Design choices in the SHRIMP system: an empirical study

Abstract

The SHRIMP cluster-computing system has progressed to a point of relative maturity; a variety of applications are running on a 16-node system. We have enough experience to understand what we did right and wrong in designing and building the system. In this paper we discuss some of the lessons we learned about computer architecture, and about the challenges involved in building a significant working system in an academic research environment. We evaluate significant design choices by modifying the network interface firmware and the system software in order to empirically compare our design to other approaches. Introduction Multicomputer and multiprocessor architectures appear to be converging due to technological and economic forces. A typical architecture is now a commodity network connecting a set of compute nodes where each node consists of one or more microprocessors, caches, DRAMs, and a network interface. The node architectures of different systems are not only sim...