GPGP: General Purpose Computation using Graphics Processors

Speaker:	Prof. Dinesh Manocha
		Department of Computer Science
		University of North Carolina at Chapel Hill

Title:		"GPGP: General Purpose Computation using Graphics
		 Processors"

Date:		Wednesday 19 October 2005

Time:		10:30am - 11:30am

Venue:		Room 3464 (Conference Room, via lift nos. 25/26)


ABSTRACT:

For years the performance and functionality of graphics processors (GPUs)
has been increasing at a faster pace than Moore's Law. Recently, the major
graphics chip manufacturers have added support for floating-point
computation and have released compilers for high-level languages.  These
GPUs are not like the array processors of the past. First, the prices of
these commodity parts are more than an order of magnitude lower the price
of the highest performance graphics cards. Furthermore, these chips are in
practically every personal computer (PC), game console and workstation
sold today. Heretofore, the primary application of GPUs has been fast
rendering of anti-aliased, textured and shaded geometric primitives (e.g.
polygons). Their main market has been mostly computer games and
entertainment business.

The performance and functionality of today's GPUs make them attractive as
co-processors for general-purpose computations. In this talk, I will give
an overview of our recent work in this area. These include many new
algorithms and applications that exploit the inherent parallelism and
vector processing capabilities of GPUs.

1.	Scientific computation including linear algebra solvers,
	differential equation solvers and applications to fluid
	dynamics, visual simulation, ice crystal growth, etc.

2.	Geometric computations including Voronoi diagrams, distance
	computation, motion planning, collision detection,
	visibility, etc.

3. 	Advanced rendering including visibility computation, shadows and
	walkthroughs.

4.	Database operations and stream data mining on complex datasets. I
	will make a case that GPU is a very useful co-processor for many
	of these applications.




**********************
Biography:

Dinesh Manocha is currently a professor of Computer Science at the
University of North Carolina at Chapel Hill.  He received his Ph.D. in
Computer Science at the University of California at Berkeley 1992.  He
received Junior Faculty Award in 1992, Alfred P. Sloan Fellowship and NSF
Career Award in 1995, Office of Naval Research Young Investigator Award in
1996, Honda Research Initiation Award in 1997, and Hettleman Prize for
Scholarly Achievements at UNC Chapel Hill in 1998.  He has also received
eight best paper & panel awards at the ACM/IEEE SuperComputing, ACM Solid
Modeling, ACM Multimedia, IEEE VR, Pacific Graphics, IEEE Visualization
and Eurographics Conferences. He has published more than 180 papers in
leading conferences and journals on computer graphics, geometric and solid
modeling, robotics, symbolic and numeric computation, virtual reality,
molecular modeling and computational geometry, and also served in the
program committee of leading conferences in these areas.