<p>In this thesis we address the problem of optimal code generation for irregular architectures such as Digital Signal Processors (DSPs).</p><p>Code generation consists mainly of three interrelated optimization tasks: instruction selection (with resource allocation), instruction scheduling and register allocation. These tasks have been discovered to be NP-hard for most architectures and most situations. A common approach to code generation consists in solving each task separately, i.e. in a decoupled manner, which is easier from a software engineering point of view. Phase-decoupled compilers produce good code quality for regular architectures, but if applied to DSPs the resulting code is of significantly lower performance due to strong interdependences between the different tasks.</p><p>We developed a novel method for fully integrated code generation at the basic block level, based on dynamic programming. It handles the most important tasks of code generation in a single optimization step and produces an optimal code sequence. Our dynamic programming algorithm is applicable to small, yet not trivial problem instances with up to 50 instructions per basic block if data locality is not an issue, and up to 20 instructions if we take data locality with optimal scheduling of data transfers on irregular processor architectures into account. For larger problem instances we have developed heuristic relaxations.</p><p>In order to obtain a retargetable framework we developed a structured architecture specification language, xADML, which is based on XML. We implemented such a framework, called OPTIMIST that is parameterized by an xADML architecture specification.</p><p>The thesis further provides an Integer Linear Programming formulation of fully integrated optimal code generation for VLIW architectures with a homogeneous register file. Where it terminates successfully, the ILP-based optimizer mostly works faster than the dynamic programming approach; on the other hand, it fails for several larger examples where dynamic programming still provides a solution. Hence, the two approaches complement each other. In particular, we show how the dynamic programming approach can be used to precondition the ILP formulation.</p><p>As far as we know from the literature, this is for the first time that the main tasks of code generation are solved optimally in a single and fully integrated optimization step that additionally considers data placement in register sets and optimal scheduling of data transfers between different registers sets.</p>

In this thesis we address the problem of optimal code generation for irregular architectures such as Digital Signal Processors (DSPs). Code generation consists mainly of three interrelated optimization tasks: instruction selection (with resource allocation), instruction scheduling and register allocation. These tasks have been discovered to be NP-hard for most architectures and most situations. A common approach to code generation consists in solving each task separately, i.e. in a decoupled manner, which is easier from a software engineering point of view. Phase-decoupled compilers produce good code quality for regular architectures, but if applied to DSPs the resulting code is of significantly lower performance due to strong interdependences between the different tasks. We developed a novel method for fully integrated code generation at the basic block level, based on dynamic programming. It handles the most important tasks of code generation in a single optimization step and produces an optimal code sequence. Our dynamic programming algorithm is applicable to small, yet not trivial problem instances with up to 50 instructions per basic block if data locality is not an issue, and up to 20 instructions if we take data locality with optimal scheduling of data transfers on irregular processor architectures into account. For larger problem instances we have developed heuristic relaxations. In order to obtain a retargetable framework we developed a structured architecture specification language, xADML, which is based on XML. We implemented such a framework, called OPTIMIST that is parameterized by an xADML architecture specification. The thesis further provides an Integer Linear Programming formulation of fully integrated optimal code generation for VLIW architectures with a homogeneous register file. Where it terminates successfully, the ILP-based optimizer mostly works faster than the dynamic programming approach; on the other hand, it fails for several larger examples where dynamic programming still provides a solution. Hence, the two approaches complement each other. In particular, we show how the dynamic programming approach can be used to precondition the ILP formulation. As far as we know from the literature, this is for the first time that the main tasks of code generation are solved optimally in a single and fully integrated optimization step that additionally considers data placement in register sets and optimal scheduling of data transfers between different registers sets.

Submitted by Nayara Passos (nayara.passos@ufpe.br) on 2015-03-12T14:23:54Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) TESE Leandro Marques do Nascimento.pdf: 4935348 bytes, checksum: 593ec08be509bd200bc5ec59fccb17d6 (MD5) / Made available in DSpace on 2015-03-12T14:23:54Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) TESE Leandro Marques do Nascimento.pdf: 4935348 bytes, checksum: 593ec08be509bd200bc5ec59fccb17d6 (MD5) Previous issue date: 2014 / CNPq, INES / É possível se observar um alto crescimento no número de aplicações Web sendo desenvolvidas. Isto está acontecendo principalmente porque a Web está entrando em uma nova fase, chamada Web programável, onde diversos sistemas baseados na Web estão disponibilizando suas APIs publicamente. Com o objetivo de lidar com a complexidade dessa Web emergente, este trabalho define a noção de uma Máquina Social (Social Machine - SM) e vislumbra uma linguagem que permite descrever redes de tais máquinas. Para começar, nós definimos uma Máquina Social como sendo “um componente conectável e programável que encapsula (WI) um sistema de processamento de informação (IPS) e define um conjunto de serviços requeridos (RS) e providos (PS), dinamicamente disponível sob certas restrições (C), as quais são determinadas por, dentre outras coisas, seus relacionamentos (Rel) com terceiros”. Em outras palavras, uma SM é uma máquina conectada, normalmente à Web, que dinamicamente provê e/ou requer um conjunto de serviços de acordo com os seus relacionamentos estabelecidos. Qualquer aplicação na Web pode ser vista como uma SM. Para que seja possível a aplicação prática do conceito de Máquina Social previamente mencionado, nós definimos SMADL, uma linguagem para descrição arquitetural de SMs, como uma tentativa de ser uma forma completamente diferente de se programar a Web, misturando conceitos de linguagens de descrição arquitetural (ADLs) e linguagens específicas de domínio (DSLs). Como uma ADL, a linguagem permite a descrição de máquinas sociais (e redes de tais) em termos de relacionamentos (Rel) como abstrações de alto nível, sem a necessidade de se especificar os detalhes de comunicação (protocolos) e/ou métodos de autenticação. Como uma DSL, ela permite a criação e integração de serviços Web usando uma sintaxe de tipos dinâmicos, integrada à máquina virtual Java e à IDE Eclipse. Cada elemento do conceito de uma SM é diretamente mapeado na linguagem. Em poucas palavras, SMADL pode ser definida como uma linguagem dirigida a relacionamentos que pode ser usada para descrever interações entre qualquer número de máquinas de inúmeras formas, como um meio de representar máquinas interagindo na Web realmente e, obviamente, como um meio de representar interações com outras máquinas sociais também. Vários outros esforços já foram feitos para definir ADLs e alguns deles foram, de alguma forma, aplicados no domínio da Web. Entretanto, há uma clara falta de base fundamental que provenha abstrações de alto nível tais como o modelo de máquinas sociais provê. SMADL foi implementada em duas versões, uma textual e outra visual. Ambas as versões foram avaliadas através de um estudo de caso e uma pesquisa baseada na opinião de especialista e indicaram ser boas soluções para problemas práticos. / We are experiencing a high growth in the number of Web applications being developed. This is happening mainly because the Web is going into a new phase, called programmable Web, where several Web-based systems make their APIs publicly available. In order to deal with the complexity of this emerging Web, we define the notion of a Social Machine and envisage a language that can describe networks of such. To start with, we define a Social Machine (SM) as a “connectable and programmable building block that wraps (WI) an information processing system (IPS) and defines a set of required (RS) and provided services (PS), dynamically available under constraints (C) which are determined by, among other things, its relationships (Rel) with others”. In other words, a SM is a connected machine, usually to the Web, which dynamically provides and/or requires a set of services according to its established relationships. Any application in the Web can be seen as a SM. In order to make feasible the practical application of the aforementioned Social Machine concept, we define SMADL – the Social Machines Architecture Description Language – as an attempt to be a completely different way to program the Web, mixing concepts from Architecture Description Languages (ADLs) and Domain-Specific Languages (DSLs). As an ADL, it allows the description of Social Machines (and networks of such) in terms of relationships (Rel) as high-level abstractions, without the need to specify details of communication (protocols) and/or authentication methods. As a DSL, it allows the implementation and integration of Web services using a dynamically typed syntax, fully integrated to the Java Virtual Machine and Eclipse IDE. Every element of the SM concept is directly mapped into the language. In few words, SMADL can be defined as a relationship-driven language which can be used to describe the interactions between any number of machines in a multitude of ways, as a means to represent real machines interacting in the real Web and, obviously, as a means to represent interactions with other social machines too. Several other efforts have been done to define ADLs, and a few of them were someway applied to the Web domain. However, there is a clear lack of fundamental base to provide high-level abstractions that the Social Machine concept does. SMADL has been implemented in two versions, one textual and one visual. Both versions have been evaluated through a case study and an expert’s opinion survey and demonstrated to be good solutions for practical problems.

La complexité croissante des Systèmes de Systèmes et autres grandes fédérations d’acteurs pose de nouvelles problématiques de conception et de réalisation. Cette complexité, induite par des structures de management toujours plus sophistiquées et un cycle de vie long, doit être maîtrisée au plus tôt dans la conception des entreprises. Cette maîtrise permet à l’ensemble des intervenants au cours du cycle de vie d’une entreprise d’identifier ses points clés et de prendre confiance en sa capacité à atteindre ses objectifs. En particulier, il importe de savoir estimer les capacités de l’entreprise à s’adapter à des situations imprévues ou exceptionnelles afin d’assurer ses missions en toutes circonstances. En réaction, de nouvelles démarches d’ingénierie émergent. Elles s’appuient sur la modélisation et la simulation de l’architecture de ces systèmes aux différents stades de leur développement et de leur fonctionnement. Dans le cadre d’une de ces démarches nommée IDEA, nous avons enrichi le langage de description d’architecture avec des concepts et des mécanismes ayant pour but d’adresser l’adaptabilité et des capacités de reconfiguration des entreprises. Ces apports ont été expérimentés avec succès par prototypage et dans des contextes d’affaires industrielles. / As the complexity of large civilian and military Systems of Systems and system federations increases, new system architecture and engineering challenge emerge. This complexity is mainly due to intricate management structures and a long lifecycle, and needs to be mastered from the early stages of architecting. All engineering stakeholders need to identify the key aspects of the enterprise and gain confidence in its ability to fulfill its missions. To ensure that the enterprise is able to satisfy its objectives despite evolving situations, there is a need to focus on its capability to adapt through reconfiguration. New engineering approaches emphasize architecture modelling and simulation to tackle the complexity of the enterprise in all stages of its lifecycle in a flexible and global way. In the context of such an approach named IDEA, we updated the architecture description language to include concepts and mechanisms dedicated to the adaptability and reconfiguration of the enterprise. We also focused on ensuring model consistency. The results were experimented through prototyping and application on industrial affairs.

This master's thesis deals with creation of generators of the code for existing virtual platforms QEMU and OVP. This work consist of study of techniques, which are used by virtual machines for their work. Main part of this work is the design of process, which transforms input instruction sets to the code used by these virtual platforms. As the result of this work functional programs, which generate the code for these virtual platforms, was created.

L'hétérogénéité et l'énergie sont deux considérations fondamentales pour les environnements informatiques ubiquitaires. Dans cette thèse, nous présentons notre approche pour gérer l'hétérogénéité et pour économiser l'énergie via des canevas de programmation intégrés. Pour gérer l'hétérogénéité, nous proposons une méthodologie et un support de programmation qui vise à faire communiquer les différentes entités de l’environnement ubiquitaire en utilisant le protocole SIP considéré alors comme un bus logique universel de communication. Nous avons intégré ce bus SIP dans le langage de description d’architecture DiaSpec développé par notre équipe Phoenix. Concernant la consommation d’énergie, nous proposons une méthodologie qui utilise les techniques d’offloading et de compression de données pour minimiser la consommation d'énergie des applications mobiles. Nous avons ainsi construit une stratégie d’aide à la conception au travers d’un outil qui permet de déterminer le meilleur mode d’exécution pour une tâche donnée que nous proposons d’intégrer dans le langage de description DiaSpec. / The topics of heterogeneity and energy are two fundamental considerations for pervasive computing environments. Inthis thesis, we describe our approach to manage heterogeneity and to handle energy concerns via a high-level programming framework.To manage heterogeneity, we describe a methodology and a programming support that use the SIP protocol as a universal communication bus in pervasive computing environments. Ourwork enables homogeneous communications between heterogeneous distributed entities. In doing so, we integrate the SIP communication bus into our programming framework. We rely on adeclarative language named DiaSpec to describe the architecture of pervasive applications. This description is passed to a generator for producing a Java programming framework dedicated to the application area. We leverage the generated framework with SIP adaptations to raise the abstraction level of SIP operations.We then present a classification of a wide variety of entities interms of features, capabilities and network connectors. Based on this classification, a methodology and a programming supportare described for connecting entities on the SIP communication bus. This work has been validated by applications using theSIP communication bus to coordinate widely varying entities,including serial-based sensors (RS232, 1-Wire), ZigBee devices,X10 devices, PDA, native SIP entities, and software components.Regarding the energy concerns, we describe a methodology that uses two strategies, namely computation offloading and data compression, to minimize energy cost of mobile applications.In doing so, we present an execution and transfer model for atask of a mobile application and define its five different stubs forthree program execution and data transfer modes. Based on this model and our two strategies, we construct a strategy scheme to determine the most efficient stub in terms of energy consumption.We then design the OffDeci tool, using this strategy scheme, toprovide energy feedback for the developer and to analyze thebalance between local and remote computing with consideration of data compression. Our experimental study demonstrates thefeasibility of the strategy scheme of our approach. Finally, weextend DiaSpec with declarations dedicated to manage energy concerns during the application design phase. We sketched the integration of this energy-handling declaration and OffDeci intoour high-level programming framework. This integration permitsto determine the best stub of a declared DiaSpec component interms of its energy cost.

L'ingénierie des systèmes embarqués repose sur deux activités complémentaires : la modélisation d'une part permet dereprésenter le système, l'analyse d’autre part permet d'évaluer les diverses propriétés non-fonctionnelles (par exemple despropriétés temporelles via l'analyse d’ordonnancement temps réel). Cette thèse s'intéresse à l'intégration entre ces modèleset analyses: comment appliquer une analyse sur une modèle ? Comment gérer le processus d’analyse ? La première partie de cette thèse présente une approche globale afin de répondre à ces questions. Cette approche s'organise autour de quatre couches applicatives: (1) les modèles qui représentent le système, (2) les accesseurs qui permettent d'extraire des données à partir d'un modèle, (3) l'analyse qui traite des données en entrée pour produire des données ou propriétés en sortie, (4) des contrats qui décrivent les interfaces d'une analyse et permettent d'orchestrer le processus d'analyse. La seconde partie de cette thèse est dédiée à l'expérimentation de cette approche sur des systèmes réels provenant du domaine aérospatial : un drone, un robot explorateur et un système de gestion de vol. Nous montrons que les accesseurs permettent d’appliquer diverses analyses d’ordonnancement temps réel sur des modèles architecturaux hétérogènes, par exemples décrits avec le standard industriel AADL (Architecture Analysis and Design Language) ou le nouveau langage dirigé par le temps CPAL (Cyber-Physical Action Language). En outre, nous montrons que les contrats peuvent être utilisés afin d’automatiser des procédures d'analyse complexes : quelle analyse peut être appliquée sur unmodèle ? Quelles analyses remplissent les objectifs visés ? Peut-on combiner des analyses ? Y-a-t-il des interférences entreles analyses ? Etc. / The engineering of embedded systems relies on two complementary activities: modeling on the one hand enables torepresent the system, analysis on the other hand makes it possible to evaluate the various non-functional properties (forexample, temporal properties with the real-time scheduling analysis). This thesis deals with the integration between thesemodels and analyses: how to apply an analysis on a model? How to manage the analysis process? The first part of this thesis presents a comprehensive approach to answer these questions. This approach is based on four application layers: (1) models to represent the system, (2) accessors to extract data from a model, (3) analyses to computeoutput data and/or properties from input data (4) contracts to represent the analysis interfaces and orchestrate the analysisprocess. The second part of this thesis deals with the experimentation of this approach with concrete systems coming fromthe aerospace: a drone, an exploratory robot and a flight management system. We demonstrate that the accessors enable toapply various real-time scheduling analyses on heterogeneous architectural models, for example written with the industrystandard AADL (Architecture Analysis and Design Language) or the new time-triggered language CPAL (Cyber-PhysicalAction Language). In addition, contracts make it possible to automate complex analysis procedures: which analysis can beapplied on a given model? Which are the analyses that meet a given goal? Are there analyses to be combined? Are thereinterferences between analyses? Etc.

[pt] No cenário atual do setor de telecomunicações, percebe-se uma tendência crescente em direção ao uso de sistemas de comunicação que permitam a criação rápida e de baixo custo de serviços. Na busca por arquiteturas de rede que respondam a essa tendência, vários grupos têm centrado seus esforços em pesquisas na área de redes programáveis. O surgimento da tecnologia de processamento de rede no mercado de equipamentos de telecomunicações abriu ainda maior espaço para pesquisas nessa área. Nesse contexto, é imprescindível que os processos de criação de serviços sejam bem estruturados e, o quanto possível, sistemáticos. Esta tese, inserida em um projeto desenvolvido no Laboratório TeleMídia da PUC-Rio, adota uma abordagem de criação de serviços em que técnicas de Arquitetura de Software e de Desenvolvimento Baseado em Componentes são aplicadas consistentemente e de modo ubíquo, desde especificações de alto nível de serviços até a implementação de software básico em unidades programáveis de processamento de rede. Os objetivos principais são expressar a adaptabilidade de múltiplos aspectos nesses serviços e, simultaneamente, reduzir a sobrecarga cognitiva em projetistas e programadores, decorrente dessa multiplicidade de aspectos. Para isso, foi desenvolvida uma linguagem de especificação baseada em XML, chamada Lindax, que permite descrever arquiteturalmente diversos aspectos de sistemas de comunicação - por meio de um arcabouço sintático único para DSLs - e restrições de adaptação em cada aspecto particular - por meio de estruturas de estilos arquiteturais. Complementando o trabalho, um conjunto de ferramentas de manipulação de descrições arquiteturais em LindaX é definido. Essas ferramentas permitem o refinamento para diferentes linguagens formais ou a síntese de configurações e mecanismos de controle de adaptações para diversas plataformas. / [en] It is increasingly noticeable, in the current telecommunications market, a trend towards using communication systems that allow rapid and cheap deployment of new services. In pursuit of network architectures that keep up with such trend, significant research has been carried out on programmable networks. This field is set to gain further impetus from developments in network processor-based equipment. In this context, it is crucial that service creation processes be well structured and, as far as possible, systematic. This thesis, which is part of an ongoing project at the TeleMídia Laboratory, PUC-Rio, adopts a service creation approach in which techniques from Software Architecture and Component-Based Software Development are uniformly and ubiquitously applied at all levels of a communication system, ranging from high- level service specifications to low-level software implementation running in network processors. The main aim is to express adaptibility in cross-cutting service aspects and, meanwhile, cut down on the cognitive overhead usually imposed upon designers and programmers due to such multiplicity of concerns. For the sake of the aforementioned aim, an XML-based specification language, called LindaX, has been developed. Such language allows various system aspects to be architecturally described - by means of a single syntactic framework for DSLs - as well as adaptable in a constrained way - through style structures. Complementing the work, a toolset for handling LindaX architecture descriptions has been defined, which allows their refinement to different formal languages or their synthesis onto system configurations and adaptation controlling mechanisms for diverse platforms.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / Architectural specification of real-time software systems is an activity that conveys analysis, knowledge and understanding of both the application domain and the parties involved in software construction. Architecture plays a key role in communication between stakeholders, in addition to planning the entire architectural process involved in the project. However, Architecture Description Languages (ADLs) have not been widely used in the industry. Another limiting factor for the e ff ective use of ADLs is the di ffi culty of these languages in e ff ectively expressing the architecture of complex systems. Considering this situation of di ffi culty in the e ff ective use of ADLs, the UML has been used in recent years to model the architecture. However, UML can not represent the important characteristics pertinent to real-time systems, such as security or real-time constraints. One of the advantages of the UML is the extensibility allowing the creation of profiles. In this sense, this work proposes using Systems Modeling Language (SysML), a UML profile, to model real-time systems architecture in two automotive systems, the airbag control system and the light control system. The objective of this work is to use UML and SysML to model and document the architecture and design of requirements traceability between software and systems elements, increasing the understanding of the project among the parties involved, and finally presenting SysML as a language for description of real-time software architecture. The ADL Architecture Analysis and Design Language (AADL) and SysML languages were compared to show the advantages of SysML. As a result, it was noticed that abstract features such as conditional deviations, loop, characteristics that are related to reality and consequently to the system can not be described in AADL. SysML has proved to be relevant in the context of architecture description, analysis, classification and modeling of real-time systems. The SysML Requirements diagram explicitly shows the various types of relationships between di ff erent requirements, the Block diagram enables the global view of the systems involved in a single project, the Internal Block diagram allows the internal view of the system under construction, the Activity diagram considers the behavioral view of the system. SysML concepts, articulated in the SysML Requirements, Activities, Blocks and Internal Blocks diagrams, are complementary, covering the purposes needed to describe the architecture of real-time systems. It is concluded that the proposed UML and SysML join technique provides elements to describe software requirements and their relationships with the system, to manage changes, to evolve and to trace requirements more easily, in addition to the communication being e ff ectively carried out between the stakeholders. This is important for the development of real-time systems because of the diversity of people / teams involved and influencing a wide range of design decisions. / A especificação da arquitetura de sistemas de software de tempo real é uma atividade que depreende análise, conhecimento e compreensão tanto do domínio da aplicação quanto das partes envolvidas na construção do software. A arquitetura tem um papel primordial na comunicação entre os stakeholders, além do planejamento de todo o processo arquitetural envolvido no projeto. Contudo, as Linguagens de Descrição de Arquiteturas (ADLs) não têm sido amplamente usadas na indústria. Outro fator limitador para o uso efetivo de ADLs é a dificuldade dessas linguagens em expressar efetivamente a arquitetura de sistemas complexos. Considerando essa situação de dificuldade do uso efetivo de ADLs, a UML tem sido utilizada nos últimos anos para modelagem da arquitetura. No entanto, a UML não consegue representar características importantes pertinentes a sistemas de tempo real, tais como segurança ou restrições de tempo real. Uma das vantagens da UML é a capacidade de extensão permitindo a criação de profiles. Neste sentido, este trabalho apresenta a Systems Modeling Language (SysML), um profile da UML, para modelagem da arquitetura de sistemas de tempo real em dois sistemas automotivos, o sistema de controle de airbag e o sistema de controle de faróis. Neste trabalho tem-se como objetivos utilizar a UML e a SysML para modelagem e documentação da arquitetura e delineamento de rastreabilidade de requisitos entre software e sistema, ampliando o entendimento do projeto entre as partes envolvidas, e por fim apresentar a SysML como uma linguagem para descrição da arquitetura de software de tempo real. As linguagens SysML e a ADL Architecture Analysis & Design Language (AADL) foram comparadas para mostrar as vantagens da SysML. Como resultado, foi percebido que características abstratas, tais como tomadas de decisão, repetição de uma funcionalidade (loop), características que são relacionadas a realidade e, consequentemente, ao sistema, não podem ser descritas em AADL. A SysML mostrou-se relevante no contexto da descrição, análise, classificação e modelagem de arquitetura para sistemas de tempo real. O diagrama de Requisitos da SysML mostra explicitamente os diversos tipos de relacionamentos entre diferentes requisitos, o diagrama de Blocos viabiliza a visão global dos sistemas envolvidos num único projeto, o diagrama de Blocos Internos possibilita a visão interna do sistema em construção, o diagrama de Atividades considera a visão comportamental do sistema. Os conceitos de SysML, articulados nos diagramas de Requisitos, Atividades, Blocos e Blocos Internos da SysML são complementares cobrindo os propósitos necessários para a descrição da arquitetura de sistemas de tempo real. Conclui-se que a técnica proposta da junção de UML e SysML fornece elementos para descrever requisitos de software e seus relacionamentos com o sistema, gerenciar mudanças, evoluir e rastrear requisitos mais facilmente, além da comunicação ser efetivamente realizada entre os stakeholders. Este aspecto é importante ao desenvolvimento de sistemas de tempo real, por causa da diversidade de pessoas / equipes envolvidas e que influenciam uma ampla série de decisões de projeto.

Cloud computing represents a fundamental change in the way organizations acquire technological resources (e.g., hardware, development and execution environments, applications); where, instead of buying them, they acquire remote access to them in the form of cloud services supplied through the Internet. Among the main characteristics of cloud computing is the allocation of resources in an agile and elastic way, reserved or released depending on the demand of the users or applications, enabling the payment model based on consumption metrics. The development of cloud applications mostly follows an incremental approach, where the incremental delivery of functionalities to the client changes - or reconfigures - successively the current architecture of the application. Cloud providers have their own standards for both implementation technologies and service management mechanisms, requiring solutions that facilitate: building, integrating and deploying portable services; interoperability between services deployed across different cloud providers; and continuity In the execution of the application while its architecture is reconfigured product of the integration of the successive increments. The principles of the model-driven development approach, the architectural style service-oriented architectures, and the dynamic reconfiguration play an important role in this context. The hypothesis of this doctoral thesis is that model-driven development methods provide cloud service developers with abstraction and automation mechanisms for the systematic application of the principles of model engineering during the design, implementation, and incremental deployment of cloud services, facilitating the dynamic reconfiguration of the service-oriented architecture of cloud applications. The main objective of this doctoral thesis is therefore to define and validate empirically DIARy, a method of dynamic and incremental reconfiguration of service-oriented architectures for cloud applications. This method will allow specifying the architectural integration of the increment with the current cloud application, and with this information to automate the derivation of implementation artifacts that facilitate the integration and dynamic reconfiguration of the service architecture of the cloud application. This dynamic reconfiguration is achieved by running reconfiguration artifacts that not only deploy / un-deploy increment's services and orchestration services between services of the increment with the services of the current cloud application; but also, they change the links between services at runtime. A software infrastructure that supports the activities of the proposed method has also been designed and implemented. The software infrastructure includes the following components: i) a set of DSLs, with their respective graphical editors, that allow to describe aspects related to the architectural integration, implementation and provisioning of increments in cloud environments; ii) transformations that generate platform-specific implementation and provisioning models; (iii) transformations that generate artifacts that implement integration logic and orchestration of services, and scripts of provisioning, deployment, and dynamic reconfiguration for different cloud vendors. This doctoral thesis contributes to the field of service-oriented architectures and in particular to the dynamic reconfiguration of cloud services architectures in an iterative and incremental development context. The main contribution is a well-defined method, based on the principles of model-driven development, which makes it easy to raise the level of abstraction and automate, through transformations, the generation of artifacts that perform the dynamic reconfiguration of cloud applications. / La computación cloud representa un cambio fundamental en la manera en la que las organizaciones adquieren recursos tecnológicos (p. ej., hardware, entornos de desarrollo y ejecución, aplicaciones); en donde, en lugar de comprarlos adquieren acceso remoto a ellos en forma de servicios cloud suministrados a través de Internet. Entre las principales características de la computación cloud está la asignación de recursos de manera ágil y elástica, reservados o liberados dependiendo de la demanda de los usuarios o aplicaciones, posibilitando el modelo de pago basado en métricas de consumo. El desarrollo de aplicaciones cloud sigue mayoritariamente un enfoque incremental, en donde la entrega incremental de funcionalidades al cliente cambia - o reconfigura - sucesivamente la arquitectura actual de la aplicación. Los proveedores cloud tienen sus propios estándares tanto para las tecnologías de implementación como para los mecanismos de gestión de servicios, requiriéndose soluciones que faciliten: la construcción, integración y despliegue de servicios portables; la interoperabilidad entre servicios desplegados en diferentes proveedores cloud; y la continuidad en la ejecución de la aplicación mientras su arquitectura es reconfigurada producto de la integración de los sucesivos incrementos. Los principios del enfoque de desarrollo dirigido por modelos, del estilo arquitectónico de arquitecturas orientadas a servicios y de la reconfiguración dinámica cumplen un papel importante en este contexto. La hipótesis de esta tesis doctoral es que los métodos de desarrollo dirigido por modelos brindan a los desarrolladores de servicios cloud mecanismos de abstracción y automatización para la aplicación sistemática de los principios de la ingeniería de modelos durante el diseño, implementación y despliegue incremental de servicios cloud, facilitando la reconfiguración dinámica de la arquitectura orientada a servicios de las aplicaciones cloud. El objetivo principal de esta tesis doctoral es por tanto definir y validar empíricamente DIARy, un método de reconfiguración dinámica e incremental de arquitecturas orientadas a servicios. Este método permitirá especificar la integración arquitectónica del incremento con la aplicación cloud actual, y con esta información automatizar la derivación de los artefactos de implementación que faciliten la integración y reconfiguración dinámica de la arquitectura de servicios de la aplicación cloud. Esta reconfiguración dinámica se consigue al ejecutar los artefactos de reconfiguración que no solo despliegan/repliegan los servicios del incremento y servicios de orquestación entre los servicios del incremento con los servicios de la aplicación cloud actual; sino también, cambian en tiempo de ejecución los enlaces entre servicios. También se ha diseñado e implementado una infraestructura software que soporta las actividades del método propuesto e incluye los siguientes componentes: i) un conjunto de DSLs, con sus respectivos editores gráficos, que permiten describir aspectos relacionados a la integración arquitectónica, implementación y aprovisionamiento de incrementos en entornos cloud; ii) transformaciones que generan modelos de implementación y aprovisionamiento; iii) transformaciones que generan artefactos que implementan la lógica de integración y orquestación de servicios, y scripts de aprovisionamiento, despliegue y reconfiguración dinámica específicos para distintos proveedores cloud. Esta tesis doctoral contribuye al campo de las arquitecturas orientadas a servicios y en particular a la reconfiguración dinámica de arquitecturas de servicios cloud en contextos de desarrollo iterativo e incremental. El principal aporte es un método bien definido, basado en los principios del desarrollo dirigido por modelos, que facilita elevar el nivel de abstracción y automatizar por medio de transformaciones la generación de artefactos que real / La computació cloud representa un canvi fonamental en la manera en què les organitzacions adquirixen recursos tecnològics (ej., maquinari, entorns de desplegament i execució, aplicacions) ; on, en compte de comprar-los adquirixen accés remot a ells en forma de servicis cloud subministrats a través d'Internet. Entre les principals característiques de la computació cloud els recursos cloud són assignats de manera àgil i elàstica, reservats o alliberats depenent de la demanda dels usuaris o aplicacions, possibilitant el model de pagament basat en mètriques de consum. El desenrotllament d'aplicacions cloud seguix majoritàriament un enfocament incremental, on l'entrega incremental de funcionalitats al client canvia - o reconfigura - successivament l'arquitectura actual de l'aplicació. Els proveïdors cloud tenen els seus propis estàndards tant per a les tecnologies d'implementació com per als mecanismes de gestió de servicis, requerint-se solucions que faciliten: la construcció, integració i desplegament de servicis portables; la interoperabilitat entre servicis desplegats en diferents proveïdors cloud; i la continuïtat en l'execució de l'aplicació mentres la seua arquitectura és reconfigurada producte de la integració dels successius increments. Els principis de l'enfocament de desenrotllament dirigit per models, de l'estil arquitectònic d'arquitectures orientades a servicis i de la reconfiguració dinàmica complixen un paper important en este context. La hipòtesi d'esta tesi doctoral és que els mètodes de desenrotllament dirigit per models brinden als desenvolupadors de servicis cloud mecanismes d'abstracció i automatització per a l'aplicació sistemàtica dels principis de l'enginyeria de models durant el disseny, implementació i desplegament incremental de servicis cloud, facilitant la reconfiguració dinàmica de l'arquitectura orientada a servicis de les aplicacions cloud. L'objectiu principal d'esta tesi doctoral és per tant de definir i validar empí-ricamente DIARy, un mètode de reconfiguració dinàmica i incremental d'arquitectures orientades a servicis per a aplicacions cloud. Este mètode permetrà especificar la integració arquitectònica de l'increment amb l'aplicació cloud actual, i amb esta informació automatitzar la derivació dels artefactes d'implementació que faciliten la integració i reconfiguració dinàmica de l'arquitectura de servicis de l'aplicació cloud. Esta reconfi-guración dinàmica s'aconseguix a l'executar els artefactes de reconfiguració que no sols despleguen/repleguen els servicis de l'increment i servicis d'orquestració entre els servicis de l'increment amb els servicis de l'aplicació cloud actual; sinó també, canvien en temps d'execució els enllaços entre servicis. També s'ha dissenyat i implementat una infraestructura programari que suporta les activitats del mètode proposat i inclou els següents components: i) un conjunt de DSLs, amb els seus respectius editors gràfics, que permeten descriure aspectes relacionats a la integració arquitectònica, implementació i aprovisionament en entorns cloud dels increments; ii) transformacions que generen models d'implementació i aprovisionament específics de la plataforma a partir dels models d'integració d'alt nivell; iii) transformacions que generen artefactes que implementen la lògica d'integració i orquestració de servicis, i scripts d'aprovisionament, desplegament i reconfiguració dinàmica específics per a distints proveïdors cloud. Esta tesi doctoral contribuïx al camp de les arquitectures orientades a servicis i en particular a la reconfiguració dinàmica d'arquitectures de servicis cloud en contextos de desenrotllament iteratiu i incremental. La principal aportació és un mètode ben definit, basat en els principis del desenrotllament dirigit per models, que facilita elevar el nivell d'abstracció i automatitzar per mitjà de transformacions la generació d'artefactes que r / Zuñiga Prieto, MÁ. (2017). Reconfiguración Dinámica e Incremental de Arquitecturas de Servicios Cloud Dirigida por Modelos [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/86288 / TESIS