Latency- and Hazard-Free Volume Memory Ar chitecture for Direct Volume Rendering

Abstract

The computational power required for direct volume rendering like ray-casting or volume ray-tracing can be provided by high­ speed rendering architectures. However the increasing proces­ sor speed makes a performance bottleneck obvious - the vol­ ume memory. This paper describes a volume memory architec­ ture that achieves at least a tenfold speed-up in read-out rate with moderate additional hardware. It has been simulated suc­ cessfully. A multi-level cache system is used with software prefetching and latency hiding. Pre- and postcaches addi­ tionally speed up the read-out rate so that a 5123 data set stored in a single memory module can be rendered at 3.125 Hz.