Mostra el registre d'ítem simple
NoC Topology synthesis using metaheuristics
dc.contributor | Espasa Sans, Roger |
dc.contributor | Izquierdo Ustrell, Miquel |
dc.contributor.author | Solà Montserrat, Jordi |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors |
dc.date.accessioned | 2020-12-25T22:47:55Z |
dc.date.available | 2020-12-25T22:47:55Z |
dc.date.issued | 2020-06-26 |
dc.identifier.uri | http://hdl.handle.net/2117/334935 |
dc.description.abstract | In this project, we have studied the potential of hybrid metaheuristics at synthesizing network on chip topologies. We make the case that the problem can be split in three sub-problems, each solved by a different metaheuristic algorithm. Also, we introduce modifications to these algorithms to better adapt them to their designated tasks. The first one, determining the amount of routers for the system is solved by using a local search algorithm. The second, determining each router's associated resources and position, is solved using the k-means algorithm. The final stage, interconnecting the routers and defining a routing strategy, is solved by using an Ant Colony Optimization algorithm. We also introduce our methodology for communication performance definition, used to define maximum latency, point-to-point bandwidth, and compound bandwidth cases. We show the potential of the hybrid metaheuristic approach by analysing topology synthesis results. We also showcase the discovered issues with the suggested approach, as well as propose solutions to them. |
dc.language.iso | eng |
dc.publisher | Universitat Politècnica de Catalunya |
dc.subject | Àrees temàtiques de la UPC::Informàtica |
dc.subject.lcsh | Heuristic programming |
dc.subject.lcsh | Algorithms |
dc.subject.other | Metaheurística |
dc.subject.other | Xarxes en xip |
dc.subject.other | generació de dissenys |
dc.subject.other | Metaheuristics |
dc.subject.other | Networks on chip |
dc.subject.other | design synthesis |
dc.title | NoC Topology synthesis using metaheuristics |
dc.type | Master thesis |
dc.subject.lemac | Programació heurística |
dc.subject.lemac | Algorismes |
dc.identifier.slug | 145087 |
dc.rights.access | Open Access |
dc.date.updated | 2020-09-21T06:45:40Z |
dc.audience.educationlevel | Màster |
dc.audience.mediator | Facultat d'Informàtica de Barcelona |
dc.audience.degree | MÀSTER UNIVERSITARI EN INNOVACIÓ I RECERCA EN INFORMÀTICA (Pla 2012) |