Institute for Data Analysis and Visualization

This paper presents a work-in-progress. The objective of our study is to derive an optimal design for high-performance rendering of irregular-grid volume data on the increasingly popular, distributed shared-memory parallel supercomputers. We experiment with a multi-threaded volume rendering algorithm for three-dimensional unstructured-grid data and discuss its performance on the SGI Origin 2000. Our preliminary test results demonstrate good rendering rates with a moderate number of processors. But we observe surprisingly poor processor scalability. We thus investigate how task partitioning and runtime memory management affect, in particular, the scalability of parallel rendering. We discover that in terms of algorithmic complexity and programming effort to attain the optimal performance on a shared memory architecture it can be as challenging and demanding as on a distributed-memory architecture.