A framework for collective personalized communication
- 22 March 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper explores collective personalized communication. For example, in all-to-all personalized communication (AAPC), each processor sends a distinct message to every other processor. However, for many applications, the collective communication pattern is many-to-many, where each processor sends a distinct message to a subset of processors. Inthis paper we first present strategies that reduce per-message cost to optimize AAPC. We then present performance results of these strategies in both all-to-all and many-to-many scenarios. These strategies are implemented in a flexible, asynchronous library with a non-blocking interface, and a message-driven runtime system. This allows the collective communication to run concurrently with the application, if desired. As a result the computational overhead of the communication is substantially reduced, at least on machines such as PSC Lemieux, which sport a co-processor capable of remote DMA. We demonstrate the advantages of our framework with performance results on several benchmarks and applications.Keywords
This publication has 15 references indexed in Scilit:
- Scheduling regular and irregular communication patterns on the CM-5Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Converse: an interoperable framework for parallel programmingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- All-to-all communication on meshes with wormhole routingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The Quadrics network: high-performance clustering technologyIEEE Micro, 2002
- A theory for total exchange in multidimensional interconnection networksIEEE Transactions on Parallel and Distributed Systems, 1998
- LoGPCPublished by Association for Computing Machinery (ACM) ,1998
- Optimal Algorithms for All-to-All Personalized Communication on Rings and Two Dimensional ToriJournal of Parallel and Distributed Computing, 1997
- Hybrid algorithms for complete exchange in 2D meshesPublished by Association for Computing Machinery (ACM) ,1996
- Worm-hole gossiping on meshesLecture Notes in Computer Science, 1996
- Multiphase complete exchange: a theoretical analysisIEEE Transactions on Computers, 1996