Research Projects: OptIPresence Tele-Immersion Testbed

From Gravity
Revision as of 11:34, 3 November 2009 by Dknoblau (Talk | contribs)

(diff) ←Older revision | view current revision (diff) | Newer revision→ (diff)
Jump to: navigation, search

Project Name OptIPresence Tele-Immersion Testbest
Team Members Falko Kuester, Kai-Uwe Doerr, Kevin Ponto, Daniel Knoblauch, Juergen Schulze, Peter Otto, Greg Dawe and Tom DeFanti
Project Sponsor King Abdullah University of Science and Technology (KAUST), California Institute for Telecommunications and Information Technology (Calit2), The Jacobs School of Engineering (JSoE)

System Specification

The OptIPresence Tele-Immersion Testbed is a highly-scalable and reconfigurable research environment in our GRAVITY lab that has now reached 315,648,000 pixel resolution, which equals the resolution of 157 x HDTV or 39 x 4K Digital Cinema feeds, and is indeed the worlds highest resolution display. It consist of a total of 82 display tiles in a networked, mixed mode configuration combining 30" diagonal tiles operating at 2,560 x 1,600 pixels resolution with 54" diagonal tiles operating at 1,920x1,080 pixels resolution. The system is powered by a total of 25 Dell XPS 710/720/730 nodes with dual graphics cards capable of driving as many as four display tiles each, interconnected at up to 10Gbit/sec with a 40 Gbit/sec uplink into the OptIPuter core. Theoretical computational performance of the GPUs alone is at 25 teraflops. Six additional streaming nodes bring the combined CPU pool for the systems to 124 processor cores, however, through its OptIPuter back end it has access to multiple orders of magnitudes more in computer cycles, at the speed of light.

OptIPresence is powered by our CGLX (Cross-Platform Cluster Graphic Library), a flexible, high-performance OpenGL-based graphics framework for the development of distributed high performance visualization systems such as OptIPortals. CGLX allows OpenGL programs to transparently scale across display clusters and fully leverage the available resources, while maximizing the achievable performance and resolution of such systems.

Personal tools
Namespaces

Variants
Actions
Navigation
Toolbox