torch-mlir/lib/Conversion
Ramiro Leal-Cavazos 51d4d55f8a
Add support for multi-dim input to `index_put_impl` (#722)
This commit adds support for multi-dimensional tensors as input to the
`_index_put_impl_` op. The support was to some degree already there,
since `ScatterOp` already supports multi-dimensional tensors. This
commit also adds a bit more error checking to `index_put` and
refactors the code for creating `ScatterOp`s to mimic the way one
would make a `Linalg::GenericOp`.
2022-03-31 09:27:21 -07:00
..
TorchToLinalg [MLIR][TORCH] Add E2E support for aten.new_empty op 2022-03-30 13:21:01 +05:30
TorchToSCF Bump LLVM at 8361c5da30588d3d4a48eae648f53be1feb5cfad 2022-03-18 13:16:14 -04:00
TorchToStd [LINALG] Add decomposition of `aten.dropout` op 2022-03-22 13:14:49 +05:30
TorchToTMTensor Add support for multi-dim input to `index_put_impl` (#722) 2022-03-31 09:27:21 -07:00
TorchToTosa tosa] Support for Aten[Gelu|GeluBackward] ops (#720) 2022-03-30 17:00:55 -07:00
Utils [MLIR][TORCH] Move common helper functions to Utils.cpp 2022-03-08 22:52:34 +05:30
CMakeLists.txt [MLIR][TORCH] Add TorchToTMTensor pass 2022-03-08 22:52:34 +05:30
PassDetail.h Dual license the torch-mlir project. 2021-10-01 10:46:08 -07:00
Passes.cpp [MLIR][TORCH] Add TorchToTMTensor pass 2022-03-08 22:52:34 +05:30