Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
svkeerthy committed Jan 26, 2024
1 parent 50407ba commit 4d26853
Showing 1 changed file with 6 additions and 6 deletions.
12 changes: 6 additions & 6 deletions README.md
@@ -1,6 +1,6 @@
# MLCompilerBridge
# ML-Compiler-Bridge

`MLCompilerBridge` is a compiler agnostic library to aid in ML-Enabled Compiler Optimizations. MLCompilerBridge supports both training and inference scenarios. Library exposes Python and C/C++ APIs to interface
`ML-Compiler-Bridge` is a compiler agnostic library to aid in ML-Enabled Compiler Optimizations. ML-Compiler-Bridge supports both training and inference scenarios. Library exposes Python and C/C++ APIs to interface
with the Python-based ML models and a C/C++ compiler. This design allows ML model development within a traditional Python framework while making end-to-end integration with an optimizing compiler possible and efficient.

This repo contains the source code and relevant information described in our paper, ["The Next 700 ML-Enabled Compiler Optimizations"](https://arxiv.org/abs/2311.10800).
Expand Down Expand Up @@ -39,7 +39,7 @@ Please see [here](https://iith-compilers.github.io/MLCompilerBridge/) for docume
(Experiments are done on an Ubuntu 20.04 machine)

## Setup
`MLCompilerBridge` can be built as a stand-alone library to generate `.a` files that can in turn be linked with any compiler.
`ML-Compiler-Bridge` can be built as a stand-alone library to generate `.a` files that can in turn be linked with any compiler.
1. `mkdir build && cd build`
2. `cmake [-DCMAKE_BUILD_TYPE=Release|Debug] [-DCMAKE_INSTALL_PREFIX=<Install_path>] -DONNXRUNTIME_ROOTDIR=<Path to ONNX install dir> -DTENSORFLOW_AOT_PATH=<Path to TensorFlow pip install dir> ../`
3. `make -j [&& make install]`
Expand All @@ -50,9 +50,9 @@ Python end points are available under [`CompilerInterface`](./CompilerInterface/

To ensure the correctness, run `make verify-all`

### Using MLCompilerBridge with LLVM and MLIR
### Using ML-Compiler-Bridge with LLVM and MLIR

`MLCompilerBridge` can be integrated and built along with the LLVM project. This can be done by adding this repository as a new project and setting `LLVM_MLBRIDGE` option to `ON`.
`ML-Compiler-Bridge` can be integrated and built along with the LLVM project. This can be done by adding this repository as a new project and setting `LLVM_MLBRIDGE` option to `ON`.

You can check the [CMakeLists.txt](https://github.com/IITH-Compilers/ml-llvm-project/blob/mlbridge-lib/llvm/CMakeLists.txt) of the [`ml-llvm-project`](https://github.com/IITH-Compilers/ml-llvm-project/tree/mlbridge-lib) repository which demonstrates such an integration.

Expand Down Expand Up @@ -99,4 +99,4 @@ Libraries are autogenerated for every relevant check-in with GitHub actions. Suc
Please feel free to raise issues to file a bug, pose a question, or initiate any related discussions. Pull requests are welcome :)

## License
MLCompilerBridge is released under Apache 2.0 license with LLVM Exceptions. See LICENSE file for more details.
ML-Compiler-Bridge is released under Apache 2.0 license with LLVM Exceptions. See LICENSE file for more details.

0 comments on commit 4d26853

Please sign in to comment.