MGO:An Optimized Collective Communication Algorithm for Heterogeneous Cluster

LI Chun-hua; ZHOU Xing-ming

您当前的位置：

首页 >

文章列表页 >

MGO:An Optimized Collective Communication Algorithm for Heterogeneous Cluster

更新时间：2025-07-16

- MGO:An Optimized Collective Communication Algorithm for Heterogeneous Cluster
- Acta Electronica Sinica Vol. 30, Issue 11, Pages: 1643-1647(2002)
- 作者机构：
  
  并行与分布处理国家重点实验室,国防科学技术大学计算机学院,湖南,长沙,410073
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP393
- Published：2002
- 稿件说明：
移动端阅览
LI Chun-hua, ZHOU Xing-ming. MGO:An Optimized Collective Communication Algorithm for Heterogeneous Cluster[J]. Acta Electronica Sinica, 2002, 30(11): 1643-1647.
DOI：

LI Chun-hua, ZHOU Xing-ming. MGO:An Optimized Collective Communication Algorithm for Heterogeneous Cluster[J]. Acta Electronica Sinica, 2002, 30(11): 1643-1647. DOI：

摘要

在异构集群环境中

网络拓扑结构的不规则性

以及计算机结点和网络性能的差异

影响了全局通讯的性能.针对这个问题

本文提出一种全局通讯的多粒度优化算法

该算法结合网络拓扑结构以及计算机结点和网络性能等参数来优化全局通讯路径.模拟结果表明

多粒度优化算法与相关优化算法相比

能显著提高全局通讯性能

并且性能提高百分比在一定范围内随着集群规模的扩大而增大.

Abstract

In heterogeneous cluster environment

the network topology is irregular

and performance gap exists among computer nodes and among interconnected networks.These factors affect the performance of collective communication.To solve this problem

we present MGO (Multi-Granularity Optimization) algorithm.In MGO algorithm

we optimize the path for collective communication by network topology and the performance of the computer nodes and the networks.The simulation results show that by comparing MGO algorithm with related optimized algorithm

the former can result in notable performance improvement.Moreover

the performance-enhancing ratio increases to some extent as the cluster scales up.

关键词

Keywords

references

Views

772

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study on Load Balancing Algorithms Based on Multiple Resources

Color Vector Morphological Operators on Graph Space

A Research of Cut-Through Communication and Topology

A Scalable Model of Spiral Inductor on Modified 1-π Topology

A Study of Bionic Micro-channel Topology for Chip Cooling

Related Author

LIAO Xiang-ke

ZHANG Min-xuan

JIANG Jiang

GAO Yan-hong

WANG Jun-ping

LI Ya-ning

黄智

刘心松

Related Institution

School of Computer, National University of Defense Technology

School of Telecommunication Engineering, Xidian University

电子科技大学计算机系

School of Communication and Information Engineering, Shanghai University

Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences

⁰