Towards a Scalable Architecture for Real-Time Volume Rendering

In this paper we present our research eff orts towards a scalable volume rendering architecture for the real-time visualization of dynamically changing high-resolution datasets. Using a linearly skewed memory interleaving we were able to develop a parallel data ow model that leads to local, fixed-bandwidth interconnections between processing elements. This parallel dataflow model diff ers from previous work in that it requires no global communication of data except at the pixel level. Using this data ow model we are developing Cube-4, an architecture that is scalable to very high performances and allows for modular and extensible hardware implementations.