|
Abstract : |
A parallel solution to the visualisation of high resolution vol-ume data is presented. Based on the ray tracing (RT) visu-alization technique, the system works on a distributed memory MIMD architecture. A hybrid strategy to ray tracing parallelization is applied, using ray dataflow within an image partition approach. This strategy allows the flexible and effective management of huge dataset on architectures with limited local memory. The dataset is distributed over the nodes using a slice-partitioning technique. The simple data partition chosen implies a straighforward communications pattern of the visualization processes and this improves both software design and eJciency, while providing deadlock prevention. The partitioning technique used and the network interconnection topology allow for the efficient implementation of a statical load balancing technique through pre-rendering of a low resolution image. Details related to the practical issues involved in the parallelization of volumetric RT are discussed, with particular reference to deadlock and termi-nation issues., |
