Abstract | ||
---|---|---|
The paper concerns task graph scheduling in parallel programs using the concept of moldable computational tasks for a parallel architecture based on dynamic SMP processor clusters with data transmissions on the fly. The presented algorithm for scheduling parallel program graphs decomposes an initial program graph to sub-graphs, which fulfill the definition of a moldable task. So identified moldable tasks are then scheduled using an algorithm with warranted schedule length. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/PARELEC.2004.44 | PARELEC |
Keywords | Field | DocType |
dynamic smp processor cluster,moldable task,paper concerns task graph,dynamic smp clusters,moldable task scheduling,parallel program graph,parallel architecture,data transmission,warranted schedule length,initial program graph,parallel program,moldable computational task,clustering algorithms,scheduling algorithm,parallel programming,computer science,data flow analysis,dynamic scheduling,network on a chip,concurrent computing,information technology | Data transmission,Scheduling (computing),Read-write memory,Computer science,Parallel computing,Network on a chip,Data-flow analysis,Concurrent computing,Dynamic priority scheduling,Cluster analysis,Distributed computing | Conference |
ISBN | Citations | PageRank |
0-7695-2080-4 | 0 | 0.34 |
References | Authors | |
4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lukasz Masko | 1 | 133 | 21.40 |
Gregory Mounie | 2 | 137 | 11.22 |
Denis Trystram | 3 | 1120 | 160.57 |
Marek Tudruj | 4 | 271 | 56.00 |