[all-commits] [llvm/llvm-project] 634e25: [mlir] Add special case for 0-D tensor when fusing...

[Evan Liu via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 634e25319e0e99affcb61cc9fba639c4d40cc420
      https://github.com/llvm/llvm-project/commit/634e25319e0e99affcb61cc9fba639c4d40cc420
  Author: Evan Liu <liuyievan at gmail.com>
  Date:   2025-03-11 (Tue, 11 Mar 2025)

  Changed paths:
    M mlir/lib/Dialect/Tensor/Transforms/ReshapePatterns.cpp
    M mlir/test/Dialect/Tensor/bubble-reshapes.mlir

  Log Message:
  -----------
  [mlir] Add special case for 0-D tensor when fusing expand from collapse (#130838)

One fusion pattern for collapse_shape -> expand_shape was added in
https://github.com/llvm/llvm-project/commit/a95ad2da36b6a996b05c79df6b385cd98bac286d,
however if the intermediate tensor between a collapse and expand is a
0-D tensor, then the `reassociation_map` for these two are special cases
and can't be generally fused in this function
`BubbleUpExpandThroughParallelCollapse`.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications