[PATCH] D74342: [mlir] Add MemRef filter to affine data copy optimization

[Uday Bondhugula via Phabricator via llvm-commits]

bondhugula accepted this revision.
bondhugula added a comment.
This revision is now accepted and ready to land.

This looks great to me! Just a few minor comments.



================
Comment at: mlir/include/mlir/Transforms/LoopUtils.h:18
 
+#include "mlir/IR/AffineMap.h"
 #include "mlir/IR/Block.h"
----------------
I think we shouldn't need this. 


================
Comment at: mlir/include/mlir/Transforms/LoopUtils.h:175
 /// position), all of the fast memory capacity is assumed to be available for
 /// processing this block range.
 uint64_t affineDataCopyGenerate(Block::iterator begin, Block::iterator end,
----------------
Doc comment update needed for filter memref.


================
Comment at: mlir/test/lib/Transforms/TestAffineDataCopy.cpp:9
+//
+// This file implements a pass to test affine data copy utility functions.
+//
----------------
-> "utility functions and options".


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D74342/new/

https://reviews.llvm.org/D74342