loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
11th IEEE International Symposium on High Performance Distributed Computing (HPDC-11 '02)
Backtracking and Re-Execution in the Automatic Debugging of Parallelized Programs
Edinburgh, Scotland
July 24-July 26
ISBN: 0-7695-1686-6
ASCII Text
x 
 
Gregory Matthews, Robert Hood, Stephen Johnson, Peter Leggett, "Backtracking and Re-Execution in the Automatic Debugging of Parallelized Programs," High-Performance Distributed Computing, International Symposium on, pp. 150, 11th IEEE International Symposium on High Performance Distributed Computing (HPDC-11 '02), 2002.
 
 
BibTex
x
 
@article{ 10.1109/HPDC.2002.1029913,
author = {Gregory Matthews and Robert Hood and Stephen Johnson and Peter Leggett},
title = {Backtracking and Re-Execution in the Automatic Debugging of Parallelized Programs},
journal ={High-Performance Distributed Computing, International Symposium on},
volume = {0},
year = {2002},
issn = {1082-8907},
pages = {150},
doi = {http://doi.ieeecomputersociety.org/10.1109/HPDC.2002.1029913},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - High-Performance Distributed Computing, International Symposium on
TI - Backtracking and Re-Execution in the Automatic Debugging of Parallelized Programs
SN - 1082-8907
SP
EP
A1 - Gregory Matthews,
A1 - Robert Hood,
A1 - Stephen Johnson,
A1 - Peter Leggett,
PY - 2002
KW - null
VL - 0
JA - High-Performance Distributed Computing, International Symposium on
ER -
 
Gregory Matthews, NASA Ames Research Center
Robert Hood, NASA Ames Research Center
Stephen Johnson, University of Greenwich
Peter Leggett, University of Greenwich
In this work we describe a new approach using relative debugging to find differences in computation between a serial program and a parallel version of that program. We use a combination of re-execution and backtracking in order to find the first difference in computation that may ultimately lead to an incorrect value that the user has indicated. In our prototype implementation we use static analysis information from a parallelization tool in order to perform the backtracking as well as the mapping required between serial and parallel computations.
Citation:
Gregory Matthews, Robert Hood, Stephen Johnson, Peter Leggett, "Backtracking and Re-Execution in the Automatic Debugging of Parallelized Programs," hpdc, pp.150, 11th IEEE International Symposium on High Performance Distributed Computing (HPDC-11 '02), 2002
Usage of this product signifies your acceptance of the Terms of Use.