5897

OptiML: An implicitly parallel domain-specific language for machine learning

Arvind K. Sujeeth, HyoukJoong Lee, Kevin J. Brown, Tiark Rompf, Hassan Chafi, Michael Wu, Anand R. Atreya, Martin Odersky, Kunle Olukotun
Stanford University, 353 Serra St., Stanford, CA 94305 USA
Proceedings of the 28th Intl. Conference on Machine Learning, ICML ’11, 2011.

@inproceedings{sujeeth2011optiml,

   title={OptiML: An implicitly parallel domain-specific language for machine learning},

   author={Sujeeth, A.K. and Lee, H. and Brown, K.J. and Rompf, T. and Chafi, H. and Wu, M. and Atreya, AR and Odersky, M. and Olukotun, K.},

   booktitle={Proceedings of the International Conference on Machine Learning. Haifa, Israel},

   year={2011}

}

Download Download (PDF)   View View   Source Source   

1001

views

As the size of datasets continues to grow, machine learning applications are becoming increasingly limited by the amount of available computational power. Taking advantage of modern hardware requires using multiple parallel programming models targeted at different devices (e.g. CPUs and GPUs). However, programming these devices to run efficiently and correctly is difficult, error-prone, and results in software that is harder to read and maintain. We present OptiML, a domain-specific language (DSL) for machine learning. OptiML is an implicitly parallel, expressive and high performance alternative to MATLAB and C++. OptiML performs domain-specific analyses and optimizations and automatically generates CUDA code for GPUs. We show that OptiML outperforms explicitly parallelized MATLAB code in nearly all cases.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: