Quantifying and Modeling the Influence of Forest on the Magnitude and Duration of Mountain Snow Storage in the Pacific Northwest, USA

Thesis (Ph.D.)--University of Washington, 2016-08

Multilevel mesh partitioning for optimising domain shape

Multilevel algorithms are a successful class of optimisation techniques which address the mesh partitioning problem for mapping meshes onto parallel computers. They usually combine a graph contraction algorithm together with a local optimisation method which refines the partition at each graph level. To date these algorithms have been used almost exclusively to minimise the cut-edge weight in the graph with the aim of minimising the parallel communication overhead. However it has been shown that for certain classes of problem, the convergence of the underlying solution algorithm is strongly influenced by the shape or aspect ratio of the subdomains. In this paper therefore, we modify the multilevel algorithms in order to optimise a cost function based on aspect ratio. Several variants of the algorithms are tested and shown to provide excellent results.

Evaluation of the JOSTLE mesh partitioning code for practical multiphysics applications

The use of unstructured mesh codes on parallel machines is one of the most effective ways to solve large computational mechanics problems. Completely general geometries and complex behaviour can be modelled and, in principle, the inherent sparsity of many such problems can be exploited to obtain excellent parallel efficiencies. However, unlike their structured counterparts, the problem of distributing the mesh across the memory of the machine, whilst minimising the amount of interprocessor communication, must be carefully addressed. This process is an overhead that is not incurred by a serial code, but is shown to rapidly computable at turn time and tailored for the machine being used.

Load-balancing for parallel adaptive unstructured grids

A parallel method for the dynamic partitioning of unstructured meshes is outlined. The method includes diffusive load-balancing techniques and an iterative optimisation technique known as relative gain optimisationwhich both balances theworkload and attempts to minimise the interprocessor communications overhead. It can also optionally include amultilevel strategy. Experiments on a series of adaptively refined meshes indicate that the algorithmprovides partitions of an equivalent or higher quality to static partitioners (which do not reuse the existing partition) and much more rapidly. Perhaps more importantly, the algorithm results in only a small fraction of the amount of data migration compared to the static partitioners.

Parallel dynamic load-balancing for adaptive unstructured meshes

This chapter describes a parallel optimization technique that incorporates a distributed load-balancing algorithm and provides an extremely fast solution to the problem of load-balancing adaptive unstructured meshes. Moreover, a parallel graph contraction technique can be employed to enhance the partition quality and the resulting strategy outperforms or matches results from existing state-of-the-art static mesh partitioning algorithms. The strategy can also be applied to static partitioning problems. Dynamic procedures have been found to be much faster than static techniques, to provide partitions of similar or higher quality and, in comparison, involve the migration of a fraction of the data. The method employs a new iterative optimization technique that balances the workload and attempts to minimize the interprocessor communications overhead. Experiments on a series of adaptively refined meshes indicate that the algorithm provides partitions of an equivalent or higher quality to static partitioners (which do not reuse the existing partition) and much more quickly. The dynamic evolution of load has three major influences on possible partitioning techniques; cost, reuse, and parallelism. The unstructured mesh may be modified every few time-steps and so the load-balancing must have a low cost relative to that of the solution algorithm in between remeshing.

Opinião dos Estudantes do Curso de Licenciatura em Enfermagem, sobre a sobrecarga do cuidador de Doentes com demência tipo de Alzheimer

Projeto de Graduação apresentado à Universidade Fernando Pessoa como parte dos requisitos para obtenção do grau de licenciada em Enfermagem

Dynamic load-balancing for parallel adaptive unstructured meshes

A parallel method for dynamic partitioning of unstructured meshes is described. The method employs a new iterative optimisation technique which both balances the workload and attempts to minimise the interprocessor communications overhead. Experiments on a series of adaptively refined meshes indicate that the algorithm provides partitions of an equivalent or higher quality to static partitioners (which do not reuse the existing partition) and much more quickly. Perhaps more importantly, the algorithm results in only a small fraction of the amount of data migration compared to the static partitioners.

Multilevel mesh partitioning for optimising subdomain aspect ratio

Multilevel algorithms are a successful class of optimisation techniques which address the mesh partitioning problem for mapping meshes onto parallel computers. They usually combine a graph contraction algorithm together with a local optimisation method which refines the partition at each graph level. To date these algorithms have been used almost exclusively to minimise the cut-edge weight in the graph with the aim of minimising the parallel communication overhead. However it has been shown that for certain classes of problem, the convergence of the underlying solution algorithm is strongly influenced by the shape or aspect ratio of the subdomains. In this paper therefore, we modify the multilevel algorithms in order to optimise a cost function based on aspect ratio. Several variants of the algorithms are tested and shown to provide excellent results.

Parallel dynamic graph-partitioning for unstructured meshes

A parallel method for the dynamic partitioning of unstructured meshes is described. The method introduces a new iterative optimisation technique known as relative gain optimisation which both balances the workload and attempts to minimise the interprocessor communications overhead. Experiments on a series of adaptively refined meshes indicate that the algorithm provides partitions of an equivalent or higher quality to static partitioners (which do not reuse the existing partition) and much more rapidly. Perhaps more importantly, the algorithm results in only a small fraction of the amount of data migration compared to the static partitioners.

Security through Obscurity: Layout Obfuscation of Digital Integrated Circuits using Don't Care Conditions

Contemporary integrated circuits are designed and manufactured in a globalized environment leading to concerns of piracy, overproduction and counterfeiting. One class of techniques to combat these threats is circuit obfuscation which seeks to modify the gate-level (or structural) description of a circuit without affecting its functionality in order to increase the complexity and cost of reverse engineering. Most of the existing circuit obfuscation methods are based on the insertion of additional logic (called “key gates”) or camouflaging existing gates in order to make it difficult for a malicious user to get the complete layout information without extensive computations to determine key-gate values. However, when the netlist or the circuit layout, although camouflaged, is available to the attacker, he/she can use advanced logic analysis and circuit simulation tools and Boolean SAT solvers to reveal the unknown gate-level information without exhaustively trying all the input vectors, thus bringing down the complexity of reverse engineering. To counter this problem, some ‘provably secure’ logic encryption algorithms that emphasize methodical selection of camouflaged gates have been proposed previously in literature [1,2,3]. The contribution of this paper is the creation and simulation of a new layout obfuscation method that uses don't care conditions. We also present proof-of-concept of a new functional or logic obfuscation technique that not only conceals, but modifies the circuit functionality in addition to the gate-level description, and can be implemented automatically during the design process. Our layout obfuscation technique utilizes don’t care conditions (namely, Observability and Satisfiability Don’t Cares) inherent in the circuit to camouflage selected gates and modify sub-circuit functionality while meeting the overall circuit specification. Here, camouflaging or obfuscating a gate means replacing the candidate gate by a 4X1 Multiplexer which can be configured to perform all possible 2-input/ 1-output functions as proposed by Bao et al. [4]. It is important to emphasize that our approach not only obfuscates but alters sub-circuit level functionality in an attempt to make IP piracy difficult. The choice of gates to obfuscate determines the effort required to reverse engineer or brute force the design. As such, we propose a method of camouflaged gate selection based on the intersection of output logic cones. By choosing these candidate gates methodically, the complexity of reverse engineering can be made exponential, thus making it computationally very expensive to determine the true circuit functionality. We propose several heuristic algorithms to maximize the RE complexity based on don’t care based obfuscation and methodical gate selection. Thus, the goal of protecting the design IP from malicious end-users is achieved. It also makes it significantly harder for rogue elements in the supply chain to use, copy or replicate the same design with a different logic. We analyze the reverse engineering complexity by applying our obfuscation algorithm on ISCAS-85 benchmarks. Our experimental results indicate that significant reverse engineering complexity can be achieved at minimal design overhead (average area overhead for the proposed layout obfuscation methods is 5.51% and average delay overhead is about 7.732%). We discuss the strengths and limitations of our approach and suggest directions that may lead to improved logic encryption algorithms in the future. References: [1] R. Chakraborty and S. Bhunia, “HARPOON: An Obfuscation-Based SoC Design Methodology for Hardware Protection,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 28, no. 10, pp. 1493–1502, 2009. [2] J. A. Roy, F. Koushanfar, and I. L. Markov, “EPIC: Ending Piracy of Integrated Circuits,” in 2008 Design, Automation and Test in Europe, 2008, pp. 1069–1074. [3] J. Rajendran, M. Sam, O. Sinanoglu, and R. Karri, “Security Analysis of Integrated Circuit Camouflaging,” ACM Conference on Computer Communications and Security, 2013. [4] Bao Liu, Wang, B., "Embedded reconfigurable logic for ASIC design obfuscation against supply chain attacks,"Design, Automation and Test in Europe Conference and Exhibition (DATE), 2014 , vol., no., pp.1,6, 24-28 March 2014.

Incorporation of Hysteretic Effects in Model-Order Reduction Analysis of Magnetic Devices

The ability to predict the properties of magnetic materials in a device is essential to ensuring the correct operation and optimization of the design as well as the device behavior over a wide range of input frequencies. Typically, development and simulation of wide-bandwidth models requires detailed, physics-based simulations that utilize significant computational resources. Balancing the trade-offs between model computational overhead and accuracy can be cumbersome, especially when the nonlinear effects of saturation and hysteresis are included in the model. This study focuses on the development of a system for analyzing magnetic devices in cases where model accuracy and computational intensity must be carefully and easily balanced by the engineer. A method for adjusting model complexity and corresponding level of detail while incorporating the nonlinear effects of hysteresis is presented that builds upon recent work in loss analysis and magnetic equivalent circuit (MEC) modeling. The approach utilizes MEC models in conjunction with linearization and model-order reduction techniques to process magnetic devices based on geometry and core type. The validity of steady-state permeability approximations is also discussed.

An IP capable data link layer protocol for narrow band half-duplex packet data radio networks

The wide adaptation of Internet Protocol (IP) as de facto protocol for most communication networks has established a need for developing IP capable data link layer protocol solutions for Machine to machine (M2M) and Internet of Things (IoT) networks. However, the wireless networks used for M2M and IoT applications usually lack the resources commonly associated with modern wireless communication networks. The existing IP capable data link layer solutions for wireless IoT networks provide the necessary overhead minimising and frame optimising features, but are often built to be compatible only with IPv6 and specific radio platforms. The objective of this thesis is to design IPv4 compatible data link layer for Netcontrol Oy's narrow band half-duplex packet data radio system. Based on extensive literature research, system modelling and solution concept testing, this thesis proposes the usage of tunslip protocol as the basis for the system data link layer protocol development. In addition to the functionality of tunslip, this thesis discusses the additional network, routing, compression, security and collision avoidance changes required to be made to the radio platform in order for it to be IP compatible while still being able to maintain the point-to-multipoint and multi-hop network characteristics. The data link layer design consists of the radio application, dynamic Maximum Transmission Unit (MTU) optimisation daemon and the tunslip interface. The proposed design uses tunslip for creating an IP capable data link protocol interface. The radio application receives data from tunslip and compresses the packets and uses the IP addressing information for radio network addressing and routing before forwarding the message to radio network. The dynamic MTU size optimisation daemon controls the tunslip interface maximum MTU size according to the link quality assessment calculated from the radio network diagnostic data received from the radio application. For determining the usability of tunslip as the basis for data link layer protocol, testing of the tunslip interface is conducted with both IEEE 802.15.4 radios and packet data radios. The test cases measure the radio network usability for User Datagram Protocol (UDP) based applications without applying any header or content compression. The test results for the packet data radios reveal that the typical success rate for packet reception through a single-hop link is above 99% with a round-trip-delay of 0.315s for 63B packets.

Forwarding and security in vehicular networks

The growing research in vehicular network solutions provided the rise of interaction in these highly dynamic environments in the market. The developed architectures do not usually focus, however, in security aspects. Common security strategies designed for the Internet require IP. Since nodes' addresses in a vehicular network are too dynamic, such solutions would require cumbersome negotiations, which would make them unsuitable to these environments. The objective of this dissertation is to develop, and test a scalable, lightweight, layer 3 security protocol for vehicular networks, in which nodes of the network are able to set up long-term security associations with a Home Network, avoiding session renegotiations due to lack of connectivity and reduce the protocol stacking. This protocol allows to provide security independent of the nodes (vehicles) position, of its addressing and of the established path to access the Internet, allowing the mobility of vehicles and of its active sessions seamlessly without communication failures.

New Directions in Commercial Secrecy and Encryption Protocols

Secure transmission of bulk data is of interest to many content providers. A commercially-viable distribution of content requires technology to prevent unauthorised access. Encryption tools are powerful, but have a performance cost. Without encryption, intercepted data may be illicitly duplicated and re-sold, or its commercial value diminished because its secrecy is lost. Two technical solutions make it possible to perform bulk transmissions while retaining security without too high a performance overhead. These are: 1. a) hierarchical encryption - the stronger the encryption, the harder it is to break but also the more computationally expensive it is. A hierarchical approach to key exchange means that simple and relatively weak encryption and keys are used to encrypt small chunks of data, for example 10 seconds of video. Each chunk has its own key. New keys for this bottom-level encryption are exchanged using a slightly stronger encryption, for example a whole-video key could govern the exchange of the 10-second chunk keys. At a higher level again, there could be daily or weekly keys, securing the exchange of whole-video keys, and at a yet higher level, a subscriber key could govern the exchange of weekly keys. At higher levels, the encryption becomes stronger but is used less frequently, so that the overall computational cost is minimal. The main observation is that the value of each encrypted item determines the strength of the key used to secure it. 2. b) non-symbolic fragmentation with signal diversity - communications are usually assumed to be sent over a single communications medium, and the data to have been encrypted and/or partitioned in whole-symbol packets. Network and path diversity break up a file or data stream into fragments which are then sent over many different channels, either in the same network or different networks. For example, a message could be transmitted partly over the phone network and partly via satellite. While TCP/IP does a similar thing in sending different packets over different paths, this is done for load-balancing purposes and is invisible to the end application. Network and path diversity deliberately introduce the same principle as a secure communications mechanism - an eavesdropper would need to intercept not just one transmission path but all paths used. Non-symbolic fragmentation of data is also introduced to further confuse any intercepted stream of data. This involves breaking up data into bit strings which are subsequently disordered prior to transmission. Even if all transmissions were intercepted, the cryptanalyst still needs to determine fragment boundaries and correctly order them. These two solutions depart from the usual idea of data encryption. Hierarchical encryption is an extension of the combined encryption of systems such as PGP but with the distinction that the strength of encryption at each level is determined by the "value" of the data being transmitted. Non- symbolic fragmentation suppresses or destroys bit patterns in the transmitted data in what is essentially a bit-level transposition cipher but with unpredictable irregularly-sized fragments. Both technologies have applications outside the commercial and can be used in conjunction with other forms of encryption, being functionally orthogonal.

Precoder Detection for Cooperative Decode-and-Forward Relaying in OFDMA Systems

We consider an LTE network where a secondary user acts as a relay, transmitting data to the primary user using a decode-and-forward mechanism, transparent to the base-station (eNodeB). Clearly, the relay can decode symbols more reliably if the employed precoder matrix indicators (PMIs) are known. However, for closed loop spatial multiplexing (CLSM) transmit mode, this information is not always embedded in the downlink signal, leading to a need for effective methods to determine the PMI. In this thesis, we consider 2x2 MIMO and 4x4 MIMO downlink channels corresponding to CLSM and formulate two techniques to estimate the PMI at the relay using a hypothesis testing framework. We evaluate their performance via simulations for various ITU channel models over a range of SNR and for different channel quality indicators (CQIs). We compare them to the case when the true PMI is known at the relay and show that the performance of the proposed schemes are within 2 dB at 10% block error rate (BLER) in almost all scenarios. Furthermore, the techniques add minimal computational overhead over existent receiver structure. Finally, we also identify scenarios when using the proposed precoder detection algorithms in conjunction with the cooperative decode-and-forward relaying mechanism benefits the PUE and improves the BLER performance for the PUE. Therefore, we conclude from this that the proposed algorithms as well as the cooperative relaying mechanism at the CMR can be gainfully employed in a variety of real-life scenarios in LTE networks.