Latency Reduction in Software-DSMs by Means of Dynamic Function Splicing

Klemm M, Veldema R, Philippsen M (2004)

Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 2004

Journal

Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems

Edited Volumes: Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems

City/Town: Anaheim, CA, USA

Pages Range: 362-367

Conference Proceedings Title: Proceedings of the 16th IASTED International Conference on Parallel and Distributed Computing and Systems

Event location: Cambridge, MA, USA US

ISBN: 0-88986-421-7

URI: http://www2.informatik.uni-erlangen.de/publication/download/pdcs04dfs.pdf

Abstract

We present a compiler-based technique to automatically identify and extract Remote Procedure Calls, so-called Function Splices, out of potentially arbitrary sequences of Java code compiled for a software DSM. The goal is to lower communication latencies and message traffic by replacing data shipping by function shipping. Dynamic Function Splicing dynamically decides at runtime whether to invoke a function splice on the local machine or to execute it remotely on the home node of the requested data. On proof-of-concept micro-benchmarks Dynamic Function Splicing reduces the execution wall time by approximately 29 %; about 25 % of the messages can be saved.

Authors with CRIS profile

Ronald Veldema Lehrstuhl für Informatik 2 (Programmiersysteme) Michael Philippsen Lehrstuhl für Informatik 2 (Programmiersysteme)

How to cite

APA:

Klemm, M., Veldema, R., & Philippsen, M. (2004). Latency Reduction in Software-DSMs by Means of Dynamic Function Splicing. In Proceedings of the 16th IASTED International Conference on Parallel and Distributed Computing and Systems (pp. 362-367). Cambridge, MA, USA, US: Anaheim, CA, USA.

MLA:

Klemm, Michael, Ronald Veldema, and Michael Philippsen. "Latency Reduction in Software-DSMs by Means of Dynamic Function Splicing." Proceedings of the 16th IASTED International Conference on Parallel and Distributed Computing and Systems (PDCS'04), Cambridge, MA, USA Anaheim, CA, USA, 2004. 362-367.

BibTeX: Download