Solving Hyperbolic PDEs using Accelerator Architectures
| dc.comment.hidden | I've adjusted the diagrams, so it appears to work in adobe now. However very few of the diagrams appear correctly in adobe, in the linux pdf viewer evince, or on the macintosh pdf viewer preview all diagrams appear as expected, if this thesis is to be printed it should not be printed from adobe reader. | en |
| dc.contributor.author | Rostrup, Scott | |
| dc.date.accessioned | 2009-07-27T13:29:05Z | |
| dc.date.available | 2009-07-27T13:29:05Z | |
| dc.date.issued | 2009-07-27T13:29:05Z | |
| dc.date.submitted | 2009-07-15 | |
| dc.description.abstract | Accelerator architectures are used to accelerate the simulation of nonlinear hyperbolic PDEs. Three different architectures, a multicore CPU using threading, IBM’s Cell Processor, and Nvidia’s Tesla GPUs are investigated. Speed-ups of between 40-75× relative to a single CPU core in single precision are obtained using the Cell processor and the GPU. The three implementations are extended to parallel computing clusters by making use of the Message Passing Interface (MPI). The resulting hybrid-parallel code is investigated for performance and scalability on both a GPU and Cell computing cluster. | en |
| dc.identifier.uri | http://hdl.handle.net/10012/4518 | |
| dc.language.iso | en | en |
| dc.pending | false | en |
| dc.publisher | University of Waterloo | en |
| dc.subject | GPU | en |
| dc.subject | Cell Processor | en |
| dc.subject | Hyperbolic PDEs | en |
| dc.subject | Hardware Optimization | en |
| dc.subject.program | Applied Mathematics | en |
| dc.title | Solving Hyperbolic PDEs using Accelerator Architectures | en |
| dc.type | Master Thesis | en |
| uws-etd.degree | Master of Mathematics | en |
| uws-etd.degree.department | Applied Mathematics | en |
| uws.peerReviewStatus | Unreviewed | en |
| uws.scholarLevel | Graduate | en |
| uws.typeOfResource | Text | en |