| Developer(s) | OpenXLA |
|---|---|
| Repository | xla on GitHub |
| Written in | C++ |
| Operating system | Linux, macOS, Windows |
| Type | compiler |
| License | Apache License 2.0 |
| Website | openxla |
XLA (Accelerated Linear Algebra) is an open-source compiler for machine learning developed by the OpenXLA project.[1] XLA is designed to improve the performance of machine learning models by optimizing the computation graphs at a lower level, making it particularly useful for large-scale computations and high-performance machine learning models. Key features of XLA include:[2]
- Compilation of Computation Graphs: Compiles computation graphs into efficient machine code.
- Optimization Techniques: Applies operation fusion, memory optimization, and other techniques.
- Hardware Support: Optimizes models for various hardware, including CPUs, GPUs, and NPUs.
- Improved Model Execution Time: Aims to reduce machine learning models' execution time for both training and inference.
- Seamless Integration: Can be used with existing machine learning code with minimal changes.
XLA represents a significant step in optimizing machine learning models, providing developers with tools to enhance computational efficiency and performance.[3][4]
Supported target devices
[edit]- x86-64
- ARM64
- NVIDIA GPU
- AMD GPU
- Intel GPU[5]
- Apple GPU[6]
- Google TPU
- AWS Trainium, Inferentia[7]
- Cerebras[8]
- Graphcore IPU[9]
See also
[edit]References
[edit]- ^ "OpenXLA Project". Retrieved December 21, 2024.
- ^ Woodie, Alex (2023-03-09). "OpenXLA Delivers Flexibility for ML Apps". Datanami. Retrieved 2023-12-10.
- ^ "TensorFlow XLA: Accelerated Linear Algebra". TensorFlow Official Documentation. Retrieved 2023-12-10.
- ^ Smith, John (2022-07-15). "Optimizing TensorFlow Models with XLA". Journal of Machine Learning Research. 23: 45–60.
- ^ "intel/intel-extension-for-openxla". GitHub. Retrieved December 29, 2024.
- ^ "Accelerated JAX on Mac - Metal - Apple Developer". Retrieved December 29, 2024.
- ^ "Developer Guide for Training with PyTorch NeuronX — AWS Neuron Documentation". awsdocs-neuron.readthedocs-hosted.com. Retrieved 29 December 2024.
- ^ Barsoum, Emad (13 April 2022). "Supporting PyTorch on the Cerebras Wafer-Scale Engine - Cerebras". Cerebras. Retrieved 29 December 2024.
- ^ Ltd, Graphcore. "Poplar® Software". graphcore.ai. Retrieved 29 December 2024.
- ^ "PyTorch/XLA documentation — PyTorch/XLA master documentation". pytorch.org. Retrieved 29 December 2024.
 | This computer-library-related article is a stub. You can help Wikipedia by expanding it. |