Exploiting Application Tunability for Efficient, Predictable Parallel Resource Management

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 generalpurpose 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 generalpurpose 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, usi...

• Type: Conference
• Year: 1999
• Where: IPPS
• Authors: Fangzhe Chang, Vijay Karamcheti, Zvi M. Kedem
• Keywords: Application Tunability, Distributed And Parallel Computing, IPPS 1999, Predictable Parallel Resource, Soft Real-time