Department of Computer Science & Engineering

Ensembles of distributed, heterogeneous resources, or Computational Grids, have emerged as popular platforms for large-scale scientific applications. This paper presents the Virtual Instrument project which targets those platforms. More specifically, the project seeks to provide an integrated application execution environment that enables end-users to run and interact with running scientific simulations on the Grid. This work is performed in the specific context of a computational biology application: MCell. Even though MCell provides the basis for running simulations, its capabilities are currently limited in terms of scale, ease-of-use, and interactivity. Those limitations preclude usage scenarios that are critical for scientific advances. Our goal is to create a scientific ``Virtual Instrument'' from MCell by allowing its users to transparently access Grid resources while being able to steer running simulations. In this paper, we motivate the need for an MCell Virtual Instrument. We then introduce a scheduling strategy that exploits the structure of MCell simulations and uses task priorities to accommodates computational steering. Finally, we describe our innovations and contributions in terms of Grid software design and development.

Pre-2018 CSE ID: CS2002-0707