English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Supporting Efficient Execution in Heterogeneous Distributed Computing Environments with Cactus and Globus

Allen, G., Dramlitsch, T., Foster, I., Karonis, N. T., Ripeanu, M., Seidel, E., et al. (2001). Supporting Efficient Execution in Heterogeneous Distributed Computing Environments with Cactus and Globus.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-56BF-1 Version Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-56C0-C
Genre: Conference Paper

Files

show Files
hide Files
:
23676.pdf (Publisher version), 203KB
Name:
23676.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
eDoc_access: PUBLIC
License:
-

Locators

show

Creators

show
hide
 Creators:
Allen, Gabrielle1, Author
Dramlitsch, Thomas1, Author
Foster, Ian, Author
Karonis, Nicolas T., Author
Ripeanu, Matei, Author
Seidel, Edward1, Author
Toonen, Brian, Author
Affiliations:
1Cactus Group, AEI-Golm, MPI for Gravitational Physics, Max Planck Society, ou_67202              

Content

show
hide
Free keywords: -
 Abstract: Improvements in the performance of processors and networks make it both feasible and interesting to treat collections of workstations, servers, clusters, and supercomputers as integrated computational resources, or Grids. However, the highly heterogeneous and dynamic nature of such Grids can make application development di.cult. Here we describe an architecture and prototype implementation for a Grid-enabled computational framework based on Cactus, the MPICH-G2 Grid-enabled message-passing library, and a variety of specialized features to support e.cient execution in Grid environments. We have used this framework to perform record-setting computations in numerical relativity, running across four supercomputers and achieving scaling of 88% (1140 CPU’s) and 63% (1500 CPUs). The problem size we were able to compute was about .ve times larger than any other previous run. Further, we introduce and demonstrate adaptive methods that automatically adjust computational parameters during run time, to increase dramatically the e.ciency of a distributed Grid simulation, without modi.cation of the application and without any knowledge of the underlying network connecting the distributed computers.

Details

show
hide
Language(s): eng - English
 Dates: 2001
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: eDoc: 23676
 Degree: -

Event

show
hide
Title: SC 2001
Place of Event: Denver, Colorado
Start-/End Date: 2001-11-10 - 2001-11-16

Legal Case

show

Project information

show

Source

show