[Mlir-commits] [mlir] [mlir][xegpu] Distribute three more convert_layout cases to lanes (PR #222693)

[llvmlistbot at llvm.org]

github-actions[bot] wrote:

<!--LLVM CODE FORMAT COMMENT: {clang-format}-->


:warning: C/C++ code formatter, clang-format found issues in your code. :warning:

<details>
<summary>
You can test this locally with the following command:
</summary>

``````````bash
git-clang-format --diff origin/main HEAD --extensions cpp -- mlir/lib/Dialect/XeGPU/Transforms/XeGPUSgToLaneDistribute.cpp --diff_from_common_commit
``````````

:warning:
The reproduction instructions above might return results for more than one PR
in a stack if you are using a stacked PR workflow. You can limit the results by
changing `origin/main` to the base branch/commit you want to compare against.
:warning:

</details>

<details>
<summary>
View the diff from clang-format here.
</summary>

``````````diff
diff --git a/mlir/lib/Dialect/XeGPU/Transforms/XeGPUSgToLaneDistribute.cpp b/mlir/lib/Dialect/XeGPU/Transforms/XeGPUSgToLaneDistribute.cpp
index 30d5eb270..aeab3217b 100644
--- a/mlir/lib/Dialect/XeGPU/Transforms/XeGPUSgToLaneDistribute.cpp
+++ b/mlir/lib/Dialect/XeGPU/Transforms/XeGPUSgToLaneDistribute.cpp
@@ -1870,11 +1870,11 @@ struct SgToLaneConvertLayout
 };
 
 /// Returns true if `layout` has rank 2, the default (row major) effective order
-/// [1, 0] and effective lane_data [1, 1], i.e. it maps the elements of the value
-/// to lanes one by one, without packing several of them into a lane. An unset
-/// lane_data is not accepted: `getEffectiveLaneDataAsInt` returns an empty
-/// vector for it, so layouts that are not lane level are rejected here. The
-/// effective lane_layout is deliberately left unconstrained: it is what the
+/// [1, 0] and effective lane_data [1, 1], i.e. it maps the elements of the
+/// value to lanes one by one, without packing several of them into a lane. An
+/// unset lane_data is not accepted: `getEffectiveLaneDataAsInt` returns an
+/// empty vector for it, so layouts that are not lane level are rejected here.
+/// The effective lane_layout is deliberately left unconstrained: it is what the
 /// conversions below redistribute.
 static bool hasDefaultOrderAndUnitLaneData(xegpu::DistributeLayoutAttr layout) {
   if (layout.getRank() != 2)

``````````

</details>


https://github.com/llvm/llvm-project/pull/222693