Skip to content

hxdtest/buddy-mlir

 
 

Repository files navigation

BUDDY MLIR

MLIR-Based Ideas Landing Project (Project page).

Getting Started

LLVM/MLIR Dependencies

This project uses LLVM/MLIR as an external library. Please make sure the dependencies are available on your machine.

Clone and Initialize

$ git clone [email protected]:buddy-compiler/buddy-mlir.git
$ cd buddy-mlir
$ git submodule update --init

Build and Test LLVM/MLIR/CLANG

$ cd buddy-mlir
$ mkdir llvm/build
$ cd llvm/build
$ cmake -G Ninja ../llvm \
    -DLLVM_ENABLE_PROJECTS="mlir;clang" \
    -DLLVM_TARGETS_TO_BUILD="host;RISCV" \
    -DLLVM_ENABLE_ASSERTIONS=ON \
    -DCMAKE_BUILD_TYPE=RELEASE
$ ninja check-mlir check-clang

If your target machine includes a Nvidia GPU, you can use the following configuration:

$ cmake -G Ninja ../llvm \
    -DLLVM_ENABLE_PROJECTS="mlir;clang" \
    -DLLVM_TARGETS_TO_BUILD="host;RISCV;NVPTX" \
    -DMLIR_ENABLE_CUDA_RUNNER=ON \
    -DLLVM_ENABLE_ASSERTIONS=ON \
    -DCMAKE_BUILD_TYPE=RELEASE

Build buddy-mlir

$ cd buddy-mlir
$ mkdir build
$ cd build
$ cmake -G Ninja .. \
    -DMLIR_DIR=$PWD/../llvm/build/lib/cmake/mlir \
    -DLLVM_DIR=$PWD/../llvm/build/lib/cmake/llvm \
    -DLLVM_ENABLE_ASSERTIONS=ON \
    -DCMAKE_BUILD_TYPE=RELEASE
$ ninja check-buddy

If you want to add domain-specific framework support, please add the following cmake options:

Framework Enable Option Other Options
OpenCV -DBUDDY_ENABLE_OPENCV=ON Add -DOpenCV_DIR=</PATH/TO/OPENCV/BUILD/> or install OpenCV release version on your local device.

Dialects

Bud Dialect

Bud dialect is designed for testing and demonstrating.

DIP Dialect

DIP dialect is designed for digital image processing abstraction.

Tools

buddy-opt

The buddy-opt is the driver for dialects and optimization in buddy-mlir project.

AutoConfig Mechanism

The AutoConfig mechanism is designed to detect the target hardware and configure the toolchain automatically.

Examples

The purpose of the examples is to give users a better understanding of how to use the passes and the interfaces in buddy-mlir. Currently, we provide three types of examples.

  • IR level conversion and transformation examples.
  • Domain-specific application level examples.
  • Testing and demonstrating examples.

For more details, please see the documentation of the examples.

Benchmarks

The benchmarks in this repo use JIT tool (mlir-cpu-runner) as the execution engine. For AOT benchmarks, please see buddy-benchmark repo.

We provide the following benchmarks:

  • Conv2D
$ cd buddy-mlir/benchmark
$ make

For more features and configurations, please see the benchmark document.

About

An MLIR-Based Ideas Landing Project

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 78.4%
  • CMake 13.8%
  • MLIR 5.1%
  • Python 1.4%
  • C 0.6%
  • Shell 0.4%
  • Makefile 0.3%