Prediction model for evaluation of reconfigurable interconnects in distributed shared-memory systems

Authors:
W. Heirman;J. Dambre;C. Debaes;H. Thienpont;D. Stroobandt;J. Van Campenhout
Affiliations:
Ghent University, Ghent, Belgium;Ghent University, Ghent, Belgium;Ghent University, Ghent, Belgium;Free University of Brussels, Brussels, Belgium;Free University of Brussels, Brussels, Belgium;Ghent University, Ghent, Belgium
Venue:
Proceedings of the 2005 international workshop on System level interconnect prediction
Year:
2005

Citing 5
Cited 3

The Stanford Dash Multiprocessor

Computer
The SPLASH-2 programs: characterization and methodological considerations

ISCA '95 Proceedings of the 22nd annual international symposium on Computer architecture
Limit to the bit-rate capacity of electrical interconnects from the aspect ratio of the system architecture

Journal of Parallel and Distributed Computing - Special issue on parallel computing with optical interconnects
Simics: A Full System Simulation Platform

Computer
Traffic Temporal Analysis for Reconfigurable Interconnects in Shared-Memory Systems

IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 3 - Volume 04

Congestion modeling for reconfigurable inter-processor networks

Proceedings of the 2006 international workshop on System-level interconnect prediction
Profiling of parallel processing programs on shared memory multiprocessors using Simics

ACM SIGARCH Computer Architecture News - Special issue on the 2005 workshop on binary instrumentation and application
Predicting reconfigurable interconnect performance in distributed shared-memory systems

Integration, the VLSI Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reconfigurable interconnection networks for distributed shared memory machines exploit properties of the workload dynamics that are not easily captured by statistical traffic models. Therefore, when designing such a network, one should make trade-offs based on full-system simulation for all viable workloads. It is however very time-consuming to do such simulations. In this paper, we present a technique that can predict the performance of a machine for different network parameters, based on the results of only one full simulation run. We also define confidence intervals for our prediction, and analyze the impact of several assumptions that were made.