Design and Simulation of Deep Nanometer SRAM Cells under Energy, Mismatch, and Radiation Constraints

La fiabilidad está pasando a ser el principal problema de los circuitos integrados según la tecnología desciende por debajo de los 22nm. Pequeñas imperfecciones en la fabricación de los dispositivos dan lugar ahora a importantes diferencias aleatorias en sus características eléctricas, que han de ser tenidas en cuenta durante la fase de diseño. Los nuevos procesos y materiales requeridos para la fabricación de dispositivos de dimensiones tan reducidas están dando lugar a diferentes efectos que resultan finalmente en un incremento del consumo estático, o una mayor vulnerabilidad frente a radiación. Las memorias SRAM son ya la parte más vulnerable de un sistema electrónico, no solo por representar más de la mitad del área de los SoCs y microprocesadores actuales, sino también porque las variaciones de proceso les afectan de forma crítica, donde el fallo de una única célula afecta a la memoria entera. Esta tesis aborda los diferentes retos que presenta el diseño de memorias SRAM en las tecnologías más pequeñas. En un escenario de aumento de la variabilidad, se consideran problemas como el consumo de energía, el diseño teniendo en cuenta efectos de la tecnología a bajo nivel o el endurecimiento frente a radiación. En primer lugar, dado el aumento de la variabilidad de los dispositivos pertenecientes a los nodos tecnológicos más pequeños, así como a la aparición de nuevas fuentes de variabilidad por la inclusión de nuevos dispositivos y la reducción de sus dimensiones, la precisión del modelado de dicha variabilidad es crucial. Se propone en la tesis extender el método de inyectores, que modela la variabilidad a nivel de circuito, abstrayendo sus causas físicas, añadiendo dos nuevas fuentes para modelar la pendiente sub-umbral y el DIBL, de creciente importancia en la tecnología FinFET. Los dos nuevos inyectores propuestos incrementan la exactitud de figuras de mérito a diferentes niveles de abstracción del diseño electrónico: a nivel de transistor, de puerta y de circuito. El error cuadrático medio al simular métricas de estabilidad y prestaciones de células SRAM se reduce un mínimo de 1,5 veces y hasta un máximo de 7,5 a la vez que la estimación de la probabilidad de fallo se mejora en varios ordenes de magnitud. El diseño para bajo consumo es una de las principales aplicaciones actuales dada la creciente importancia de los dispositivos móviles dependientes de baterías. Es igualmente necesario debido a las importantes densidades de potencia en los sistemas actuales, con el fin de reducir su disipación térmica y sus consecuencias en cuanto al envejecimiento. El método tradicional de reducir la tensión de alimentación para reducir el consumo es problemático en el caso de las memorias SRAM dado el creciente impacto de la variabilidad a bajas tensiones. Se propone el diseño de una célula que usa valores negativos en la bit-line para reducir los fallos de escritura según se reduce la tensión de alimentación principal. A pesar de usar una segunda fuente de alimentación para la tensión negativa en la bit-line, el diseño propuesto consigue reducir el consumo hasta en un 20 % comparado con una célula convencional. Una nueva métrica, el hold trip point se ha propuesto para prevenir nuevos tipos de fallo debidos al uso de tensiones negativas, así como un método alternativo para estimar la velocidad de lectura, reduciendo el número de simulaciones necesarias. Según continúa la reducción del tamaño de los dispositivos electrónicos, se incluyen nuevos mecanismos que permiten facilitar el proceso de fabricación, o alcanzar las prestaciones requeridas para cada nueva generación tecnológica. Se puede citar como ejemplo el estrés compresivo o extensivo aplicado a los fins en tecnologías FinFET, que altera la movilidad de los transistores fabricados a partir de dichos fins. Los efectos de estos mecanismos dependen mucho del layout, la posición de unos transistores afecta a los transistores colindantes y pudiendo ser el efecto diferente en diferentes tipos de transistores. Se propone el uso de una célula SRAM complementaria que utiliza dispositivos pMOS en los transistores de paso, así reduciendo la longitud de los fins de los transistores nMOS y alargando los de los pMOS, extendiéndolos a las células vecinas y hasta los límites de la matriz de células. Considerando los efectos del STI y estresores de SiGe, el diseño propuesto mejora los dos tipos de transistores, mejorando las prestaciones de la célula SRAM complementaria en más de un 10% para una misma probabilidad de fallo y un mismo consumo estático, sin que se requiera aumentar el área. Finalmente, la radiación ha sido un problema recurrente en la electrónica para aplicaciones espaciales, pero la reducción de las corrientes y tensiones de los dispositivos actuales los está volviendo vulnerables al ruido generado por radiación, incluso a nivel de suelo. Pese a que tecnologías como SOI o FinFET reducen la cantidad de energía colectada por el circuito durante el impacto de una partícula, las importantes variaciones de proceso en los nodos más pequeños va a afectar su inmunidad frente a la radiación. Se demuestra que los errores inducidos por radiación pueden aumentar hasta en un 40 % en el nodo de 7nm cuando se consideran las variaciones de proceso, comparado con el caso nominal. Este incremento es de una magnitud mayor que la mejora obtenida mediante el diseño de células de memoria específicamente endurecidas frente a radiación, sugiriendo que la reducción de la variabilidad representaría una mayor mejora. ABSTRACT Reliability is becoming the main concern on integrated circuit as the technology goes beyond 22nm. Small imperfections in the device manufacturing result now in important random differences of the devices at electrical level which must be dealt with during the design. New processes and materials, required to allow the fabrication of the extremely short devices, are making new effects appear resulting ultimately on increased static power consumption, or higher vulnerability to radiation SRAMs have become the most vulnerable part of electronic systems, not only they account for more than half of the chip area of nowadays SoCs and microprocessors, but they are critical as soon as different variation sources are regarded, with failures in a single cell making the whole memory fail. This thesis addresses the different challenges that SRAM design has in the smallest technologies. In a common scenario of increasing variability, issues like energy consumption, design aware of the technology and radiation hardening are considered. First, given the increasing magnitude of device variability in the smallest nodes, as well as new sources of variability appearing as a consequence of new devices and shortened lengths, an accurate modeling of the variability is crucial. We propose to extend the injectors method that models variability at circuit level, abstracting its physical sources, to better model sub-threshold slope and drain induced barrier lowering that are gaining importance in FinFET technology. The two new proposed injectors bring an increased accuracy of figures of merit at different abstraction levels of electronic design, at transistor, gate and circuit levels. The mean square error estimating performance and stability metrics of SRAM cells is reduced by at least 1.5 and up to 7.5 while the yield estimation is improved by orders of magnitude. Low power design is a major constraint given the high-growing market of mobile devices that run on battery. It is also relevant because of the increased power densities of nowadays systems, in order to reduce the thermal dissipation and its impact on aging. The traditional approach of reducing the voltage to lower the energy consumption if challenging in the case of SRAMs given the increased impact of process variations at low voltage supplies. We propose a cell design that makes use of negative bit-line write-assist to overcome write failures as the main supply voltage is lowered. Despite using a second power source for the negative bit-line, the design achieves an energy reduction up to 20% compared to a conventional cell. A new metric, the hold trip point has been introduced to deal with new sources of failures to cells using a negative bit-line voltage, as well as an alternative method to estimate cell speed, requiring less simulations. With the continuous reduction of device sizes, new mechanisms need to be included to ease the fabrication process and to meet the performance targets of the successive nodes. As example we can consider the compressive or tensile strains included in FinFET technology, that alter the mobility of the transistors made out of the concerned fins. The effects of these mechanisms are very dependent on the layout, with transistor being affected by their neighbors, and different types of transistors being affected in a different way. We propose to use complementary SRAM cells with pMOS pass-gates in order to reduce the fin length of nMOS devices and achieve long uncut fins for the pMOS devices when the cell is included in its corresponding array. Once Shallow Trench isolation and SiGe stressors are considered the proposed design improves both kinds of transistor, boosting the performance of complementary SRAM cells by more than 10% for a same failure probability and static power consumption, with no area overhead. While radiation has been a traditional concern in space electronics, the small currents and voltages used in the latest nodes are making them more vulnerable to radiation-induced transient noise, even at ground level. Even if SOI or FinFET technologies reduce the amount of energy transferred from the striking particle to the circuit, the important process variation that the smallest nodes will present will affect their radiation hardening capabilities. We demonstrate that process variations can increase the radiation-induced error rate by up to 40% in the 7nm node compared to the nominal case. This increase is higher than the improvement achieved by radiation-hardened cells suggesting that the reduction of process variations would bring a higher improvement.

A methodology to analyze, design and implement very fast and robust controls of Buck-type converters

La electrónica digital moderna presenta un desafío a los diseñadores de sistemas de potencia. El creciente alto rendimiento de microprocesadores, FPGAs y ASICs necesitan sistemas de alimentación que cumplan con requirimientos dinámicos y estáticos muy estrictos. Específicamente, estas alimentaciones son convertidores DC-DC de baja tensión y alta corriente que necesitan ser diseñados para tener un pequeño rizado de tensión y una pequeña desviación de tensión de salida bajo transitorios de carga de una alta pendiente. Además, dependiendo de la aplicación, se necesita cumplir con otros requerimientos tal y como proveer a la carga con ”Escalado dinámico de tensión”, donde el convertidor necesitar cambiar su tensión de salida tan rápidamente posible sin sobreoscilaciones, o ”Posicionado Adaptativo de la Tensión” donde la tensión de salida se reduce ligeramente cuanto más grande sea la potencia de salida. Por supuesto, desde el punto de vista de la industria, las figuras de mérito de estos convertidores son el coste, la eficiencia y el tamaño/peso. Idealmente, la industria necesita un convertidor que es más barato, más eficiente, más pequeño y que aún así cumpla con los requerimienos dinámicos de la aplicación. En este contexto, varios enfoques para mejorar la figuras de mérito de estos convertidores se han seguido por la industria y la academia tales como mejorar la topología del convertidor, mejorar la tecnología de semiconducores y mejorar el control. En efecto, el control es una parte fundamental en estas aplicaciones ya que un control muy rápido hace que sea más fácil que una determinada topología cumpla con los estrictos requerimientos dinámicos y, consecuentemente, le da al diseñador un margen de libertar más amplio para mejorar el coste, la eficiencia y/o el tamaño del sistema de potencia. En esta tesis, se investiga cómo diseñar e implementar controles muy rápidos para el convertidor tipo Buck. En esta tesis se demuestra que medir la tensión de salida es todo lo que se necesita para lograr una respuesta casi óptima y se propone una guía de diseño unificada para controles que sólo miden la tensión de salida Luego, para asegurar robustez en controles muy rápidos, se proponen un modelado y un análisis de estabilidad muy precisos de convertidores DC-DC que tienen en cuenta circuitería para sensado y elementos parásitos críticos. También, usando este modelado, se propone una algoritmo de optimización que tiene en cuenta las tolerancias de los componentes y sensados distorsionados. Us ando este algoritmo, se comparan controles muy rápidos del estado del arte y su capacidad para lograr una rápida respuesta dinámica se posiciona según el condensador de salida utilizado. Además, se propone una técnica para mejorar la respuesta dinámica de los controladores. Todas las propuestas se han corroborado por extensas simulaciones y prototipos experimentales. Con todo, esta tesis sirve como una metodología para ingenieros para diseñar e implementar controles rápidos y robustos de convertidores tipo Buck. ABSTRACT Modern digital electronics present a challenge to designers of power systems. The increasingly high-performance of microprocessors, FPGAs (Field Programmable Gate Array) and ASICs (Application-Specific Integrated Circuit) require power supplies to comply with very demanding static and dynamic requirements. Specifically, these power supplies are low-voltage/high-current DC-DC converters that need to be designed to exhibit low voltage ripple and low voltage deviation under high slew-rate load transients. Additionally, depending on the application, other requirements need to be met such as to provide to the load ”Dynamic Voltage Scaling” (DVS), where the converter needs to change the output voltage as fast as possible without underdamping, or ”Adaptive Voltage Positioning” (AVP) where the output voltage is slightly reduced the greater the output power. Of course, from the point of view of the industry, the figures of merit of these converters are the cost, efficiency and size/weight. Ideally, the industry needs a converter that is cheaper, more efficient, smaller and that can still meet the dynamic requirements of the application. In this context, several approaches to improve the figures of merit of these power supplies are followed in the industry and academia such as improving the topology of the converter, improving the semiconductor technology and improving the control. Indeed, the control is a fundamental part in these applications as a very fast control makes it easier for the topology to comply with the strict dynamic requirements and, consequently, gives the designer a larger margin of freedom to improve the cost, efficiency and/or size of the power supply. In this thesis, how to design and implement very fast controls for the Buck converter is investigated. This thesis proves that sensing the output voltage is all that is needed to achieve an almost time-optimal response and a unified design guideline for controls that only sense the output voltage is proposed. Then, in order to assure robustness in very fast controls, a very accurate modeling and stability analysis of DC-DC converters is proposed that takes into account sensing networks and critical parasitic elements. Also, using this modeling approach, an optimization algorithm that takes into account tolerances of components and distorted measurements is proposed. With the use of the algorithm, very fast analog controls of the state-of-the-art are compared and their capabilities to achieve a fast dynamic response are positioned de pending on the output capacitor. Additionally, a technique to improve the dynamic response of controllers is also proposed. All the proposals are corroborated by extensive simulations and experimental prototypes. Overall, this thesis serves as a methodology for engineers to design and implement fast and robust controls for Buck-type converters.

Lock-in amplifiers for AMR sensors

Anisotropic magnetoresistive (AMR) magnetic sensors are often chosen as the magnetic transducer for magnetic field sensing in applications with low to moderate magnetic field resolution because of the relative low mass of the sensor and their ease of use. They measure magnetic fields in the order of the Earth magnetic field (with typical sensitivities of 1‰/G or 10−2‰/μT), have typical minimum detectable fields in order of nT and even 0.1 nT but they are seriously limited by the thermal drifts due to the variation of the resistivity with temperature (∼2.5‰/°C) and the variation of the magnetoresistive effect with temperature (which affects both the sensitivity of the sensors: ∼2.7‰/°C, and the offset: ±0.5‰/°C). Therefore, for lower magnetic fields, fluxgate vector sensors are generally preferred. In the present work these limitations of AMR sensors are outlined and studied. Three methods based on lock-in amplifiers are proposed as low noise techniques. Their performance has been simulated, experimentally tested and comparatively discussed. The developed model has been also used to derive a technique for temperature compensation of AMR response. The final goal to implement these techniques in a space qualified applied specific integrated circuit (ASIC) for Mars in situ exploration with compact miniaturized magnetometers.

Detectores monolíticos y sensores compatibles con altos campos magnéticos para tomografía por emisión de positrones

Esta tesis recoje un trabajo experimental centrado en profundizar sobre el conocimiento de los bloques detectores monolíticos como alternativa a los detectores segmentados para tomografía por emisión de positrones (Positron Emission Tomography, PET). El trabajo llevado a cabo incluye el desarrollo, la caracterización, la puesta a punto y la evaluación de prototipos demostradores PET utilizando bloques monolíticos de ortosilicato de lutecio ytrio dopado con cerio (Cerium-Doped Lutetium Yttrium Orthosilicate, LYSO:Ce) usando sensores compatibles con altos campos magnéticos, tanto fotodiodos de avalancha (Avalanche Photodiodes, APDs) como fotomultiplicadores de silicio (Silicon Photomultipliers, SiPMs). Los prototipos implementados con APDs se construyeron para estudiar la viabilidad de un prototipo PET de alta sensibilidad previamente simulado, denominado BrainPET. En esta memoria se describe y caracteriza la electrónica frontal integrada utilizada en estos prototipos junto con la electrónica de lectura desarrollada específicamente para los mismos. Se muestran los montajes experimentales para la obtención de las imágenes tomográficas PET y para el entrenamiento de los algoritmos de red neuronal utilizados para la estimación de las posiciones de incidencia de los fotones γ sobre la superficie de los bloques monolíticos. Con el prototipo BrainPET se obtuvieron resultados satisfactorios de resolución energética (13 % FWHM), precisión espacial de los bloques monolíticos (~ 2 mm FWHM) y resolución espacial de la imagen PET de 1,5 - 1,7 mm FWHM. Además se demostró una capacidad resolutiva en la imagen PET de ~ 2 mm al adquirir simultáneamente imágenes de fuentes radiactivas separadas a distancias conocidas. Sin embargo, con este prototipo se detectaron también dos limitaciones importantes. En primer lugar, se constató una falta de flexibilidad a la hora de trabajar con un circuito integrado de aplicación específica (Application Specific Integrated Circuit, ASIC) cuyo diseño electrónico no era propio sino comercial, unido al elevado coste que requieren las modificaciones del diseño de un ASIC con tales características. Por otra parte, la caracterización final de la electrónica integrada del BrainPET mostró una resolución temporal con amplio margen de mejora (~ 13 ns FWHM). Tomando en cuenta estas limitaciones obtenidas con los prototipos BrainPET, junto con la evolución tecnológica hacia matrices de SiPM, el conocimiento adquirido con los bloques monolíticos se trasladó a la nueva tecnología de sensores disponible, los SiPMs. A su vez se inició una nueva estrategia para la electrónica frontal, con el ASIC FlexToT, un ASIC de diseño propio basado en un esquema de medida del tiempo sobre umbral (Time over Threshold, ToT), en donde la duración del pulso de salida es proporcional a la energía depositada. Una de las características más interesantes de este esquema es la posibilidad de manejar directamente señales de pulsos digitales, en lugar de procesar la amplitud de las señales analógicas. Con esta arquitectura electrónica se sustituyen los conversores analógicos digitales (Analog to Digital Converter, ADCs) por conversores de tiempo digitales (Time to Digital Converter, TDCs), pudiendo implementar éstos de forma sencilla en matrices de puertas programmable ‘in situ’ (Field Programmable Gate Array, FPGA), reduciendo con ello el consumo y la complejidad del diseño. Se construyó un nuevo prototipo demostrador FlexToT para validar dicho ASIC para bloques monolíticos o segmentados. Se ha llevado a cabo el diseño y caracterización de la electrónica frontal necesaria para la lectura del ASIC FlexToT, evaluando su linealidad y rango dinámico, el comportamiento frente a ruido así como la no linealidad diferencial obtenida con los TDCs implementados en la FPGA. Además, la electrónica presentada en este trabajo es capaz de trabajar con altas tasas de actividad y de discriminar diferentes centelleadores para aplicaciones phoswich. El ASIC FlexToT proporciona una excelente resolución temporal en coincidencia para los eventos correspondientes con el fotopico de 511 keV (128 ps FWHM), solventando las limitaciones de resolución temporal del prototipo BrainPET. Por otra parte, la resolución energética con bloques monolíticos leidos por ASICs FlexToT proporciona una resolución energética de 15,4 % FWHM a 511 keV. Finalmente, se obtuvieron buenos resultados en la calidad de la imagen PET y en la capacidad resolutiva del demostrador FlexToT, proporcionando resoluciones espaciales en el centro del FoV en torno a 1,4 mm FWHM. ABSTRACT This thesis is focused on the development of experimental activities used to deepen the knowledge of monolithic detector blocks as an alternative to segmented detectors for Positron Emission Tomography (PET). It includes the development, characterization, setting up, running and evaluation of PET demonstrator prototypes with monolithic detector blocks of Cerium-doped Lutetium Yttrium Orthosilicate (LYSO:Ce) using magnetically compatible sensors such as Avalanche Photodiodes (APDs) and Silicon Photomultipliers (SiPMs). The prototypes implemented with APDs were constructed to validate the viability of a high-sensitivity PET prototype that had previously been simulated, denominated BrainPET. This work describes and characterizes the integrated front-end electronics used in these prototypes, as well as the electronic readout system developed especially for them. It shows the experimental set-ups to obtain the tomographic PET images and to train neural networks algorithms used for position estimation of photons impinging on the surface of monolithic blocks. Using the BrainPET prototype, satisfactory energy resolution (13 % FWHM), spatial precision of monolithic blocks (~ 2 mm FWHM) and spatial resolution of the PET image (1.5 – 1.7 mm FWHM) in the center of the Field of View (FoV) were obtained. Moreover, we proved the imaging capabilities of this demonstrator with extended sources, considering the acquisition of two simultaneous sources of 1 mm diameter placed at known distances. However, some important limitations were also detected with the BrainPET prototype. In the first place, it was confirmed that there was a lack of flexibility working with an Application Specific Integrated Circuit (ASIC) whose electronic design was not own but commercial, along with the high cost required to modify an ASIC design with such features. Furthermore, the final characterization of the BrainPET ASIC showed a timing resolution with room for improvement (~ 13 ns FWHM). Taking into consideration the limitations obtained with the BrainPET prototype, along with the technological evolution in magnetically compatible devices, the knowledge acquired with the monolithic blocks were transferred to the new technology available, the SiPMs. Moreover, we opted for a new strategy in the front-end electronics, the FlexToT ASIC, an own design ASIC based on a Time over Threshold (ToT) scheme. One of the most interesting features underlying a ToT architecture is the encoding of the analog input signal amplitude information into the duration of the output signals, delivering directly digital pulses. The electronic architecture helps substitute the Analog to Digital Converters (ADCs) for Time to Digital Converters (TDCs), and they are easily implemented in Field Programmable Gate Arrays (FPGA), reducing the consumption and the complexity of the design. A new prototype demonstrator based on SiPMs was implemented to validate the FlexToT ASIC for monolithic or segmented blocks. The design and characterization of the necessary front-end electronic to read-out the signals from the ASIC was carried out by evaluating its linearity and dynamic range, its performance with an external noise signal, as well as the differential nonlinearity obtained with the TDCs implemented in the FPGA. Furthermore, the electronic presented in this work is capable of working at high count rates and discriminates different phoswich scintillators. The FlexToT ASIC provides an excellent coincidence time resolution for events that correspond to 511 keV photopeak (128 ps FWHM), resolving the limitations of the poor timing resolution of the BrainPET prototype. Furthermore, the energy resolution with monolithic blocks read by FlexToT ASICs provides an energy resolution of 15.4 % FWHM at 511 keV. Finally, good results were obtained in the quality of the PET image and the resolving power of the FlexToT demonstrator, providing spatial resolutions in the centre of the FoV at about 1.4 mm FWHM.

Implementing fully homomorphic encryption schemes in FPGA-based systems

LLas nuevas tecnologías orientadas a la nube, el internet de las cosas o las tendencias "as a service" se basan en el almacenamiento y procesamiento de datos en servidores remotos. Para garantizar la seguridad en la comunicación de dichos datos al servidor remoto, y en el manejo de los mismos en dicho servidor, se hace uso de diferentes esquemas criptográficos. Tradicionalmente, dichos sistemas criptográficos se centran en encriptar los datos mientras no sea necesario procesarlos (es decir, durante la comunicación y almacenamiento de los mismos). Sin embargo, una vez es necesario procesar dichos datos encriptados (en el servidor remoto), es necesario desencriptarlos, momento en el cual un intruso en dicho servidor podría a acceder a datos sensibles de usuarios del mismo. Es más, este enfoque tradicional necesita que el servidor sea capaz de desencriptar dichos datos, teniendo que confiar en la integridad de dicho servidor de no comprometer los datos. Como posible solución a estos problemas, surgen los esquemas de encriptación homomórficos completos. Un esquema homomórfico completo no requiere desencriptar los datos para operar con ellos, sino que es capaz de realizar las operaciones sobre los datos encriptados, manteniendo un homomorfismo entre el mensaje cifrado y el mensaje plano. De esta manera, cualquier intruso en el sistema no podría robar más que textos cifrados, siendo imposible un robo de los datos sensibles sin un robo de las claves de cifrado. Sin embargo, los esquemas de encriptación homomórfica son, actualmente, drás-ticamente lentos comparados con otros esquemas de encriptación clásicos. Una op¬eración en el anillo del texto plano puede conllevar numerosas operaciones en el anillo del texto encriptado. Por esta razón, están surgiendo distintos planteamientos sobre como acelerar estos esquemas para un uso práctico. Una de las propuestas para acelerar los esquemas homomórficos consiste en el uso de High-Performance Computing (HPC) usando FPGAs (Field Programmable Gate Arrays). Una FPGA es un dispositivo semiconductor que contiene bloques de lógica cuya interconexión y funcionalidad puede ser reprogramada. Al compilar para FPGAs, se genera un circuito hardware específico para el algorithmo proporcionado, en lugar de hacer uso de instrucciones en una máquina universal, lo que supone una gran ventaja con respecto a CPUs. Las FPGAs tienen, por tanto, claras difrencias con respecto a CPUs: -Arquitectura en pipeline: permite la obtención de outputs sucesivos en tiempo constante -Posibilidad de tener multiples pipes para computación concurrente/paralela. Así, en este proyecto: -Se realizan diferentes implementaciones de esquemas homomórficos en sistemas basados en FPGAs. -Se analizan y estudian las ventajas y desventajas de los esquemas criptográficos en sistemas basados en FPGAs, comparando con proyectos relacionados. -Se comparan las implementaciones con trabajos relacionados New cloud-based technologies, the internet of things or "as a service" trends are based in data storage and processing in a remote server. In order to guarantee a secure communication and handling of data, cryptographic schemes are used. Tradi¬tionally, these cryptographic schemes focus on guaranteeing the security of data while storing and transferring it, not while operating with it. Therefore, once the server has to operate with that encrypted data, it first decrypts it, exposing unencrypted data to intruders in the server. Moreover, the whole traditional scheme is based on the assumption the server is reliable, giving it enough credentials to decipher data to process it. As a possible solution for this issues, fully homomorphic encryption(FHE) schemes is introduced. A fully homomorphic scheme does not require data decryption to operate, but rather operates over the cyphertext ring, keeping an homomorphism between the cyphertext ring and the plaintext ring. As a result, an outsider could only obtain encrypted data, making it impossible to retrieve the actual sensitive data without its associated cypher keys. However, using homomorphic encryption(HE) schemes impacts performance dras-tically, slowing it down. One operation in the plaintext space can lead to several operations in the cyphertext space. Because of this, different approaches address the problem of speeding up these schemes in order to become practical. One of these approaches consists in the use of High-Performance Computing (HPC) using FPGAs (Field Programmable Gate Array). An FPGA is an integrated circuit designed to be configured by a customer or a designer after manufacturing - hence "field-programmable". Compiling into FPGA means generating a circuit (hardware) specific for that algorithm, instead of having an universal machine and generating a set of machine instructions. FPGAs have, thus, clear differences compared to CPUs: - Pipeline architecture, which allows obtaining successive outputs in constant time. -Possibility of having multiple pipes for concurrent/parallel computation. Thereby, In this project: -We present different implementations of FHE schemes in FPGA-based systems. -We analyse and study advantages and drawbacks of the implemented FHE schemes, compared to related work.

Telemetría de vehículos FSAE con microcontrolador PIC32 y transceptor de radio CC1101

Quizás el campo de las telecomunicaciones sea uno de los campos en el que más se ha progresado en este último siglo y medio, con la ayuda de otros campos de la ciencia y la técnica tales como la computación, la física electrónica, y un gran número de disciplinas, que se han utilizado estos últimos 150 años en conjunción para mejorarse unas con la ayuda de otras. Por ejemplo, la química ayuda a comprender y mejorar campos como la medicina, que también a su vez se ve mejorada por los progresos en la electrónica creados por los físicos y químicos, que poseen herramientas más potentes para calcular y simular debido a los progresos computacionales. Otro de los campos que ha sufrido un gran avance en este último siglo es el de la automoción, aunque estancados en el motor de combustión, los vehículos han sufrido enormes cambios debido a la irrupción de los avances en la electrónica del automóvil con multitud de sistemas ya ampliamente integrados en los vehículos actuales. La Formula SAE® o Formula Student es una competición de diseño, organizada por la SAE International (Society of Automotive Engineers) para estudiantes de universidades de todo el mundo que promueve la ingeniería a través de una competición donde los miembros del equipo diseñan, construyen, desarrollan y compiten en un pequeño y potente monoplaza. En el ámbito educativo, evitando el sistema tradicional de clases magistrales, se introducen cambios en las metodologías de enseñanza y surge el proyecto de la Fórmula Student para lograr una mejora en las acciones formativas, que permitan ir incorporando nuevos objetivos y diseñar nuevas situaciones de aprendizaje que supongan una oportunidad para el desarrollo de competencias de los alumnos, mejorar su formación como ingenieros y contrastar sus progresos compitiendo con las mejores universidades del mundo. En este proyecto se pretende dotar a los alumnos de las escuelas de ingeniería de la UPM que desarrollan el vehículo de FSAE de una herramienta de telemetría con la que evaluar y probar comportamiento del vehículo de FSAE junto con sus subsistemas que ellos mismos diseñan, con el objetivo de evaluar el comportamiento, introducir mejoras, analizar resultados de una manera más rápida y cómoda, con el objetivo de poder progresar más rápidamente en su desarrollo, recibiendo y almacenando una realimentación directa e instantánea del funcionamiento mediante la lectura de los datos que circulan por el bus CAN del vehículo. También ofrece la posibilidad de inyectar datos a los sistemas conectados al bus CAN de manera remota. Se engloba en el conjunto de proyectos de la FSAE, más concretamente en los basados en la plataforma PIC32 y propone una solución conjunta con otros proyectos o también por sí sola. Para la ejecución del proyecto se fabricó una placa compuesta de dos placas de circuito impreso, la de la estación base que envía comandos, instrucciones y datos para inyectar en el bus CAN del vehículo mediante radiofrecuencia y la placa que incorpora el vehículo que envía las tramas que circulan por el bus CAN del vehículo con los identificadores deseados, ejecuta los comandos recibidos por radiofrecuencia y salva las tramas CAN en una memoria USB o SD Card. Las dos PCBs constituyen el hardware del proyecto. El software se compone de dos programas. Un programa para la PCB del vehículo que emite los datos a la estación base, codificado en lenguaje C con ayuda del entorno de desarrollo MPLAB de Microchip. El otro programa hecho con LabView para la PCB de la estación base que recibe los datos provenientes del vehículo y los interpreta. Se propone un hardware y una capa o funciones de software para los microcontroladores PIC32 (similar al de otros proyectos del FSAE) para la transmisión de las tramas del bus CAN del vehículo de manera inalámbrica a una estación base, capaz de insertar tramas en el bus CAN del vehículo enviadas desde la estación base. También almacena estas tramas CAN en un dispositivo USB o SD Card situado en el vehículo. Para la transmisión de los datos se hizo un estudio de las frecuencias de transmisión, la legislación aplicable y los tipos de transceptores. Se optó por utilizar la banda de radiofrecuencia de uso común ISM de 433MHz mediante el transceptor integrado CC110L de Texas Instruments altamente configurable y con interfaz SPI. Se adquirieron dos parejas de módulos compatibles, con amplificador de potencia o sin él. LabView controla la estación que recoge las tramas CAN vía RF y está dotada del mismo transceptor de radio junto con un puente de comunicaciones SPI-USB, al que se puede acceder de dos diferentes maneras, mediante librerías dll, o mediante NI-VISA con transferencias RAW-USB. La aplicación desarrollada posee una interfaz configurable por el usuario para la muestra de los futuros sensores o actuadores que se incorporen en el vehículo y es capaz de interpretar las tramas CAN, mostrarlas, gráfica, numéricamente y almacenar esta información, como si fuera el cuadro de instrumentos del vehículo. Existe una limitación de la velocidad global del sistema en forma de cuello de botella que se crea debido a las limitaciones del transceptor CC110L por lo que si no se desea filtrar los datos que se crean necesarios, sería necesario aumentar el número de canales de radio para altas ocupaciones del bus CAN. Debido a la pérdida de relaciones con el INSIA, no se pudo probar de manera real en el propio vehículo, pero se hicieron pruebas satisfactorias (hasta 1,6 km) con una configuración de tramas CAN estándar a una velocidad de transmisión de 1 Mbit/s y un tiempo de bit de 1 microsegundo. El periférico CAN del PIC32 se programará para cumplir con estas especificaciones de la ECU del vehículo, que se presupone que es la MS3 Sport de Bosch, de la que LabView interpretará las tramas CAN recibidas de manera inalámbrica. Para poder probar el sistema, ha sido necesario reutilizar el hardware y adaptar el software del primer prototipo creado, que emite tramas CAN preprogramadas con una latencia también programable y que simulará al bus CAN proporcionando los datos a transmitir por el sistema que incorpora el vehículo. Durante el desarrollo de este proyecto, en las etapas finales, el fabricante del puente de comunicaciones SPI-USB MCP2210 liberó una librería (dll) compatible y sin errores, por lo que se nos ofrecía una oportunidad interesante para la comparación de las velocidades de acceso al transceptor de radio, que se presuponía y se comprobó más eficiente que la solución ya hecha mediante NI-VISA. ABSTRACT. The Formula SAE competition is an international university applied to technological innovation in vehicles racing type formula, in which each team, made up of students, should design, construct and test a prototype each year within certain rules. The challenge of FSAE is that it is an educational project farther away than a master class. The goal of the present project is to make a tool for other students to use it in his projects related to FSAE to test and improve the vehicle, and, the improvements that can be provided by the electronics could be materialized in a victory and win the competition with this competitive advantage. A telemetry system was developed. It sends the data provided by the car’s CAN bus through a radio frequency transceiver and receive commands to execute on the system, it provides by a base station on the ground. Moreover, constant verification in real time of the status of the car or data parameters like the revolutions per minute, pressure from collectors, water temperature, and so on, can be accessed from the base station on the ground, so that, it could be possible to study the behaviour of the vehicle in early phases of the car development. A printed circuit board, composed of two boards, and two software programs in two different languages, have been developed, and built for the project implementation. The software utilized to design the PCB is Orcad10.5/Layout. The base station PCB on a PC receives data from the PCB connected to the vehicle’s CAN bus and sends commands like set CAN filters or masks, activate data logger or inject CAN frames. This PCB is connected to a PC via USB and contains a bridge USB-SPI to communicate with a similar transceiver on the vehicle PCB. LabView controls this part of the system. A special virtual Instrument (VI) had been created in order to add future new elements to the vehicle, is a dashboard, which reads the data passed from the main VI and represents them graphically to studying the behaviour of the car on track. In this special VI other alums can make modifications to accommodate the data provided from the vehicle CAN’s bus to new elements on the vehicle, show or save the CAN frames in the form or format they want. Two methods to access to SPI bus of CC110l RF transceiver over LabView have been developed with minimum changes between them. Access through NI-VISA (Virtual Instrument Software Architecture) which is a standard for configuring, programming, USB interfaces or other devices in National Instruments LabView. And access through DLL (dynamic link library) supplied by the manufacturer of the bridge USB-SPI, Microchip. Then the work is done in two forms, but the dll solution developed shows better behaviour, and increase the speed of the system because has less overload of the USB bus due to a better efficiency of the dll solution versus VISA solution. The PCB connected to the vehicle’s CAN bus receives commands from the base station PCB on a PC, and, acts in function of the command or execute actions like to inject packets into CAN bus or activate data logger. Also sends over RF the CAN frames present on the bus, which can be filtered, to avoid unnecessary radio emissions or overflowing the RF transceiver. This PCB consists of two basic pieces: A microcontroller with 32 bit architecture PIC32MX795F512L from Microchip and the radio transceiver integrated circuit CC110l from Texas Instruments. The PIC32MX795F512L has an integrated CAN and several peripherals like SPI controllers that are utilized to communicate with RF transceiver and SD Card. The USB controller on the PIC32 is utilized to store CAN data on a USB memory, and change notification peripheral is utilized like an external interrupt. Hardware for other peripherals is accessible. The software part of this PCB is coded in C with MPLAB from Microchip, and programming over PICkit 3 Programmer, also from Microchip. Some of his libraries have been modified to work properly with this project and other was created specifically for this project. In the phase for RF selection and design is made a study to clarify the general aspects of regulations for the this project in order to understand it and select the proper band, frequency, and radio transceiver for the activities developed in the project. From the different options available it selects a common use band ICM, with less regulation and free to emit with restrictions and disadvantages like high occupation. The transceiver utilized to transmit and receive the data CC110l is an integrated circuit which needs fewer components from Texas Instruments and it can be accessed through SPI bus. Basically is a state machine which changes his state whit commands received over an SPI bus or internal events. The transceiver has several programmable general purpose Inputs and outputs. These GPIOs are connected to PIC32 change notification input to generate an interrupt or connected to GPIO to MCP2210 USB-SPI bridge to inform to the base station for a packet received. A two pair of modules of CC110l radio module kit from different output power has been purchased which includes an antenna. This is to keep away from fabrication mistakes in RF hardware part or designs, although reference design and gerbers files are available on the webpage of the chip manufacturer. A neck bottle is present on the complete system, because the maximum data rate of CC110l transceiver is a half than CAN bus data rate, hence for high occupation of CAN bus is recommendable to filter the data or add more radio channels, because the buffers can’t sustain this load along the time. Unfortunately, during the development of the project, the relations with the INSIA, who develops the vehicle, was lost, for this reason, will be made impossible to test the final phases of the project like integration on the car, final test of integration, place of the antenna, enclosure of the electronics, connectors selection, etc. To test or evaluate the system, it was necessary to simulate the CAN bus with a hardware to feed the system with entry data. An early hardware prototype was adapted his software to send programed CAN frames at a fixed data rate and certain timing who simulate several levels of occupation of the CAN Bus. This CAN frames emulates the Bosch ECU MS3 Sport.

Scientific bases of human-machine communication by voice.

The scientific bases for human-machine communication by voice are in the fields of psychology, linguistics, acoustics, signal processing, computer science, and integrated circuit technology. The purpose of this paper is to highlight the basic scientific and technological issues in human-machine communication by voice and to point out areas of future research opportunity. The discussion is organized around the following major issues in implementing human-machine voice communication systems: (i) hardware/software implementation of the system, (ii) speech synthesis for voice output, (iii) speech recognition and understanding for voice input, and (iv) usability factors related to how humans interact with machines.

Three Generations of FPGA DAQ Development for the ATLAS Pixel Detector

Thesis (Master's)--University of Washington, 2016-06

Characterization of ultra wideband antennas for personal communication devices using finite difference time domain technique

The current mobile networks don't offer sufficient data rates to support multimedia intensive applications in development for multifunctional mobile devices. Ultra wideband (UWB) wireless technology is being considered as the solution to overcome data rate bottlenecks in the current mobile networks. UWB is able to achieve such high data transmission rates because it transmits data over a very large chunk of the frequency spectrum. As currently approved by the U.S. Federal Communication Commission it utilizes 7.5 GHz of spectrum between 3.1 GHz and 10.6 GHz. ^ Successful transmission and reception of information data using UWB wireless technology in mobile devices, requires an antenna that has linear phase, low dispersion and a voltage standing wave ratio (VSWR) ≤ 2 throughout the entire frequency band. Compatibility with an integrated circuit requires an unobtrusive and electrically small design. The previous techniques that have been used to optimize the performance of UWB wireless systems, involve proper design of source pulses for optimal UWB performance. The goal of this work is directed towards the designing of antennas for personal communication devices, with optimal UWB bandwidth performance. Several techniques are proposed for optimal UWB bandwidth performance of the UWB antenna designs in this Ph.D. dissertation. ^ This Ph.D. dissertation presents novel UWB antenna designs for personal communication devices that have been characterized and optimized using the finite difference time domain (FDTD) technique. The antenna designs reported in this research are physically compact, planar for low profile use, with sufficient impedance bandwidth (>20%), antenna input impedance of 50-Ω, and an omni-directional (±1.5 dB) radiation pattern in the operating bandwidth. ^

System-on-a-Chip (SoC) based hardware acceleration in Register Transfer Level (RTL) design

Today, modern System-on-a-Chip (SoC) systems have grown rapidly due to the increased processing power, while maintaining the size of the hardware circuit. The number of transistors on a chip continues to increase, but current SoC designs may not be able to exploit the potential performance, especially with energy consumption and chip area becoming two major concerns. Traditional SoC designs usually separate software and hardware. Thus, the process of improving the system performance is a complicated task for both software and hardware designers. The aim of this research is to develop hardware acceleration workflow for software applications. Thus, system performance can be improved with constraints of energy consumption and on-chip resource costs. The characteristics of software applications can be identified by using profiling tools. Hardware acceleration can have significant performance improvement for highly mathematical calculations or repeated functions. The performance of SoC systems can then be improved, if the hardware acceleration method is used to accelerate the element that incurs performance overheads. The concepts mentioned in this study can be easily applied to a variety of sophisticated software applications. The contributions of SoC-based hardware acceleration in the hardware-software co-design platform include the following: (1) Software profiling methods are applied to H.264 Coder-Decoder (CODEC) core. The hotspot function of aimed application is identified by using critical attributes such as cycles per loop, loop rounds, etc. (2) Hardware acceleration method based on Field-Programmable Gate Array (FPGA) is used to resolve system bottlenecks and improve system performance. The identified hotspot function is then converted to a hardware accelerator and mapped onto the hardware platform. Two types of hardware acceleration methods – central bus design and co-processor design, are implemented for comparison in the proposed architecture. (3) System specifications, such as performance, energy consumption, and resource costs, are measured and analyzed. The trade-off of these three factors is compared and balanced. Different hardware accelerators are implemented and evaluated based on system requirements. 4) The system verification platform is designed based on Integrated Circuit (IC) workflow. Hardware optimization techniques are used for higher performance and less resource costs. Experimental results show that the proposed hardware acceleration workflow for software applications is an efficient technique. The system can reach 2.8X performance improvements and save 31.84% energy consumption by applying the Bus-IP design. The Co-processor design can have 7.9X performance and save 75.85% energy consumption.

A heuristic algorithm to generate test program sequences for moving probe electronic test equipment

The electronics industry, is experiencing two trends one of which is the drive towards miniaturization of electronic products. The in-circuit testing predominantly used for continuity testing of printed circuit boards (PCB) can no longer meet the demands of smaller size circuits. This has lead to the development of moving probe testing equipment. Moving Probe Test opens up the opportunity to test PCBs where the test points are on a small pitch (distance between points). However, since the test uses probes that move sequentially to perform the test, the total test time is much greater than traditional in-circuit test. While significant effort has concentrated on the equipment design and development, little work has examined algorithms for efficient test sequencing. The test sequence has the greatest impact on total test time, which will determine the production cycle time of the product. Minimizing total test time is a NP-hard problem similar to the traveling salesman problem, except with two traveling salesmen that must coordinate their movements. The main goal of this thesis was to develop a heuristic algorithm to minimize the Flying Probe test time and evaluate the algorithm against a "Nearest Neighbor" algorithm. The algorithm was implemented with Visual Basic and MS Access database. The algorithm was evaluated with actual PCB test data taken from Industry. A statistical analysis with 95% C.C. was performed to test the hypothesis that the proposed algorithm finds a sequence which has a total test time less than the total test time found by the "Nearest Neighbor" approach. Findings demonstrated that the proposed heuristic algorithm reduces the total test time of the test and, therefore, production cycle time can be reduced through proper sequencing.

Especificações e concepções de front-end UHF integrado e multipadrão em tecnologia CMOS 130nm

The Brazilian Environmental Data Collecting System (SBCDA) collects and broadcasts meteorological and environmental data, to be handled by dozens of institutions and organizations. The system space segment, composed by the data collecting satellites, plays an important role for the system operation. To ensure the continuity and quality of these services, efforts are being made to the development of new satellite architectures. Aiming a reduction of size and power consumption, the design of an integrated circuit containing a receiver front-end is proposed, to be embedded in the next SBCDA satellite generations. The circuit will also operate under the requirements of the international data collecting standard ARGOS. This work focuses on the design of an UHF low noise amplifier and mixers in a CMOS standard technology. The specifi- cations are firstly described and the circuit topologies presented. Then the circuit conception is discussed and the design variables derived. Finally, the layout is designed and the final results are commented. The chip will be fabricated in a 130 nm technology from ST Microelectronics.

Modelo comportamental do capacitor ferroelétrico como unidade básica de neurônios artificiais e sua implementação em FPGA

This work proposes the use of the behavioral model of the hysteresis loop of the ferroelectrics capacitor as a new alternative to the usually costly techniques in the computation of nonlinear functions in artificial neurons implemented on reconfigurable hardware platform, in this case, a FPGA device. Initially the proposal has been validated by the implementation of the boolean logic through the digital models of two artificial neurons: the Perceptron and a variation of the model Integrate and Fire Spiking Neuron, both using the model also digital of the hysteresis loop of the ferroelectric capacitor as it’s basic nonlinear unit for the calculations of the neurons outputs. Finally, it has been used the analog model of the ferroelectric capacitor with the goal of verifying it’s effectiveness and possibly the reduction of the number of necessary logic elements in the case of implementing the artificial neurons on integrated circuit. The implementations has been carried out by Simulink models and the synthesizing has been done through the DSP Builder software from Altera Corporation.

Amplificador integrador com ganho programável por largura de pulso

This work deals with the research and development of a Pulse Width Programmable Gain Integrating Amplifier. Two Pulse Width Programmable Gain Amplifier architectures are proposed, one based on discrete components and another based on switched capacitors. From the operating requirements defined for the study, parameters are defined and simulations are carried out to validate the architecture. Subsequently, the circuit and the software are developed and tested. It is performed the evaluation of the circuits regarding the two proposed architectures, and from that, an architecture is selected to be improved, aiming the development of an integrated circuit in a future work.

Mecanismo de tolerância a falhas através de escalonamento para uma arquitetura reconfigurável de grão grosso

The continuous evolution of integrated circuit technology has allowed integrating thousands of transistors on a single chip. This is due to the miniaturization process, which reduces the diameter of wires and transistors. One drawback of this process is that the circuit becomes more fragile and susceptible to break, making the circuit more susceptible to permanent faults during the manufacturing process as well as during their lifetime. Coarse Grained Reconfigurable Architectures (CGRAs) have been used as an alternative to traditional architectures in an attempt to tolerate such faults due to its intrinsic hardware redundancy and high performance. This work proposes a fault tolerance mechanism in a CGRA in order to increase the architecture fault tolerance even considering a high fault rate. The proposed mechanism was added to the scheduler, which is the mechanism responsible for mapping instructions onto the architecture. The instruction mapping occurs at runtime, translating binary code without the need for recompilation. Furthermore, to allow faster implementation, instruction mapping is performed using a greedy module scheduling algorithm, which consists of a software pipeline technique for loop acceleration. The results show that, even with the proposed mechanism, the time for mapping instructions is still in order of microseconds. This result allows that instruction mapping process remains at runtime. In addition, a study was also carried out mapping scheduler rate. The results demonstrate that even at fault rates over 50% in functional units and interconnection components, the scheduler was able to map instructions onto the architecture in most of the tested applications.