No description available.

Demands on modern computing are becoming more intensive. Keeping up with these demands has increasing complexity. Moore's Law is in decline. Increasing the number of cores on a device has diminishing returns. Specialised architectures provide more efficient and higher performing processors. However, it is not always practical to include every architecture on every device. Running non-native tasks on architectures often results in a drop in performance. This research examines the benefits and limitations of Field Programmable Gate Arrays - Systems on Chip (FPGA-SoC) devices to provide flexible hardware accelerators for heterogeneous architectures. A number of topics are covered, including hardware acceleration of floating-point mathematical functions, dynamic reconfiguration and high-level synthesis. A number of case studies are presented. Dynamic reconfiguration is used to change the configuration of the FPGA at runtime, allowing the hardware accelerators to be changed depending on the current processor tasks. Changing accelerators at runtime has limitations, such as data perturbation. Context switching techniques are applied to the hardware to prevent loss of data and enable de-fragmentation of the FPGA. High level synthesis techniques are used in conjunction with the presented hardware accelerators to synthesise high-level languages into hardware descriptions with optimisations. Techniques for runtime synthesis of hardware accelerators are presented. These can be combined with dynamic reconfiguration to configure FPGAs with appropriate hardware accelerators from a high-level language at runtime. The research demonstrates that FPGA-SoC devices have the potential for providing reconfigurable accelerators for processors in heterogeneous architectures. Metrics show that the FPGA configurations can perform better than other commercial processors. It was demonstrated that it is possible to context switch hardware at runtime, meaning the most can be made of the FPGA-SoC at all times, even as situations change. However, there are many limitations that still need to be overcome, such as management of the implemented hardware, synthesis of new hardware at runtime, reconfiguration times, interfacing of hardware with software and the design of hardware accelerators.

The need to achieve extended service life by battery powered Wireless Sensor Networks (WSNs) requires new concepts and technqiues beyond the state-of-the-art low-power designs based on fixed hardware platforms or energy-efficient protocols. This thesis investigates reconfiguration techniques that enable sensor hardware to adapt its energy consumption to external dynamics, by means of Dynamic Voltage Scaling (DVS), Dynamic Modulation Scaling (DMS), and other related concepts. For sensor node-level reconfiguration, an integration of DVS and DMS techniques was proposed to minimize the total energy consumption. A dynamic time allocation algorithm was developed, demonstrating an average of 55% energy reduction. For network-level reconfiguration, a node activation technique was presented to reduce the cost of recharging energy-depleted sensor nodes. Network operation combined with node activation was modeled as a stochastic decision process, where the activation decisions directly affected the energy efficiency of the network. An experimental test bed based on the Imote2 sensor node platform was realized, which demonstrated energy reduction of up to 50%. Such energy saving can be effectively translated into prolonged service life of the sensor network.

This work discusses <i>autonomous computing systems</i>, as implemented in hardware, and the properties required for such systems to function. Particular attention is placed on shifting the associated complexity into the systems themselves, and making them responsible for their own resources and operation. The resulting systems present simpler interfaces to their environments, and are able to respond to changes within themselves or their environments with little or no outside intervention. This work proposes a roadmap for the development of autonomous computing systems, and shows that their individual components can be implemented with present day technology. This work further implements a proof-of-concept demonstration system that advances the state-of-the-art. The system detects activity on connected inputs, and responds to the conditions without external assistance. It works from mapped netlists, that it dynamically parses, places, routes, configures, connects, and implements within itself, at the finest granularity available, while continuing to run. The system also models itself and its resource usage, and keeps that model synchronized with the changes that it undergoes—a critical requirement for autonomous systems. Furthermore, because the system assumes responsibility for its resources, it is able to dynamically avoid resources that have been masked out, in a manner suitable for defect tolerance. / Ph. D.

The purpose of this research is to investigate fault management methodologies within Integrated Modular Avionics (IMA) systems, and develop techniques by which the use of dynamic reconfiguration can be implemented to restore higher levels of systems redundancy in the event of a systems fault. A proposed concept of dynamic configuration has been implemented on a test facility that allows controlled injection of common faults to a representative IMA system. This facility allows not only the observation of the response of the system management activities to manage the fault, but also analysis of real time data across the network to ensure distributed control activities are maintained. IMS technologies have evolved as a feasible direction for the next generation of avionic systems. Although federated systems are logical to design, certify and implement, they have some inherent limitations that are not cost beneficial to the customer over long life-cycles of complex systems, and hence the fundamental modular design, i.e. common processors running modular software functions, provides a flexibility in terms of configuration, implementation and upgradability that cannot be matched by well-established federated avionic system architectures. For example, rapid advances of computing technology means that dedicated hardware can become outmoded by component obsolescence which almost inevitably makes replacements unavailable during normal life-cycles of most avionic systems. To replace the obsolete part with a newer design involves a costly re-design and re-certification of any relevant or interacting functions with this unit. As such, aircraft are often known to go through expensive mid-life updates to upgrade all avionics systems. In contrast, a higher frequency of small capability upgrades would maximise the product performance, including cost of development and procurement, in constantly changing platform deployment environments. IMA is by no means a new concept and work has been carried out globally in order to mature the capability. There are even examples where this technology has been implemented as subsystems on service aircraft. However, IMA flexible configuration properties are yet to be exploited to their full extent; it is feasible that identification of faults or failures within the system would lead to the exploitation of these properties in order to dynamically reconfigure and maintain high levels of redundancy in the event of component failure. It is also conceivable to install redundant components such that an IMS can go through a process of graceful degradation, whereby the system accommodates a number of active failures, but can still maintain appropriate levels of reliability and service. This property extends the average maintenance-free operating period, ensuring that the platform has considerably less unscheduled down time and therefore increased availability. The content of this research work involved a number of key activities in order to investigate the feasibility of the issues outlined above. The first was the creation of a representative IMA system and the development of a systems management capability that performs the required configuration controls. The second aspect was the development of hardware test rig in order to facilitate a tangible demonstration of the IMA capability. A representative IMA was created using LabVIEW Embedded Tool Suit (ETS) real time operating system for minimal PC systems. Although this required further code written to perform IMS middleware functions and does not match up to the stringent air safety requirements, it provided a suitable test bed to demonstrate systems management capabilities. The overall IMA was demonstrated with a 100kg scale Maglev vehicle as a test subject. This platform provides a challenging real-time control problem, analogous to an aircraft flight control system, requiring the calculation of parallel control loops at a high sampling rate in order to maintain magnetic suspension. Although the dynamic properties of the test rig are not as complex as a modern aircraft, it has much less stringent operating requirements and therefore substantially less risk associated with failure to provide service. The main research contributions for the PhD are: 1. A solution for the dynamic reconfiguration problem for assigning required systems functions (namely a distributed, real-time control function with redundant processing channels) to available computing resources whilst protecting the functional concurrency and time critical needs of the control actions. 2. A systems management strategy that utilises the dynamic reconfiguration properties of an IMA System to restore high levels of redundancy in the presence of failures. The conclusion summarises the level of success of the implemented system in terms of an appropriate dynamic reconfiguration to the response of a fault signal. In addition, it highlights the issues with using an IMA to as a solution to operational goals of the target hardware, in terms of design and build complexity, overhead and resources.

This study describes the platform Atmel FPSLIC, which is created by means of the logic arrays FPGA and the micro-sequencer controller AVR. The developmental kit STK594 is described here as well, with its programming possibilities, as for the logic arrays FPGA, as for the micro-sequencers AVR. Also the separate circuit AT94K is described there. This circuit can be programmed by the language VHDL (the field FPGA), or by means of the assembler and language C for the micro-sequencer. All this can be integrated into the one output file by means of program System Designer, comprising a set of software tools for given programming languages and for generation of the whole circuit. Furthermore, the study describes a simple application for the both platform parts. Also the description of the dynamic reconfiguration of the circuit gate part is included.

Emerging reconfiguration techniques that include partial dynamic reconfiguration and partial bitstream relocation have been addressed in the past in order to expose the flexibility of field programmable gate array at runtime. Partial bitstream relocation is a technique used to target a partial bitstream of a partial reconfigurable region (PRR) onto other identical reconfigurable regions inside an FPGA, while partial dynamic reconfiguration is used to target a single reconfigurable region. Prior works in this domain aim to minimize "relocation time" with the help of on-chip or on-line processing. In this thesis, a novel PRR-PRR relocation algorithm is proposed and implemented both in software and hardware. Dedicated hardware architecture, called the accelerated relocation circuit (ARC), is designed and presented for fast relocation. An analytical model is also proposed to evaluate the performance of the PRR-PRR relocation algorithm and highlight the speed-up obtained by the proposed hardware implementation. ARC has been tested on two categories of designs: dynamically scalable systolic array designs and fault tolerant designs. It has been compared against the software implementation of the algorithm, BiRF, hardware architecture for bitstream relocation, and a software solution for bitstream relocation. An average speed-up of 153x for ARC over BiRF is observed, with the additional advantage of not storing any bitstreams, thus saving invaluable block random access memory (BRAMs). Accuracy of proposed analytical model was found to be more than 95% for all the test cases.

No description available.

<p> Architecture Description Languages were developed to support the abstract level of software structuring that is the subject matter of software architecture. CommUnity is an ADL built on co-ordination principles and a categorical framework to support the composition of specifications of components to form the system's specification. However, an important problem of CommUnity is the lack of support for specifying the system's architectural changes in both the set of components and the connections between them.</p> <p> This thesis presents DynaComm, an extension of CommUnity to support hierarchical design and dynamic reconfiguration of component based systems. Several new language constructs are introduced into DynaComm: subsystems are coarse grained components which are considered as the basic unit for the construction of systems, connectors encapsulate a component interaction pattern that can organize the possibly complicated interactions between the components of a subsystem. We also propose the idea of interface manager to solve the problem of incorrectly synchronized actions in CommUnity, and the concept of population manager to manage the live instances of components in a subsystem, through which we can model potentially complicated dynamic reconfigurations in a system.</p> <p> To use the semantics of CommUnity in defining the semantics of DynaComm, a "normalization" technique is introduced to transform the parameterized (indexed) actions into "normal" actions of CommUnity and reduce the specification of connectors and subsystems to flat CommUnity designs, so that we can derive the system's semantics in a certain state.</p> <p> Two illustrative examples, fault-tolerant dynamic client-server and vending machine systems, are also given to show the usage of DynaComm in modeling complicated and dynamic systems.</p> / Thesis / Master of Science (MSc)

The focus of this thesis is on specialising the configuration of a field-programmable gate array (FPGA) to allow dynamic reconfiguration of real-time applications. The dynamic reconfiguration of an application has numerous advantages, but due to the overhead introduced by this process, it is only advantageous if the execution time exceeds reconfiguration time. This implies that dynamic reconfiguration is more suited to quasi-static applications, and real-time applications are therefore typically not reconfigured. A method proposed in the literature to ameliorate the overhead from the configuration process is to use a block-RAM (BRAM) based, hardware-controlled reconfiguration architecture, eliminating the need for a processor bus by storing the configuration in localised memory. The drawback of this architecture is the limited size of the BRAM, implying only a subset of configurations can be stored. The work presented in this thesis aim to address this size limitation by proposing a specialiser capable of adapting the configuration stored in the BRAM to represent different sets of hardware. This is done by directly manipulating the bits in the configuration using passive hardware. This not only allows the configuration to be specialised practically immediately, but also allows this specialiser to be device independent. By incorporating this specialiser into the BRAM-based architecture, this study sets out to establish that it is possible to reduce the overhead of the reconfiguration process to such an extent that dynamic reconfiguration can be used for real-time applications. Since the composition of the configuration is not publicly available, a method had to be found to parse and analyse the configuration in order to map the configuration space of the device. The approach used was to compare numerous different configurations and mapping the differences. By analysing these differences, it was found that there is a logical relationship between the slice coordinates and the configuration space of the device. The encoding of the lookup tables was also determined from their initialisation parameters. This allows the configuration of any lookup table to be changed by simply changing the corresponding bits in the configuration. Using this proposed reconfiguration architecture, a distributed multiply-accumulate was reconi figured and its functional density measured. The reason for selecting this specific application is because the multiply-accumulate instruction can be found at the heart of many real-time applications. If the functional density of the reconfigured application is comparable to those of its static equivalent, a strong case can be made for real-time reconfiguration in general. Functional density is an indication of the composite benefits dynamic reconfiguration obtains above its static generic counterpart. Due to the overhead of the reconfiguration process, the functional density of reconfigured applications is traditionally significantly lower than those of static applications. If the functional density of the reconfigured application can rival those of the static equivalent, the overhead from the reconfiguration process becomes negligible. Using this metric, the functional density of the distributed multiply-accumulate was compared for different reconfiguration implementations. It was found that the reconfiguration architecture proposed in this thesis yields a significant improvement over other reconfiguration methods. In fact, the functional density of this method rivalled that of its static equivalent, implying that it is possible to dynamically reconfigure a real-time application. It was also found that the proposed architecture reduces specialisation and reconfiguration time to such an extent that it is possible complete the reconfiguration process within strict time constraints. Even though the proposed method is only capable of reconfiguring the LUTs of a real-time application, this is the first step towards allowing full reconfiguration of applications with dynamic characteristics. The first contribution this thesis makes is a novel method to parse and analyse the configuration of a XilinxR VirtexR -5 FPGA. It also successfully maps the configuration space to the configuration data. Even though this method is applied to a specific device, it is device independent and can easily be applied to any other FPGA. The second contribution comes from using the information obtained from this analysis to design and implement a configuration specialiser, capable of adapting lookup tables in real time. Lastly, the third contribution combines this specialiser with the BRAM-based architecture to allow the reconfiguration of applications typically not reconfigured. / PhD (Computer and Electronic Engineering), North-West University, Potchefstroom Campus, 2015