[all-commits] [llvm/llvm-project] ae76fa: [mlir][sparse] sparse transpose operation

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ae76fafc3f1671d619f0e6c2f42458616697c8bc
      https://github.com/llvm/llvm-project/commit/ae76fafc3f1671d619f0e6c2f42458616697c8bc
  Author: Aart Bik <ajcbik at google.com>
  Date:   2022-02-15 (Tue, 15 Feb 2022)

  Changed paths:
    A mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_transpose.mlir

  Log Message:
  -----------
  [mlir][sparse] sparse transpose operation

This test shows that when access patterns do not match (e.g. transposing
a row-wise sparse matrix into another row-wise sparse matrix), a conversion
operation in between can enable codegen (i.e. avoid cycle in iteration graph).

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D119864