Calibration of Network Simulations Against Hardware Implementations
Simulation represents the most flexible and available method for modelling interconnection networks. E.g. when simulating large InfiniBand clusters, that are infeasible to build for the sake of testing, simulation is a valuable tool to predict the performance characteristics of the cluster. In order to strengthen our confidence in the simulation results it is useful to calibrate the simulation model with a small prototype of its real world equivalent, when such a prototype is feasible.
Simulation represents the most flexible and available method for modelling interconnection networks. E.g. when simulating large InfiniBand clusters, that are infeasible to build for the sake of testing, simulation is a valuable tool to predict the performance characteristics of the cluster. In order to strengthen our confidence in the simulation results it is useful to calibrate the simulation model with a small prototype of its real world equivalent, when such a prototype is feasible.
The purpose of this thesis will the calibration of simulations against actual network hardware and to understand shortcomings and pitfalls of simulations.
What you will do:
- you will perform performance measurement on real hardware
- you will perform performance measurement on a simulation model and calibrate the model against the hardware
What you will learn:
- you will get to know the InfiniBand architecture, a state of the art high performance networking technology
- you will obtain a thorough understanding of the OpenSM software and the OFED stack
- you will learn to analyse network performance through simulations and measurements
References
