The Hierarchical Radiosity Algorithm (HRA) is one of the most efficient sequential algorithms for physically based rendering. Unfortunately, it is hard to implement in parallel. There exist fairly efficient shared-memory implementations but things get worst in a distributed memory (DM) environment. In this paper we examine the structure of the HRA in a graph partitioning setting. Various measurements performed on the task access graph of the HRA indicate the existance of several bottlenecks in a potential DM implementation. We compare "optimal" partitioning results obtained by the partitioning software Metis with a trivial and a spatial partitioning algorithm, and show that the spatial partitioning copes with most of the bottlenecks well.
Parallelizing dynamic scientific applications involves solving the dynamic load balancing problem. The balancing should take the communication requirements of the application into account. Especially in the field of computer graphics many problems are dealing with objects in L-dimensional space with very special communication patterns. We describe a load balancing strategy based on a geometric clustering of objects with provable good performance, that is well suited to applications with interdependencies between neighbouring objects or between objects that have at least one coordinate in common.
This paper presents an efficient, highly scalable implementation of the Hierarchical Radiosity Algorithm. We present a clever mapping of Hierarchical Radiosity to high-dimensional spaces that manifests a locality property, which can greatly reduce communication on parallel distributed memory architectures. We use a very simple dynamic spatial partitioning method to keep the mapping balanced. We describe solutions for the key implementation problems: asynchronous calculation, grouping of elements and links, and data reference locality. Speedup plots give an impression of the scalability of our implementation. On a Cray T3E the speedup curve is almost linear up to 64 processors. This is better than previously published attempts on massively parallel distributed memory computers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.