Title :
Exploiting application tunability for efficient, predictable parallel resource management
Author :
Chang, Fangzhe ; Karamcheti, Vijay ; Kedem, Zvi
Author_Institution :
Courant Inst. of Math. Sci., New York Univ., NY, USA
Abstract :
Parallel computing is becoming increasing central and mainstream, driven both by the widespread availability of commodity SMP and high-performance cluster platforms, as well as the growing use of parallelism in general-purpose applications such as image recognition, virtual reality, and media processing. In addition to performance requirements, the latter computations impose soft real-time constraints, necessitating efficient, predictable parallel resource management. In this paper we propose a novel approach for increasing parallel system utilization while meeting application soft real-time deadlines. Our approach exploits the application tunability found in several general-purpose computations. Tunability refers to an application´s ability to trade off resource requirements over time, while maintaining a desired level of output quality. We first describe language extensions to support tunability in the Calypso system, then characterize the performance benefits of tunability, using a synthetic task system to systematically identify its benefits. Our results show that application tunability is convenient to express and can significantly improve parallel system utilization for computations with predictability requirements
Keywords :
parallel processing; real-time systems; resource allocation; Calypso system; SMP platforms; application soft real-time deadlines; application tunability; efficient parallel resource management; general-purpose computations; high-performance cluster platforms; image recognition; language extensions; media processing; output quality; parallel computing; parallel system utilization; parallelism; performance requirements; predictable parallel resource management; resource requirements trade-off; soft real-time constraints; synthetic task system; virtual reality; Availability; Concurrent computing; Costs; Delay; Hardware; Image recognition; Parallel processing; Real time systems; Resource management; Virtual reality;
Conference_Titel :
Parallel Processing, 1999. 13th International and 10th Symposium on Parallel and Distributed Processing, 1999. 1999 IPPS/SPDP. Proceedings
Conference_Location :
San Juan
Print_ISBN :
0-7695-0143-5
DOI :
10.1109/IPPS.1999.760560