Proceedings of 1995 1st IEEE Symposium on High Performance Computer Architecture (1995)
Raleigh, North Carolina
Jan. 22, 1995 to Jan. 25, 1995
A. Sivasubramaniam , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
M. Singla , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
U. Ramachandran , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
H. Venkateswaran , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
Abstracting features of parallel systems is a technique that has been traditionally used in theoretical and analytical models for program development and performance evaluation. We explore the use of abstractions in execution-driven simulators in order to speed up simulation. In particular, we evaluate abstractions for the interconnection network and locality, properties of parallel systems in the context of simulating cache-coherent shared memory (CC-NUMA) multiprocessors. We use the recently proposed LogP model to abstract the network. We abstract locality by modeling a cache at each processing node in the system which is maintained coherent, without modeling the overheads associated with coherence maintenance. Such an abstraction tries to capture the true communication characteristics of the application without modeling any hardware induced artifacts. Using a suite of applications and three network topologies simulated on a novel simulation platform, we show that the latency overhead modeled by LogP is fairly accurate. On the other hand, the contention overhead can become pessimistic when the applications display sufficient communication locality. Our abstraction for data locality closely models the behavior of the target system over the chosen range of applications. The simulation model which incorporated these abstractions was around 250-300% faster than the simulation of the target machine.
performance evaluation; parallel architectures; virtual machines; multiprocessor interconnection networks; message passing; cache storage; shared memory systems; network characteristics; locality properties; parallel systems; execution-driven simulators; interconnection network; cache-coherent shared memory multiprocessors; coherence maintenance; communication characteristics; hardware induced artifacts; latency overhead; contention overhead; communication locality; LogP model
H. Venkateswaran, U. Ramachandran, A. Sivasubramaniam and M. Singla, "Abstracting network characteristics and locality properties of parallel systems," Proceedings of 1995 1st IEEE Symposium on High Performance Computer Architecture(HPCA), Raleigh, North Carolina, 1995, pp. 54.