COBRA: An adaptive runtime binary optimization framework for multithreaded applications

Jinpyo Kim, Wei Chung Hsu, Pen Chung Yew

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

This paper presents COBRA (Continuous Binary Re-Adaptation), a runtime binary optimization framework, for multithreaded applications. It is currently implemented on Itanium 2 based SMP and cc-NUMA systems. Using OpenMP NAS parallel benchmark, we show how COBRA can adaptively choose appropriate optimizations according to observed changing runtime program behavior. Coherent cache misses caused by true/false data sharing often limit the scalability of multithreaded applications. This paper shows that COBRA can significantly improve the performance of some applications parallelized with OpenMP, by reducing the aggressiveness of data prefetching and by using exclusive hints for prefetch instructions. For example, we show that COBRA can improve the performance of OpenMP NAS parallel benchmarks up to 68%, with an average of 17.5% on the SGI Altix cc-NUMA system.

Original languageEnglish (US)
Title of host publication2007 International Conference on Parallel Processing, ICPP
DOIs
StatePublished - Dec 1 2007
Event36th International Conference on Parallel Processing in Xi'an, ICPP - Xi'an, China
Duration: Sep 10 2007Sep 14 2007

Publication series

NameProceedings of the International Conference on Parallel Processing
ISSN (Print)0190-3918

Other

Other36th International Conference on Parallel Processing in Xi'an, ICPP
Country/TerritoryChina
CityXi'an
Period9/10/079/14/07

Fingerprint

Dive into the research topics of 'COBRA: An adaptive runtime binary optimization framework for multithreaded applications'. Together they form a unique fingerprint.

Cite this