Architecture and Performance of the BlueGene/L Message Layer

The BlueGene/L supercomputer is planned to consist of 65,536 dual-processor compute nodes interconnected by high speed torus and tree networks. Compute nodes can only address local memory, making message passing the natural programming model for the machine. In this paper we present the architecture and performance of the BlueGene/L message layer, the software library that makes an efficient MPI implementation possible. We describe the components and protocols of the message layer, and present microbenchmark based performance results for several aspects of the library.

By: Gheorghe Almasi; Charles Archer; John A. Gunnels; Philip Heidelberger; Xavier Martorell; Jose E. Moreira

Published in: Lecture Notes in Computer Science, volume 3241, (no ), pages 405-14 in 2004

Please obtain a copy of this paper from your local library. IBM cannot distribute this paper externally.

Questions about this service can be mailed to .