Title :
Runtime incremental parallel scheduling (RIPS) for large-scale parallel computers
Author :
Shu, Wei ; Wu, Min-You
Author_Institution :
Dept. of Comput. Sci., State Univ. of New York, Buffalo, NY, USA
Abstract :
Runtime incremental parallel scheduling (RIPS) is an alternative strategy to the commonly used dynamic scheduling. In this scheduling strategy, the system scheduling activity alternates with the underlying computation work. RIPS utilizes advanced parallel scheduling techniques to produce a low-overhead, high-quality load balancing and adapts to applications of nonuniform structures
Keywords :
parallel processing; parallel programming; scheduling; dynamic scheduling; large-scale parallel computers; load balancing; nonuniform structures; runtime incremental parallel scheduling; system scheduling activity; Computer science; Concurrent computing; Dynamic scheduling; Large-scale systems; Load management; Parallel machines; Parallel programming; Processor scheduling; Runtime; Scheduling algorithm;
Conference_Titel :
Frontiers of Massively Parallel Computation, 1995. Proceedings. Frontiers '95., Fifth Symposium on the
Conference_Location :
McLean, VA
Print_ISBN :
0-8186-6965-9
DOI :
10.1109/FMPC.1995.380479
