19147

MIOpen: An Open Source Library For Deep Learning Primitives

Jehandad Khan, Paul Fultz, Artem Tamazov, Daniel Lowell, Chao Liu, Michael Melesse, Murali Nandhimandalam, Kamil Nasyrov, Ilya Perminov, Tejash Shah, Vasilii Filippov, Jing Zhang, Jing Zhou, Bragadeesh Natarajan, Mayank Daga
AMD Inc.
arXiv:1910.00078 [cs.LG], (30 Sep 2019)

@misc{jeh2019miopen,

   title={MIOpen: An Open Source Library For Deep Learning Primitives},

   author={Jehandad Khan and Paul Fultz and Artem Tamazov and Daniel Lowell and Chao Liu and Michael Melesse and Murali Nandhimandalam and Kamil Nasyrov and Ilya Perminov and Tejash Shah and Vasilii Filippov and Jing Zhang and Jing Zhou and Bragadeesh Natarajan and Mayank Daga},

   year={2019},

   eprint={1910.00078},

   archivePrefix={arXiv},

   primaryClass={cs.LG}

}

Deep Learning has established itself to be a common occurrence in the business lexicon. The unprecedented success of deep learning in recent years can be attributed to: abundance of data, availability of gargantuan compute capabilities offered by GPUs, and adoption of open-source philosophy by the researchers and industry. Deep neural networks can be decomposed into a series of different operators. MIOpen, AMD’s open-source deep learning primitives library for GPUs, provides highly optimized implementations of such operators, shielding researchers from internal implementation details and hence, accelerating the time to discovery. This paper introduces MIOpen and provides details about the internal workings of the library and supported features. MIOpen innovates on several fronts, such as implementing fusion to optimize for memory bandwidth and GPU launch overheads, providing an auto-tuning infrastructure to overcome the large design space of problem configurations, and implementing different algorithms to optimize convolutions for different filter and input sizes. MIOpen is one of the first libraries to publicly support the bfloat16 data-type for convolutions, allowing efficient training at lower precision without the loss of accuracy.
Rating: 5.0/5. From 1 vote.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: