@inbook{23a83775048149c59572fd37c228f03a,
title = "Implementing MPI on the BlueGene/L supercomputer",
abstract = "The BlueGene/L supercomputer will consist of 65,536 dual-processor compute nodes interconnected by two high-speed networks: a three-dimensional torus network and a tree topology network. Each compute node can only address its own local memory, making message passing the natural programming model for BlueGene/L. In this paper we present our implementation of MPI for BlueGene/L. In particular, we discuss how we leveraged the architectural features of BlueGene/L to arrive at an efficient implementation of MPI in this machine. We validate our approach by comparing MPI performance against the hardware limits and also the relative performance of the different modes of operation of BlueGene/L. We show that dedicating one of the processors of a node to communication functions greatly improves the bandwidth achieved by MPI operation, whereas running two MPI tasks per compute node can have a positive impact on application performance.",
author = "George Alm{\'a}si and Charles Archer and Castan{\~o}s, {Jos{\'e} G.} and {Chris Erway}, C. and Philip Heidelberger and Xavier Martorell and Moreira, {Jos{\'e} E.} and Kurt Pinnow and Joe Ratterman and Nils Smeds and Burkhard Steinmacher-burow and William Gropp and Brian Toonen",
year = "2004",
doi = "10.1007/978-3-540-27866-5_112",
language = "English (US)",
isbn = "3540229248",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer",
pages = "833--845",
editor = "Marco Danelutto and Marco Vanneschi and Domenico Laforenza",
booktitle = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
address = "Germany",
}