Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Parallel simulation is a technique to accelerate microarchi-tecture simulation of CMPs by exploiting the inherent paral-

Parallel simulation is a technique to accelerate microarchi-
tecture simulation of CMPs by exploiting the inherent paral-
lelism of CMPs. In this paper, we explore the simulation
paradigm of simulating each core of a target CMP in one
thread and then spreading the threads across the hardware
thread contexts of a host CMP. We start with cycle-by-cycle
simulation and then relax the synchronization condition in
various schemes, which we call slack simulations.
In slack simulations, the Pthreads simulating different simu-
lated cores do not synchronize after each simulated cycle, but
rather they are given some slack. The slack is the difference
in cycle between the simulated times of any two target cores.
Small slacks, such as a few cycles, greatly improve the effi-
ciency of parallel CMP simulations, with no or negligible
simulation error. We have developed a simulation framework
called SlackSim to experiment with various slack simulation
schemes. Unlike previous attempts to parallelize multiproces-
sor simulations on distributed memory machines, SlackSim
takes advantage of the efficient sharing of data in the host


Source: Annavaram, Murali - Department of Electrical Engineering, University of Southern California


Collections: Engineering; Computer Technologies and Information Sciences