[all-commits] [llvm/llvm-project] a2c9d4: [mlir][sparse] Introduce proper sparsification passes

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a2c9d4bb04a91c947d17672acbda56fae09173be
      https://github.com/llvm/llvm-project/commit/a2c9d4bb04a91c947d17672acbda56fae09173be
  Author: Aart Bik <ajcbik at google.com>
  Date:   2021-05-04 (Tue, 04 May 2021)

  Changed paths:
    M mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h
    M mlir/include/mlir/Dialect/SparseTensor/CMakeLists.txt
    A mlir/include/mlir/Dialect/SparseTensor/Transforms/CMakeLists.txt
    A mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.h
    A mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.td
    R mlir/include/mlir/Dialect/SparseTensor/Transforms/Transforms.h
    M mlir/include/mlir/InitAllPasses.h
    M mlir/lib/Dialect/Linalg/Transforms/CMakeLists.txt
    R mlir/lib/Dialect/Linalg/Transforms/Sparsification.cpp
    M mlir/lib/Dialect/SparseTensor/Transforms/CMakeLists.txt
    A mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorConversion.cpp
    R mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorLowering.cpp
    A mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorPasses.cpp
    A mlir/lib/Dialect/SparseTensor/Transforms/Sparsification.cpp
    R mlir/test/Dialect/Linalg/sparse_1d.mlir
    R mlir/test/Dialect/Linalg/sparse_2d.mlir
    R mlir/test/Dialect/Linalg/sparse_3d.mlir
    R mlir/test/Dialect/Linalg/sparse_invalid.mlir
    R mlir/test/Dialect/Linalg/sparse_lower.mlir
    R mlir/test/Dialect/Linalg/sparse_nd.mlir
    R mlir/test/Dialect/Linalg/sparse_parallel.mlir
    R mlir/test/Dialect/Linalg/sparse_storage.mlir
    R mlir/test/Dialect/Linalg/sparse_vector.mlir
    A mlir/test/Dialect/SparseTensor/conversion.mlir
    R mlir/test/Dialect/SparseTensor/lowering.mlir
    A mlir/test/Dialect/SparseTensor/sparse_1d.mlir
    A mlir/test/Dialect/SparseTensor/sparse_2d.mlir
    A mlir/test/Dialect/SparseTensor/sparse_3d.mlir
    A mlir/test/Dialect/SparseTensor/sparse_invalid.mlir
    A mlir/test/Dialect/SparseTensor/sparse_lower.mlir
    A mlir/test/Dialect/SparseTensor/sparse_nd.mlir
    A mlir/test/Dialect/SparseTensor/sparse_parallel.mlir
    A mlir/test/Dialect/SparseTensor/sparse_storage.mlir
    A mlir/test/Dialect/SparseTensor/sparse_vector.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matvec.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sampled_matmul.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum.mlir
    M mlir/test/lib/Transforms/CMakeLists.txt
    R mlir/test/lib/Transforms/TestSparsification.cpp
    M mlir/tools/mlir-opt/mlir-opt.cpp

  Log Message:
  -----------
  [mlir][sparse] Introduce proper sparsification passes

This revision migrates more code from Linalg into the new permanent home of
SparseTensor. It replaces the test passes with proper compiler passes.

NOTE: the actual removal of the last glue and clutter in Linalg will follow

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D101811