[all-commits] [llvm/llvm-project] c1f0a1: [mlir][tensor][bufferize] Lower tensor.generate to...

[Matthias Springer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c1f0a15c65af3f9d2a140c4a73dcbfb3fcfc765d
      https://github.com/llvm/llvm-project/commit/c1f0a15c65af3f9d2a140c4a73dcbfb3fcfc765d
  Author: Matthias Springer <springerm at google.com>
  Date:   2022-10-27 (Thu, 27 Oct 2022)

  Changed paths:
    M mlir/lib/Dialect/Tensor/Transforms/BufferizableOpInterfaceImpl.cpp
    M mlir/lib/Dialect/Tensor/Transforms/CMakeLists.txt
    M mlir/test/Dialect/Tensor/bufferize.mlir
    M mlir/test/Dialect/Tensor/one-shot-bufferize.mlir
    M utils/bazel/llvm-project-overlay/mlir/BUILD.bazel

  Log Message:
  -----------
  [mlir][tensor][bufferize] Lower tensor.generate to linalg.map

There is no memref equivalent of tensor.generate. The purpose of this change is to avoid creating scf.parallel loops during bufferization.

Differential Revision: https://reviews.llvm.org/D136767