[Mlir-commits] [mlir] [MLIR][NVVM] Add support for f6x2 conversion (PR #136537)

[Srinivasa Ravi]

================
@@ -1066,6 +1066,56 @@ def NVVM_CvtFloatToTF32Op : NVVM_Op<"cvt.float.to.tf32"> {
   }];
 }
 
+def CVTFP6E2M3 : I32EnumAttrCase<"E2M3", 0, "e2m3">;
+def CVTFP6E3M2 : I32EnumAttrCase<"E3M2", 1, "e3m2">;
+
+def CVTFP6Type : I32EnumAttr<"CVTFP6Type", "NVVM CVTFP6Type kind",
+  [CVTFP6E2M3, CVTFP6E3M2]> {
+  let genSpecializedAttr = 0;
+  let cppNamespace = "::mlir::NVVM";
+}
+def CVTFP6TypeAttr : EnumAttr<NVVM_Dialect, CVTFP6Type, "cvt_fp6_type"> {
+  let assemblyFormat = "`<` $value `>`";
+}
+
+def NVVM_CvtToF6x2Op : NVVM_Op<"cvt.to.f6x2"> {
+  let summary = "Convert the given float input to f6x2";
+  let description = [{
+    This Op converts the given float input to f6x2.
+    The result `dst` is represented either as an i16 type or a vector
+    of two i8 types.
+    The `relu` attribute, when set, lowers to the '.relu' variant of
+    the cvt instruction. The `rnd` and `sat` attributes specify the
+    the rounding and saturation modes respectively.
+
+    [For more information, see PTX ISA](https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cvt)
+  }];
+  let results = (outs AnyTypeOf<[I16, VectorOfLengthAndType<[2], [I8]>]>:$dst);
+  let arguments = (ins 
+    CVTFP6TypeAttr:$type,
+    F32:$a,
+    F32:$b,
+    DefaultValuedAttr<FPRoundingModeAttr, "FPRoundingMode::RN">:$rnd,
+    DefaultValuedAttr<SaturationModeAttr, "SaturationMode::SATFINITE">:$sat,
+    DefaultValuedAttr<BoolAttr, "false">:$relu);
+  let assemblyFormat = "$type $a `,` $b attr-dict `:` type($dst)";
+  
+  let extraClassDeclaration = [{
+    static llvm::Intrinsic::ID getIntrinsicID(NVVM::CVTFP6Type,
+                                              bool hasRelu);
+    bool isPacked();                                          
+    llvm::Value* getCastedResult(llvm::Value* packedI16, llvm::IRBuilderBase &builder);
+  }];
+
+  string llvmBuilder = [{
+    auto intId = NVVM::CvtToF6x2Op::getIntrinsicID($type, $relu);
+    llvm::Value *packedI16 = createIntrinsicCall(builder, intId, {$a, $b});
+    $dst = op.getCastedResult(packedI16, builder);
----------------
Wolfram70 wrote:

Moved the check here in the latest revision, thanks!

https://github.com/llvm/llvm-project/pull/136537