Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
projects:asphalt [2009/07/08 19:35]
pollock created
projects:asphalt [2012/01/23 17:24] (current)
sprenkle [Publications]
Line 1: Line 1:
 ====== Integrated Approach to Improving Performance of MPI Programs ====== ====== Integrated Approach to Improving Performance of MPI Programs ======
  
-The concept of "​Beowulf"​ clusters, or cheap clusters formed by a network of workstations,​ increased dramatically the performance-over-price ratio in the high performance computing world. Nevertheless,​ many domain scientists and engineers using such clustershave realized that the performance they can actually harness is only a fraction of what is available. Two reasons are mainly responsible for this effect. First, the level of complexity required for the communication of an application to be optimized for a particular cluster makes such optimizations out of reach for most non-expert systems programmers. At the same time the lack of portability experienced by applications tuned for specific clusterled most domain scientists and engineers to follow high-level generic communication solutions in their applications. In this project we are trying to use compiler technology to automatically fine tune applications while preserving the simplicity experienced by the programmer. ​+The concept of "​Beowulf"​ clusters, or cheap clusters formed by a network of workstations,​ increased dramatically the performance-over-price ratio in the high performance computing world. Nevertheless,​ many domain scientists and engineers using such clusters have realized that the performance they can actually harness is only a fraction of what is available. Two reasons are mainly responsible for this effect. First, the level of complexity required for the communication of an application to be optimized for a particular cluster makes such optimizations out of reach for most non-expert systems programmers. At the same time the lack of portability experienced by applications tuned for specific cluster led most domain scientists and engineers to follow high-level generic communication solutions in their applications. In this project we use compiler technology to automatically fine-tune applications while preserving the simplicity experienced by the programmer. ​
  
 Some of the research contributions have been: Some of the research contributions have been:
Line 18: Line 18:
  
  
 +===== Publications =====
  
 +[[http://​servo.cs.wlu.edu/​pubs/​handle/​id/​244/​browse?​value=Optimization+of+Parallel+Applications+for+Cluster+Computing&​type=project&​sort_by=2&​order=DESC|Complete List of Our Publications]]
 ===== Contributors ===== ===== Contributors =====
   * **Faculty**:​ Lori Pollock, Martin Swany   * **Faculty**:​ Lori Pollock, Martin Swany
   * **Ph.D. Students**: Antonios Danalis   * **Ph.D. Students**: Antonios Danalis
-  * **Undergraduates**: ​ 
   * **Collaborators**:​ John Cavazos, University of Delaware   * **Collaborators**:​ John Cavazos, University of Delaware
   * **Past Undergraduate Students**: Lewis Fishgold, Ki-Yong Kim, Aaron Brown   * **Past Undergraduate Students**: Lewis Fishgold, Ki-Yong Kim, Aaron Brown
  
projects/asphalt.1247096122.txt.gz ยท Last modified: 2009/07/08 19:35 by pollock
  • 213 Smith Hall   •   Computer & Information Sciences   •   Newark, DE 19716  •   USA
    Phone: 302-831-6339  •   Fax: 302-831-8458