[all-commits] [llvm/llvm-project] 046922: [mlir][linalg] Add support for scalar input operands.

[Tobias Gysi via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 046922e1003795d67df89721e6b76c01b214d408
      https://github.com/llvm/llvm-project/commit/046922e1003795d67df89721e6b76c01b214d408
  Author: Tobias Gysi <gysit at google.com>
  Date:   2021-06-14 (Mon, 14 Jun 2021)

  Changed paths:
    M mlir/include/mlir/Dialect/Linalg/IR/LinalgBase.td
    M mlir/include/mlir/Dialect/Linalg/IR/LinalgInterfaces.td
    M mlir/include/mlir/Dialect/Linalg/IR/LinalgOps.td
    M mlir/include/mlir/Dialect/Linalg/IR/LinalgStructuredOps.td
    M mlir/lib/Dialect/Linalg/IR/LinalgInterfaces.cpp
    M mlir/lib/Dialect/Linalg/IR/LinalgOps.cpp
    M mlir/lib/Dialect/Linalg/Transforms/ComprehensiveBufferize.cpp
    M mlir/lib/Dialect/Linalg/Transforms/DropUnitDims.cpp
    M mlir/lib/Dialect/Linalg/Transforms/Fusion.cpp
    M mlir/lib/Dialect/Linalg/Transforms/Loops.cpp
    M mlir/lib/Dialect/Linalg/Transforms/Transforms.cpp
    M mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
    M mlir/lib/Dialect/SparseTensor/Transforms/Sparsification.cpp
    M mlir/test/Dialect/Linalg/drop-unit-extent-dims.mlir
    M mlir/test/Dialect/Linalg/fusion-tensor-pattern.mlir
    M mlir/test/Dialect/Linalg/fusion-tensor.mlir
    M mlir/test/Dialect/Linalg/invalid.mlir
    M mlir/test/Dialect/Linalg/loops.mlir
    M mlir/test/Dialect/Linalg/reshape_fusion.mlir
    M mlir/test/Dialect/Linalg/roundtrip.mlir
    M mlir/test/Dialect/Linalg/tile-and-pad-tensors.mlir
    M mlir/test/Dialect/Linalg/vectorization.mlir
    M mlir/test/lib/Dialect/Linalg/TestLinalgFusionTransforms.cpp
    M mlir/test/lib/Dialect/Linalg/TestLinalgTransforms.cpp

  Log Message:
  -----------
  [mlir][linalg] Add support for scalar input operands.

Up to now all structured op operands are assumed to be shaped. The patch relaxes this assumption and allows scalar input operands. In contrast to shaped operands scalar operands are not indexed and directly forwarded to the body of the operation. As all other operands, scalar operands are associated to an indexing map that in case of a scalar or a 0D-operand has an empty range.

We will use scalar operands as a replacement for the capture mechanism. In contrast to captures, the approach ensures we can generate the function signature from the operand list and it prevents outdated capture values in case a transformation updates only the capture operand but not the hidden body of a named operation.

Removing captures and updating existing operations such as linalg.fill is left for a later patch.

The patch depends on https://reviews.llvm.org/D103891 and https://reviews.llvm.org/D103890.

Differential Revision: https://reviews.llvm.org/D104109