm/llvm-project/pull/184291