Departmental Papers (CIS)

Date of this Version

June 2003

Document Type

Conference Paper

Comments

Copyright 2003 IEEE. Reprinted from Proceedings of the 30th Annual International Symposium on Computer Architecture (ISCA’03), pages 206-217.

This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or 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 must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

At the time of publication, author Milo M.K. Martin was affiliated with the University of Wisconsin. Currently, November 2006, he is a faculty member in the Department of Computer and Information Science at the University of Pennsylvania.

Abstract

Destination-set prediction can improve the latency/bandwidth tradeoff in shared-memory multiprocessors. The destination set is the collection of processors that receive a particular coherence request. Snooping protocols send requests to the maximal destination set (i.e., all processors), reducing latency for cache-to-cache misses at the expense of increased traffic. Directory protocols send requests to the minimal destination set, reducing bandwidth at the expense of an indirection through the directory for cache-to-cache misses. Recently proposed hybrid protocols trade-off latency and bandwidth by directly sending requests to a predicted destination set.

This paper explores the destination-set predictor design space, focusing on a collection of important commercial workloads. First, we analyze the sharing behavior of these workloads. Second, we propose predictors that exploit the observed sharing behavior to target different points in the latency/bandwidth tradeoff. Third, we illustrate the effectiveness of destination-set predictors in the context of a multicast snooping protocol. For example, one of our predictors obtains almost 90% of the performance of snooping while using only 15% more bandwidth than a directory protocol (and less than half the bandwidth of snooping).

Additional Files

isca03_destination_set_prediction.ppt (240 kB)
Powerpoint presentation at ISCA 2003 International Symposium

Share

COinS
 

Date Posted: 08 November 2006