ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Non-Strict Cache Coherence: Exploiting Data-Race Tolerance in Emerging Applications

Tambat, Siddhartha V and Vajapeyam, Sriram (2000) Non-Strict Cache Coherence: Exploiting Data-Race Tolerance in Emerging Applications. In: 2000 International Conference on Parallel Processing, 21-24 August, Toronto,Canada, pp. 87-94.

[img]
Preview
PDF
non-strict.pdf

Download (853Kb)

Abstract

Software distributed shared memory (DSM) platforms on networks of workstations tolerate large network latencies by employing one of several weak memory consistency models. Data-race tolerant applications, such as Genetic Algorithms (GAS), Probabilistic Inference, etc., offer an additional degree of freedom to tolerate network latency: they do not synchronize shared memory references, and behave correctly when supplied outdated shared data. However; these algorithms often have a high communication-to-computation ratio and can jlood the network with messages in the presence of large message delays. We study the performance of controlled asynchronous implementations of these algorithms via the use of our previously proposed blocking GlobalRead memory access primitive. GlobalRead implements non-strict cache coherence by guaranteeing to return to the reader a shared datum value from within a specified staleness range. Experiments on an IBM SP2 multicomputer with an Ethernet show significant performance improvements for controlled asynchronous implementations. On a lightly loaded Ethernet network, most of the GA benchmarks see 30% to 40% improvement over the best competitor for 2 to 16 processors, while two of the Probabilistic Inference benchmarks see more than 80% improvement for 2 processors. As the network load increases, the benefits of non-strict cache coherence increase significantly.

Item Type: Conference Paper
Additional Information: Copyright 1990 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Department/Centre: Division of Information Sciences > Supercomputer Education & Research Centre
Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)
Date Deposited: 28 Feb 2006
Last Modified: 19 Sep 2010 04:24
URI: http://eprints.iisc.ernet.in/id/eprint/5725

Actions (login required)

View Item View Item