Graduate Exam Abstract
Luis Briceno
Ph.D. Final
June 25, 2010, 1:00pm
ISTeC Conf Rm CS305
Study of Robust Resource Allocation in Various Different Heterogeneous Computing Environments
Abstract: Heterogeneous computing (HC) is the coordinated use of di erent types of machines, networks,
and interfaces to maximize the combined performance and/or cost e ectiveness of
the system. Heuristics for allocating resources in an HC system have di erent optimization
criteria. In the environments considered in this thesis, the optimization criteria was based
on robustness. For each di erent environment, a robustness metric was derived and resource
allocation heuristics were designed to maximize the robustness. The environments studies
are: a weather data-processing system, a massive multi-player online gaming system, and a
distributed massive satellite image processing system. Also, the performance of a few greedy
heuristics working iteratively on smaller subsets of the total machine/task data (at the end
of each iteration the makespan machine and tasks assigned to it are removed) is studied.
Adviser: H. J. Siegel
Co-Adviser: Anthony A. Maciejewski
Non-ECE Member: A. P. Willem Bohm
Member 3: Anura P. Jayasumana
Addional Members: N/A
Publications:
Program of Study:
