Computer Systems Group

The Computer Systems Group (CSG) was set-up in June 2017. Computer Systems Group undertakes research and development in all fundamental aspects of Computing Systems spanning across hardware and software. This group is actively involved in research and imparting advanced training through workshops, seminars, and semester long courses in the fields of computer architecture, compilers, computer networks, operating systems and other related topics. As a new group CSG today has about 3 faculty members and about 15 research students including Phd, Masters and honors students working on research topics that directly contribute and make an impact on the next-generation computing hardware and software.

Energy-time Performance of Heterogeneous Computing Systems

Research Area
Parallel and Distributed Computing, Cloud and Edge Computing, Computer Architecture, Performance Modeling
Keyword
Energy-Efficient Computing, Heterogeneous Systems, Pareto-Optimal
Technology Description
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
Potential Applications
1. Can be useful in parallel application, time and energy efficient system configuration, heterogeneous computing platforms
Related Publications
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