Aart Bik 6607fdf749 [mlir][sparse] add memSizes array to sparse storage format ...

Rationale:
For every dynamic memref (memref<?xtype>), the stored size really
indicates the capacity and the entry in the memSizes indicates
the actual size. This allows us to use memref's as "vectors".

Reviewed By: Peiming

Differential Revision: https://reviews.llvm.org/D133724

2022-09-12 14:04:01 -07:00

..

BufferizableOpInterfaceImpl.cpp

[mlir][bufferization][NFC] Move sparse_tensor.release to bufferization dialect

2022-07-19 09:18:19 +02:00

CMakeLists.txt

[mlir][sparse] Refactoring: remove dependence on tuple type when lowering sparse tensors.

2022-09-07 17:53:48 +00:00

CodegenUtils.cpp

[mlir][sparse] add more dimension level types and properties

2022-08-30 10:37:49 -07:00

CodegenUtils.h

[mlir][sparse] add support for complex zero/one building

2022-05-20 08:53:30 -07:00

DenseBufferizationPass.cpp

[mlir] Remove redundant member initialization (NFC)

2022-08-14 12:51:59 -07:00

SparseTensorCodegen.cpp

[mlir][sparse] add memSizes array to sparse storage format

2022-09-12 14:04:01 -07:00

SparseTensorConversion.cpp

[mlir][sparse] Avoid generating DimOp in conversion passes.

2022-09-09 18:08:05 +00:00

SparseTensorPasses.cpp

[mlir][sparse] Add new option (enable-runtime-library) to sparse compiler pipeline

2022-09-09 20:54:47 +00:00

SparseTensorRewriting.cpp

[mlir][sparse] Add new option (enable-runtime-library) to sparse compiler pipeline

2022-09-09 20:54:47 +00:00

Sparsification.cpp

[mlir][sparse] properly record dimension level type and properties

2022-09-12 09:59:53 -07:00