On the automatic integration of hardware accelerators into FPGA-based embedded systems

This paper proposes an automatic framework for the seamless integration of hardware accelerators, starting from an OpenMP-based application and an XML file describing the HW/SW partitioning. It extends a fully software architecture by generating and integrating the cores, along with the proper interfaces, and the code for scheduling and synchronization. Experimental results show that it is possible to validate different solutions only by varying the input code.

Dreams: A tool for the design of dynamically reconfigurable embedded and modular systems

Dynamically Reconfigurable Systems are attracting a growing interest, mainly due to the emergence of novel applications based on this technology. However, commercial tools do not provide enough flexibility to design solutions, while keeping an acceptable design productivity. In this paper, a novel design flow is proposed, targeting dynamically reconfigurable systems. It is fully supported by a tool called Dreams, which is able to implement flexible systems, starting from a set of netlists corresponding to the modules, as well as a system description provided by the user. The tool automatically post-processes the nets, implementing a solution for the communications between reconfigurable regions, as well as the handling of routing conflicts, by means of a custom router. Since the design process of every module and the static system are independent, the proposed flow is compatible with system upgrade at run-time. In this paper, a use case corresponding to the design of a highly regular and parallel mesh-type architecture is described, in order to show the architectural flexibility offered by the tool.

Portado del algoritmo de Viterbi a una arquitectura multiprocesador

Cada vez es más frecuente que los sistemas de comunicaciones realicen buena parte de sus funciones (modulación y demodulación, codificación y decodificación...) mediante software en lugar de utilizar hardware dedicado. Esta técnica se denomina “Radio software”. El objetivo de este PFC es estudiar un algoritmo implementado en C empleado en sistemas de comunicaciones modernos, en concreto la decodificación de Viterbi, el cual se encarga de corregir los posibles errores producidos a lo largo de la comunicación, para poder trasladarlo a sistemas empotrados multiprocesador. Partiendo de un código en C para el decodificador que realiza todas sus operaciones en serie, en este Proyecto fin de carrera se ha paralelizado dicho código, es decir, que el trabajo que realizaba un solo hilo para el caso del código serie, es procesado por un número de hilos configurables por el usuario, persiguiendo que el tiempo de ejecución se reduzca, es decir, que el programa paralelizado se ejecute de una manera más rápida. El trabajo se ha realizado en un PC con sistema operativo Linux, pero la versión paralelizada del código puede ser empleada en un sistema empotrado multiprocesador en el cual cada procesador ejecuta el código correspondiente a uno de los hilos de la versión de PC. ABSTRACT It is increasingly common for communications systems to perform most of its functions (modulation and demodulation, coding and decoding) by software instead of than using dedicated hardware. This technique is called: “Software Radio”. The aim of the PFC is to study an implemented algorithm in C language used in modern communications systems, particularly Viterbi decoding, which amends any possible error produced during the communication, in order to be able to move multiprocessor embedded systems. Starting from a C code of the decoder that performs every single operation in serial, in this final project, this code has been parallelized, which means that the work used to be done by just a single thread in the case of serial code, is processed by a number of threads configured by the user, in order to decrease the execution time, meaning that the parallelized program is executed faster. The work has been carried out on a PC using Linux operating system, but the parallelized version of the code could also be used in an embedded multiprocessor system in which each processor executes the corresponding code to every single one of the threads of the PC version.

Development of Embedded Linux Applications Using ZedBoard

The purpose of this document is to create a modest integration guide for embedding a Linux Operating System on ZedBoard development platform, based on Xilinx’s Zynq-7000 All Programmable System on Chip which contains a dual core ARM Cortex-A9 and a 7 Series FPGA Artix-7. The integration process has been structured in four chapters according to the logic generation of the different parts that compose the embedded system. With the intention of automating the generation process of a complete Linux distribution specific for ZedBoard platform, BuildRoot development platform it is used. Once the embedding process finished, it was decided to add to the system the required functionalities for adding support for IEEE1588 Standard for Precision Clock Synchronization Protocol for Networked Measurement and Control Systems, through a user space Linux program which implements the protocol. That PTP user space implementation program has been cross-compiled, executed on target and tested for evaluating the functionalities added. RESUMEN El propósito de este documento es crear una modesta guía de integración de un sistema operativo Linux para la plataforma de desarrollo ZedBoard, basada en un System on Chip del fabricante Xilinx llamado Zynq-7000. Este System on Chip está compuesto por un procesador de doble núcleo ARM Cortex-A9 y una FPGA de la Serie 7 equiparable a una Artix-7. El proceso de integración se ha estructurado en cuatro grandes capítulos que se rigen según el orden lógico de generación de las distintas partes por las que el sistema empotrado está compuesto. Con el ánimo de automatizar el proceso de creación de una distribución de Linux específica para la plataforma ZedBoard, se ha utilizado la plataforma de desarrollo BuildRoot. Una vez terminado el proceso de integración del sistema empotrado, se procedió a dar dotar al sistema de las funcionalidades necesarias para dar soporte al estándar de sincronización de relojes en redes de área local, PTP IEEE1588, a través de una implementación del mismo en un programa de lado de usuario el cual ha sido compilado, ejecutado y testeado para evaluar el correcto funcionamiento de las funcionalidades añadidas.

Methodologies for implement video decoders over multiprocessor platforms

The latest video coding standards developed, like HEVC (High Efficiency Video Coding, approved in January 2013), require for their implementation the use of devices able to support a high computational load. Considering that currently it is not enough the usage of one unique Digital Signal Processor (DSP), multicore devices have appeared recently in the market. However, due to its novelty, the working methodology that allows produce solutions for these configurations is in a very initial state, since currently the most part of the work needs to be performed manually. In consequence, the objective set consists on finding methodologies that ease this process. The study has been focused on extend a methodology, under development, for the generation of solutions for PCs and embedded systems. During this study, the standards RVC (Reconfigurable Video Coding) and HEVC have been employed, as well as DSPs of the Texas Instruments company. In its development, it has been tried to address all the factors that influence both the development and deployment of these new implementations of video decoders, ranging from tools up to aspects of the partitioning of algorithms, without this can cause a drop in application performance. The results of this study are the description of the employed methodology, the characterization of the software migration process and performance measurements for the HEVC standard in an RVC-based implementation. RESUMEN Los estándares de codificación de vídeo desarrollados más recientemente, como HEVC (High Efficiency Video Coding, aprobado en enero de 2013), requieren para su implementación el uso de dispositivos capaces de soportar una elevada carga computacional. Teniendo en cuenta que actualmente no es suficiente con utilizar un único Procesador Digital de Señal (DSP), han aparecido recientemente dispositivos multinúcleo en el mercado. Sin embargo, debido a su novedad, la metodología de trabajo que permite elaborar soluciones para tales configuraciones se encuentra en un estado muy inicial, ya que actualmente la mayor parte del trabajo debe realizarse manualmente. En consecuencia, el objetivo marcado consiste en encontrar metodologías que faciliten este proceso. El estudio se ha centrado en extender una metodología, en desarrollo, para la generación de soluciones para PC y sistemas empotrados. Durante dicho estudio se han empleado los estándares RVC (Reconfigurable Video Coding) y HEVC, así como DSPs de la compañía Texas Instruments. En su desarrollo se ha tratado de atender a todos los factores que influyen tanto en el desarrollo como en la puesta en marcha de estas nuevas implementaciones de descodificadores de vídeo; abarcando desde las herramientas a utilizar hasta aspectos del particionado de los algoritmos, sin que por ello se produzca una reducción en el rendimiento de las aplicaciones. Los resultados de este estudio son una descripción de la metodología empleada, la caracterización del proceso de migración de software, y medidas de rendimiento para el estándar HEVC en una implementación basada en RVC.

Ada real-time services and virtualization

Virtualization techniques have received increased attention in the field of embedded real-time systems. Such techniques provide a set of virtual machines that run on a single hardware platform, thus allowing several application programs to be executed as though they were running on separate machines, with isolated memory spaces and a fraction of the real processor time available to each of them.This papers deals with some problems that arise when implementing real-time systems written in Ada on a virtual machine. The effects of virtualization on the performance of the Ada real-time services are analysed, and requirements for the virtualization layer are derived. Virtual-machine time services are also defined in order to properly support Ada real-time applications. The implementation of the ORK+ kernel on the XtratuM supervisor is used as an example.

An embedded cohesive crack model for finite element analysis of quasi-brittle materials

This paper presents a numerical implementation of the cohesive crack model for the anal-ysis of quasibrittle materials based on the strong discontinuity approach in the framework of the finite element method. A simple central force model is used for the stress versus crack opening curve. The additional degrees of freedom defining the crack opening are determined at the crack level, thus avoiding the need for performing a static condensation at the element level. The need for a tracking algorithm is avoided by using a consistent pro-cedure for the selection of the separated nodes. Such a model is then implemented into a commercial program by means of a user subroutine, consequently being contrasted with the experimental results. The model takes into account the anisotropy of the material. Numerical simulations of well-known experiments are presented to show the ability of the proposed model to simulate the fracture of quasibrittle materials such as mortar, concrete and masonry.

On correctness in RDF stream processor benchmarking

Two complementary benchmarks have been proposed so far for the evaluation and continuous improvement of RDF stream processors: SRBench and LSBench. They put a special focus on different features of the evaluated systems, including coverage of the streaming extensions of SPARQL supported by each processor, query processing throughput, and an early analysis of query evaluation correctness, based on comparing the results obtained by different processors for a set of queries. However, none of them has analysed the operational semantics of these processors in order to assess the correctness of query evaluation results. In this paper, we propose a characterization of the operational semantics of RDF stream processors, adapting well-known models used in the stream processing engine community: CQL and SECRET. Through this formalization, we address correctness in RDF stream processor benchmarks, allowing to determine the multiple answers that systems should provide. Finally, we present CSRBench, an extension of SRBench to address query result correctness verification using an automatic method.

Explointing FPGA block memories for protected cryptographic implementations

Modern Field Programmable Gate Arrays (FPGAs) are power packed with features to facilitate designers. Availability of features like huge block memory (BRAM), Digital Signal Processing (DSP) cores, embedded CPU makes the design strategy of FPGAs quite different from ASICs. FPGA are also widely used in security-critical application where protection against known attacks is of prime importance. We focus ourselves on physical attacks which target physical implementations. To design countermeasures against such attacks, the strategy for FPGA designers should also be different from that in ASIC. The available features should be exploited to design compact and strong countermeasures. In this paper, we propose methods to exploit the BRAMs in FPGAs for designing compact countermeasures. BRAM can be used to optimize intrinsic countermeasures like masking and dual-rail logic, which otherwise have significant overhead (at least 2X). The optimizations are applied on a real AES-128 co-processor and tested for area overhead and resistance on Xilinx Virtex-5 chips. The presented masking countermeasure has an overhead of only 16% when applied on AES. Moreover Dual-rail Precharge Logic (DPL) countermeasure has been optimized to pack the whole sequential part in the BRAM, hence enhancing the security. Proper robustness evaluations are conducted to analyze the optimization for area and security.

Desarrollo de aplicaciones basadas en Linux Embedded en una arquitectura basada en Cyclone V SoC (System on Chip) de Altera

We attempt to integrate and start up the set of necessary tools to deploy the design cycle of embedded systems based on Embedded Linux on a "Cyclone V SoC" made by Altera. First, we will analyze the available tools for designing the hardware system of the SoCkit development kit, made by Arrow, which has a "Cyclone V SoC" system (based on a "ARM Cortex-A9 MP Core" architecture). When designing the SoCkit board hardware, we will create a new peripheral to integrate it into the hardware system, so it can be used as any other existent resource of the SoCkit board previously configured. Next, we will analyze the tools to generate an Embedded Linux distribution adapted to the SoCkit board. In order to generate the Linux distribution we will use, on the one hand, a software package from Yocto recommended by Altera; on the other hand, the programs and tools of Altera, Embedded Development Suite. We will integrate all the components needed to build the Embedded Linux distribution, creating a complete and functional system which can be used for developing software applications. Finally, we will study the programs for developing and debugging applications in C or C++ language that will be executed in this hardware platform, then we will program a Linux application as an example to illustrate the use of SoCkit board resources. RESUMEN Se pretende integrar y poner en funcionamiento el conjunto de herramientas necesarias para desplegar el ciclo de diseño de sistemas embebidos basados en "Embedded Linux" sobre una "Cyclone V SoC" de Altera. En primer lugar, se analizarán las diversas herramientas disponibles para diseñar el sistema hardware de la tarjeta de desarrollo SoCkit, fabricada por Arrow, que dispone de un sistema "Cyclone V SoC" (basado en una arquitectura "ARM Cortex A9 MP Core"). En el diseño hardware de la SoCkit se creará un periférico propio y se integrará en el sistema, pudiendo ser utilizado como cualquier otro recurso de la tarjeta ya existente y configurado. A continuación, también se analizarán las herramientas para generar una distribución de "Embedded Linux" adaptado a la placa SoCkit. Para generar la distribución de Linux se utilizará, por una parte, un paquete software de Yocto recomendado por Altera y, por otra parte, las propias herramientas y programas de Altera. Se integrarán todos los componentes necesarios para construir la distribución Linux, creando un sistema completo y funcional que se pueda utilizar para el desarrollo de aplicaciones software. Por último, se estudiarán las herramientas para el diseño y depuración de aplicaciones en lenguaje C ó C++ que se ejecutarán en esta plataforma hardware. Se pretende desarrollar una aplicación de ejemplo para ilustrar el uso de los recursos más utilizados de la SoCkit.

Desarrollo de un sistema automático de medida para el control del consumo en sistemas empotrados

El Grupo de Diseño Electrónico y Microelectrónico de la Universidad Politécnica de Madrid -GDEM- se dedica, entre otras cosas, al estudio y mejora del consumo en sistemas empotrados. Es en este lugar y sobre este tema donde el proyecto a exponer ha tomado forma y desarrollo. Según un artículo de la revista online Revista de Electrónica Embebida, un sistema empotrado o embebido es aquel “sistema controlado por un microprocesador y que gracias a la programación que incorpora o que se le debe incorporar, realiza una función específica para la que ha sido diseñado, integrando en su interior la mayoría de los elementos necesarios para realizar dicho función”. El porqué de estudiar sobre este tema responde a que, cada vez, hay mayor presencia de sistemas empotrados en nuestra vida cotidiana. Esto es debido a que se está tendiendo a dotar de “inteligencia” a todo lo que puedan hacer nuestra vida un poco más fácil. Nos podemos encontrar dichos sistemas en fábricas, oficinas de atención a los ciudadanos, sistemas de seguridad de hogar, relojes, móviles, lavadoras, hornos, aspiradores y un largo etcétera en cualquier aparato que nos podamos imaginar. A pesar de sus grandes ventajas, aún hay grandes inconvenientes. El mayor problema que supone a día de hoy es la autonomía del mismo sistema, ya que hablamos de aparatos que muchas veces están alimentados por baterías -para ayudar a su portabilidad–. Por esto, se está intentando dotar a dichos sistemas de una capacidad de ahorro de energía y toma de decisiones que podrían ayudar a duplicar la autonomía de dicha batería. Un ejemplo claro son los Smartphones de hoy en día, unos aparatos casi indispensables que pueden tener una autonomía de un día. Esto es poco práctico para el usuario en caso de viajes, trabajo u otras situaciones en las que se le dé mucho uso y no pueda tener acceso a una red eléctrica. Es por esto que surge la necesidad de investigar, sin necesidad de mejorar el hardware del sistema, una manera de mejorar esta situación. Este proyecto trabajará en esa línea creando un sistema automático de medida el cual generará las corrientes que servirán como entrada para verificar el sistema de adquisición que junto con la tarjeta Beagle Board permitirá la toma de decisiones en relación con el consumo de energía. Para realizar este sistema, nos ayudaremos de diferentes herramientas que podremos encontrar en el laboratorio del GDEM, como la fuente de alimentación Agilent y la Beagle Board –como principales herramientas de trabajo- . El objetivo principal será la simulación de unas señales que, después de pasar un proceso de conversión y tratado, harán la función de representación del consumo de cada una de las partes que pueden formar un sistema empotrado genérico. Por lo tanto, podemos decir que el sistema hará la funcionalidad de un banco de pruebas que ayudará a simular dicho consumo para que el microprocesador del sistema pueda llegar a tomar alguna decisión. ABSTRACT. The Electronic and Microelectronic Design Group of Universidad Politécnica de Madrid -GDEM- is in charge, between other issues, of improving the embedded system’s consumption. It is in this place and about this subject where the exposed project has taken shape and development. According to an article from de online magazine Revista de Electronica Embebida, an embedded system is “the one controlled by a microprocessor and, thanks to the programing that it includes, it carries out a specific function what it has been designed for, being integrated in it the most necessary elements for realizing the already said function”. The because of studying this subject, answers that each time there is more presence of the embedded system in our daily life. This is due to the tendency of providing “intelligence” to all what can make our lives easier. We can find this kind of systems in factories, offices, security systems, watchers, mobile phones, washing machines, ovens, hoovers and, definitely, in all kind of machines what we can think of. Despite its large vantages, there are still some inconveniences. Nowadays, the most important problem is the autonomy of the system itself when machines that have to be supplied by batteries –making easier the portability-. Therefore, this project is going after a save capacity of energy for the system as well as being able to take decisions in order to duplicate batteries’ autonomy. Smartphones are a clear example. They are a very successful product but the autonomy is just one day. This is not practical for users, at all, if they have to travel, to work or to do any activity that involves a huge use of the phone without a socket nearby. That is why the need of investigating a way to improve this situation. This project is working on this line, creating an automatic system that will generate the currents for verifying the acquisition system that, with the beagle board, will help taking decisions regarding the energy’s consumption. To carry out this system, we need different tools that we can find in the laboratory of the group previously mentioned, like power supply Agilent and the Beagle Board – as main working tools –. The main goal is the simulation of some signals that, after a conversion process, will represent de consumption of each of the parts in the embedded generic system. Therefore, the system will be a testing ground that simulate the consumption, once sent to the processor, to be processed and so the microprocessor system might take some decision.

Mixed-criticality design of a satellite software system

The continuous increment of processors computational power and the requirements on additional functionality and services are motivating a change in the way embedded systems are built. Components with different criticality level are allocated in the same processor, which give rise to mixed-criticality systems. The use of partitioned systems is a way of preventing undesirable interferences between components with different criticality level. An hypervisor provides these partitions or virtual machines, ensuring spatial, temporal and fault isolation between them. The purpose of this paper is to illustrate the development of a mixed-critical system. The attitude control subsystem is used for showing the different steps, which are supported by a toolset developed in the context of the MultiPARTES research project.

Cooperative Learning Model based on Multi-Agent Architecture for Embedded Intelligent Systems

Cooperative systems are suitable for many types of applications and nowadays these system are vastly used to improve a previously defined system or to coordinate multiple devices working together. This paper provides an alternative to improve the reliability of a previous intelligent identification system. The proposed approach implements a cooperative model based on multi-agent architecture. This new system is composed of several radar-based systems which identify a detected object and transmit its own partial result by implementing several agents and by using a wireless network to transfer data. The proposed topology is a centralized architecture where the coordinator device is in charge of providing the final identification result depending on the group behavior. In order to find the final outcome, three different mechanisms are introduced. The simplest one is based on majority voting whereas the others use two different weighting voting procedures, both providing the system with learning capabilities. Using an appropriate network configuration, the success rate can be improved from the initial 80% up to more than 90%.

Memory isolation in many-core embedded systems

The current approach to developing mixed-criticality sys- tems is by partitioning the hardware resources (processors, memory and I/O devices) among the different applications. Partitions are isolated from each other both in the temporal and the spatial domain, so that low-criticality applications cannot compromise other applications with a higher level of criticality in case of misbehaviour. New architectures based on many-core processors open the way to highly parallel systems in which each partition can be allocated to a set of dedicated proces- sor cores, thus simplifying partition scheduling and temporal separation. Moreover, spatial isolation can also benefit from many-core architectures, by using simpler hardware mechanisms to protect the address spaces of different applications. This paper describes an architecture for many- core embedded partitioned systems, together with some implementation advice for spatial isolation.

Integration of embedded data processing algorithms inside PAMELA devices

PAMELA (Phased Array Monitoring for Enhanced Life Assessment) SHMTM System is an integrated embedded ultrasonic guided waves based system consisting of several electronic devices and one system manager controller. The data collected by all PAMELA devices in the system must be transmitted to the controller, who will be responsible for carrying out the advanced signal processing to obtain SHM maps. PAMELA devices consist of hardware based on a Virtex 5 FPGA with a PowerPC 440 running an embedded Linux distribution. Therefore, PAMELA devices, in addition to the capability of performing tests and transmitting the collected data to the controller, have the capability of perform local data processing or pre-processing (reduction, normalization, pattern recognition, feature extraction, etc.). Local data processing decreases the data traffic over the network and allows CPU load of the external computer to be reduced. Even it is possible that PAMELA devices are running autonomously performing scheduled tests, and only communicates with the controller in case of detection of structural damages or when programmed. Each PAMELA device integrates a software management application (SMA) that allows to the developer downloading his own algorithm code and adding the new data processing algorithm to the device. The development of the SMA is done in a virtual machine with an Ubuntu Linux distribution including all necessary software tools to perform the entire cycle of development. Eclipse IDE (Integrated Development Environment) is used to develop the SMA project and to write the code of each data processing algorithm. This paper presents the developed software architecture and describes the necessary steps to add new data processing algorithms to SMA in order to increase the processing capabilities of PAMELA devices.An example of basic damage index estimation using delay and sum algorithm is provided.