[all-commits] [llvm/llvm-project] 41a07e: [mlir][sparse] recognize NVidia 2:4 type for matmu...

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 41a07e668c29e219ed2f26d61da8b6b3295ff967
      https://github.com/llvm/llvm-project/commit/41a07e668c29e219ed2f26d61da8b6b3295ff967
  Author: Aart Bik <39774503+aartbik at users.noreply.github.com>
  Date:   2024-01-02 (Tue, 02 Jan 2024)

  Changed paths:
    M mlir/lib/Dialect/SparseTensor/Transforms/SparseGPUCodegen.cpp
    M mlir/lib/ExecutionEngine/CudaRuntimeWrappers.cpp
    A mlir/test/Dialect/SparseTensor/GPU/gpu_matmul24_lib.mlir
    R mlir/test/Dialect/SparseTensor/GPU/gpu_matmul_lib_2to4.mlir
    A mlir/test/Integration/Dialect/SparseTensor/GPU/CUDA/sm80-lt/sparse-matmul-2-4-hand.mlir
    R mlir/test/Integration/Dialect/SparseTensor/GPU/CUDA/sm80-lt/sparse-matmul-2-4-lib-from-linalg.mlir
    M mlir/test/Integration/Dialect/SparseTensor/GPU/CUDA/sm80-lt/sparse-matmul-2-4-lib.mlir
    M mlir/test/Integration/Dialect/SparseTensor/GPU/CUDA/sm80-lt/sparse-matmul-2-4-prune.mlir

  Log Message:
  -----------
  [mlir][sparse] recognize NVidia 2:4 type for matmul (#76758)

This removes the temporary DENSE24 attribute and replaces it with proper
recognition of dense to 24 conversion. The compressionh will be
performed on the device prior to performing the matrix mult. Note that
we no longer need to start with the linalg version, we can lift this to
the proper named linalg op. Also renames some files into more consistent
names.