llvm
/
torch-mlir
mirror of https://github.com/llvm/torch-mlir
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
torch-mlir/lib/Dialect/Torch/Utils/CMakeLists.txt

13 lines
243 B
CMake
Raw Normal View History

E2e support for aten.softmax.int and aten.embedding - Added a DecomposeComplexOps pass to decompose complex torchOps. - Refactored `visitAtenArgmaxOp` and `visitAtenAnyDimOp` to `visitReductionAlongDimIntOp`. - Moved some helper functions into torch-mlir/Dialect/Torch/Utils/Utils.h to be shared by multiple files. - Added support for f64 tensor as argument and return types.
2021-10-16 06:23:59 +08:00
add_mlir_dialect_library(TorchMLIRTorchUtils
Utils.cpp
[sparse] propagate sparsity properly when decompose torch operations. (#3318)
2024-05-16 01:09:27 +08:00
SparsityUtils.cpp
Add type promotion code to refine types. The types have different levels of categories: where complex > floating > integral > boolean (> means left hand side has higher category). The operands have different levels of priorities where: dimensioned tensor > 0-dim tensor > scalar == wrapped 0-dim tensor. This is represented by the `ResultTypeState.dimResult`, `ResultTypeState.zeroResult` and `ResultTypeState..wrappedResult` in the source code. For operands of the same priorities, the result type should be the highest categories with sufficient width to hold all operands. By default, only the highest priority operands participate in the type promotion logic. Lower priority operands participate if they are in a higher category than any higher priority operands. For example, <[],f32> (lower priority) and <[1], si64> tensor would result in <[?],f32> tensor because floating > integeral. Another example <[],f64> (lower priority) and <[1], f32> tensor would result in <[?], f32> tensor because f32 and f64 are the same category. The ScalarType enum definition, type promotion table, ResultTypeState struct definition and some helpers are copied from aten/src/ATen/native/TypeProperties.* Other references: - https://pytorch.org/docs/stable/tensor_attributes.html#type-promotion-doc - https://github.com/pytorch/pytorch/issues/9515 Other minor changes: 1. Fix `visitExpandLikeOp` to consider cases where the given sizes list size is larger than the input rank. 2. Add back the somehow deleted `torch.aten.softmax.int` tests in decompose-complex-ops.mlir.
2021-10-21 03:31:28 +08:00
TorchUpstream.cpp
E2e support for aten.softmax.int and aten.embedding - Added a DecomposeComplexOps pass to decompose complex torchOps. - Refactored `visitAtenArgmaxOp` and `visitAtenAnyDimOp` to `visitReductionAlongDimIntOp`. - Moved some helper functions into torch-mlir/Dialect/Torch/Utils/Utils.h to be shared by multiple files. - Added support for f64 tensor as argument and return types.
2021-10-16 06:23:59 +08:00
ADDITIONAL_HEADER_DIRS
${PROJECT_SOURCE_DIR}/include/torch-mlir/Dialect/Torch/Utils
mlir: add missing dependency on TableGen targets (#1537) lib/Dialect/Torch/Utils/Utils.cpp includes TorchOps.h, which, by way of included header files, refers to both TorchOps.h.inc as well as TorchTypes.h.inc. However, the build rules do not specify the dependency of the `TorchMLIRTorchUtils` target on the TableGen generated header files, causing spurious build errors. This patch fixes the problem by adding `MLIRTorchOpsIncGen` and `MLIRTorchTypesIncGen` to the list of dependencies of `TorchMLIRTorchUtils`.
2022-11-02 03:59:11 +08:00
DEPENDS
MLIRTorchOpsIncGen
MLIRTorchTypesIncGen
)