llvm-project

History

[MLIR][Bufferization] Choose default memory space in tensor copy insertion (#88500 )

Tensor copy insertion currently uses memory_space = 0 when creating a
tensor copy using alloc_tensor. This memory space should instead be the
default memory space provided in bufferization options.

2024-04-12 17:56:46 +02:00

AllocationOpInterface.cpp

Revert "Revert "[mlir] Move AllocationOpInterface to Bufferize/IR/AllocationOpInterface.td.""

2021-11-23 10:49:26 +01:00

BufferDeallocationOpInterface.cpp

[ADT] Rename llvm::erase_value to llvm::erase (NFC) (#70156 )

2023-10-24 23:03:13 -07:00

BufferizableOpInterface.cpp

[MLIR][Bufferization] Choose default memory space in tensor copy insertion (#88500 )

2024-04-12 17:56:46 +02:00

BufferizationDialect.cpp

[mlir][bufferization] Ownership-based deallocation: Allow manual (de)allocs (#68648 )

2023-10-23 09:45:33 +09:00

BufferizationOps.cpp

[mlir][tensor] fix out-of-bound index in tensor.dim (#85901 )

2024-03-25 21:08:18 +08:00

BufferViewFlowOpInterface.cpp

[mlir][bufferization] Add BufferViewFlowOpInterface (#78718 )

2024-03-24 12:48:19 +09:00

CMakeLists.txt

[mlir][bufferization] Add BufferViewFlowOpInterface (#78718 )

2024-03-24 12:48:19 +09:00

UnstructuredControlFlow.cpp

[mlir][bufferization] Support unstructured control flow

2023-08-31 12:55:53 +02:00