EXPERIMENTAL RESULTS ABOUT MPI COLLECTIVE COMMUNICATION OPERATIONS

Author:

BERNASCHI MASSIMO1,IANNELLO GIULIO2,CREA SAVERIO1

Affiliation:

1. Istituto Applicazioni del Calcolo, Consiglio Nazionale delle Ricerche, 137 viale del Policlinico, Roma, 00161, Italy

2. Facoltà di Ingegneria, Università Campus Bio-Medico di Roma, 83 Via Emilio Longoni, Roma, 00155, Italy

Abstract

Collective communication performance is critical in a number of MPI applications. In this paper we focus on two widely used primitives, broadcast and reduce, and present experimental results obtained on a cluster of PC connected by InfiniBand. We integrated our algorithms in the MPICH library and we used MPICH implementation of broadcast and reduce primitives to compare the performance of our algorithms based on α-trees. Our tests show that the MPICH implementation can be improved.

Publisher

World Scientific Pub Co Pte Lt

Subject

Hardware and Architecture,Theoretical Computer Science,Software

Reference8 articles.

1. Message Passing Interface ForumThe International Journal of Supercomputer Applications and High Performance Computing 8(3/4), (1994).

2. Collective communication operations: experimental results vs. theory

3. Improving the Performance of Collective Operations in MPICH

4. Collective Communication on Dedicated Clusters of Workstations

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3