[Mlir-commits] [mlir] [MLIR][XeGPU] XeVM lowering support for load_matrix/store_matrix (PR #162780)

[Adam Siemieniuk]

================
@@ -1298,14 +1298,16 @@ def XeGPU_CreateMemDescOp: XeGPU_Op<"create_mem_desc", [Pure,
 }
 
 def XeGPU_LoadMatrixOp: XeGPU_Op<"load_matrix", [MemoryEffects<[MemRead]>,
-                              AllElementTypesMatch<["mem_desc", "res"]>,
-                              AllRanksMatch<["mem_desc", "res"]>]>  {
+                              AllElementTypesMatch<["mem_desc", "res"]>]>  {
   let arguments = (ins XeGPU_MemDesc:$mem_desc,
     Variadic<Index>: $offsets,
     DenseI64ArrayAttr: $const_offsets,
+    OptionalAttr<I32Attr>:$vec_length,
+    OptionalAttr<MatrixAccessDirectionAttr>:$vec_direction,
+    OptionalAttr<UnitAttr>:$subgroup_block_io,
----------------
adam-smnk wrote:

Whose responsibility will it be to assign this option?
Can't rewrite pick the best/suitable lowering target?

https://github.com/llvm/llvm-project/pull/162780