| dc.rights.license | CC-BY-NC-ND | |
| dc.contributor.advisor | Bisseling, Rob | |
| dc.contributor.author | Noordam, Pieter | |
| dc.date.accessioned | 2025-04-03T14:00:59Z | |
| dc.date.available | 2025-04-03T14:00:59Z | |
| dc.date.issued | 2025 | |
| dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/48775 | |
| dc.description.abstract | In parallel Sparse Matrix-Vector Multiplication (SpMV), finding an efficient matrix partitioning is crucial
to minimize communication cost. This thesis explores the use of Simulated Annealing to find optimal
matrix bipartitions. The method uses row/column-based moves to explore the possible partitioning
solutions.
Our findings indicate that the introduced method is promising for bipartitioning large sparse matrices,
especially when exact algorithms prove to be computationally expensive. | |
| dc.description.sponsorship | Utrecht University | |
| dc.language.iso | EN | |
| dc.subject | In parallel Sparse Matrix-Vector Multiplication (SpMV), finding an efficient matrix partitioning is crucialto minimize communication cost. This thesis explores the use of Simulated Annealing to find optimalmatrix bipartitions. The method uses row/column-based moves to explore the possible partitioningsolutions. | |
| dc.title | Optimal matrix distribution by simulated annealing for a parallel sparse matrix-vector multiplication | |
| dc.type.content | Bachelor Thesis | |
| dc.rights.accessrights | Open Access | |
| dc.subject.keywords | parallel;SpMV;partitioning;partition;bipartitioning;bipartition;Simulated;Annealing;cost;communication;optimal;matrix;matrices;algorithm;minimize | |
| dc.subject.courseuu | Wiskunde & Toepassingen | |
| dc.thesis.id | 19024 | |
