Self-Tuning Intel Transactional Synchronization Extensions

Authors: 

Nuno Diegues and Paolo Romano, INESC-ID and Instituto Superior Técnico, University of Lisbon

Awarded Best Paper!

Abstract: 

Transactional Memory was recently integrated in Intel processors under the name TSX.We show that its performance can be significantly affected by the configuration of its interplay with the software-based fallback: in fact, there does not seem to exist a single configuration that can perform best independently of the application and workload. We address this challenge by introducing an innovative self-tuning approach that exploits lightweight reinforcement learning techniques to identify the optimal TSX configuration in a workload-oblivious manner, i.e. not requiring any off-line/a-priori sampling of the application’s workload. To achieve total transparency for the programmer, we integrated the proposed algorithm in the GCC compiler. Our evaluation shows improvements up to 2× over state of the art approaches, while remaining within 5% from the performance achievable using optimal static configurations.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {183061,
author = {Nuno Diegues and Paolo Romano},
title = {{Self-Tuning} Intel Transactional Synchronization Extensions},
booktitle = {11th International Conference on Autonomic Computing (ICAC 14)},
year = {2014},
isbn = {978-1-931971-11-9},
address = {Philadelphia, PA},
pages = {209--219},
url = {https://www.usenix.org/conference/icac14/technical-sessions/presentation/diegues},
publisher = {USENIX Association},
month = jun
}