[Mlir-commits] [mlir] [MLIR][XeGPU] Add Layout Propagation support for multi-reduction/reduction op with scalar result (PR #189133)

[Artem Kroviakov]

================
@@ -546,6 +548,38 @@ xegpu::SliceAttr xegpu::setupMultiReductionResultLayout(
                                DenseI64ArrayAttr::get(context, reductionDims));
 }
 
+/// Sets up layout for Reduction operations by creating a SliceAttr for the
+/// result.
+xegpu::SliceAttr
+xegpu::setupReductionResultLayout(xegpu::LayoutKind layoutKind,
+                                  VectorType srcVecTy,
+                                  const xegpu::uArch::uArch *uArch) {
+
+  auto srcShape = srcVecTy.getShape();
+  auto context = srcVecTy.getContext();
+  auto subgroupSize = uArch->getSubgroupSize();
+  xegpu::LayoutAttr srcLayout;
+
+  if (layoutKind == xegpu::LayoutKind::Subgroup) {
+    assert(true &&
+           "subgroup layout assignment not supported for insertStridedSlice.");
+  } else if (layoutKind == xegpu::LayoutKind::InstData) {
+    assert(true &&
+           "instData layout assignment not supported for insertStridedSlice.");
----------------
akroviakov wrote:

Perhaps 
```suggestion
           "instData layout assignment not supported (op is not expected at this level).");
```
would make it clearer.

https://github.com/llvm/llvm-project/pull/189133