Hot3D

• High-Speed Distributed Rendering in the HoloVizio System
  › Péter Tamás Kovács, Holografika

  Abstract:
  

  We present the HoloVizio system design and give an overview about Holografika's approach to the 3D displaying. The patented HoloVizio technology uses a specially arranged array of optical modules and a holographic screen. Each point of the holographic screen emits light beams of different color and intensity to the various directions. The light beams generated in the optical modules hit the screen points in various angles and the holographic screen makes the necessary optical transformation to compose these beams into a perfectly continuous 3D view. With proper software control, light beams leaving the pixels propagate in multiple directions, as if they were emitted from the points of 3D objects at fixed spatial locations. We show that the direction selective light emission is a general requirement for every 3D systems and provide quantitative data on the FOV, on the angular resolution, determining field of depth of the displays, affecting the total number of light beams necessary for high-end 3D displaying. We present the results with the 10 Mpixel desktop display and the 50 Mpixel large-scale system. The large-scale system uses a rendering cluster consisting of nodes each having multiple 3D graphics boards driving the optical modules. We discuss the choices made during the design of this architecture, as well as the desired “ideal” graphics system for this purpose. We cover the real-time control issues at high pixel-count systems with the HoloVizio software environment and describe concrete 3D applications developed in the frame of European projects.

  This is joint work with Tibor Balogh, Tamás Forgács, Eric Nivel, and Attila Barsi.

• The NVIDIA Quadro Plex Visual Computing System
  › Mark Harris, Ian Williams, NVIDIA

  Abstract:
  

  NVIDIA Quadro Plex 1000 is a new external dedicated visual computing system that irepresents a 20x leap in visual compute density — graphics computation per cubic inch. Its compact, ultra-quiet design can be quickly deployed in any desktop workspace or can be easily transformed to fit into any standard 19” rack environment. Utilized as a single VCS node (two NVIDIA Quadro Plex VCSs connected to a single certified SLI-capable system) up to eight GPUs can be deployed in 3U of rack space to deliver the power and capability required by even the most demanding applications. This presentation will introduce Quadro Plex and discuss technical specifications and capabilities as well as applications.

• A Performance-Oriented Data Parallel Virtual Machine for GPUs
  › Derek Gerstmann, ATI

  Abstract:
  

  Existing GPU programming interfaces require that applications employ a graphics-centric programming model exported by a device driver tuned for real-time graphics and games. This programming model impedes development of non-graphics applications by hiding hardware resources behind its graphics-oriented interface. We present an abstraction for GPUs that provides policy-free, low-level access to the hardware and is designed for high-performance, data-parallel applications.