HPC Applications Deployment on Distributed Heterogeneous Computing Platforms via OMF, OML and P2PDC

Abstract

A new tool and web portal are presented for deployment of High Performance Computing applications on distributed heterogeneous computing platforms. This tool relies on the decentralized environment P2PDC and the OMF and OML multithreaded control, instrumentation and measurement libraries. Deployment on PlanetLab of a numerical simulation application is studied. A first series of computational results is displayed and analyzed.

On Parallel or Distributed Asynchronous Iterations with Unbounded Delays and Possible Out of Order Messages or Flexible Communication for Convex Optimization Problems and Machine Learning

“…We have also considered distributed computing platforms such as Planetlab, whereby computations were carried out on several computing nodes scattered on different continents. In particular, computing experiments were performed on a network with nodes located in Australia and North America, see [27] and optimization as well as numerical simulation problems were solved thanks to the cooperation of these distant computing nodes. Finally, we have considered clusters and grid computing infrastructures such as GRID5000 (see [28]), whereby computations were distributed among several clusters situated in different cities in a multicore and multi network configuration, i.e., a configuration that combines Infiniband, Myrinet and fast Ethernet network for the same computing application.…”