This thesis introduces an alternative Fault-Tolerant Power-Aware Hybrid Adder (or simply FARHAD) for high-performance processors. FARHAD, similar to earlier studies, relies on performing add operations twice to detect errors. Unlike previous studies, FARHAD uses an aggressive adder to produce the initial outcome and a low-power adder to generate the second outcome, referred to as the checker. FARHAD uses checkpoints, a feature already available to high-performance processors, to recover from errors. FARHAD achieves the high energy-efficiency of time-redundant solutions and the high performance of resource-redundant adders. We evaluate FARHAD from power and performance points of view using a subset of SPEC’2K benchmarks. Our evaluations show that FARHAD outperforms an alternative time-redundant solution by 20%. FARHAD reduces the power dissipation of an alternative resource-redundant adder by 40% while maintaining performance. / Graduate / 0544

Continuous scaling of the transistor size and reduction of the operating voltage have led to a significant performance improvement of integrated circuits. However, the vulnerability of the scaled circuits to transient data upsets or soft errors, which are caused by alpha particles and cosmic neutrons, has emerged as a major reliability concern. In this thesis, we have investigated the effects of soft errors in combinational circuits and proposed soft error detection techniques for high speed adders. In particular, we have proposed an area-efficient 64-bit soft error robust logarithmic adder (SRA). The adder employs the carry merge Sklansky adder architecture in which carries are generated every 4 bits. Since the particle-induced transient, which is often referred to as a single event transient (SET) typically lasts for 100~200 ps, the adder uses time redundancy by sampling the sum outputs twice. The sampling instances have been set at 110 ps apart. In contrast to the traditional time redundancy, which requires two clock cycles to generate a given output, the SRA generates an output in a single clock cycle. The sampled sum outputs are compared using a 64-bit XOR tree to detect any possible error. An energy efficient 4-input transmission gate based XOR logic is implemented to reduce the delay and the power in this case. The pseudo-static logic (PSL), which has the ability to recover from a particle induced transient, is used in the adder implementation. In comparison with the space redundant approach which requires hardware duplication for error detection, the SRA is 50% more area efficient. The proposed SRA is simulated for different operands with errors inserted at different nodes at the inputs, the carry merge tree, and the sum generation circuit. The simulation vectors are carefully chosen such that the SET is not masked by error masking mechanisms, which are inherently present in combinational circuits. Simulation results show that the proposed SRA is capable of detecting 77% of the errors. The undetected errors primarily result when the SET causes an even number of errors and when errors occur outside the sampling window.

Continuous scaling of the transistor size and reduction of the operating voltage have led to a significant performance improvement of integrated circuits. However, the vulnerability of the scaled circuits to transient data upsets or soft errors, which are caused by alpha particles and cosmic neutrons, has emerged as a major reliability concern. In this thesis, we have investigated the effects of soft errors in combinational circuits and proposed soft error detection techniques for high speed adders. In particular, we have proposed an area-efficient 64-bit soft error robust logarithmic adder (SRA). The adder employs the carry merge Sklansky adder architecture in which carries are generated every 4 bits. Since the particle-induced transient, which is often referred to as a single event transient (SET) typically lasts for 100~200 ps, the adder uses time redundancy by sampling the sum outputs twice. The sampling instances have been set at 110 ps apart. In contrast to the traditional time redundancy, which requires two clock cycles to generate a given output, the SRA generates an output in a single clock cycle. The sampled sum outputs are compared using a 64-bit XOR tree to detect any possible error. An energy efficient 4-input transmission gate based XOR logic is implemented to reduce the delay and the power in this case. The pseudo-static logic (PSL), which has the ability to recover from a particle induced transient, is used in the adder implementation. In comparison with the space redundant approach which requires hardware duplication for error detection, the SRA is 50% more area efficient. The proposed SRA is simulated for different operands with errors inserted at different nodes at the inputs, the carry merge tree, and the sum generation circuit. The simulation vectors are carefully chosen such that the SET is not masked by error masking mechanisms, which are inherently present in combinational circuits. Simulation results show that the proposed SRA is capable of detecting 77% of the errors. The undetected errors primarily result when the SET causes an even number of errors and when errors occur outside the sampling window.

Objektdetektering har fått stort forskningsintresse de senaste åren, eftersom det är maskiners ögon och är en grundläggande uppgift inom datorseende som syftar till att identifiera och lokalisera föremål av intresse. Hårdvaruacceleratorer syftar vanligtvis till att öka genomströmningen för realtidskrav samtidigt som energiförbrukningen sänks. Studier av feltolerans säkerställer att algoritmen utförs korrekt även med felpresentation. Denna avhandling täcker dessa ämnen och tillhandahåller en Field-Programmable Gate Array (FPGA)-implementering av en objektdetekteringsalgoritm, You Only Look Once (YOLO), samtidigt som man undersöker implementeringens feltolerans. En baslinjeimplementering på FPGA tillhandahålls först och sedan tillämpas, implementeras och testas två feltoleranta implementeringar, en med trippelmodulär redundans och en med tidsredundans. Fastnade fel injiceras i implementeringarna för att studera feltoleransen. Vår FPGA-implementering av YOLO ger en höghastighets, låg strömförbrukning och mycket konfigurerbar hårdvaruaccelerator för objektdetektering. I detta examensarbete görs implementeringsdesignen med en kombination av egendesignade moduler med VHDL och Xilinx-försedd Intellectual Property (IP). Jämfört med andra forsknings- eller öppen källkodsversioner som använder High-Level Synthesis (HLS), är denna design mer konfigurerbar för framtida referenser och tar bort onödiga hårdvarusvarta lådor. Jämfört med andra studier om hårdvaruacceleratorer fokuserar denna avhandling på feltolerans. Detta examensarbete skapar utrymme för mer arbete med att utforska feltolerans, t.ex. skapa en mer feltolerant implementering eller undersöka hur vissa fel kan påverka resultatet. Det är också möjligt att använda implementeringen från denna avhandling som baslinje för andra forskningsändamål, eftersom implementeringen är fristående och mycket konfigurerbar. / Object detection gets great research interest in recent years, as it is the eyes of machines and is a fundamental task in computer vision that aims at identifying and locating objects of interest. Hardware accelerators usually aim at boosting the throughput for real-time requirements while lowering power consumption. Studies on fault tolerance ensure the algorithm to be performed correctly even with error presenting. This thesis covers these topics and provides a Field-Programmable Gate Array (FPGA) implementation of an object detection algorithm, You Only Look Once (YOLO), while investigating the fault tolerance of the implementation. A baseline implementation on FPGA is first provided and then two fault-tolerant implementations, one with triple-modular redundancy and one with time redundancy are applied, implemented, and tested. Stuck-at faults are injected into the implementations to study the fault tolerance. Our FPGA implementation of YOLO provides a high-speed, low-power-consumption, and highly-configurable hardware accelerator for object detection. In this thesis, the implementation design is done with a combination of self-designed modules with VHDL and Xilinx-provided Intellectual Property (IP). Compared to other research or open-source versions using High-Level Synthesis (HLS), this design is more configurable for future references and removes unnecessary hardware black boxes. Compared to other studies on hardware accelerators, this thesis focuses on fault tolerance. This thesis creates space for more work on exploring fault tolerance, e.g., creating a more fault-tolerant implementation or investigating how certain faults could affect the result. It is also possible to use the implementation from this thesis as a baseline for other research purposes, as the implementation is stand-alone and highly configurable.

Safe airspace of airports worldwide is crucial to ensure that passengers, workers, and airplanes are safe from external threats, whether malicious or not. In recent years, several airports worldwide experienced intrusions into their airspace by unmanned aerial vehicles. Based on this observation, there is a need for a reliable detection system capable of detecting unmanned aerial vehicles with high accuracy and integrity. This thesis proposes time redundant triplex parallel diverse convolutional neural network architectures trained to detect unmanned aerial vehicles to address the aforementioned issue. The thesis aims at producing a system capable of real-time performance coupled with previously mentioned networks. The hypothesis in this method will result in lower mispredictions of objects other than drones and high accuracy compared to singular convolutional neural networks. Several improvements to accuracy, lower mispredictions, and faster detection times were observed during the performed experiments with the proposed system. Furthermore, a new way of interpreting the intersection over union results for all neural networks is introduced to ensure the correctness and reliability of results. Lastly, the system produced by this thesis is analyzed from a dependability viewpoint to provide an overview of how this contributes to dependability research.