Doomhowl-Interactive/llvm-project
0
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity
Files
main
llvm-project/mlir/test/Dialect/SparseTensor
History
Vito Secona 871c9bb238 [mlir][SparseTensor] add numSymbols information to simplify affine expressions (#191649) 
Previously, the `translateShape` function hard-coded the `numSymbols`
parameter to 0. This makes the affine expression fail when the sparse
tensor encoding has symbols.

This PR fixes the issue by extracting and passing the `numSymbols`
information during translation. A regression test has also been added to
ensure this behavior remains supported.

Closes #191209
2026-04-20 09:56:53 -07:00
..
GPU
[mlir][sparse][gpu] fix sparse GPU codegen out buffer (#189221)
2026-04-10 16:22:12 -07:00
binary_valued.mlir
…
buffer_rewriting.mlir
…
canonicalize.mlir
…
codegen_buffer_initialization.mlir
…
codegen_invalid.mlir
…
codegen_sparse_alloc.mlir
…
codegen_to_llvm.mlir
…
codegen.mlir
…
constant_index_map.mlir
…
conversion_invalid.mlir
…
conversion.mlir
…
convert_dense2sparse.mlir
…
convert_sparse2dense.mlir
…
convert_sparse2sparse_element.mlir
…
convert_sparse2sparse.mlir
…
dense.mlir
…
encoding_with_symbols.mlir
[mlir][SparseTensor] add numSymbols information to simplify affine expressions (#191649)
2026-04-20 09:56:53 -07:00
external_after_codegen.mlir
[mlir][sparse] Fix crash in SparseAssembler when run after SparseTensorCodegen (#183896)
2026-03-05 12:27:09 +01:00
external_direct.mlir
…
external.mlir
…
fold.mlir
…
fuse_sparse_concat_with_extract_slice.mlir
…
fuse_sparse_convert_into_producer.mlir
…
fuse_sparse_pad_with_consumer.mlir
…
invalid_encoding.mlir
[mlir][sparse] Reject dense level after non-unique level in encoding verifier (#184157)
2026-03-03 12:42:49 +01:00
invalid.mlir
[mlir] Defer LoopLikeOpInterface type checks to RegionBranchOpInterface (#184116)
2026-03-06 15:43:00 +03:00
minipipeline_parallel.mlir
…
minipipeline_vector.mlir
…
no_lowering.mlir
…
one_shot_bufferize_invalid.mlir
…
one_shot_bufferize_tensor_copy_insertion.mlir
…
one_trip.mlir
…
pack_copy.mlir
…
pre_rewriting.mlir
…
rejected.mlir
…
rewriting_for_codegen.mlir
…
roundtrip_encoding.mlir
…
roundtrip.mlir
…
scf_1_N_conversion.mlir
…
semi_ring.mlir
…
sorted_coo.mlir
…
sparse_1d.mlir
…
sparse_2d.mlir
…
sparse_3d.mlir
…
sparse_affine.mlir
…
sparse_batch.mlir
…
sparse_broadcast.mlir
…
sparse_concat.mlir
…
sparse_conv_2d_slice_based.mlir
…
sparse_expand.mlir
…
sparse_extract_slice.mlir
…
sparse_fill_zero.mlir
…
sparse_foreach_rank0.mlir
[mlir][sparse] Fix crash in ForeachRewriter for rank-0 dense tensors (#183903)
2026-03-03 12:42:30 +01:00
sparse_foreach.mlir
…
sparse_fp_ops.mlir
…
sparse_fusion.mlir
…
sparse_index.mlir
…
sparse_int_ops.mlir
…
sparse_iteration_to_scf.mlir
…
sparse_itertion_licm.mlir
…
sparse_kernels_to_iterator.mlir
…
sparse_kernels.mlir
…
sparse_lower_col.mlir
…
sparse_lower_inplace.mlir
…
sparse_lower.mlir
…
sparse_matmul_codegen.mlir
…
sparse_matmul_one.mlir
…
sparse_nd.mlir
…
sparse_out.mlir
…
sparse_outbuf.mlir
…
sparse_pack.mlir
…
sparse_parallel_reduce.mlir
…
sparse_parallel.mlir
…
sparse_perm_lower.mlir
…
sparse_perm.mlir
…
sparse_reinterpret_map.mlir
…
sparse_relu.mlir
…
sparse_reshape.mlir
…
sparse_scalars.mlir
…
sparse_sddmm_org.mlir
…
sparse_sddmm.mlir
…
sparse_space_collapse.mlir
[mlir][sparse] Fix use-after-free crash in SparseSpaceCollapsePass (#184001)
2026-03-03 12:43:04 +01:00
sparse_storage.mlir
…
sparse_tensor_reshape.mlir
…
sparse_transpose.mlir
…
sparse_vector_chain.mlir
…
sparse_vector_concat.mlir
…
sparse_vector_index.mlir
…
sparse_vector_mv.mlir
…
sparse_vector_ops.mlir
…
sparse_vector_peeled.mlir
…
sparse_vector.mlir
…
specifier_to_llvm.mlir
…
spy_sddmm_bsr.mlir
…
spy_sddmm.mlir
[mlir][sparse] Fix crash in sparsification when unary/binary present block captures sparse tensor argument (#184597)
2026-03-05 12:50:13 +01:00
torch_linalg.mlir
…
transform-ops.mlir
…
unsparsifiable_dense_op.mlir
…
unused-tensor.mlir
…
vectorize_reduction.mlir
…