[Mlir-commits] [mlir] [mlir][memref] Fold subview into nd-tensor descriptor (PR #88698)

[Oleksandr Alex Zinenko]

================
@@ -22,6 +22,7 @@
 #include "mlir/Dialect/NVGPU/IR/NVGPUDialect.h"
 #include "mlir/Dialect/Utils/IndexingUtils.h"
 #include "mlir/Dialect/Vector/IR/VectorOps.h"
+#include "mlir/Dialect/XeGPU/IR/XeGPU.h"
----------------
ftynse wrote:

We shouldn't have a dependency from the generic dialect (memref) on the target-specific dialect (xegpu).

https://github.com/llvm/llvm-project/pull/88698