Abstract: "Volume rendering is a powerful, but computationally intensive, computer graphics technique for visualizing volumetric datasets. This paper presents results of investigations into techniques for volume rendering using parallel processing on a shared-memory, multiple- instruction, multiple-data (MIMD) architecture. In particular, two widely used algorithms for volume rendering, raycasting and projection, have been parallelized on a BBN TC2000, and their performance has been measured and analyzed. Preliminary results indicate that the raycasting approach to volume rendering has some advantages for parallelization on this type of architecture."

Given the computing industry trend of increasing processing capacity by adding more cores to a chip, the focus of this work is tuning the performance of a staple visualization algorithm, raycasting volume rendering, for shared-memory parallelism on multi-core CPUs and many-core GPUs. Our approach is to vary tunable algorithmic settings, along with known algorithmic optimizations and two different memory layouts, and measure performance in terms of absolute runtime and L2 memory cache misses. Our results indicate there is a wide variation in runtime performance on all platforms, as much as 254% for the tunable parameters we test on multi-core CPUs and 265% on many-core GPUs, and the optimal configurations vary across platforms, often in a non-obvious way. For example, our results indicate the optimal configurations on the GPU occur at a crossover point between those that maintain good cache utilization and those that saturate computational throughput. This result is likely to be extremely difficult to predict with an empirical performance model for this particular algorithm because it has an unstructured memory access pattern that varies locally for individual rays and globally for the selected viewpoint. Our results also show that optimal parameters on modern architectures are markedly different from those in previous studies run on older architectures. And, given the dramatic performance variation across platforms for both optimal algorithm settings and performance results, there is a clear benefit for production visualization and analysis codes to adopt a strategy for performance optimization through auto-tuning. These benefits will likely become more pronounced in the future as the number of cores per chip and the cost of moving data through the memory hierarchy both increase.

This comprehensive work merges two of the hottest topics in computer science: parallel computing and computer graphics. Selected Topics from the Table of Contents: -Overview of Accelerated Rendering Techniques -Overview of Parallel Methods for Image Generation -Issues in Parallel Algorithm Development -Overview of Base Level Implementation -Compari

The Austrian Center for Parallel Computation (ACPC) is a cooperative research organization founded in 1989 to promote research and education in the field of software for parallel computer systems. The areas in which the ACPC is active include algorithms, languages, compilers, programming environments, and applications for parallel and high-performance computing systems. This volume contains the proceedings of the Second International Conference of the ACPC, held in Gmunden, Austria, October 1993. Authors from 17 countries submitted 44 papers, of which 15 were selected for inclusion in this volume, which also includes 4 invited papers by distinguished researchers. The volume is organized into parts on architectures (2 papers), algorithms (7 papers), languages (6 papers), and programming environments (4 papers).

Proceedings -- Parallel Computing.