Aart Bik 0e34dbb4f4

[mlir][sparse] fix bug with all-dense assembler (#108615) ...

When only all-dense "sparse" tensors occur in a function prototype, the
assembler would skip the method conversion purely based on input/output
counts. It should rewrite based on the presence of any annotation,
however.

2024-09-13 17:24:48 -07:00

..

Utils

[mlir][sparse] partially support lowering sparse coiteration loops to scf.while/for. (#105565)

2024-08-23 10:47:44 -07:00

BufferizableOpInterfaceImpl.cpp

[mlir][sparse_tensor] Implement bufferization interface for foreach (#85183)

2024-03-15 13:28:09 +09:00

CMakeLists.txt

Reapply "[mlir] NFC: fix dependence of (Tensor|Linalg|MemRef|Complex) dialects on LLVM Dialect and LLVM Core in CMake build (#104832)" (#105703)

2024-08-28 22:34:14 -06:00

SparseAssembler.cpp

[mlir][sparse] fix bug with all-dense assembler (#108615)

2024-09-13 17:24:48 -07:00

SparseBufferRewriting.cpp

[mlir] Construct SmallVector with ArrayRef (NFC) (#101896)

2024-08-04 11:43:05 -07:00

SparseGPUCodegen.cpp

[mlir][sparse] use a consistent order between [dis]assembleOp and sto… (#84079)

2024-03-06 09:57:41 -08:00

SparseIterationToScf.cpp

[mlir][sparse] unify block arguments order between iterate/coiterate operations. (#105567)

2024-08-23 14:49:00 -07:00

SparseReinterpretMap.cpp

Use llvm::less_first (NFC) (#94136)

2024-06-02 07:45:50 -07:00

SparseSpaceCollapse.cpp

[mlir][sparse] introduce sparse_tensor.coiterate operation. (#101100)

2024-07-31 15:14:27 -07:00

SparseStorageSpecifierToLLVM.cpp

[mlir][sparse] refactor utilities into transform/utils dir (#75250)

2023-12-12 15:34:31 -08:00

SparseTensorCodegen.cpp

[mlir][sparse] support 'batch' dimensions in sparse_tensor.print (#91411)

2024-05-07 19:01:36 -07:00

SparseTensorConversion.cpp

[mlir][sparse] allow for direct-out passing of sparse tensor buffers (#88327)

2024-04-11 10:07:24 -07:00

SparseTensorPasses.cpp

[mlir][sparse] implement lowering rules for ExtractIterSpaceOp. (#89143)

2024-06-12 10:49:12 -07:00

SparseTensorRewriting.cpp

[mlir][sparse] support sparsification to coiterate operations. (#102546)

2024-08-20 11:13:38 -07:00

SparseVectorization.cpp

[mlir] Construct SmallVector with ArrayRef (NFC) (#101896)

2024-08-04 11:43:05 -07:00

Sparsification.cpp

[mlir][sparse] support sparsification to coiterate operations. (#102546)

2024-08-20 11:13:38 -07:00

SparsificationAndBufferizationPass.cpp

[mlir][sparse] add parallelization options to mini pipeline (#104233)

2024-08-30 17:47:37 -04:00

StageSparseOperations.cpp

[mlir][sparse] best effort finalization of escaping empty sparse tensors (#85482)

2024-03-15 16:43:09 -07:00