Personal tools


Home » People » Affiliated Faculty » Jaspal Subhlok

Jaspal Subhlok

Jaspal Subhlok
Associate professor, Department of Computer Science

Homepage

Through his work with the University of Houston's (UH) Department of Computer Science, Jaspal Subhlok designs and develops algorithms and systems for high-performance and grid computing. In addition to his research and teaching duties with UH, Dr. Subhlok is currently involved with the development of an interactive multimedia program, a pilot project for the university. The program will function as an introduction to a select set of courses offered by the Computer Science department, and includes a multimedia introduction to the syllabus, audio/video clips from lectures, interactive quizzes to test background knowledge, and animations to demonstrate key concepts and problem solving. The goal of the project is to lead the way to similar interactive multimedia prospectuses for courses and degree programs across UH, making the university more accessible to a broad range of students.

Dr. Subhlok has written a number of journal articles and delivered guest lectures at universities and conferences worldwide, and is mentor to a number of master's degree and post-graduate students. He also acts as the host of a biweekly radio show dedicated to Houston's South Asian community. He holds a PhD in computer science from Rice University.

Jaspal Subhlok

Research interests

Dr. Subhlok studies programming, compilation and runtime support for high-performance computing, network measurement and modeling, scheduling and resource management for grid computing, and adaptive distributed Web caching.

Research projects

GRAM (Grid Resource and Application Matching)

Research is focused on tools and techniques for high-performance computing on networks ; specifically, identifying the ' best ' resources for the execution of a parallel or distributed application. The GRAM team is developing a methodology to determine key application characteristics (e.g. CPU processing time, communication pattern, synchronization, load balancing) by measuring usage of system resources (e.g. CPU busy/idle times and patterns, communication traffic patterns) while the application is executing. At the same time, researchers are developing a methodology to logically characterize the available resources on a network (e.g. bottleneck routers, shared links) based on a suite of dynamic traffic measurements.

DANCE (Distributed Adaptive Network Caching)

Web caching, along with related content delivery technologies, has a very important role to play in obtaining good access to documents on the Web. Currently most Web browsers use a local cache, and many organizations and ISPs employ a shared ' proxy cache' to improve Web access. The focus of this project is on creating a set of distributed proxy caches that will work together effectively. The team is researching how to use dynamic network measurements, like available bandwidth and CPU loads, to customize the runtime behavior of distributed proxy caches. The project is also building a farm of dynamically inter-connected Squid caches.

Research partners

Dr. Subhlok’s research is supported by Carnegie Mellon University, Compaq Computer Corporation, the U.S. Department of Energy, iMimic Corporation, Rice University and the Texas Higher Education Co-ordinating Board.

Significant publications

"Automatic node selection for high performance applications on networks" (with P. Lieu and B. Lowekamp), Proceedings of the Seventh ACMSIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 163-172, Atlanta, GA, May 1999.

"A resource query interface for network-aware applications" (with T. Gross, B. Lowekamp, N. Miller, P. Steenkiste and D. Sutherland), Cluster Computing, 2(2), July 1999.

"Airshed pollution modeling in an HPF-style environment" (with P. Steenkiste), Journal of Parallel and Distributed Computing, 60(6):690-715, June 2000.

"Optimal use of mixed task and data parallelism for pipelined computations" (with G. Vondran), Journal of Parallel and Distributed Computing, 60(3):295-319, March 2000.

"A new model for integrated nested task and data parallel programming" (with B. Yang), Proceedings of the Sixth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pages 1-12, Las Vegas, NV, June 1997.