A Study of Process Arrival Patterns for MPI Collective Operations
- 1 February 2008
- journal article
- Published by Springer Nature in International Journal of Parallel Programming
- Vol. 36 (6) , 543-570
Abstract
No abstract availableKeywords
This publication has 16 references indexed in Scilit:
- A Message Scheduling Scheme for All-to-All Personalized Communication on Ethernet Switched ClustersIEEE Transactions on Parallel and Distributed Systems, 2007
- Pipelined broadcast on Ethernet switched clusters2006
- An MPI prototype for compiled communication on Ethernet switched clustersJournal of Parallel and Distributed Computing, 2005
- Automatic generation and tuning of MPI collective communication routines2005
- Performance Analysis of MPI Collective Operations2005
- The Case of the Missing Supercomputer Performance2003
- Statistical analysis of message passing programs to guide computer design2002
- Efficient algorithms for all-to-all communications in multiport message-passing systemsIEEE Transactions on Parallel and Distributed Systems, 1997
- A high-performance, portable implementation of the MPI message passing interface standardParallel Computing, 1996
- Static communications in parallel scientific programs1994