Predicting reconfigurable interconnect performance in distributed shared-memory systems

Abstract

Reconfigurable interconnection networks have been shown to benefit performance in distributed shared-memory multiprocessor machines. Usually, performance measurements for these networks require large numbers of slow full-system simulations, making design-space exploration a cumbersome and time-consuming task. In this paper, we present a prediction model for the performance of a reconfigurable network, based on a single full-system simulation and a much shorter, per parameter set post-processing phase. We provide simulation results establishing the relative accuracy of the technique and analyze the impact of several assumptions that were made. With our method, a quick evaluation of a large range of parameters is now possible, allowing the designer to make well-founded design trade-offs.