[all-commits] [llvm/llvm-project] d2e787: [mlir][sparse][tensor] replace bufferization with ...

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d2e787d5d7ee49a0a77a6ca88b020e0297591790
      https://github.com/llvm/llvm-project/commit/d2e787d5d7ee49a0a77a6ca88b020e0297591790
  Author: Aart Bik <39774503+aartbik at users.noreply.github.com>
  Date:   2023-09-15 (Fri, 15 Sep 2023)

  Changed paths:
    M mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_f16.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/dual_sparse_conv_2d.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_abs.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_binary.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_cmp.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_codegen_dim.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex32.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex64.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex_ops.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_1d_nwc_wcf.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_2d.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_2d_nchw_fchw.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_2d_nhwc_hwcf.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_3d.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_3d_ndhwc_dhwcf.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_dot.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_expand.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_filter_conv2d.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_index.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_index_dense.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_insert_1d.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_insert_2d.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_insert_3d.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matmul.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matmul_slice.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matrix_ops.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_mult_elt.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_reduction.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_pooling_nhwc.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_re_im.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reduce_custom.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reduce_custom_prod.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sampled_mm_fusion.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_scf_nested.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_select.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_semiring_select.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sign.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_strided_conv_2d_nhwc_hwcf.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_c32.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_tensor_mul.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_tensor_ops.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_transpose.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_transpose_coo.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_unary.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_vector_ops.mlir
    M mlir/test/Integration/Dialect/SparseTensor/GPU/CUDA/sparse-gemm-lib.mlir

  Log Message:
  -----------
  [mlir][sparse][tensor] replace bufferization with empty tensor (#66450)

Rationale:
    A bufferization.alloc_tensor can be directly replaced
    with tensor.empty since these are more or less semantically
    equivalent. The latter is considered a bit more "pure"
    with respect to SSA semantics.