[PATCH] D146724: [mlir][MemRef] Add patterns to extract address computations

[Quentin Colombet via Phabricator via llvm-commits]

qcolombet updated this revision to Diff 508029.
qcolombet added a comment.

- Add support for vector.transfer_read/write
- Move the populate function in its own header (we'll want to move others as well in an NFC patch)
- Fix the dropping of the nontemporal flag (and add a test for that)
- Refactor getSrcMemRef to not choke on tensor type
- Refactor getViewSizeForEachDim to use the same implementation for ldmatrix, vector.transfer_read/write
- Add tests for vector.transfer_read/write


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D146724/new/

https://reviews.llvm.org/D146724

Files:
  mlir/include/mlir/Dialect/MemRef/Transforms/Transforms.h
  mlir/lib/Dialect/MemRef/Transforms/CMakeLists.txt
  mlir/lib/Dialect/MemRef/Transforms/ExtractAddressComputations.cpp
  mlir/test/Dialect/MemRef/extract-address-computations.mlir
  mlir/test/lib/Dialect/MemRef/CMakeLists.txt
  mlir/test/lib/Dialect/MemRef/TestExtractAddressComputations.cpp
  mlir/tools/mlir-opt/mlir-opt.cpp
  utils/bazel/llvm-project-overlay/mlir/BUILD.bazel

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D146724.508029.patch
Type: text/x-patch
Size: 37876 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230324/3017863e/attachment-0001.bin>