12 juillet 2010

Yudith Cardinale

Big scale computing models such as Grid Computing paradigm and more recently the Cloud Computing paradigm, empowers an efficient and cost effective use of distributed computing resources and collaborative work among groups of users and researchers with similar scientific or commercial interests, namely Virtual Organizations (VOs). The main goal of the Grid Computing paradigm, targeted specifically at scientific research communities, is to transparently offer computing and data resources at the disposal of VO members. A special software layer called middleware takes care of efficient and transparent management of resources. On the other hand, the Cloud computing paradigm, mainly targeted at commercial uses, tries to fully virtualise infrastructure, platform, and applications layers, offering them as services under the so called Everything as a Service (EaaS) model. The main goal is based on the principle of economy of scale, which establishes that costs are reduced proportionally to the production volume. In this talk, I will present a brief overview of Grid and Cloud computing concepts, and then describe some projects that are developed at USB, Venezuela:

  • SUMA/G: A Java-based middleware for Grid computing,
  • Jadima: A distributed framework for remote publication, compilation, and execution of Java applications which use distributed libraries.
  • Distributed Shared Memory for cluster, grid, and cloud computing: KRC and XTremoos
  • Web Service Composition on Grid platforms