[all-commits] [llvm/llvm-project] 2848f6: [mlir] Set top-down traversal for LinalgElementwis...

[Tres via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 2848f6966ea35a1e8bdf1668ee4ae8fb0170235c
      https://github.com/llvm/llvm-project/commit/2848f6966ea35a1e8bdf1668ee4ae8fb0170235c
  Author: Tres Popp <tpopp at google.com>
  Date:   2021-08-16 (Mon, 16 Aug 2021)

  Changed paths:
    M mlir/lib/Dialect/Linalg/Transforms/ElementwiseOpFusion.cpp

  Log Message:
  -----------
  [mlir] Set top-down traversal for LinalgElementwiseOpFusion

The primary pattern for this pass clones many operations from producers
to consumers. Doing this top down prevents duplicated work when a
producer has multiple consumers, if it also is consuming another
linalg.generic.

As an example, a chain of ~2600 generics that are fused into ~70
generics was resulting in 16255 pattern invocations. This took 14
seconds on one machine but takes only 0.3 seconds with top-down
traversal.

Differential Revision: https://reviews.llvm.org/D107818