[Mlir-commits] [mlir] [mlir][xegpu] Remove chunk_size attribute; infer from types (PR #205122)

[Jianhui Li]

================
@@ -888,8 +875,9 @@ def XeGPU_StoreScatterOp : XeGPU_Op<"store", [MemoryEffects<[MemWrite]>, AnchorL
   ```
 
   Example 2 (Lane level):
-  Lane level IR only accepts the offsets variant. chunk_size can be inferred from value
-  type. In this example, chunk_size is 8.
+  Lane level IR only accepts the offsets variant. Each lane stores a contiguous
+  1D vector whose length is given by the value type; here each lane stores 8
+  elements.
----------------
Jianhui-Li wrote:

please make offsets/mask shape size as 8 to match the value.

https://github.com/llvm/llvm-project/pull/205122