5.3 KiB

Raw Blame History

torch-mlir

The Torch-MLIR project aims to provide first class support from the Pytorch ecosystem to the MLIR ecosystem.

This project is participating in the LLVM Incubator process: as such, it is not part of any official LLVM release. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project is not yet endorsed as a component of LLVM.

Pytorch An open source machine learning framework that accelerates the path from research prototyping to production deployment.

MLIR The MLIR project is a novel approach to building reusable and extensible compiler infrastructure. MLIR aims to address software fragmentation, improve compilation for heterogeneous hardware, significantly reduce the cost of building domain specific compilers, and aid in connecting existing compilers together.

Torch-MLIR Multiple Vendors use MLIR as the middle layer mapping from Platform Frameworks like Pytorch, JAX, Tensorflow onto MLIR and then progressively lower down to their target hardware. We have seen half a dozen custom lowerings from PyTorch to MLIR. Having a canonical lowering from the Pytorch ecosystem to the MLIR ecosystem would provide much needed relief to Hardware Vendors to focus on their unique value rather than implementing another Pytorch frontend for MLIR. It would be similar to current hardware vendors adding LLVM target support instead of each one also implementing the Clang/C++ frontend.

All the roads from PyTorch to Torch MLIR Dialect

We have few paths to lower down to the Torch MLIR Dialect.

Torchscript This is the most tested path down to Torch MLIR Dialect.
TorchFX This provides a path to lower from TorchFX down to MLIR. This a functional prototype that we expect to mature as TorchFX matures
Lazy Tensor Core (Based on lazy-tensor-core staging branch) This path provides the upcoming LTC path of capture. It is based of an unstable devel branch but is the closest way for you to adapt any existing torch_xla derivatives.
“ACAP” - Deprecated torch_xla based capture Mentioned here for completeness.

Check out the code

git clone https://github.com/llvm/torch-mlir
cd torch-mlir
git submodule update --init

Setup your Python Environment

python -m venv mlir_venv
source mlir_venv/bin/activate
python -m pip install --upgrade pip #Some older pip installs may not be able to handle the recent PyTorch deps
# Install latest PyTorch nightlies
python -m pip install --pre torch torchvision pybind11 -f https://download.pytorch.org/whl/nightly/cpu/torch_nightly.html

Build

cmake -GNinja -Bbuild \
  -DCMAKE_C_COMPILER=clang \
  -DCMAKE_CXX_COMPILER=clang++ \
  -DLLVM_ENABLE_PROJECTS=mlir \
  -DLLVM_EXTERNAL_PROJECTS=torch-mlir \
  -DLLVM_EXTERNAL_TORCH_MLIR_SOURCE_DIR=`pwd` \
  -DMLIR_ENABLE_BINDINGS_PYTHON=ON \
  -DLLVM_TARGETS_TO_BUILD=host \
  external/llvm-project/llvm

# Additional quality of life CMake flags:
# Enable ccache:
#   -DCMAKE_C_COMPILER_LAUNCHER=ccache -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
# Enale LLD (links in seconds compared to minutes)
# -DCMAKE_EXE_LINKER_FLAGS_INIT="-fuse-ld=lld" -DCMAKE_MODULE_LINKER_FLAGS_INIT="-fuse-ld=lld" -DCMAKE_SHARED_LINKER_FLAGS_INIT="-fuse-ld=lld"
# Use --ld-path= instead of -fuse-ld=lld for clang > 13

cmake --build build

Demos

Setup ENV

export PYTHONPATH=`pwd`/build/tools/torch-mlir/python_packages

TorchScript

Running execution (end-to-end) tests:

# Run E2E TorchScript tests. These compile and run the TorchScript program
# through torch-mlir with a simplified linalg-on-tensors based backend we call
# RefBackend (more production-grade backends at this same abstraction layer
# exist in the MLIR community, such as IREE).
./tools/torchscript_e2e_test.sh --filter Conv2d --verbose

Standalone script to generate and run a ResNet18 model:

# Run ResNet18 as a standalone script.
python examples/torchscript_resnet18_e2e.py

Jupyter notebook:

python -m ipykernel install --user --name=torch-mlir --env PYTHONPATH "$PYTHONPATH"
# Open in jupyter, and then navigate to
# `examples/resnet_inference.ipynb` and use the `torch-mlir` kernel to run.
jupyter notebook

TorchFX

TODO

Lazy Tensor Core