Title :
Block data decomposition for data-parallel programming on a heterogeneous workstation network
Author :
Crandall, Phyllis E. ; Quinn, Michael J.
Author_Institution :
Dept. of Comput. Sci., Oregon State Univ., Corvallis, OR, USA
Abstract :
The authors present a block data decomposition algorithm for two-dimensional grid problems. Their method includes local balancing to accommodate heterogeneous processors, and they characterize the conditions that must be met for their partitioning strategy to be of value. While they concentrate on the workstation network model of parallel processing because of its high communication costs and inherent heterogeneity, their method is applicable to other parallel architectures
Keywords :
parallel processing; parallel programming; virtual machines; block data decomposition; data-parallel programming; heterogeneity; heterogeneous workstation network; local balancing; parallel processing; two-dimensional grid problems; Bandwidth; Computational modeling; Computer networks; Concurrent computing; Costs; Ethernet networks; FDDI; Load management; Parallel processing; Workstations;
Conference_Titel :
High Performance Distributed Computing, 1993., Proceedings the 2nd International Symposium on
Conference_Location :
Spokane, WA
Print_ISBN :
0-8186-3900-8
DOI :
10.1109/HPDC.1993.263859
