[all-commits] [llvm/llvm-project] 8faf35: [mlir][linalg] Add scf.for loop peeling to codegen...

[Matthias Springer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 8faf35c0a5aa8069b02badc7d8c11147b9bfd720
      https://github.com/llvm/llvm-project/commit/8faf35c0a5aa8069b02badc7d8c11147b9bfd720
  Author: Matthias Springer <springerm at google.com>
  Date:   2021-09-14 (Tue, 14 Sep 2021)

  Changed paths:
    M mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h
    M mlir/lib/Dialect/Linalg/Transforms/Transforms.cpp
    M mlir/test/Dialect/Linalg/tile-and-pad-tensors.mlir
    A mlir/test/Dialect/Linalg/tile-and-peel-tensors.mlir
    M mlir/test/lib/Dialect/Linalg/TestLinalgTransforms.cpp

  Log Message:
  -----------
  [mlir][linalg] Add scf.for loop peeling to codegen strategy

Only scf.for loops are supported at the moment. linalg.tiled_loop support will be added in a subsequent commit.

Only static tensor sizes are supported. Loops for dynamic tensor sizes can be peeled, but the generated code is not optimal due to a missing canonicalization pattern.

Differential Revision: https://reviews.llvm.org/D109043