Aart Bik 6a45339bac

[mlir][sparse] refine sparse fusion with empty tensors materialization (#66563) ...

This is a minor step towards deprecating bufferization.alloc_tensor().
It replaces the examples with tensor.empty() and adjusts the underlying
rewriting logic to prepare for this upcoming change.

2023-09-18 09:01:11 -07:00

..

BufferizableOpInterfaceImpl.cpp

[mlir][sparse] Better error handling when bufferizing sparse_tensor ops

2023-08-25 08:34:05 +02:00

CMakeLists.txt

[mlir][sparse] Make sparse_tensor::StorageLayout publicly available.

2023-05-18 20:29:46 +00:00

CodegenEnv.cpp

[mlir][sparse] Pass down constant coefficients of affine index expressions to LoopEmitter.

2023-08-30 18:44:50 +00:00

CodegenEnv.h

[mlir][sparse] Pass down constant coefficients of affine index expressions to LoopEmitter.

2023-08-30 18:44:50 +00:00

CodegenUtils.cpp

[mlir][sparse] Fix strict weak ordering in sorting

2023-08-22 17:15:10 -07:00

CodegenUtils.h

[mlir][sparse] supports sparse_tensor.pack on libgen path

2023-08-15 20:20:54 +00:00

LoopEmitter.cpp

[mlir] Use a range-based for loop (NFC)

2023-09-05 00:30:40 -07:00

LoopEmitter.h

[mlir][sparse] Support strided convolution on compressed level.

2023-08-30 19:37:50 +00:00

SparseBufferRewriting.cpp

[mlir][sparse] Modify the pivot selection method for quick sort.

2023-03-15 13:53:00 -07:00

SparseGPUCodegen.cpp

[mlir][sparse][gpu] minor code cleanup for sparse gpu ops

2023-08-14 15:08:57 -07:00

SparseStorageSpecifierToLLVM.cpp

[mlir][sparse] Make sparse_tensor::StorageLayout publicly available.

2023-05-18 20:29:46 +00:00

SparseTensorCodegen.cpp

[sparse] allow unpack op to return 0-ranked tensor type. (#66269)

2023-09-13 11:33:01 -07:00

SparseTensorConversion.cpp

[mlir][bufferization] Remove allow-return-allocs and create-deallocs pass options, remove bufferization.escape attribute (#66619)

2023-09-18 16:44:48 +02:00

SparseTensorDescriptor.cpp

[mlir][sparse] Make sparse_tensor::StorageLayout publicly available.

2023-05-18 20:29:46 +00:00

SparseTensorDescriptor.h

[mlir][sparse] extend unpack operation to unpack arbitrary encodings.

2023-05-23 22:34:01 +00:00

SparseTensorPasses.cpp

[sparse] allow unpack op to return 0-ranked tensor type. (#66269)

2023-09-13 11:33:01 -07:00

SparseTensorRewriting.cpp

[mlir][sparse] refine sparse fusion with empty tensors materialization (#66563)

2023-09-18 09:01:11 -07:00

SparseVectorization.cpp

[mlir][VectorType] Remove numScalableDims from the vector type

2023-06-28 13:53:45 +01:00

Sparsification.cpp

[mlir][sparse] Migrate more tests to use new syntax (#66443)

2023-09-14 23:19:57 +00:00

SparsificationAndBufferizationPass.cpp

[mlir][bufferization] Remove allow-return-allocs and create-deallocs pass options, remove bufferization.escape attribute (#66619)

2023-09-18 16:44:48 +02:00