Title :
Analytic performance model for speculative, synchronous, discrete-event simulation
Author :
Noble, Bradley L. ; Chamberlain, Roger D.
Author_Institution :
Dept. of Electr. & Comput. Eng., Southern Illinois Univ., Edwardsville, IL, USA
Abstract :
Performance models exist that reliably describe the execution time and efficiency of parallel discrete-event simulations executed in a synchronous iterative fashion. These performance models incorporate the effects of processor heterogeneity, other processor load due to shared computational resources, application workload imbalance, and the use of speculative computation. This includes modeling the effects of predictive optimism, a technique for improving the accuracy of speculative assumptions. We extend these models to incorporate correlated workloads across the set of processors and validate the models with two different applications
Keywords :
discrete event simulation; parallel programming; software performance evaluation; analytic performance model; application workload imbalance; correlated workloads; parallel discrete-event simulations; predictive optimism; processor heterogeneity; processor load; shared computational resources; speculative synchronous discrete-event simulation; synchronous iteration; Computational modeling; Computer applications; Concurrent computing; Discrete event simulation; Iterative algorithms; Logic; Parallel processing; Performance analysis; Predictive models; Very large scale integration;
Conference_Titel :
Parallel and Distributed Simulation, 2000. PADS 2000. Proceedings. Fourteenth Workshop on
Conference_Location :
Bologne
Print_ISBN :
0-7695-0677-1
DOI :
10.1109/PADS.2000.847142
