Optimization strategies for MPI-interoperable active messages

Xin Zhao, Pavan Balaji, William D Gropp, Rajeev Thakur

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

Abstract

Data-intensive applications, such as those in bioinformatics and social network analysis, differ from traditional scientific applications in that they often involve data-driven and irregular computation/communication patterns, making them ill-suited for traditional data movement approaches. Active Messages (AM) is an alternative programming model that allows dynamically moving computation closer to data, rather than moving the data to the local process. In our previous work, we proposed an MPI-interoperable AM framework that allows existing MPI applications to incrementally take advantage of AM capabilities. While that work presented a baseline implementation of how AMs semantically interact with the rest of the MPI infrastructure, it had several performance shortcomings. In this paper, we analyze these performance shortcomings and propose three optimization strategies: one implicitly derived by the MPI implementation and two explicitly hinted to by the application user. In addition to the detailed description of these optimization strategies, the paper presents a thorough performance evaluation on a 4096-core cluster that demonstrates considerable performance advantages from these strategies.

Original languageEnglish (US)
Title of host publicationProceedings - 2013 IEEE 11th International Conference on Dependable, Autonomic and Secure Computing, DASC 2013
PublisherIEEE Computer Society
Pages508-515
Number of pages8
ISBN (Print)9781479933815
DOIs
StatePublished - Jan 1 2013
Event11th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2013 - Chengdu, Sichuan, China
Duration: Dec 21 2013Dec 22 2013

Publication series

NameProceedings - 2013 IEEE 11th International Conference on Dependable, Autonomic and Secure Computing, DASC 2013

Other

Other11th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2013
CountryChina
CityChengdu, Sichuan
Period12/21/1312/22/13

Keywords

  • Active messages
  • Data-intensive applications
  • MPI
  • Multicore
  • RMA

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Optimization strategies for MPI-interoperable active messages'. Together they form a unique fingerprint.

  • Cite this

    Zhao, X., Balaji, P., Gropp, W. D., & Thakur, R. (2013). Optimization strategies for MPI-interoperable active messages. In Proceedings - 2013 IEEE 11th International Conference on Dependable, Autonomic and Secure Computing, DASC 2013 (pp. 508-515). [6844416] (Proceedings - 2013 IEEE 11th International Conference on Dependable, Autonomic and Secure Computing, DASC 2013). IEEE Computer Society. https://doi.org/10.1109/DASC.2013.116