Load Balancing for Massive Model Rendering using Multiple GPUs

Rendering massive 3D models at high frame rates has been recognized as a challenging task. In this work, we present a device-independent parallel algorithm to achieve high-performance rendering on a multi-GPU system. To optimize the GPU usage, our algorithm seamlessly integrates with parallel LOD and CPU-GPU data streaming approaches, and solves the load-balancing issues across GPU devices. As a result, we demonstrate the ability to interactively visualize the 3D model composed of hundreds of millions of polygon primitives on a tiled display panel.

Members: 
Name Department College
Yong Cao Computer Science College of Engineering
Chao Peng Computer Science College of Engineering
Collaborative Colleges: 
Engineering