[all-commits] [llvm/llvm-project] 1dce51: [mlir] Add TensorToLinalgPass

[Tres via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 1dce51b88865120f96dfd697c852742d8eee988b
      https://github.com/llvm/llvm-project/commit/1dce51b88865120f96dfd697c852742d8eee988b
  Author: Tres Popp <tpopp at google.com>
  Date:   2022-05-13 (Fri, 13 May 2022)

  Changed paths:
    M mlir/include/mlir/Conversion/Passes.h
    M mlir/include/mlir/Conversion/Passes.td
    A mlir/include/mlir/Conversion/TensorToLinalg/TensorToLinalg.h
    A mlir/include/mlir/Conversion/TensorToLinalg/TensorToLinalgPass.h
    M mlir/lib/Conversion/CMakeLists.txt
    M mlir/lib/Conversion/PassDetail.h
    A mlir/lib/Conversion/TensorToLinalg/CMakeLists.txt
    A mlir/lib/Conversion/TensorToLinalg/TensorToLinalg.cpp
    A mlir/lib/Conversion/TensorToLinalg/TensorToLinalgPass.cpp
    A mlir/test/Conversion/TensorToLinalg/tensor-ops-to-linalg.mlir
    M utils/bazel/llvm-project-overlay/mlir/BUILD.bazel

  Log Message:
  -----------
  [mlir] Add TensorToLinalgPass

This pass is to handle computationally complex operations like
tensor.pad which are not simply lowered to the exact same operation in
the memref dialect.

Differential Revision: https://reviews.llvm.org/D125384