HLogGP: a new parallel computational model for heterogeneous clusters

Heterogeneous clusters claim for new models and algorithms. In this paper a new parallel computational model is presented. The model, based on the LogGP model, has been extended to be able to deal with heterogeneous parallel systems. For that purpose, the LogGP´s scalar parameters have been replaced by vector and matrix parameters to take into account the different node´s features. The work presented here includes the parameterization of a real cluster which illustrates the impact of node heterogeneity over the model´s parameters. Finally, the paper presents some experiments performed in a real heterogeneous cluster that can be used for assessing the method´s validity, together with the main conclusions and future work.