Shared Memory Parallel Programming with Open MP: 5th International Workshop on Open MP Applications and Tools, WOMPAT 2004, Houston, TX, USA, May 17-18, 2004, Revised Selected Papers

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

This book contains the Proceedings of the 5th Workshop on OpenMP Appli- tionsandTools(WOMPAT2004),whichtookplaceattheUniversityofHouston, Houston, Texas on May 17 and 18, 2004. Previous workshops in this series took place in Toronto, Canada, Fairbanks, Alaska, Purdue, Indiana, and San Diego, California.Thepurposeoftheworkshopwastobringtogetherusersanddevel- ers of the OpenMP API for shared memory parallel programming to disseminate their ideas and experiences and discuss the latest developments in OpenMP and its application. To support this aim, the program comprised a mixture of invited talks from research and industry, experience reports, and submitted papers, the last of which are presented in this volume. A tutorial introduction to OpenMP was held at the same location on May 18 by Ruud van der Pas from Sun Microsystems. Further, a two-day lab session called OMPlab was held immediately following the workshop and the tutorial on May 19 and 20, and was attended by both novice and advanced users. Many of the hardware vendors and several researchers gave in-depth tutorials on their softwareandmadetheirsystemsavailabletobothnoviceandadvancedattendees during OMPlab. Contributors to the WOMPAT 2004 OMPlab included IBM, Intel, Sun, the University of Tennessee, NASA, the University of Greenwich, Cornell University, the University of Oregon and the University of Houston. TheOpenMPAPIisawidelyacceptedstandardforhigh-levelsharedmemory parallel programming that was put forth by a consortium of vendors in 1997.

Author(s): Jonathan L. Bentz, Ricky A. Kendall (auth.), Barbara M. Chapman (eds.)
Series: Lecture Notes in Computer Science 3349 : Theoretical Computer Science and General Issues
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2005

Language: English
Pages: 154
Tags: Software Engineering/Programming and Operating Systems; Computer Systems Organization and Communication Networks; Theory of Computation; Mathematics of Computing

Front Matter....Pages -
Parallelization of General Matrix Multiply Routines Using OpenMP....Pages 1-11
Performance Analysis of Hybrid OpenMP/MPI N-Body Application....Pages 12-18
Performance and Scalability of OpenMP Programs on the Sun Fire TM E25K Throughput Computing Server....Pages 19-28
What Multilevel Parallel Programs Do When You Are Not Watching: A Performance Analysis Case Study Comparing MPI/OpenMP, MLP, and Nested OpenMP....Pages 29-40
SIMT/OMP: A Toolset to Study and Exploit Memory Locality of OpenMP Applications on NUMA Architectures....Pages 41-52
Dragon: A Static and Dynamic Tool for OpenMP....Pages 53-66
The ParaWise Expert Assistant – Widening Accessibility to Efficient and Scalable Tool Generated OpenMP Code....Pages 67-82
Automatic Scoping of Variables in Parallel Regions of an OpenMP Program....Pages 83-97
An Evaluation of Auto-Scoping in OpenMP....Pages 98-109
Structure and Algorithm for Implementing OpenMP Workshares....Pages 110-120
Efficient Implementation of OpenMP for Clusters with Implicit Data Distribution....Pages 121-136
Runtime Adjustment of Parallel Nested Loops....Pages 137-147
Back Matter....Pages -