A distributed, parallel, interactive volume rendering package

Abstract

This paper presents a parallel ray-casting volume rendering algorithm and its implementation on the massively parallel IBM SP-1 computer using the Chameleon message passing library. Though this algorithm takes advantage of many of the unique features of the SP-1 (e.g. high-speed switch, large memory per node, high-speed disk array, HIPPI display, et al.), the use of Chameleon allows the code to be executed on any collection of workstations. The algorithm is image-ordered and distributes the data and the computational load to individual processors. After the volume data is distributed, all processors then perform local ray tracing of their respective subvolumes concurrently. No interprocess communication takes place during the ray tracing process. After a subimage is generated by each processor, the final image is obtained by composing subimages between all the processors. The program itself is implemented as an interactive process through a GUI residing on a graphics workstation which is coupled to the parallel rendering algorithm via sockets. The paper highlights the Chameleon implementation, the GUI, some optimization improvements, static load balancing, and direct parallel display to a HIPPI framebuffer.<>