Toward Exascale Computing Systems: An Energy Efficient Massive Parallel Computational Model
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2018, Vol 9, Issue 2
Abstract
The emerging Exascale supercomputing system expected till 2020 will unravel many scientific mysteries. This extreme computing system will achieve a thousand-fold increase in computing power compared to the current petascale computing system. The forthcoming system will assist system designers and development communities in navigating from traditional homogeneous to the heterogeneous systems that will be incorporated into powerful accelerated GPU devices beside traditional CPUs. For achieving ExaFlops (10^18 calculations per second) performance through the ultrascale and energy-efficient system, the current technologies are facing several challenges. Massive parallelism is one of these challenges, which requires a novel energy-efficient parallel programming (PP) model for providing the massively parallel performance. In the current study, a new parallel programming model has been proposed, which is capable of achieving massively parallel performance through coarse-grained and fine-grained parallelism over inter-node and intra-node architectural-based processing. The suggested model is a tri-level hybrid of MPI, OpenMP and CUDA that is computable over a heterogeneous system with the collaboration of traditional CPUs and energy-efficient GPU devices. Furthermore, the developed model has been demonstrated by implementing dense matrix multiplication (DMM). The proposed model is considered an initial and leading model for obtaining massively parallel performance in an Exascale computing system.
Authors and Affiliations
Muhammad Usman Ashraf, Fathy Alburaei Eassa, Aiiad Ahmad Albeshri, Abdullah Algarni
Keywords
Related Articles
- EP ID EP276400
- DOI 10.14569/IJACSA.2018.090217
- Views 87
- Downloads 0
Design of an Intelligent Combat Robot for war fields
The objective of this paper is to minimize human casualties in terrorist attack such as 26/11. The combat robot [1] has been designed to tackle such a cruel terror attacks. This robot is radio operated, self- powered, an...
Deep Gated Recurrent and Convolutional Network Hybrid Model for Univariate Time Series Classification
Hybrid LSTM-fully convolutional networks (LSTM-FCN) for time series classification have produced state-of-the-art classification results on univariate time series. We empirically show that replacing the LSTM with a gated...
Developing a Feasible and Maintainable Ontology for Automatic Landscape Design
In general, landscape architecture includes analysis, planning, design, administration and management of natural and artificial. An important aspect is the formation of so-called sustainable landscapes that allow maximum...
AMBA Based Advanced DMA Controller for SoC
This paper describes the implementation of an AMBA Based Advanced DMA Controller for SoC. It uses AMBA Specifications, where two buses AHB and APB are defined and works for processor as system bus and peripheral bus resp...
Defining Network Exposure Metrics in Security Risk Scoring Models
Organizations are exposed to cyber-attacks on a regular basis. Managers in these organizations are using scoring systems to evaluate the risks of the attacks they are exposed to. Information security methodologies define...