Co-design Architecture and Implementation for Point-Based Rendering on FPGAs

Current graphic cards include advanced graphic processing units to accelerate the rendering of 3D objects with millions of polygons. As object models grow in complexity, the rendering approach based on points as primitives is regarded superior in terms of scalability and efficiency. Next generation graphic cards could contain reconfigurable fabrics, similar to those implemented in current FPGAs, to offer two advantages: a) fast rendering units and b) new mechanisms for custom, run-time exchangeable accelerators. In this paper, we propose a hardware point-rendering architecture tailored specifically for reconfigurable systems. The presented implementation on a real FPGA-based platform demonstrates on the one hand the effectiveness of the approach and on the other hand it provides valuable insights into possible future improvements for this problem scenario.