On the Role of Autonomics in Emerging Computational Ecosystems

Manish Parashar
Center for Advanced Information Processing
Rutgers University
New Brunswick, New Jersey, USA


Abstract:

Significant strategic investments are quickly realizing a pervasive computational infrastructure that integrates computers, networks, data archives, instruments, observatories, and embedded sensors and actuators. This in turn has the potential for enabling new paradigms and practices in computational science and engineering ? those that symbiotically and opportunistically combine computations, experiments, observations, and real-time information. However the ability of scientists to realize this potential is being severely hampered primarily due to the increased complexity and dynamism of the applications and computing environments. Autonomic computing has the potential to fundamentally address these challenges. In this talk, I will motivate autonomics for computational science and engineering. I will then describe research efforts at TASSL, Rutgers University as part of the NSF Center for Autonomic Computing aimed at enabling autonomic scientific and engineering applications that can address the challenges of (and benefit from) pervasive computational ecosystems.

Biography: Manish Parashar is Professor of Electrical and Computer Engineering at Rutgers University, where he also is director of the NSF Center for Autonomic Computing (CAC) and director of the Applied Software Systems Laboratory. He received a BE degree in Electronics and Telecommunications from Bombay University, India and MS and Ph.D. degrees in Computer Engineering from Syracuse University. He has received the IBM Faculty Award (2008) Rutgers Board of Trustees Award for Excellence in Research (2004-2005), NSF CAREER Award (1999) and the Enrico Fermi Scholarship from Argonne National Laboratory (1996). His research is in the broad area of applied parallel & distributed computing and computational science, and specifically on solving science and engineering problems on very large systems. For more information please visit http://www.ece.rutgers.edu/~parashar/.