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/Conversion/CMakeLists.txt

34 lines
917 B
CMake
Raw Normal View History

Initial TorchOnnxToTorch conversion pipeline. (#2585) Adds a pipeline to convert custom ops and metadata represented as `torch.operator` custom ops to corresponding `torch` ops where possible. This is part of a multi-part approach for building ONNX import in as a regular feature of torch-mlir. It is focused on the conversions vs the infra. We will end up maintaining a [pure-python importer](https://github.com/nod-ai/SHARK-Turbine/blob/main/python/shark_turbine/importers/onnx_importer.py) to go with this in torch-mlir, and we will also maintain test case generation utilities derived from it. I have left substantial documentation in the README of the conversion directory, including the recommended approach that we will take to keep building this out. (note that this organizes the code to coincide with the refactoring in #2442 versus the current flat arrangement)
2023-11-22 13:02:55 +08:00
add_subdirectory(TorchOnnxToTorch)
Move TorchConversion dialect and TorchTo* into torch-mlir
2021-09-24 11:59:12 +08:00
add_subdirectory(TorchToLinalg)
add_subdirectory(TorchToSCF)
Rename TorchToStd pass as TorchToArith (#1163) All the converters in this pass appear to create ops from the arith dialect. Hence the full rename. Fix GH Issue #409.
2022-08-11 03:12:51 +08:00
add_subdirectory(TorchToArith)
Add a basic TOSA E2E backend. We lower through linalg-on-tensors and use RefBackend to run it. This adds enough support for a "tanh" op. Adding more ops should be fairly mechanical now that things are wired up. Run with: ``` ./tools/torchscript_e2e_test.sh -c tosa ``` The backend structure is very similar to linalg-on-tensors based E2E backends and is a nice parallel (see `tosa_backend.py`). Actually, this forced a nice refactoring to the layering here. We removed `torchscript-module-to-linalg-on-tensors-backend-pipeline` and instead require separately running ``` torchscript-function-to-torch-backend-pipeline,torch-backend-to-linalg-on-tensors-backend-pipeline ``` This highlights the step that lowers to the "torch backend contract" of cleaned up `torch` dialect ops is a critical step in the lowering. Going forward, that is the key load-bearing contract of the torch-mlir project, not the linalg-on-tensors backend contract. Recommended review order: - `TorchToTosa.cpp` / `TorchToTosa/basic.mlir` - `python/torch_mlir_e2e_test/torchscript/configs/tosa_backend.py` and the new `utils.py` file there. - `python/torch_mlir_e2e_test/tosa_backends/linalg_on_tensors.py` and `abc.py` in that directory for the TOSA backend e2e interface. - other misc mechanical changes
2021-10-08 10:07:03 +08:00
add_subdirectory(TorchToTosa)
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
if(TORCH_MLIR_ENABLE_STABLEHLO)
add_subdirectory(TorchToStablehlo)
[MHLO] Init MHLO integration. (#1083) Co-authored-by: Bairen Yi <yibairen.byron@bytedance.com> Co-authored-by: Jiawei Wu <xremold@gmail.com> Co-authored-by: Tianyou Guo <tianyou.gty@alibaba-inc.com> Co-authored-by: Xu Yan <yancey.yx@alibaba-inc.com> Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2022-07-21 07:18:16 +08:00
endif()
[MLIR][TORCH] Add TorchToTMTensor pass This pass is added to lower ops, which can not be lowered via the TorchToLinalg pass, such as `torch.bincount` op. This pass also uses torch-mlir's TMTensor Dialect to lower the complex ops. Also add torch.bincount op lowering with the help of TMTensor dialect Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-03-03 00:48:15 +08:00
add_subdirectory(TorchToTMTensor)
[MLIR][TORCH] Add TorchConversionToMLProgram and MLProgramBufferize pass This commit changes the `InsertRngGlobalsPass` to `TorchConversionToMLProgram` pass. This commit also adds the `MLProgramBufferize` pass for the bufferization of ml_program dialect ops to run on refbackend. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-24 12:33:47 +08:00
add_subdirectory(TorchConversionToMLProgram)
[MLIR][TORCH] Move common helper functions to Utils.cpp This commit moves the helper function which are common across different torch-mlir conversion passes into a common directory Utils. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-03-03 00:42:25 +08:00
add_subdirectory(Utils)
Move TorchConversion dialect and TorchTo* into torch-mlir
2021-09-24 11:59:12 +08:00
# TODO: Automate this with add_torch_mlir_conversion_library.
[MHLO] Init MHLO integration. (#1083) Co-authored-by: Bairen Yi <yibairen.byron@bytedance.com> Co-authored-by: Jiawei Wu <xremold@gmail.com> Co-authored-by: Tianyou Guo <tianyou.gty@alibaba-inc.com> Co-authored-by: Xu Yan <yancey.yx@alibaba-inc.com> Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2022-07-21 07:18:16 +08:00
set(linked_libs TorchMLIRTorchToLinalg
TorchMLIRTorchToSCF
Rename TorchToStd pass as TorchToArith (#1163) All the converters in this pass appear to create ops from the arith dialect. Hence the full rename. Fix GH Issue #409.
2022-08-11 03:12:51 +08:00
TorchMLIRTorchToArith
[MHLO] Init MHLO integration. (#1083) Co-authored-by: Bairen Yi <yibairen.byron@bytedance.com> Co-authored-by: Jiawei Wu <xremold@gmail.com> Co-authored-by: Tianyou Guo <tianyou.gty@alibaba-inc.com> Co-authored-by: Xu Yan <yancey.yx@alibaba-inc.com> Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2022-07-21 07:18:16 +08:00
TorchMLIRTorchToTosa
TorchMLIRTorchToTMTensor
[MLIR][TORCH] Add TorchConversionToMLProgram and MLProgramBufferize pass This commit changes the `InsertRngGlobalsPass` to `TorchConversionToMLProgram` pass. This commit also adds the `MLProgramBufferize` pass for the bufferization of ml_program dialect ops to run on refbackend. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-24 12:33:47 +08:00
TorchMLIRTorchConversionToMLProgram
[MHLO] Init MHLO integration. (#1083) Co-authored-by: Bairen Yi <yibairen.byron@bytedance.com> Co-authored-by: Jiawei Wu <xremold@gmail.com> Co-authored-by: Tianyou Guo <tianyou.gty@alibaba-inc.com> Co-authored-by: Xu Yan <yancey.yx@alibaba-inc.com> Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2022-07-21 07:18:16 +08:00
TorchMLIRConversionUtils)
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
if(TORCH_MLIR_ENABLE_STABLEHLO)
list(APPEND linked_libs TorchMLIRTorchToStablehlo)
[MHLO] Init MHLO integration. (#1083) Co-authored-by: Bairen Yi <yibairen.byron@bytedance.com> Co-authored-by: Jiawei Wu <xremold@gmail.com> Co-authored-by: Tianyou Guo <tianyou.gty@alibaba-inc.com> Co-authored-by: Xu Yan <yancey.yx@alibaba-inc.com> Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2022-07-21 07:18:16 +08:00
endif()
Move TorchConversion dialect and TorchTo* into torch-mlir
2021-09-24 11:59:12 +08:00
add_mlir_library(TorchMLIRConversionPasses
Passes.cpp
DEPENDS
TorchMLIRConversionPassIncGen
LINK_LIBS PUBLIC
[MHLO] Init MHLO integration. (#1083) Co-authored-by: Bairen Yi <yibairen.byron@bytedance.com> Co-authored-by: Jiawei Wu <xremold@gmail.com> Co-authored-by: Tianyou Guo <tianyou.gty@alibaba-inc.com> Co-authored-by: Xu Yan <yancey.yx@alibaba-inc.com> Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2022-07-21 07:18:16 +08:00
${linked_libs}
Move TorchConversion dialect and TorchTo* into torch-mlir
2021-09-24 11:59:12 +08:00
)