Home > Research > Publications & Outputs > End-to-end Deep Learning of Optimization Heuris...

Electronic data

  • pact17-paper47

    Accepted author manuscript, 1 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

End-to-end Deep Learning of Optimization Heuristics

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

End-to-end Deep Learning of Optimization Heuristics. / Cummins, Chris; Petoumenos, Pavlos ; Wang, Zheng et al.
The 26th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2017. IEEE, 2017. p. 219-232.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Cummins, C, Petoumenos, P, Wang, Z & Leather, H 2017, End-to-end Deep Learning of Optimization Heuristics. in The 26th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2017. IEEE, pp. 219-232. https://doi.org/10.1109/PACT.2017.24

APA

Cummins, C., Petoumenos, P., Wang, Z., & Leather, H. (2017). End-to-end Deep Learning of Optimization Heuristics. In The 26th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2017 (pp. 219-232). IEEE. https://doi.org/10.1109/PACT.2017.24

Vancouver

Cummins C, Petoumenos P, Wang Z, Leather H. End-to-end Deep Learning of Optimization Heuristics. In The 26th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2017. IEEE. 2017. p. 219-232 doi: 10.1109/PACT.2017.24

Author

Cummins, Chris ; Petoumenos, Pavlos ; Wang, Zheng et al. / End-to-end Deep Learning of Optimization Heuristics. The 26th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2017. IEEE, 2017. pp. 219-232

Bibtex

@inproceedings{ca661601a16d4fdf8e80fc9b909acc52,
title = "End-to-end Deep Learning of Optimization Heuristics",
abstract = "Accurate automatic optimization heuristics are necessary for dealing with the complexity and diversity of modern hardware and software. Machine learning is a proven technique for learning such heuristics, but its success is bound by the quality of the features used. These features must be hand crafted by developers through a combination of expert domain knowledge and trial and error. This makes the quality of the final model directly dependent on the skill and available time of the system architect.Our work introduces a better way for building heuristics. We develop a deep neural network that learns heuristics over raw code, entirely without using code features. The neural network simultaneously constructs appropriate representations of the code and learns how best to optimize, removing the need for manual feature creation. Further, we show that our neural nets can transfer learning from one optimization problem to another, improving the accuracy of new models, without the help of human experts.We compare the effectiveness of our automatically generated heuristics against ones with features hand-picked by experts. We examine two challenging tasks: predicting optimal mapping forheterogeneous parallelism and GPU thread coarsening factors. In 89% of the cases, the quality of our fully automatic heuristics matches or surpasses that of state-of-the-art predictive modelsusing hand-crafted features, providing on average 14% and 12% more performance with no human effort expended on designing features.",
author = "Chris Cummins and Pavlos Petoumenos and Zheng Wang and Hugh Leather",
year = "2017",
month = sep,
day = "9",
doi = "10.1109/PACT.2017.24",
language = "English",
isbn = "9781509067657",
pages = "219--232",
booktitle = "The 26th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2017",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - End-to-end Deep Learning of Optimization Heuristics

AU - Cummins, Chris

AU - Petoumenos, Pavlos

AU - Wang, Zheng

AU - Leather, Hugh

PY - 2017/9/9

Y1 - 2017/9/9

N2 - Accurate automatic optimization heuristics are necessary for dealing with the complexity and diversity of modern hardware and software. Machine learning is a proven technique for learning such heuristics, but its success is bound by the quality of the features used. These features must be hand crafted by developers through a combination of expert domain knowledge and trial and error. This makes the quality of the final model directly dependent on the skill and available time of the system architect.Our work introduces a better way for building heuristics. We develop a deep neural network that learns heuristics over raw code, entirely without using code features. The neural network simultaneously constructs appropriate representations of the code and learns how best to optimize, removing the need for manual feature creation. Further, we show that our neural nets can transfer learning from one optimization problem to another, improving the accuracy of new models, without the help of human experts.We compare the effectiveness of our automatically generated heuristics against ones with features hand-picked by experts. We examine two challenging tasks: predicting optimal mapping forheterogeneous parallelism and GPU thread coarsening factors. In 89% of the cases, the quality of our fully automatic heuristics matches or surpasses that of state-of-the-art predictive modelsusing hand-crafted features, providing on average 14% and 12% more performance with no human effort expended on designing features.

AB - Accurate automatic optimization heuristics are necessary for dealing with the complexity and diversity of modern hardware and software. Machine learning is a proven technique for learning such heuristics, but its success is bound by the quality of the features used. These features must be hand crafted by developers through a combination of expert domain knowledge and trial and error. This makes the quality of the final model directly dependent on the skill and available time of the system architect.Our work introduces a better way for building heuristics. We develop a deep neural network that learns heuristics over raw code, entirely without using code features. The neural network simultaneously constructs appropriate representations of the code and learns how best to optimize, removing the need for manual feature creation. Further, we show that our neural nets can transfer learning from one optimization problem to another, improving the accuracy of new models, without the help of human experts.We compare the effectiveness of our automatically generated heuristics against ones with features hand-picked by experts. We examine two challenging tasks: predicting optimal mapping forheterogeneous parallelism and GPU thread coarsening factors. In 89% of the cases, the quality of our fully automatic heuristics matches or surpasses that of state-of-the-art predictive modelsusing hand-crafted features, providing on average 14% and 12% more performance with no human effort expended on designing features.

U2 - 10.1109/PACT.2017.24

DO - 10.1109/PACT.2017.24

M3 - Conference contribution/Paper

SN - 9781509067657

SP - 219

EP - 232

BT - The 26th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2017

PB - IEEE

ER -