[all-commits] [llvm/llvm-project] bcb698: [mlir][sparse][gpu] various cuSparse refinements

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: bcb698bfdc723cb5e626e61808933583287ad928
      https://github.com/llvm/llvm-project/commit/bcb698bfdc723cb5e626e61808933583287ad928
  Author: Aart Bik <ajcbik at google.com>
  Date:   2023-05-24 (Wed, 24 May 2023)

  Changed paths:
    M mlir/lib/Dialect/SparseTensor/Transforms/SparseGPUCodegen.cpp
    M mlir/lib/ExecutionEngine/CudaRuntimeWrappers.cpp
    M mlir/test/Dialect/SparseTensor/GPU/gpu_matmul_lib.mlir
    M mlir/test/Dialect/SparseTensor/GPU/gpu_matvec_lib.mlir

  Log Message:
  -----------
  [mlir][sparse][gpu] various cuSparse refinements

(1) keep all cuSparse ops on single stream without wait() in right order
(2) use more type precise memref types for COO
(3) use ToTensor on resulting memref (even though it folds away again)

Reviewed By: K-Wu

Differential Revision: https://reviews.llvm.org/D151404