• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 2
  • 1
  • 1
  • Tagged with
  • 4
  • 4
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Study and design of a manycore architecture with multithreaded processors for dynamic embedded applications

Bechara, Charly 08 December 2011 (has links) (PDF)
Embedded systems are getting more complex and require more intensive processing capabilities. They must be able to adapt to the rapid evolution of the high-end embedded applications that are characterized by their high computation-intensive workloads (order of TOPS: Tera Operations Per Second), and their high level of parallelism. Moreover, since the dynamism of the applications is becoming more significant, powerful computing solutions should be designed accordingly. By exploiting efficiently the dynamism, the load will be balanced between the computing resources, which will improve greatly the overall performance. To tackle the challenges of these future high-end massively-parallel dynamic embedded applications, we have designed the AHDAM architecture, which stands for "Asymmetric Homogeneous with Dynamic Allocator Manycore architecture". Its architecture permits to process applications with large data sets by efficiently hiding the processors' stall time using multithreaded processors. Besides, it exploits the parallelism of the applications at multiple levels so that they would be accelerated efficiently on dedicated resources, hence improving efficiently the overall performance. AHDAM architecture tackles the dynamism of these applications by dynamically balancing the load between its computing resources using a central controller to increase their utilization rate.The AHDAM architecture has been evaluated using a relevant embedded application from the telecommunication domain called "spectrum radio-sensing". With 136 cores running at 500 MHz, AHDAM architecture reaches a peak performance of 196 GOPS and meets the computation requirements of the application.
2

Modèles de conception et d'exécution pour la médiation et l'intégration de services / Conception and execution models to mediate and integrate service

Garcia Garza, Issac Noe 18 June 2012 (has links)
Les systèmes logiciels s'orientent vers des environnements de plus en plus hétérogènes et dynamiques. Cette évolution est induite par différents facteurs : explosion des dispositifs embarqués avec de fortes capacités de calcul, adoption rapide des services distants fournis par des tiers, mobilité des usagers et évolution du contexte associé, etc. Ces facteurs ouvrent de grandes possibilités pour la construction de nouveaux services numériques dans des domaines aussi divers que la santé, le divertissement, la domotique, ou encore le transport. Ces nouveaux domaines d'applications demandent la mise en œuvre des opérations d'intégration dans des contextes dynamiques et hétérogènes. Il est aujourd'hui admis que les approches à services facilitent l'intégration logicielle par la définition de protocoles standard de découverte et de liaison. La problématique d'intégration, au sens médiation, reste néanmoins entière. Le problème principal abordé par cette thèse est l'intégration de services dans des contextes hétérogènes et dynamiques. Plus précisément, nous avons conçu un modèle à composant spécifique à l'intégration logicielle, nommé CILIA. Ce modèle repose sur des composants, appelés médiateurs, et sur un langage d'assemblage de ces médiateurs. CILIA reprend les grands principes du Génie Logiciel tels que l'abstraction, la séparation de préoccupations et la modularité, et s'appuie sur des patrons d'intégration bien connus (Enterprise Integration Patterns). CILIA est implanté sous la forme d'un framework dynamique qui permet la mise à jour à l'exécution des solutions d'intégration. Ce framework CILIA est pleinement opérationnel et disponible en open source. Il est utilisé dans plusieurs projets collaboratifs. / Software systems are moving toward highly dynamic and heterogeneous environments. This dynamism is derived by several factors: the massive arrival of embedded devices with computing capabilities, the rapid adoption of newer distributed services provided by third parties, the user mobility and the constantly changing context, etc. These factors open up great opportunities for the construction of new and innovative services on several application domains, such as health-care systems, entertainment systems, home automation systems, transportation or traceability systems. These new application areas require the implementation of integration operations in dynamic and heterogeneous environments. It is well known that service-oriented computing eases the implementation of integrating systems by defining standard protocols to perform the discovery and the binding. However, some interoperability concerns, such as mediating, have been still unresolved. In this work we address the integration concern of service integration in dynamic and highly evolving environments. Specifically, we have developed an integration-specific component model called CILIA. This model is based on components, called mediators, and its assembly language. CILIA respects software engineering principles such as abstraction, separation of concerns, modularity, and anticipation of change and also it is influenced by the well-known enterprise integration patterns (EIP). CILIA has been developed as a dynamic framework that allows us to perform dynamic modifications at run-time on the integrated solutions. This framework is entirely developed and operational. It is available as an open source project and has been used by several collaborative projects.
3

Aplicação de políticas de middleboes com o uso de softaware-definidned networking

PINHEIRO, Antônio Janael 24 February 2016 (has links)
Submitted by Fabio Sobreira Campos da Costa (fabio.sobreira@ufpe.br) on 2017-03-02T14:42:14Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Dissertação_Antônio_Janael_Pinheiro.pdf: 3669454 bytes, checksum: b097ebe7fc031e2189613f6f98fadd4d (MD5) / Made available in DSpace on 2017-03-02T14:42:14Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Dissertação_Antônio_Janael_Pinheiro.pdf: 3669454 bytes, checksum: b097ebe7fc031e2189613f6f98fadd4d (MD5) Previous issue date: 2016-02-24 / FACEPE / Middleboxes são dispositivos de rede essenciais a inúmeras organizações, utilizados primordialmente na adição de serviços à rede. Middleboxes realizam operações complexas e variadas sobre o tráfego, introduzindo vários desafios ao funcionamento das redes atuais. Estes dispositivos são configurados manualmente pelo operador de rede, o que dificulta a aplicação correta das políticas destesmiddleboxes diante de aplicações de rede dinâmicas. Diversas soluções foram propostas para mitigar problemas gerados pela presença demiddleboxes, porém tais soluções não tratam das dificuldades que surgem na operação de aplicações dinâmicas. Muitas destas soluções tornam a rede mais complexa, aumentam o seu custo e exigem a substituição completa dosmiddleboxes existentes. Neste trabalho, é apresentada uma arquitetura baseada em Software-Defined Networking (SDN) que tem como objetivo garantir a aplicação correta de políticas de middleboxes na presença de aplicações dinâmicas. A arquitetura emprega o controle centralizado e a programabilidade dos dispositivos de rede presentes em SDN para tornar osmiddleboxes existentes capazes de aplicar corretamente suas políticas sem introdução de complexidade à rede, sem aumento de seu custo e sem interferência no funcionamento das aplicações. Para avaliar a arquitetura proposta, foi desenvolvido um protótipo no ambiente de emulação Mininet com três middleboxes: um firewall, um Intrusion Detection System (IDS) e um balanceador de carga. As aplicações utilizadas foram Voice over IP (VoIP) e web, e as métricas de desempenho foram o atraso de pacotes, a perda de pacotes e o jitter. Testes de hipóteses baseados noWilcoxonSigned-RankTest aplicados aos resultados atestam que, apesar de adicionar um acréscimo tolerável no atraso de pacotes, a arquitetura proposta não gera perda de pacotes, tampouco impacta o jitter, sendo capaz de configurar corretamente políticas de middleboxes em um cenário de aplicações dinâmicas. / Middleboxes are essential network devices to numerous organizations, primarily to add services to the network. Middleboxes perform complex and varied operations on the traffic, introducing several challenges to the functioning of today’s networks. These devices are manually configured by the network operator, what hinders the correct application of the policies of these middleboxes dynamic network applications. Several solutions have been proposed to mitigate problems caused by the presence of middleboxes, but these solutions do not address the difficulties that arise in the operation of dynamic applications. Many of these solutions make the network more complex, increase its cost and require complete replacement of existing middleboxes. In this work, an architecture based on Software-Defined Networking (SDN) is presented that aim at ensuring the correct application of middlebox policies in the presence of dynamic applications. The architecture employs the centralized control and programmability of network devices present in SDN to make existing middleboxes able to correctly apply their policies without introducing complexity to the network, without increasing their cost and without interfering in the operation of applications. To evaluate the proposed architecture, a prototype in the Mininet emulation environment was developed with three middleboxes: a firewall, an Intrusion Detection System (IDS) and a load balancer. The applications used were Voice over IP (VoIP) calls and HTTP requests, and the performance metrics were packet delay, packet loss and jitter. Hypothesis testing based on Wilcoxon Signed-Rank Test applied to the results show that, while adding a tolerable increase in packet delay, the proposed architecture neither generates packet loss, nor impacts the jitter, being able to correctly configure middleboxes policies in a scenario of dynamic applications.
4

Study and design of a manycore architecture with multithreaded processors for dynamic embedded applications / Etude et mise en œuvre d’une architecture multiprocesseur constituée de ressources de calculs multitâches pour les systèmes embarqués

Bechara, Charly 08 December 2011 (has links)
Les systèmes embarqués sont de plus en plus complexes et requièrent des besoins en puissance de calcul toujours plus importants. Ils doivent être capables de s'adapter à l'évolution rapide de leurs applications qui requièrent un haut niveau de performance (ordre du TOPS: Téra-opérations par seconde) et de parallélisme. Par ailleurs, la complexité des parties irrégulières étant de plus en plus importantes, des solutions de calcul performantes et adaptées doivent être mises en œuvre afin de prendre en compte leur dynamisme. Une prise en compte efficace du dynamisme réduit le déséquilibre de charge entre les ressources de calcul et améliore grandement les performances globales.Pour répondre aux besoins de ces applications de calcul intensif massivement parallèle et dynamique, nous proposons dans cette thèse l’architecture AHDAM qui signifie « Asymmetric Homogeneous with Dynamic Allocator Manycore architecture ». Cette architecture a été conçue afin de masquer efficacement la latence d’accès à la mémoire extérieure dont de nombreux accès sont nécessaires lors de la manipulation de grands volumes de données. Pour cela, des processeurs multitâches ont été utilisés. Par ailleurs, l’architecture AHDAM imbrique plusieurs niveaux de parallélisme afin de tirer partie efficacement des différentes formes de parallélisme des applications, et ainsi atteindre un haut niveau de performance. Enfin, cette architecture utilise un contrôleur centralisé pour équilibrer la charge de calcul entre ses ressources de calcul afin d’augmenter leur taux d’utilisation et supporter les applications fortement dynamiques.L’architecture AHDAM a été évaluée en portant une application de radio logicielle appelée «spectrum radio-sensing ». Avec 136 cœurs cadencés à 500 MHz, l'architecture AHDAM atteint une performance crête de 196 GOPS et répond aux exigences de l'application. / Embedded systems are getting more complex and require more intensive processing capabilities. They must be able to adapt to the rapid evolution of the high-end embedded applications that are characterized by their high computation-intensive workloads (order of TOPS: Tera Operations Per Second), and their high level of parallelism. Moreover, since the dynamism of the applications is becoming more significant, powerful computing solutions should be designed accordingly. By exploiting efficiently the dynamism, the load will be balanced between the computing resources, which will improve greatly the overall performance. To tackle the challenges of these future high-end massively-parallel dynamic embedded applications, we have designed the AHDAM architecture, which stands for “Asymmetric Homogeneous with Dynamic Allocator Manycore architecture". Its architecture permits to process applications with large data sets by efficiently hiding the processors' stall time using multithreaded processors. Besides, it exploits the parallelism of the applications at multiple levels so that they would be accelerated efficiently on dedicated resources, hence improving efficiently the overall performance. AHDAM architecture tackles the dynamism of these applications by dynamically balancing the load between its computing resources using a central controller to increase their utilization rate.The AHDAM architecture has been evaluated using a relevant embedded application from the telecommunication domain called “spectrum radio-sensing”. With 136 cores running at 500 MHz, AHDAM architecture reaches a peak performance of 196 GOPS and meets the computation requirements of the application.

Page generated in 0.1376 seconds