THU-DSP-LAB
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
2
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity
llvm-project/mlir/test/Integration/Dialect/SparseTensor/CPU
History
wren romano 2af2e4dbb7 [mlir][sparse] Breaking up openSparseTensor to better support non-permutations 
This commit updates how the `SparseTensorConversion` pass handles `NewOp`.  It breaks up the underlying `openSparseTensor` function into two parts (`SparseTensorReader::create` and `SparseTensorReader::readSparseTensor`) so that the pass can inject code for constructing `lvlSizes` between those two parts.  Migrating the construction of `lvlSizes` out of the runtime and into the pass is a necessary first step toward fully supporting non-permutations.  (The alternative would be for the pass to generate a `FuncOp` for performing the construction and then passing that to the runtime; which doesn't seem to have any benefits over the design of this commit.)  And since the pass now generates the code to call these two functions, this change also removes the `Action::kFromFile` value from the enum used by `_mlir_ciface_newSparseTensor`.

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D138363
 		2022-12-02 11:10:57 -08:00
..
concatenate.mlir [mlir][sparse] Improve concatenate operator rewrite for annotated all dense dimensions results. 2022-11-29 12:25:52 -08:00
dense_output.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
dense_output_bf16.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
dense_output_f16.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
lit.local.cfg [mlir][sparse] add a "release" operation to sparse tensor dialect 2021-10-05 09:35:59 -07:00
sparse_abs.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_binary.mlir [mlir][NFC] Remove trailing whitespaces from `*.td` and `*.mlir` files. 2022-11-28 15:26:30 -08:00
sparse_cast.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_codegen_dim.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_codegen_foreach.mlir [mlir][NFC] Remove trailing whitespaces from `*.td` and `*.mlir` files. 2022-11-28 15:26:30 -08:00
sparse_complex32.mlir [mlir][sparse] Make three integration tests run with the codegen path. 2022-11-17 13:22:04 -08:00
sparse_complex64.mlir [mlir][sparse] Make three integration tests run with the codegen path. 2022-11-17 13:22:04 -08:00
sparse_complex_ops.mlir [mlir][sparse] fix crash on sparse_tensor.foreach operation on tensors with complex<T> elements. 2022-11-17 19:36:15 +00:00
sparse_constant_to_sparse_tensor.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_conv_1d_nwc_wcf.mlir [mlir][NFC] Remove trailing whitespaces from `*.td` and `*.mlir` files. 2022-11-28 15:26:30 -08:00
sparse_conv_2d.mlir [mlir][NFC] Remove trailing whitespaces from `*.td` and `*.mlir` files. 2022-11-28 15:26:30 -08:00
sparse_conv_2d_nhwc_hwcf.mlir [mlir][NFC] Remove trailing whitespaces from `*.td` and `*.mlir` files. 2022-11-28 15:26:30 -08:00
sparse_conv_3d.mlir [mlir][NFC] Remove trailing whitespaces from `*.td` and `*.mlir` files. 2022-11-28 15:26:30 -08:00
sparse_conv_3d_ndhwc_dhwcf.mlir [mlir][NFC] Remove trailing whitespaces from `*.td` and `*.mlir` files. 2022-11-28 15:26:30 -08:00
sparse_conversion.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_conversion_dyn.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_conversion_ptr.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_conversion_sparse2dense.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_conversion_sparse2sparse.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_dot.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_expand.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_file_io.mlir [mlir][sparse] Breaking up openSparseTensor to better support non-permutations 2022-12-02 11:10:57 -08:00
sparse_filter_conv2d.mlir [mlir][NFC] Remove trailing whitespaces from `*.td` and `*.mlir` files. 2022-11-28 15:26:30 -08:00
sparse_flatten.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_index.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_index_dense.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_insert_1d.mlir [mlir][sparse] first general insertion implementation with pure codegen 2022-11-08 13:10:05 -08:00
sparse_insert_2d.mlir [mlir][sparse] first general insertion implementation with pure codegen 2022-11-08 13:10:05 -08:00
sparse_insert_3d.mlir [mlir][sparse] 3-dimensional sparse tensor insertion test 2022-11-08 14:49:31 -08:00
sparse_matmul.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_matrix_ops.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_matvec.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_mttkrp.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_out_mult_elt.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_out_reduction.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_out_simple.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_quantized_matmul.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_re_im.mlir [mlir][sparse] Make three integration tests run with the codegen path. 2022-11-17 13:22:04 -08:00
sparse_reduce_custom.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_reductions.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_reshape.mlir [mlir][NFC] Remove trailing whitespaces from `*.td` and `*.mlir` files. 2022-11-28 15:26:30 -08:00
sparse_rewrite_push_back.mlir [mlir][sparse] Implement the rewrite for sparse_tensor.push_back a value n times. 2022-10-31 08:19:12 -07:00
sparse_rewrite_sort.mlir [mlir][sparse] Improve the non-stable sort implementation. 2022-11-07 07:38:42 -08:00
sparse_rewrite_sort_coo.mlir [mlir][sparse] Add rewriting rules for sparse_tensor.sort_coo. 2022-11-14 08:48:53 -08:00
sparse_sampled_matmul.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_sampled_mm_fusion.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_scale.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_scf_nested.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_select.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_sign.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_sorted_coo.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_spmm.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_storage.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_sum.mlir [mlir][sparse] Add expand_symmetry attribute to the new operator. 2022-11-23 16:32:15 -08:00
sparse_sum_bf16.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_sum_c32.mlir [mlir][sparse] Add expand_symmetry attribute to the new operator. 2022-11-23 16:32:15 -08:00
sparse_sum_f16.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_tanh.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_tensor_mul.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_tensor_ops.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_transpose.mlir [mlir][sparse] Run an integration test with codegen. 2022-11-17 09:59:53 -08:00
sparse_unary.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00
sparse_vector_ops.mlir [mlir][sparse] Make integration tests run on both library and codegen pathes. 2022-11-16 12:01:14 -08:00