A Static Load Balancing Scheme for Parallel Volume Rendering on Multi-GPU Clusters

GPU-based clusters are an attractive option for parallel volume rendering. One of the key issues in parallel volume rendering is load balancing, keeping a balanced workload per node is essential for improving performance. A good number of dynamic load balancing schemes have been proposed throughout the years. However, most of these approaches require runtime dynamic data movement or data duplication. For the large datasets routinely generated by scientific applications, frequent data transfer can be prohibitively expensive. In this work, we propose a static load balancing scheme. By optimizing data placement, a balanced workload can be achieved with minimal or no data movement, therefore improving the rendering speed and user experience.