DSIM: Scaling Time Warp to 1,033 Processors Gilbert Chen Boleslaw K. Szymanski This paper describes the design and implementation of a new Time Warp simulator, called DSIM that targets clusters comprised of thousands of processors. DSIM employs a novel technique for efficient, scalable GVT computation, called the Time Quantum GVT algorithm that requires no message acknowledgement and relies on constant-length messages. In addition, DSIM implements a Local Fossil Collection mechanism that alleviates the overhead associated with memory reclamation and an efficient event management to ensure fast event manipulation during simulation. It is also equipped with a simple programming interface to ease programming and debugging of simulations. Experimental results obtained on the PHOLD benchmark demonstrate that DSIM can process as many as 228 million events per second on 1033 processors. Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY cs-05-12
DSIM: Scaling Time Warp to 1,033 Processors
Gilbert Chen
Boleslaw K. Szymanski
This paper describes the design and implementation of a new Time Warp simulator, called DSIM that targets clusters comprised of thousands of processors. DSIM employs a novel technique for efficient, scalable GVT computation, called the Time Quantum GVT algorithm that requires no message acknowledgement and relies on constant-length messages. In addition, DSIM implements a Local Fossil Collection mechanism that alleviates the overhead associated with memory reclamation and an efficient event management to ensure fast event manipulation during simulation. It is also equipped with a simple programming interface to ease programming and debugging of simulations. Experimental results obtained on the PHOLD benchmark demonstrate that DSIM can process as many as 228 million events per second on 1033 processors.
Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY
cs-05-12