Abstract | ||
---|---|---|
This paper presents a set of architecture-aware performance and integration improvements for a recent screenspace ambient obscurance algorithm. These improvements collectively produce a 7 x performance increase at 2560 x1600, generalize the algorithm to both forward and deferred renderers, and eliminate the radius- and scene-dependence of the previous algorithm to provide a hard real-time guarantee of fixed execution time. The optimizations build on three strategies: pre-filter the depth buffer to maximize memory hierarchy efficiency; reduce total bandwidth by carefully reconstructing positions and normals at high precision from a depth buffer; and exploit low-level intra- and inter-thread techniques for parallel, floating-point architectures.
|
Year | DOI | Venue |
---|---|---|
2012 | 10.2312/EGGH/HPG12/097-103 | High Performance Graphics |
Keywords | Field | DocType |
performance increase,hard real-time guarantee,floating-point architecture,fixed execution time,scalable ambient obscurance,deferred renderers,high precision,depth buffer,previous algorithm,architecture-aware performance,integration improvement,clustering,deferred shading | Deferred shading,Memory hierarchy,Computer science,Parallel computing,Exploit,Bandwidth (signal processing),Execution time,Cluster analysis,Scalability | Conference |
ISBN | Citations | PageRank |
978-3-905674-41-5 | 6 | 0.86 |
References | Authors | |
9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Morgan Mcguire | 1 | 752 | 54.30 |
Michael Mara | 2 | 36 | 4.52 |
David Luebke | 3 | 2196 | 140.84 |