Message proxies for efficient, protected communication on SMP clusters

Beng Hong Lim, Philip Heidelberger, Pratap Pattnaik, Marc Snir

Research output: Contribution to conferencePaper

Abstract

This research addresses the problem of providing efficient, protected communication in an SMP cluster without incurring the overhead of system calls or the cost of custom hardware. It analyzes an approach that uses an idle SMP processor to run a message proxy, a communication process that provides protected access to the network. We implement message proxy based communication between a pair of IBM Model G30 SMPs and analyze the resulting overheads. We derive a performance model that shows that cache-miss latency within an SMP influences message proxy performance significantly. Simulations of a suite of ten parallel applications demonstrate that message proxies match the performance of custom hardware for three of the ten applications, and are between 10-30% slower for the other seven applications. A direct cache-update mechanism to reduce cache misses improves the performance of message proxies on communication-intensive programs by 7-25%. We conclude that message proxies provide a viable alternative to custom hardware for protected communication.

Original languageEnglish (US)
Pages116-127
Number of pages12
StatePublished - Jan 1 1997
Externally publishedYes
EventProceedings of the 1997 3rd International Symposium on High-Performance Computer Architecture, HPCA - San Antonio, TX, USA
Duration: Feb 1 1997Feb 5 1997

Other

OtherProceedings of the 1997 3rd International Symposium on High-Performance Computer Architecture, HPCA
CitySan Antonio, TX, USA
Period2/1/972/5/97

ASJC Scopus subject areas

  • Hardware and Architecture

Fingerprint Dive into the research topics of 'Message proxies for efficient, protected communication on SMP clusters'. Together they form a unique fingerprint.

  • Cite this

    Lim, B. H., Heidelberger, P., Pattnaik, P., & Snir, M. (1997). Message proxies for efficient, protected communication on SMP clusters. 116-127. Paper presented at Proceedings of the 1997 3rd International Symposium on High-Performance Computer Architecture, HPCA, San Antonio, TX, USA, .