[Mlir-commits] [mlir] [AMDGPU] fold memref.subview/expand_shape/collapse_shape into amdgpu.gather_to_lds for DST operand (PR #152277)

[Alan Li]

================
@@ -12,6 +12,7 @@
 #include "mlir/Dialect/Affine/ViewLikeInterfaceUtils.h"
 #include "mlir/Dialect/MemRef/IR/MemRef.h"
 #include "mlir/Dialect/MemRef/Utils/MemRefUtils.h"
+#include "mlir/IR/ValueRange.h"
----------------
lialan wrote:

nit: probably not need this, vscode sometimes add unnecessary 

https://github.com/llvm/llvm-project/pull/152277