update doc

Author: chencha3

mlir/include/mlir/Dialect/XeGPU/IR/XeGPUAttrs.td

@@ -202,9 +202,9 @@ def XeGPU_LayoutAttr : XeGPUAttr<"Layout", "layout"> {
       ```mlir
       #xegpu.layout<inst_data = [8, 16], lane_layout = [2, 8], lane_data = [2, 2]>
       ```
-      In this example, the original problem size is divided into smaller subproblems of size [8, 16],
-      which are further distributed across 16 work-items organized as [[0, 1, 2, ..., 7], [8, 9, ..., 15]].
-      Each work-item is assigned a contiguous 2x2 block.
+      In this example, the original problem size is partitioned into smaller subproblems of dimensions [8, 16],
+      which are then distributed among 16 work-items arranged as [[0, 1, 2, ..., 7], [8, 9, ..., 15]]. Each
+      work-item is assigned four 2x2 blocks in a round-robin manner.
 
       4. Workgroup level layout:
       ```mlir

mlir/lib/Dialect/XeGPU/IR/XeGPUOps.cpp

@@ -105,6 +105,12 @@ isArgShapesValid(TensorDescType tdescTy, VectorType valueTy,
                    << " for tensor descriptor " << tdescTy;
 }
 
+// Checks if the given shape is evenly distributed based on the layout
+// and data factors provided by the LayoutAttr. The function ensures that
+// each dimension of the shape can be evenly divided by the corresponding
+// data factor, and the resulting quotient can be evenly divided by the
+// layout factor. Returns `true` if the shape is evenly distributed,
+// otherwise `false`.
 static bool isEvenDistributed(llvm::ArrayRef<int64_t> shape,
                               xegpu::LayoutAttr attr) {
   assert(attr && "Layout attribute is missing.");
@@ -121,7 +127,6 @@ static bool isEvenDistributed(llvm::ArrayRef<int64_t> shape,
   }
   for (auto [dimSize, dataFactor, layoutFactor] :
        llvm::zip_equal(shape, data, layout)) {
-    // check dimSize % (dataFactor * layoutFactor) != 0
     if (dimSize % dataFactor != 0 || (dimSize / dataFactor) % layoutFactor != 0)
       return false;
   }