The High Performance Internet of Things: Using GVirtuS to Share High-End GPUs with ARM Based Cluster Computing Nodes

The availability of computing resources and the need for high quality services are rapidly evolving the vision about the acceleration of knowledge development, improvement and dissemination. The Internet of Things is growing up. The high performance cloud computing is behind the scene powering the next big thing. In this paper, using the GVirtuS, general purpose virtualization service, we demonstrate the feasibility of accelerate inexpensive ARM based computing nodes with high-end GPUs hosted on \(\mathrm{x}86\_64\) machines. We draw the vision of a possible next generation of low-cost, off the shelf, computing clusters we call Neowulf characterized by high heterogenic parallelism and expected as low electric power demanding and head producing.

[1]  Marco Lapegna,et al.  A Performance Contract System in a Grid Enabling, Component Based Programming Environment , 2005, EGC.

[2]  Raffaele Montella,et al.  SIaaS - Sensing Instrument as a Service Using Cloud Computing to Turn Physical Instrument into Ubiquitous Service , 2012, 2012 IEEE 10th International Symposium on Parallel and Distributed Processing with Applications.

[3]  Almerico Murli,et al.  Monitoring and Migration of a PETSc-based Parallel Application for Medical Imaging in a Grid computing PSE , 2006, Grid-Based Problem Solving Environments.

[4]  Ian T. Foster,et al.  Using Hybrid Grid/Cloud Computing Technologies for Environmental Data Elastic Storage, Processing, and Provisioning , 2010, Handbook of Cloud Computing.

[5]  Lucia Maddalena,et al.  A fusion-based approach to digital movie restoration , 2009, Pattern Recognit..

[6]  Ian T. Foster,et al.  SOLE: Linking Research Papers with Science Objects , 2012, IPAW.

[7]  Borko Furht,et al.  Handbook of Cloud Computing , 2010 .

[8]  Mario Rosario Guarracino,et al.  A grid enabled PSE for medical imaging: experiences on MedIGrid , 2005, 18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).

[9]  Francisco Javier García Blas,et al.  A General-Purpose Virtualization Service for HPC on Cloud Computing: An Application to GPUs , 2011, PPAM.

[10]  Giulio Giunta,et al.  Multidimensional Environmental Data Resource Brokering on Computational Grids and Scientific Clouds , 2010, Handbook of Cloud Computing.

[11]  Zoran Constantinescu,et al.  Advances in Grid Computing , 2011 .

[12]  Raffaele Montella,et al.  A globus toolkit 4 based instrument service for environmental data acquisition and distribution , 2008, UPGRADE '08.

[13]  James C. T. Pool,et al.  Grid-Based Problem Solving Environments - IFIP TC2/ WG 2.5 Working Conference on Grid-Based Problem Solving Environments: Implications for Development and Deployment of Numerical Software July 17-21, 2006, Prescott, Arizona, USA , 2007, Grid-Based Problem Solving Environments.

[14]  Almerico Murli,et al.  MGF: A grid-enabled MPI library , 2008, Future Gener. Comput. Syst..

[15]  Giulio Giunta,et al.  A GPGPU Transparent Virtualization Component for High Performance Computing Clouds , 2010, Euro-Par.

[16]  Giulio Giunta,et al.  Five Dimension Environmental Data Resource Brokering on Computational Grids and Scientific Clouds , 2008, 2008 IEEE Asia-Pacific Services Computing Conference.

[17]  Francisco Javier García Blas,et al.  A GPU Accelerated High Performance Cloud Computing Infrastructure for Grid Computing Based Virtual Environmental Laboratory , 2011 .