Title :
Parallel program development and execution in the grid
Author_Institution :
MTA SZTAKI, Budapest, Hungary
Abstract :
Integration of P-GRADE with Condor and parallel check-pointing results in an environment under which both interactive parallel program development and batch mode execution is possible for the Grid. The integrated P-GRADE/Condor Grid system will guarantee reliable, fault-tolerant parallel program execution in the Grid, like the Condor system guarantees such features for sequential programs. The GRM/PROVE performance monitoring and visualisation toolset has been separated from P-GRADE and extended towards the Grid to create the basis of a general Grid application monitoring infrastructure for parallel programs.
Keywords :
parallel programming; software engineering; software fault tolerance; Condor; P-GRADE; batch mode execution; fault-tolerant parallel program execution; parallel checkpointing; parallel program development; performance monitoring; visualisation toolset; Availability; Fault tolerant systems; Grid computing; Metacomputing; Monitoring; Parallel processing; Resource management; Supercomputers; Telecommunication network reliability; Visualization;
Conference_Titel :
Parallel Computing in Electrical Engineering, 2002. PARELEC '02. Proceedings. International Conference on
Print_ISBN :
0-7695-1730-7
DOI :
10.1109/PCEE.2002.1115221