Proposta de um processador multithreading com caracter?sticas de previsibilidade

• Main Author: Siqueira, Hadley Magno da Costa
• Other Authors: 58534296049
• Language: Portuguese
• Published: Universidade Federal do Rio Grande do Norte 2016
• Subjects: CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO; Sistemas embarcados; Precision timed machines; Tempo real; VLIW; Simultaneous multithreading; Mem?ria
• Online Access: http://repositorio.ufrn.br/handle/123456789/20709

Submitted by Automa??o e Estat?stica ([e-mail]) on 2016-06-14T19:51:32Z No. of bitstreams: 1 HadleyMagnoDaCostaSiqueira_DISSERT.pdf: 1452990 bytes, checksum: 84d7f3a1709799f4355ce71e68b94d8b (MD5) === Approved for entry into archive by Arlan Eloi Leite Silva ([e-mail]) on 2016-06-15T22:22:57Z (GMT) No. of bitstreams: 1 HadleyMagnoDaCostaSiqueira_DISSERT.pdf: 1452990 bytes, checksum: 84d7f3a1709799f4355ce71e68b94d8b (MD5) === Made available in DSpace on 2016-06-15T22:22:57Z (GMT). No. of bitstreams: 1 HadleyMagnoDaCostaSiqueira_DISSERT.pdf: 1452990 bytes, checksum: 84d7f3a1709799f4355ce71e68b94d8b (MD5) Previous issue date: 2015-08-18 === O projeto de sistemas embarcados de tempo real requer um controle preciso da passagem de tempo na computa??o realizada pelos m?dulos e na comunica??o entre os mesmos. Geralmente, esses sistemas s?o constitu?dos de v?rios m?dulos, cada um projetado para uma tarefa espec?fica e com comunica??o restrita com os demais m?dulos a fim de se obter a temporiza??o necess?ria. Essa estrat?gia, chamada de arquitetura federada, j? est? se tornando invi?vel em frente as demandas atuais de custo, desempenho e qualidade exigidas dos sistema embarcados. Para atacar esse problema, atualmente se prop?e o uso de arquiteturas integradas, que consistem em um ou poucos circuitos realizando v?rias tarefas em paralelo de forma mais eficiente e com redu??o de custos. Entretanto, ? preciso garantir que a arquitetura integrada possua componibilidade temporal, ou seja, a capacidade de projetar cada tarefa temporalmente isolada das demais a fim de manter as caracter?sticas individuais de cada tarefa. As ?Precision Timed Machines? s?o uma abordagem de arquitetura integrada que advoca o uso de processadores ?multithreaded? para garantir componibilidade temporal. Dessa forma, o presente trabalho apresenta a implementa??o de uma ?Precision Timed Machine? chamada Hivek-RT. Este processador, que ? um VLIW com suporte ? ?Simultaneous Multithreading?, ? capaz de executar eficientemente tarefas de tempo real quando comparado ? um processador tradicional. Al?m da execu??o eficiente, a arquitetura facilita a implementa??o, do ponto de vista de programa??o, de tarefas de tempo real. === The real-time embedded systems design requires precise control of the passage of time in the computation performed by the modules and communication between them. Generally, these systems consist of several modules, each designed for a specific task and restricted communication with other modules in order to obtain the required timing. This strategy, called federated architecture, is already becoming unviable in front of the current demands of cost, required performance and quality of embedded system. To address this problem, it has been proposed the use of integrated architectures that consist of one or few circuits performing multiple tasks in parallel in a more efficient manner and with reduced costs. However, one has to ensure that the integrated architecture has temporal composability, ie the ability to design each task temporally isolated from the others in order to maintain the individual characteristics of each task. The Precision Timed Machines are an integrated architecture approach that makes use of multithreaded processors to ensure temporal composability. Thus, this work presents the implementation of a Precision Machine Timed named Hivek-RT. This processor which is a VLIW supporting Simultaneous Multithreading is capable of efficiently execute real-time tasks when compared to a traditional processor. In addition to the efficient implementation, the proposed architecture facilitates the implementation real-time tasks from a programming point of view.