dc.contributor.author | Otten, Yoeri Daniel | |
dc.date.accessioned | 2024-01-25T00:38:23Z | |
dc.date.available | 2024-01-25T00:38:23Z | |
dc.date.issued | 2023-11-20 | |
dc.date.submitted | 2023-11-20T11:06:17Z | |
dc.identifier | INF399 0 MAO ORD 2023 HØST | |
dc.identifier.uri | https://hdl.handle.net/11250/3113663 | |
dc.description.abstract | More specialized hardware is being created to improve the efficiency of demanding algorithms. Graphcore introduced their Intelligence processors: a specialized true MIMD architecture which specializes in machine learning problems. Earlier work has shown that this architecture can also be used to solve breadth-first search competitively. We explore the possibilities of this machine by implementing several graph algorithms on this machine. Specifically, we look at Sparse-matrix vector multiplication and its usage within an algebraic approach to the breadth-first search algorithm, and show an algebraic solution to Prim's algorithm on the machine. Finally, we discuss the possibilities and problems of the Graphcore IPU. | |
dc.language.iso | eng | |
dc.publisher | The University of Bergen | |
dc.rights | Copyright the Author. All rights reserved | |
dc.subject | breath-first search | |
dc.subject | spmv | |
dc.subject | ipu | |
dc.subject | graphcore | |
dc.subject | mimd | |
dc.subject | prims | |
dc.subject | sparse-matrix vector multiplication | |
dc.title | Exploration of Linear-Algebra Graph Algorithms on the Graphcore IPU | |
dc.type | Master thesis | |
dc.date.updated | 2023-11-20T11:06:17Z | |
dc.rights.holder | Copyright the Author. All rights reserved | |
dc.description.degree | Masteroppgave i informatikk | |
dc.description.localcode | INF399 | |
dc.description.localcode | MAMN-PROG | |
dc.description.localcode | MAMN-INF | |
dc.subject.nus | 754199 | |
fs.subjectcode | INF399 | |
fs.unitcode | 12-12-0 | |