RAID-6 is a data encoding scheme used to provide single drive error detection and dual drive error correction for data redundancy on an array of disks. Here we present a thorough study of efficient implementations of RAID-6 on field programmable gate arrays (FPGAs). Since RAID-6 relies heavily on Galois Field Algebra (GFA), an efficient implementation of a GFA FPGA library is also presented. Through rigorous performance analysis, this work shows the most efficient ways to tradeoff FPGA resources and execution time when implementing GFA functions as well as RAID-6 encoding and decoding.

O paradigma Network Function Virtualization (NFV) promete tornar as redes de computadores mais escaláveis e flexíveis, através do desacoplamento das funções de rede de hardware dedicado e fornecedor específico. No entanto, funções de rede computacionalmente intensivas podem ser difíceis de virtualizar sem degradação de desempenho. Neste contexto, Field-Programmable Gate Arrays (FPGAs) têm se mostrado uma boa opção para aceleração por hardware de funções de rede virtuais que requerem alta vazão, sem se desviar do conceito de uma infraestrutura NFV que visa alta flexibilidade. A avaliação de expressões regulares é um mecanismo importante e computacionalmente intensivo, usado para realizar Deep Packet Inpection, que pode ser acelerado por FPGA para atender aos requisitos de desempenho. Esta solução, no entanto, apresenta novos desafios em relação aos requisitos de confiabilidade. Particularmente para FPGAs baseados em SRAM, soft errors na memória de configuração são uma ameaça de confiabilidade significativa. Neste trabalho, apresentamos um mecanismo de tolerância a falhas abrangente para lidar com falhas de configuração na funcionalidade de módulos de avaliação de expressões regulares baseados em FPGA. Além disso, é introduzido um mecanismo de correção de erros que considera o posicionamento desses módulos no FPGA para reduzir o tempo de reparo do sistema, melhorando a confiabilidade e a disponibilidade. Os resultados experimentais mostram que a taxa de falha geral e o tempo de reparo do sistema podem ser reduzidos em 95% e 90%, respectivamente, com custos de área e performance admissíveis. / The Network Function Virtualization (NFV) paradigm promises to make computer networks more scalable and flexible by decoupling the network functions (NFs) from dedicated and vendor-specific hardware. However, network and compute intensive NFs may be difficult to virtualize without performance degradation. In this context, Field-Programmable Gate Arrays (FPGAs) have been shown to be a good option for hardware acceleration of virtual NFs that require high throughput, without deviating from the concept of an NFV infrastructure which aims at high flexibility. Regular expression matching is an important and compute intensive mechanism used to perform Deep Packet Inspection, which can be FPGA-accelerated to meet performance constraints. This solution, however, introduces new challenges regarding dependability requirements. Particularly for SRAM-based FPGAs, soft errors on the configuration memory are a significant dependability threat. In this work we present a comprehensive fault tolerance mechanism to deal with configuration faults on the functionality of FPGA-based regular expression matching engines. Moreover, a placement-aware scrubbing mechanism is introduced to reduce the system repair time, improving the system reliability and availability. Experimental results show that the overall failure rate and the system mean time to repair can be reduced in 95% and 90%, respectively, with manageable area and performance costs.

Nowadays the ever increasing algorithmic complexity of embedded applications requires the designers to turn towards heterogeneous and highly integrated systems denoted as SoC (System-on-a-Chip). These architectures may embed CPU-based processors, dedicated datapaths as well as recon gurable units. However, embedded SoCs are submitted to stringent requirements in terms of speed, size, cost, power consumption, throughput, etc. Therefore, new computing paradigms are required to ful l the constraints of the applications and the requirements of the architecture. Recon gurable Computing is a promising paradigm that provides probably the best trade-o between these requirements and constraints. Dynamically recon gurable architectures are their key enabling technology. They enable the hardware to adapt to the application at runtime. However, these architectures raise new challenges in SoC design. For example, on one hand, designing a system that takes advantage of dynamic recon guration is still very time consuming because of the lack of design methodologies and tools. On the other hand, scheduling hardware tasks di ers from classical software tasks scheduling on microprocessor or multiprocessors systems, as it bears a further complicated placement problem. This thesis deals with the problem of scheduling online real-time hardware tasks on Dynamically Recon gurable Hardware Devices (DRHWs). The problem is addressed from two angles : (i) Investigating novel algorithms for online real-time scheduling/placement on DRHWs. (ii) Scheduling/Placement algorithms library for RTOS-driven Design Space Exploration (DSE). Regarding the first point, the thesis proposes two main runtime-aware scheduling and placement techniques and assesses their suitability for online real-time scenarios. The first technique discusses the impact of synthesizing, at design time, several shapes and/or sizes per hardware task (denoted as multi-shape task), in order to ease the online scheduling process. The second technique combines a looking-ahead scheduling approach with a slots-based recon gurable areas management that relies on a 1D placement. The results show that in both techniques, the scheduling and placement quality is improved without signi cantly increasing the algorithm time complexity. Regarding the second point, in the process of designing SoCs embedding recon gurable parts, new design paradigms tend to explore and validate as early as possible, at system level, the architectural design space. Therefore, the RTOS (Real-Time Operating System) services that manage the recon gurable parts of the SoC can be re fined. In such a context, gathering numerous hardware tasks scheduling and placement algorithms of various complexity vs performance trade-o s in a kind of library is required. In this thesis, proposed algorithms in addition to some existing ones are purposely implemented in C++ language, in order to insure the compatibility with any C++/SystemC based SoC design methodology.

A new heuristic method to improve the I/O pad assignment for the sea-of-gates placement algorithm "PROUD" is proposed. In PROUD, the preplaced I/O pads are used as the boundary conditions in solving sparse linear equations to obtain the optimal module placement. Due to the total wire length determined by the module positions is the strong function of the preplaced I/O pad positions, the optimization of the I/O pad circular order and their assignment to the physical locations on the chip are attempted in the thesis. The proposed I/O pad assignment program is used as a predecessor of PROUD. The results have revealed excellent improvement.

Outer space is a very harsh environment that can cause electronics to not operate as they were originally intended. Aside from the extreme amount of radiation found in space, temperatures can also change very dramatically in a relatively small time frame. In order to test electronics that will be used in this environment, they first need to be tested on Earth under replicated conditions. Vanderbilt University designed a dewar that allows devices to be tested at these extreme temperatures while being radiated. For this thesis, a test setup that met all of the dewar's constraints was designed that would allow a 12-bit, 16-channel analog-to-digital converter to be tested while inside.

Academic Clustering and Placement Tools for Modern Field-Programmable Gate Array Architectures Daniele Giuseppe Paladino Masters of Applied Science Graduate Department of Electrical and Computer Engineering University of Toronto 2008 Abstract Academic tools have been used in many research studies to investigate Field-Programmable Gate Array (FPGA) architecture, but these tools are not sufficiently flexible to represent modern commercial devices. This thesis describes two new tools, the Dynamic Clusterer (DC) and the Dynamic Placer (DP) that perform the clustering and placement steps in the FPGA CAD flow. These tools are developed in direct extension of the popular Versatile Place and Route (VPR) academic tools. We describe the changes that are necessary to the traditional tools in order to model modern devices, and provide experimental results that show the quality of the algorithms achieved is similar to a commercial CAD tool, Quartus II. Finally, a small number of research experiments were investigated using the clustering and placement tools created to demonstrate the practical use of these tools for academic research studies of FPGA CAD tools.

Academic Clustering and Placement Tools for Modern Field-Programmable Gate Array Architectures Daniele Giuseppe Paladino Masters of Applied Science Graduate Department of Electrical and Computer Engineering University of Toronto 2008 Abstract Academic tools have been used in many research studies to investigate Field-Programmable Gate Array (FPGA) architecture, but these tools are not sufficiently flexible to represent modern commercial devices. This thesis describes two new tools, the Dynamic Clusterer (DC) and the Dynamic Placer (DP) that perform the clustering and placement steps in the FPGA CAD flow. These tools are developed in direct extension of the popular Versatile Place and Route (VPR) academic tools. We describe the changes that are necessary to the traditional tools in order to model modern devices, and provide experimental results that show the quality of the algorithms achieved is similar to a commercial CAD tool, Quartus II. Finally, a small number of research experiments were investigated using the clustering and placement tools created to demonstrate the practical use of these tools for academic research studies of FPGA CAD tools.

Outer space is a very harsh environment that can cause electronics to not operate as they were originally intended. Aside from the extreme amount of radiation found in space, temperatures can also change very dramatically in a relatively small time frame. In order to test electronics that will be used in this environment, they first need to be tested on Earth under replicated conditions. Vanderbilt University designed a dewar that allows devices to be tested at these extreme temperatures while being radiated. For this thesis, a test setup that met all of the dewar's constraints was designed that would allow a 12-bit, 16-channel analog-to-digital converter to be tested while inside.

Thesis (Ph. D.)--University of Texas at Austin, 2003. / Vita. Includes bibliographical references. Available also from UMI Company.

Σε μία εποχή όπου η ψηφιοποίηση δεδομένων έχει αυξηθεί ραγδαία η ανάγκη για τη βέλτιστη μετάδοσή τους είναι απαραίτητη. Από τα πλέον σημαντικά μέρη των προτύπων μετάδοσης είναι η κωδικοποίηση του καναλιού μέσω ειδικών αλγορίθμων ώστε να επιτευχθεί η εύρεση και διόρθωση τυχών λαθών. Οι κώδικες Bose, Chaudhuri και Hocquenghem (BCH) είναι τέτοιου είδους κώδικες που χρησιμοποιούνται ευρέως σε εφαρμογές όπως τα CD, DVD, σκληροί δίσκοι, δίσκοι στερεάς κατάστασης (SSD) και το πρότυπο δορυφορικής μετάδοσης τηλεόρασης υψηλής ανάλυσης (HDTV), DVB-S2. Στην παρούσα διπλωματική εργασία σχεδιάστηκε και υλοποιήθηκε κωδικοποιητής και αποκωδικοποιητής BCH για τις 11 περιπτώσεις κανονικού πλαισίου που προσφέρει το πρότυπο DVB-S2. Κύριος στόχος ήταν η όσο το δυνατόν καλύτερη υλοποίηση με γνώμονα το μέγεθος, με τη χρήση κοινών κυκλωμάτων και για τις 11 περιπτώσεις. Αποτέλεσμα αυτής της βελτιστοποίησης μεγέθους, ήταν κάποιες τεχνικές βελτιστοποίησης της ταχύτητας αποκωδικοποίησης, όπως το shortening, να μη χρησιμοποιηθούν καθώς θα είχαν ως αποτέλεσμα την αύξηση της επιφάνειας μερών του αποκωδικοποιητή κατά περίπου 11 φορές. Καθώς σκοπός της διπλωματικής ήταν η μελέτη της απόδοσης των κωδίκων BCH, μελετήθηκε ο ρυθμός λαθών σε διάφορες τιμές της αναλογίας ενέργειας – θορύβου (Eb / N0 ), αφού πρώτα υλοποιήθηκε σε FPGA. / The amount of digital information is growing rapidly the recent decades, making transmission optimization one of the top priorities in digital information systems. One of the main parts of every transmission standard is channel encoding, with the use of algorithms aimed at finding and correcting errors (Forward Error Correction – FEC). Such codes are Bose, Chaudhuri and Hocquenghem (BCH) code, which are widely used in applications like CDs, DVDs, Hard Drives, Solid State Drives (SSDs) and DVB-S2, a satellite transmission standard mostly used for High Definition Television (HDTV). This thesis sets out to account for the design and implementation of a BCH encoder and decoder for all 11 different code rates proposed by the DVB-S2 standard for normal frames. The design was area optimized in order for all 11 code rate encoders and decoders to work on the same FPGA. This lead to some optimization techniques being unused. Even though the codes are shortened, no shortening algorithms which aim at clock cycle optimization were used. Were they used, would lead parts of the decoder to be almost 11 times larger. The main goal of the thesis is to analyze the performance of the codes, so the error rate was measured under different values of the energy to noise ratio (Eb/ N0 ).