A knowledge discovery methodology for behavior analysis of large-scale applications on parallel architectures

Abstract

The focus of this paper is the application and extension of the knowledge discovery in databases process [5] developed in PYTHIA recommender system, to analyze the behavior of a DOE ASCI application/hardware pairs in the context of POEMS project[4]. The POEMS project has built a library of models for modeling scalable architectures like those in the ASCI program. Moreover, it supports detail simulation of a variety of state-of-the-art processors and memory hierarchies and incorporates parallel evaluation of discrete-event simulation. The driver application used is SWEEP3D.