Locality-Aware Software Throttling for Sparse Matrix Operation on GPUs


Yanhao Chen and Ari B. Hayes, Rutgers University; Chi Zhang, University of Pittsburgh; Timothy Salmon and Eddy Z. Zhang, Rutgers University


This paper tackles the cache thrashing problem caused by the non-deterministic scheduling feature of bulk synchronous parallel (BSP) execution in GPUs. In the BSP model, threads can be executed and interleaved in any order before reaching a barrier synchronization point, which requires the entire working set to be in cache for maximum data reuse over time. However, it is not always possible to fit all the data in cache at once. Thus, we propose a locality-aware software throttling framework that throttles the number of active execution tasks, prevents cache thrashing, and enhances data reuse over time. Our locality-aware software throttling framework focuses on an important class of applications that operate on sparse matrices (graphs). These applications come from the domains of linear algebra, graph processing, machine learning and scientific simulation. Evaluated on over 200 real sparse matrices and graphs that suffer from cache thrashing in the Florida sparse matrix collection, our technique achieves an average of 2.01X speedup, a maximum of 6.45X speedup, and a maximum performance loss ≤5%.

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.

@inproceedings {215961,
author = {Yanhao Chen and Ari B. Hayes and Chi Zhang and Timothy Salmon and Eddy Z. Zhang},
title = {{Locality-Aware} Software Throttling for Sparse Matrix Operation on {GPUs}},
booktitle = {2018 USENIX Annual Technical Conference (USENIX ATC 18)},
year = {2018},
isbn = {978-1-939133-01-4},
address = {Boston, MA},
pages = {413--426},
url = {https://www.usenix.org/conference/atc18/presentation/chen-yanhao},
publisher = {USENIX Association},
month = jul

Presentation Audio