Analytical modeling of multithreaded architectures

Multithreading is used for hiding long memory latency in uniprocessors and multiprocessor computer systems and aims at increasing system efficiency. I n such an architecture, a number of threads are allocated to each processin g element (PE) and whenever a running thread becomes suspended the PE switc hes to another ready thread. In this paper, we discuss analytical modeling of coarsely multithreaded arc hitectures and present two analytical models: (i) a deterministic model, wh ere the timing parameters (e.g., context switching time, threads's run leng th, and memory latency) are assumed to be constant, and (ii) a stochastic m odel where the timing parameters are random variables. Both models provide a framework to study the dependence of the MTA efficien cy on design parameters of the target architecture and its workload. The de terministic model, as well as asymptotic bounding analysis of the stochasti c model, allows to determine upper bounds and some break points of the MTA efficiency such as stability (saturation) points, whereas the stochastic mo del provides more accurate prediction of the efficiency. (C) 2000 Elsevier Science B.V. All rights reserved.