Energy-time Performance of Heterogeneous Computing Systems
Parallel and Distributed Computing, Cloud and Edge Computing, Computer Architecture, Performance Modeling
Energy-Efficient Computing, Heterogeneous Systems, Pareto-Optimal
With heterogeneity becoming the norm in most computing platforms today, one of the key challenges is to determine the set of energy-time efficient system configurations among the large system configuration space to execute a parallel application. The project addresses the challenges using a measurement-driven analytical model that determines both time and energy-efficient system configurations.
Key novelties include modeling both inter and intra-node resource overlaps and resource contention. The core model and its extensions are applied to determine energy and time efficient system configurations and expose a number of insights. Firstly, there are multiple Pareto-optimal configurations that can be approximated using a distinct energy-deadline Pareto-frontier. Secondly, the energy-proportionality analysis reveals that inter-node heterogeneous clusters enable the scaling of the energy proportionality wall by exposing sub-linear energy-proportional configurations. Lastly, it uses a new metric called useful-computation-ratio which can be used to further optimize the Pareto-frontier.
Type of Work
System design, Software tool to determine optimal hardware configuration
Current State of work
Problem identified and Technology being developed around the work
1. Can be useful in parallel application, time and energy efficient system configuration, heterogeneous computing platforms
1. Modeling the Energy-Time Performance of MIC Architecture System, IEEE Conference on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, pp 85-94, 2016
2. A Time-Energy Performance Analysis of MapReduce on Heterogeneous Systems with GPUs, Performance Evaluation - An International Journal, Vol 91, pp 255-269, Sep 2015