%0 Journal Article
%A Villar, Juan A.
%A Andujar, Francisco
%A Alfaro, Francisco J.
%A Sanchez, Jose L.
%A Duato, Jose
%D 2009
%F heidok:9116
%R 10.11588/heidok.00009116
%T PGAS Model for the Implementation of Scalable Cluster Systems
%U https://archiv.ub.uni-heidelberg.de/volltextserver/9116/
%X This paper introduces an extended version of the traditional Partitioned Global Address Space (PGAS) model, for the implementation of scalable cluster systems, that the HyperTransport Consortium Advanced Technology Group (ATG) is working on. Using the Simics and GEMS simulators, we developed a software module that approximates the behavior of a PGAS cluster. This approach mainly provides the simplest mechanism to evaluate how much the PGAS infrastructure will affect overall the application performance. The aim of this work is to study the feasibility of the ATG’s PGAS model for running applications with high memory requirements. Such a model, will let manufacturers build clusters that enable the execution of these applications, in such a way that it will be impossible to run them in a single processor, or in a multi–processor.