Abstract
An MPI library, called MPICH-PM/CLUMP, has been implemented on a cluster of SMPs. MPICH-PM/CLUMP realizes zero copy message passing between nodes while using one copy message passing within a node to achieve high performance communication. To realize one copy message passing on an SMP, a kernel primitive has been designed which enables a process to read the data of another process. The get protocol using this primitive was added to MPICH. MPICH-PM/CLUMP has been run on an SMP cluster consisting of 64 Pentium II dual processors and Myrinet. It achieves 98 MByte/sec between nodes and 100 MBytes/sec within a node.
MRI Systems, Inc.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Message Passing Interface Implementation on Active Messages. http://now.CS.Berkeley.EDU/Fastcomm/MPI/.
MPI-BIP An implementation of MPI over Myrinet. http://lhpca.univ-lyon1.fr/mpibip.html.
MPI-FM: Message Passing Interface on Fast Messages. http://www-csag.cs.uiuc.edu/projects/comm/mpi-fm.html.
Myrinet. http://www.myri.com.
NAS Parallel Benchmarks.
PM: High-Performance Communication Library. http://www.rwcp.or.jp/lab/pdslab/pm/home.html.
Erik D. Demaine. A Threads-Only MPI Implementation for the Development of Parallel Programs. In 11th International Symposium on High Performance Computing Systems (HPCS’97), pp. 153–163, July 1997.
William Gropp and Ewing Lusk. MPICH Working Note: Creating a new MPICH device using the Channel interface. Technical report, Mathematics and Computer Science Division, Argonne National Laboratory, 1995.
Message-Passing Interface Forum. MPI: A message passing interface standard, version 1.1, June 1995.
Francis O’Carroll, Hiroshi Tezuka, Atsushi Hori, and Yutaka Ishikawa. The Design and Implementation of Zero Copy MPI Using Commodity Hardware with a High Performance Network. In ICS’98, July 1998.
Hiroshi Tezuka, Atsushi Hori, and Yutaka Ishikawa. Design and Implementation of PM: a Communication Library for Workstation Cluster. In JSPP’96 (in Japanese). IPSJ, June 1996. (in Japanese).
Hiroshi Tezuka, Atsushi Hori, Yutaka Ishikawa, and Mitsuhisa Sato. PM: An Operating System Coordinated High Performance Communication Library. In High-Performance Computing and Networking ’97, 1997.
Hiroshi Tezuka, Atsushi Hori, Francis O’Carroll, Hiroshi Harada, and Yutaka Ishikawa. A User level Zero-copy Communication using Pin-down cache. In IPSJ SIG Notes. IPSJ, August 1997. (in Japanese).
Hiroshi Tezuka, Francis O’Carroll, Atsushi Hori, and Yutaka Ishikawa. Pin-down Cache: A Virtual Memory Management Technique for Zero-copy Communication. In IPPS’98, April 1998.
Author information
Authors and Affiliations
Consortia
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag
About this paper
Cite this paper
Takahashi, T. et al. (1999). Implementation and evaluation of MPI on an SMP cluster. In: Rolim, J., et al. Parallel and Distributed Processing. IPPS 1999. Lecture Notes in Computer Science, vol 1586. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0098001
Download citation
DOI: https://doi.org/10.1007/BFb0098001
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65831-3
Online ISBN: 978-3-540-48932-0
eBook Packages: Springer Book Archive