Prediction model for evaluation of reconfigurable interconnects in distributed shared-memory systems
Wim Heirman, Joni Dambre, Christof Debaes, Hugo Thienpont, Dirk Stroobandt, Jan Van Campenhout · 2005
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.