Concurrent Solutions to Linear Systems using Hybrid CPU/GPU Nodes
| dc.contributor.author | Adenikinju, Oluwapelumi | |
| dc.contributor.author | Gilyard, Julian | |
| dc.contributor.author | Massey, Joshua | |
| dc.contributor.author | Stitt, Thomas | |
| dc.date.accessioned | 2018-10-01T14:09:22Z | |
| dc.date.available | 2018-10-01T14:09:22Z | |
| dc.date.issued | 2015-06-09 | |
| dc.description.abstract | We investigate the parallel solutions to linear systems with the application focus as the global illumination problem in computer graphics. An existing CPU serial implementation using the radiosity method is given as the performance baseline where a scene and corresponding form-factor coeffcients are provided. The initial computational radiosity solver uses the basic Jacobi method with a fixed iteration count as an iterative approach to solving the radiosity linear system. We add the option of using the modern BiCG-STAB method with the aim of reduced runtime for complex problems. It is found that for the test scenes used, the problem complexity was not great enough to take advantage of mathematical reformulation through BiCG-STAB. Single-node parallelization techniques are implemented through OpenMP-based multi- threading, GPU-offloading using CUDA, and hybrid multi-threading/GPU offloading. It is seen that in general OpenMP is optimal by requiring no expensive memory transfers. Finally, we investigate two storage schemes of the system to determine whether storage through arrays of structures or structures of arrays results in better performance. We nd that the usage of arrays of structures in conjunction with OpenMP results in the best performance except for small scene sizes, where CUDA shows the minimal runtime. | en_US |
| dc.description.sponsorship | These results were obtained as part of the REU Site: Interdisciplinary Program in High Performance Computing (www.umbc.edu/hpcreu) in the Department of Mathematics and Statistics at the University of Maryland, Baltimore County (UMBC) in Summer 2014. This program is funded jointly by the National Science Foundation and the National Security Agency (NSF grant no. DMS{1156976), with additional support from UMBC, the Department of Mathematics and Statistics, the Center for Interdisciplinary Research and Consulting (CIRC), and the UMBC High Performance Computing Facility (HPCF). HPCF is supported by the U.S. National Science Foundation through the MRI program (grant nos. CNS{0821258) and CNS{1228778) and the SCREMS program (grant no. DMS{0821311), with additional substantial support from UMBC. Co-authors Oluwapelumi Adenikinju and Joshua Massey were supported, in part, by the UMBC National Security Agency (NSA) Scholars Program through a contract with the NSA. The project problem was proposed by Yu Wang and Dr. Marc Olano from the Department of Computer Science and Electrical Engineering at UMBC. Our team worked on the problem with the support of graduate assistants Jonathan Graf, Samuel Khuvis, and Xuan Huang, and faculty mentor Dr. Matthias K. Gobbert from the Department of Mathematics and Statistics at UMBC. The open-source package RRV (Radiosity Renderer and Visualizer) [1] is a global illumination solving and visualizing suite written in C++ and OpenGL. The radiosity computation engine uses a Jacobi iterative method with a xed number of iterations. The RRV-compute program is used in conjunction with an .xml scene description format of the geometric components (i.e., primitives, such as polygons) that make up the scene, to compute the global illumination for visualization with RRV-visualize. The radiosity algorithm solving RRV-compute program is the focus. The source code for RRV is available for download at http://dudka.cz/rrv. | en_US |
| dc.description.uri | https://archive.siam.org/students/siuro/vol8/index.php | en_US |
| dc.format.extent | 10 pages | en_US |
| dc.genre | undergraduate journal article | en_US |
| dc.identifier | doi:10.13016/M2SF2MG17 | |
| dc.identifier.citation | Oluwapelumi Adenikinju, Julian Gilyard, Joshua Massey, Thomas Stitt, Matthias K. Gobbert, Concurrent Solutions to Linear Systems using Hybrid CPU/GPU Nodes, SIAM Undergraduate Research Online (SIURO), Volume 8, http://dx.doi.org/10.1137/15S013776 | en_US |
| dc.identifier.uri | http://dx.doi.org/10.1137/15S013776 | |
| dc.identifier.uri | http://hdl.handle.net/11603/11428 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Society for Industrial and Applied Mathematics (SIAM) | en_US |
| dc.relation.isAvailableAt | The University of Maryland, Baltimore County (UMBC) | |
| dc.relation.ispartof | UMBC Computer Science and Electrical Engineering Department Collection | |
| dc.relation.ispartof | UMBC Student Collection | |
| dc.rights | This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author. | |
| dc.subject | UMBC High Performance Computing Facility (HPCF) | en_US |
| dc.subject | parallel solutions to linear systems | en_US |
| dc.subject | global illumination problem in computer graphics | en_US |
| dc.subject | radiosity method | en_US |
| dc.subject | BiCG-STAB method | en_US |
| dc.title | Concurrent Solutions to Linear Systems using Hybrid CPU/GPU Nodes | en_US |
| dc.type | Text | en_US |