Combining Workstations and Supercomputers to Support Grid Applications: The Parallel Tomography Experience
Heterogeneous Computing Workshop (2000)
May 1, 2000 to May 1, 2000
Shava Smallen , University of California at San Diego
Walfredo Cirne , University of California at San Diego
Francine Berman , University of California at San Diego
Steve Young , University of California at San Diego
Mark Ellisman , University of California at San Diego
Jaime Frey , University of Wisconsin
Rich Wolski , University of Tennessee
Mei-Hui Su , University of Southern California
Carl Kesselman , University of Southern California
Computational Grids are becoming an increasingly important and powerful platform for the execution of large-scale, resource-intensive applications. However, it remains a challenge for applications to tap into the potential of Grid resources in order to achieve performance. In this paper, we illustrate how work queue applications can leverage Grids to achieve performance through coallocation. We describe our experiences developing a scheduling strategy for a production tomography application targeted to Grids that contain both workstations and parallel supercomputers.Our strategy uses dynamic information exported by a supercomputer's batch scheduler to simultaneously schedule tasks on workstations and immediately available supercomputer nodes. This strategy is of great practical interest because it combines resources available to the typical research lab: time-shared workstations and CPU time in remote space-shared supercomputers. We show that this strategy improves the performance of the tomography application compared to traditional scheduling strategies, which target the application to either type of resource alone.
application-level scheduling, coallocation, Computational Grids, workstations, supercomputers, tomography
J. Frey et al., "Combining Workstations and Supercomputers to Support Grid Applications: The Parallel Tomography Experience," Heterogeneous Computing Workshop(HCW), Cancun, Mexico, 2000, pp. 241.