[all-commits] [llvm/llvm-project] a61a9a: [mlir][sparse] first end-to-end matmul with codegen

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a61a9a700a35ad0def066acd030d98f19c81cabd
      https://github.com/llvm/llvm-project/commit/a61a9a700a35ad0def066acd030d98f19c81cabd
  Author: Aart Bik <ajcbik at google.com>
  Date:   2022-11-09 (Wed, 09 Nov 2022)

  Changed paths:
    M mlir/lib/Dialect/SparseTensor/Transforms/CodegenUtils.cpp
    M mlir/lib/Dialect/SparseTensor/Transforms/CodegenUtils.h
    M mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorConversion.cpp
    M mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorRewriting.cpp
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matmul.mlir

  Log Message:
  -----------
  [mlir][sparse] first end-to-end matmul with codegen

(1) also fixes memory leak in sparse2dense rewriting
(2) still needs fix in dense2sparse by skipping zeros

Reviewed By: wrengr

Differential Revision: https://reviews.llvm.org/D137736