Publikationen

Autor	Mueller-Roemer, Johannes; Stork, André; Fellner, Dieter W.
Datum	2019
Art	Conference Paper
Abstrakt	Large sparse matrices with compound entries, i.e., complex and quaternionic matrices as well as matrices with dense blocks, are a core component of many algorithms in geometry processing, physically based animation, and other areas of computer graphics. We generalize several matrix layouts and apply joint schedule and layout autotuning to improve the performance of the sparse matrix-vector product on massively parallel graphics processing units. Compared to schedule tuning without layout tuning, we achieve speedups of up to 5:5x. In comparison to cuSPARSE, we achieve speedups of up to 4:7x.
Konferenz	International Symposium on Vision, Modeling, and Visualization (VMV) 2019
Projekt	CloudiFacturing
Url	https://publica.fraunhofer.de/handle/publica/405527

Joint Schedule and Layout Autotuning for Sparse Matrices with Compound Entries on GPUs