[Mlir-commits] [mlir] [mlir][xegpu] Add definitons of MatrixDescType and related ops. (PR #153273)

[Jianhui Li]

================
@@ -1101,4 +1101,149 @@ def XeGPU_ConvertLayoutOp: XeGPU_Op<"convert_layout", [Pure, AllTypesMatch<["sou
     let hasCanonicalizer = 1;
 }
 
+def isSharedPred : CPred<"isSharedMemory(llvm::cast<mlir::MemRefType>($_self))">;
+class StaticShared1DMemRefOf<list<Type> allowedTypes> :
+  ConfinedType<MemRefRankOf<allowedTypes, [1]>, [HasStaticShapePred, isSharedPred],
+     "statically shaped " # MemRefOf<allowedTypes>.summary # " for shared memory",
+     "mlir::MemRefType">;
+
+class SizeInBits<string name> :
+  StrFunc<"llvm::cast<mlir::ShapedType>($" # name # ".getType()).getNumElements()"
+          "*llvm::cast<mlir::ShapedType>($" # name # ".getType()).getElementTypeBitWidth()">;
+class AllMemSizesMatch<list<string> names> :
+    AllMatchSameOperatorTrait<names, SizeInBits<"_self">.result,
+                              "size in bits">;
+
+def XeGPU_CreateMatrixDescOp: XeGPU_Op<"create_matrix_desc", [Pure,
+      AllMemSizesMatch<["source", "matrix_desc"]>]>  {
----------------
Jianhui-Li wrote:

This operation takes a memory buffer (1D int8 memref with no strides) and create a structured representation of the share local memory as matrix_desc. So I don't expect "AllMemSizeMatch" here. 

https://github.com/llvm/llvm-project/pull/153273