“School of Computer Science”
Back to Papers HomeBack to Papers of School of Computer Science
| Paper IPM / Computer Science / 10774 |
|
||||||
| Abstract: | |||||||
|
Performance evaluation is an important engineering tool that provides valuable feedback on design choices in the implementation of multi-core systems such as parallel systems, multicomputers, and Systems-on-Chip (SoCs). The significant advantage of analytical models over simulation is that they can be used to obtain performance results for large systems under different configurations and working conditions which may not be feasible to study using simulation on conventional computers due to the excessive computation demands. We present Caspian, a novel analytic performance model, aimed to minimize prediction cost, while providing prediction accuracy. This is accomplished by using a G/G/1 priority queueing model which is used for arbitrary network topology with wormhole routing under arbitrary traffic pattern. The accuracy of this model is examined through extensive simulation results.
Download TeX format |
|||||||
| back to top | |||||||
