[llvm] [mlir] [MLIR][AMDGPU] Adding dynamic size check to avoid subword buffer load (PR #135014)

[via llvm-commits]

================
@@ -9,12 +9,21 @@
 #include "mlir/Dialect/AMDGPU/Transforms/Passes.h"
 
 #include "mlir/Dialect/AMDGPU/IR/AMDGPUDialect.h"
----------------
Max191 wrote:

nit: Are all of these new includes necessary?

https://github.com/llvm/llvm-project/pull/135014