An aI based tool for networks-on-chip design space exploration
With the increasing number of cores in Systems on Chip (SoCs), bus architectures have suffered some limitations regarding performance. As applications demand more bandwidth and lower latencies, busses could not comply with such requirements due to longer wires and increased capacitancies. Facing...
Sábháilte in:
Príomhchruthaitheoir: | |
---|---|
Rannpháirtithe: | |
Formáid: | Dissertação |
Teanga: | por |
Foilsithe / Cruthaithe: |
Brasil
|
Ábhair: | |
Rochtain ar líne: | https://repositorio.ufrn.br/jspui/handle/123456789/25937 |
Clibeanna: |
Cuir clib leis
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!
|
id |
ri-123456789-25937 |
---|---|
record_format |
dspace |
spelling |
ri-123456789-259372019-01-30T07:34:18Z An aI based tool for networks-on-chip design space exploration Silva, Jefferson Igor Duarte Kreutz, Márcio Eduardo Matos, Débora da Silva Motta Pereira, Monica Magalhães Network-on-chip Artificial intelligence Design space exploration CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO With the increasing number of cores in Systems on Chip (SoCs), bus architectures have suffered some limitations regarding performance. As applications demand more bandwidth and lower latencies, busses could not comply with such requirements due to longer wires and increased capacitancies. Facing this scenario, Networks-on-Chip (NoCs) emerged as a way to overcome limitations found in bus-based systems. NoCs are composed of a set of routers and communication links. Each component has its own characteristics. Fully exploring all possible NoC characteristics settings is unfeasible due to the huge design space to cover. Therefore, some methods to speed up this process are needed. In this work, we propose the usage of Artificial Intelligence techniques to optimize NoC architectures. This is accomplished by developing an AI based tool to explore the design space in terms of area, latency, and power prediction for different NoCs components configuration. Up to now, nine classifiers were evaluated. To evaluate this tool, tests were performed on Audio/Video applications with Bit-Reversal, Butterfly, Uniform, Perfect Shuffle, and Transpose Matrix traffic patterns, with four different communication requirements. The first result show an accuracy up to 88% and to 100%, using Decision Trees to predict latency and area/power values, respectively. As second step, a Genetic Algorithm was applied to explore the design space and the reached results ratify that the solutions found are valid and adequate to the constraints of the designer. 2018-10-04T21:23:30Z 2018-10-04T21:23:30Z 2018-08-29 masterThesis SILVA, Jefferson Igor Duarte. An aI based tool for networks-on-chip design space exploration. 2018. 91f. Dissertação (Mestrado em Sistemas e Computação) - Centro de Ciências Exatas e da Terra, Universidade Federal do Rio Grande do Norte, Natal, 2018. https://repositorio.ufrn.br/jspui/handle/123456789/25937 por Acesso Aberto application/pdf Brasil UFRN PROGRAMA DE PÓS-GRADUAÇÃO EM SISTEMAS E COMPUTAÇÃO |
institution |
Repositório Institucional |
collection |
RI - UFRN |
language |
por |
topic |
Network-on-chip Artificial intelligence Design space exploration CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO |
spellingShingle |
Network-on-chip Artificial intelligence Design space exploration CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO Silva, Jefferson Igor Duarte An aI based tool for networks-on-chip design space exploration |
description |
With the increasing number of cores in Systems on Chip (SoCs), bus architectures have
suffered some limitations regarding performance. As applications demand more bandwidth
and lower latencies, busses could not comply with such requirements due to longer wires
and increased capacitancies. Facing this scenario, Networks-on-Chip (NoCs) emerged as
a way to overcome limitations found in bus-based systems. NoCs are composed of a set
of routers and communication links. Each component has its own characteristics. Fully
exploring all possible NoC characteristics settings is unfeasible due to the huge design
space to cover. Therefore, some methods to speed up this process are needed. In this
work, we propose the usage of Artificial Intelligence techniques to optimize NoC architectures.
This is accomplished by developing an AI based tool to explore the design space in
terms of area, latency, and power prediction for different NoCs components configuration.
Up to now, nine classifiers were evaluated. To evaluate this tool, tests were performed
on Audio/Video applications with Bit-Reversal, Butterfly, Uniform, Perfect Shuffle, and
Transpose Matrix traffic patterns, with four different communication requirements. The
first result show an accuracy up to 88% and to 100%, using Decision Trees to predict
latency and area/power values, respectively. As second step, a Genetic Algorithm was
applied to explore the design space and the reached results ratify that the solutions found
are valid and adequate to the constraints of the designer. |
author2 |
Kreutz, Márcio Eduardo |
author_facet |
Kreutz, Márcio Eduardo Silva, Jefferson Igor Duarte |
format |
masterThesis |
author |
Silva, Jefferson Igor Duarte |
author_sort |
Silva, Jefferson Igor Duarte |
title |
An aI based tool for networks-on-chip design space exploration |
title_short |
An aI based tool for networks-on-chip design space exploration |
title_full |
An aI based tool for networks-on-chip design space exploration |
title_fullStr |
An aI based tool for networks-on-chip design space exploration |
title_full_unstemmed |
An aI based tool for networks-on-chip design space exploration |
title_sort |
ai based tool for networks-on-chip design space exploration |
publisher |
Brasil |
publishDate |
2018 |
url |
https://repositorio.ufrn.br/jspui/handle/123456789/25937 |
work_keys_str_mv |
AT silvajeffersonigorduarte anaibasedtoolfornetworksonchipdesignspaceexploration AT silvajeffersonigorduarte aibasedtoolfornetworksonchipdesignspaceexploration |
_version_ |
1773967156276363264 |