[MLIR][ROCDL]Add MFMA_*_F8F6F4 instructions to the ROCDL dialect (#123830)

This PR adds mfma.scale.f32.32x32x64.f8f6f4 and
mfma.scale.f32.16x16x128.f8f6f4 to the ROCDL dialect. They are converted
to the corresponding intrinsics in the mlir-to-llvmir pass.

Author: yiqian1

mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td

@@ -343,6 +343,18 @@ class ROCDL_Mfma_IntrOp<string mnemonic, list<Trait> traits = []> :
     "$args attr-dict `:` functional-type($args, $res)";
 }
 
+//===---------------------------------------------------------------------===//
+// MFMA intrinsics with overloaded operands
+class ROCDL_Mfma_OO_IntrOp<string mnemonic, list<int> overloadedOperands,
+                        list<Trait> traits = []> :
+  LLVM_IntrOpBase<ROCDL_Dialect, mnemonic,
+                  "amdgcn_" # !subst(".","_", mnemonic),
+                  [], overloadedOperands, traits, 1>,
+  Arguments<(ins Variadic<LLVM_Type>:$args)> {
+  let assemblyFormat =
+    "$args attr-dict `:` functional-type($args, $res)";
+}
+
 // Available on all CDNA.
 def ROCDL_mfma_f32_32x32x1f32 : ROCDL_Mfma_IntrOp<"mfma.f32.32x32x1f32">;
 def ROCDL_mfma_f32_16x16x1f32 : ROCDL_Mfma_IntrOp<"mfma.f32.16x16x1f32">;
@@ -394,7 +406,8 @@ def ROCDL_mfma_f32_16x16x32_f16 : ROCDL_Mfma_IntrOp<"mfma.f32.16x16x32.f16">;
 def ROCDL_mfma_f32_32x32x16_bf16 : ROCDL_Mfma_IntrOp<"mfma.f32.32x32x16.bf16">;
 def ROCDL_mfma_i32_32x32x32_i8 : ROCDL_Mfma_IntrOp<"mfma.i32.32x32x32.i8">;
 def ROCDL_mfma_f32_32x32x16_f16 : ROCDL_Mfma_IntrOp<"mfma.f32.32x32x16.f16">;
-
+def ROCDL_mfma_scale_f32_16x16x128_f8f6f4 : ROCDL_Mfma_OO_IntrOp<"mfma.scale.f32.16x16x128.f8f6f4", [0,1]>;
+def ROCDL_mfma_scale_f32_32x32x64_f8f6f4 : ROCDL_Mfma_OO_IntrOp<"mfma.scale.f32.32x32x64.f8f6f4", [0,1]>;
 //===---------------------------------------------------------------------===//
 // WMMA intrinsics
 class ROCDL_Wmma_IntrOp<string mnemonic, list<int> overloadedOperands,