No description available.

No description available.

This study comprises two tasks. The first is to implement gate-level circuit camouflage techniques. The second is to implement the Oracle-guided incremental de-camouflage algorithm and apply it to the camouflaged designs. The circuit camouflage algorithms are implemented in Python, and the Oracle- guided incremental de-camouflage algorithm is implemented in C++. During this study, I evaluate the Oracle-guided de-camouflage tool (Solver, in short) performance by de-obfuscating the ISCAS-85 combinational benchmarks, which are camouflaged by the camouflage algorithms. The results show that Solver is able to efficiently de-obfuscate the ISCAS-85 benchmarks regardless of camouflaging style, and is able to do so 10.5x faster than the best existing approaches. And, based on Solver, this study also measures the de-obfuscation runtime for each camouflage style.

<p>The amount of recyclable material being processed worldwide is increasing. There is a demand for new technologies that can quickly sort these materials for maxi-mum purity while maintaining high throughput. This thesis proposes a method toautomatically sort two materials: Polycoat containers and Polyethylene terephtha-late (PET) bottles. This method utilizes a visible light camera and does not relyon Near-Infrared spectrometry. A high-speed method to automatically locate re-gions that likely contain these materials within the image and remove them from thebackground is presented. These regions are merged into whole containers and are classified as either a Polycoat container or PET bottle. This is accomplished using alinear support vector machine (SVM) trained on the histogram of pixel intensities. Anovel graph theoretic based region growing technique is proposed and experimental results are provided to characterize the system. The proposed method obtained a93% recognition rate while running in real-time on an FPGA.</p> / Master of Applied Science (MASc)

En esta tesis se presenta el análisis de paralelismo en sus diferentes niveles para una Sistema en Chip que consta de múltiples procesadores y una memoria de almacenamiento de datos de alta densidad. El objetivo es utilizar el paralelismo como una estrategia para reducir el consumo de energía de las arquitecturas de cómputo VLSI. En particular, se describe la aplicación de técnicas de paralelismo en una arquitectura de reconocimiento automático de voz y su integración en el sistema mencionado implementado en una tecnología CMOS de 55nm. Se describe la aplicación del paralelismo a nivel micro-arquitectura y a nivel de Sistema y se analiza el punto óptimo de paralelismo para obtener una arquitectura de cómputo eficiente desde el punto de vista de tiempo de procesamiento y consumo de energía. / In this thesis an analysis of data parallelism implemented in a System on Chip that integrates multiple processing cores and a high density memory is presented. The aim of this work is to optimally utilize dfferent levels of spatial parallelism as a strategy to reduce energy consumption of the whole architecture. The core chosen for this work is an automatic speech recognition architecture integrated in the mentioned System and implemented in a technology CMOS node of 55 nm. Parallelism is included at the microarchitecture level and also at the multiple core chip level. An analysis of the optimal point of the applied parallelism that provides an architecture that minimizes both the energy consumption and the processing time simultaneously is presented.

Many embedded applications implement block ciphers and sorting and searching algorithms which use multiple loop iterations for computation. These applications often demand low power operation. The power consumption of designs varies with the implementation choices made by designers. The sequential implementation of loop operations consumes minimal area, but latency and clock power are high. Alternatively, loop unrolling causes high glitch power. In this work, we propose a low area overhead approach for unrolling loop iterations that exhibits reduced glitch power. A latch based glitch filter is introduced that reduces the propagation of glitches from one iteration to next. We explore the optimal number of filters to be inserted for different applications that give a good balance between area and power. We also implement partial unrolling with glitch filters. This approach consumes less area while still giving energy savings comparable to the fully unrolled implementation. Our approach is targeted to Xilinx and Altera FPGAs. We simulate different implementation choices and compare energy results to evaluate the savings. We demonstrate our approach on SIMON-128 and AES-256 block ciphers and a sorting algorithm. We prototype our design on Xilinx Artix-7 and Altera Cyclone-IV-GX FPGA development boards and measure the actual power savings. Results show up-to 90% dynamic energy reduction in Xilinx designs, and 97% reduction in Altera designs with our glitch filtering approach due to glitch power reduction.

Network-On-Chip (NoC) architecture forms the new design framework in extending single processor to multiprocessor SoC. Similar to other SoCs and systems, NoCs are also susceptible to Denial of Service (DoS) attacks which degrade the performance by limiting the availability of resources to the processing cores. The stability of NoC is maintained by employing hardware monitors to detect illegal/abnormal activity or by congestion aware arbitration to obfuscate and balance the network load. Typical DoS attack model selects a random target resource and injects multiple flooding flits to reduce its functionality. The random DoS attack will not be practically effective on congestion aware NoC as the flooding path flow changes dynamically based on the congestion in network and the same victim node selection will not be effectual on different traffic profiles. Thus this paper proposes an effective DoS attack model to dynamically synthesize the selection of target node in NoC, arbitrating on congestion information. We describe the design and implementation of the proposed attack model and compare the performance degradation for different synthetic traffic profiles against random target selection. We also put forth a novel design of an effective offline congestion aware routing algorithm by exploiting the advantages of deterministic and adaptive routing. The proposed routing technique showed better latency saturation compared to adaptive (DyAD) and deterministic (OE) protocol.

In the past, various approaches to the high performance numerical computing problem have been explored. Recently, researchers have begun to explore the possibilities of using Field Programmable Gate Arrays (FPGAs) to solve numerically intensive problems. FPGAs offer the possibility of customization to any given application, while not sacrificing applicability to a wide problem domain. Further, the implementation of data flow graphs directly in silicon makes FPGAs very attractive for these types of problems. Unfortunately, current FPGAs suffer from a number of inadequacies with respect to the task. They have lower transistor densities than ASIC solutions, and hence less potential computational power per unit area. Routing overhead generally makes an FPGA solution slower than an ASIC design. Bit-oriented computational units make them unnecessarily inefficient for implementing tasks that are generally word-oriented. And finally, in large volumes, FPGAs tend to be more expensive per unit due to their lower transistor density. To combat these problems, researchers are now exploiting the unique advantage that FPGAs exhibit over ASICs: reconfigurability. By customizing the FPGA to the task at hand, as the application executes, it is hoped that the cost-performance product of an FPGA system can be shown to be a better solution than a system implemented by a collection of custom ASICs. Such a system is called a Configurable Computing Machine (CCM). Many aspects of the design of the FPGAs available today hinder the exploration of this field. This thesis addresses many of these problems and presents the embodiment of those solutions in the Colt CCM. By offering word grain reconfiguration and the ability to partially reconfigure at computational element resolution, the Colt can offer higher effective utilization over traditional FPGAs. Further, the majority of the pins of the Colt can be used for both normal I/O and for chip reconfiguration. This provides higher reconfiguration bandwidth contrasted with the low percentage of pins used for reconfiguration of FPGAs. Finally, Colt uses a distributed reconfiguration mechanism called Wormhole Run-Time Reconfiguration (RTR) that allows multiple data ports to simultaneously program different sections of the chip independently. Used as the primary example of Wormhole RTR in the patent application, Colt is the first system to employ this computing paradigm. / Ph. D.

Networked wireless sensor systems have the potential to play a major role in critical applications including: environmental monitoring of chemical/biological attacks; condition-based maintenance of vehicles, ships and aircraft; real-time monitoring of civil infrastructure including roads, bridges etc.; security and surveillance for homeland defense systems; and battlefield surveillance and monitoring. Such wireless sensor networks can provide remote monitoring and control of operations of large-scale systems using low-power, low-cost, "throw-away" sensor nodes. This thesis focuses on two aspects of wireless sensor node development: (1) post-IC assembly of nanosensor devices onto prefabricated complementary-metal-oxide-semiconductor (CMOS) integrated circuits using a technique called dielectrophoretic (DEP) assembly; and (2) design of a low-power SiGe BiCMOS multi-band ultra-wideband (UWB) transmitter for wireless communications with other nodes and/or a central control unit in a wireless sensor network. For the first part of this work, a DEP assembly test chip was designed and fabricated using the five-metal core CMOS platform technology of Motorola's HiP6W low-voltage 0.18_m Si/SiGe BiCMOS process. The CMOS chip size was 2.5mm x 2.5 mm. The required AC signal for assembling nanowires is provided to the bottom electrodes defined in the Metal 4 (M4) layer of the IC process. This signal is then capacitively coupled to the top/assembly electrodes defined in the top metal (M5) layer that is also interconnected to appropriate readout circuitry. The placement and alignment of the nanowires on the top electrodes are defined by dielectrophoretic forces that act on the nanowires. For proof of concept purposes, metallic rhodium nanowires ((length = 5μm and diameter = 250 nm) were used in this thesis to demonstrate assembly onto the prefabricated CMOS chip. The rhodium nanowires were manufactured using a nanotemplated electroplating technique. In general, the DEP assembly technique can be used to manipulate a wider range of nanoscale devices (nanowire sensors, nanotubes, etc.), allowing their individual assembly onto prefabricated CMOS chips and can be extended to integrate diverse functionalized nanosensors with sensor readout, data conversion and data communication functionalities in a single-chip environment. In addition, this technique provides a highly-manufacturable platform for the development of multifunctional wireless sensor nodes based on assembled nano-sensor devices. The resistances of the assembled nanowires were measured to be on the order of 110 Ω consistent with prior prototype results. Several issues involved in achieving successful assembly of nanowires and good electrical continuity between the nanowires and metal layers of IC processes are addressed in this thesis. The importance of chemical/mechanical planarization (CMP) technique in modern IC processes and considerations for electrical isolation of readout circuit from the assembly sites are discussed. For the second part of this work, a multi-band hopping ultrawideband transmitter was designed to operate in three different frequency bands namely, 4.8 GHz, 6.4 GHz and 8.0 GHz. As a part of this effort, this thesis includes the design of a CMOS phase/frequency detector (PFD), a CMOS pseudo-random code generator and an on-chip passive loop filter, which were designed for the multi-band PLL frequency synthesizer. The CMOS PFD provided phase tracking over a range of -2π to +2π radians. The on-chip passive loop filter was designed for a 62_ phase margin, 250 μA-charge pump output current and 4 MHz-PLL loop-bandwidth. The CMOS pseudorandom code generator provided a two-bit output that helped switch the frequency bands of the UWB transmitter. With all these components, along with a BiCMOS VCO, a CMOS charge pump and a CMOS frequency divider, the simulated PLL frequency synthesizer locked within a relatively short time of 700ns in all three design frequency bands. The die area for the multi-band UWB transmitter as laid out was 1.5 mm x 1.0 mm. Future work proposed by this thesis includes sequential assembly of diverse functionalized gas/chemical nanosensor elements into arrays in order to realize highly sensitive "electronic noses". With integration of such diverse functionalized nano-scale sensors with low-power read-out and data communication system, a versatile and commercially viable low-power wireless sensor system can be realized. / Master of Science

The SINDy (Sparse Identification of Non-linear Dynamics) algorithm is a method of turning a set of data representing non-linear dynamics into a much smaller set of equations comprised of non-linear functions summed together. This provides a human readable system model the represents the dynamic system analyzed. The SINDy algorithm is important for a variety of applications, including high precision industrial and robotic applications. A Hardware Accelerator was designed to decrease the time spent doing calculations. This thesis proposes an efficient hardware accelerator approach for a broad range of applications that use SINDy and similar system identification algorithms. The accelerator is leverages both systolic arrays for integrated neural network models with other numerical solvers. The novel and efficient reuse of similar processing elements allows this approach to only use a minimal footprint, so that it could be added to microcontroller devices or implemented on lower cost FPGA devices. Our proposed approach also allows the designer to offload calculations onto edge devices from controller nodes and requires less communication from those edge devices to the controller due to the reduced equation space.