[all-commits] [llvm/llvm-project] d22df0: [mlir][sparse] refine insertion code

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d22df0ebba3f28700248c6de8a9d302628d0d2fb
      https://github.com/llvm/llvm-project/commit/d22df0ebba3f28700248c6de8a9d302628d0d2fb
  Author: Aart Bik <ajcbik at google.com>
  Date:   2022-10-18 (Tue, 18 Oct 2022)

  Changed paths:
    M mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorCodegen.cpp
    M mlir/test/Dialect/SparseTensor/codegen.mlir

  Log Message:
  -----------
  [mlir][sparse] refine insertion code

builds SSA cycle for compress insertion loop
adds casting on index mismatch during push_back

Reviewed By: Peiming

Differential Revision: https://reviews.llvm.org/D136186