Massively parallel programming is an increasingly growing field with the recent introduction of general purpose GPU computing. Modern graphics processors from NVIDIA and AMD have massively parallel architectures that can be used for such applications as 3D rendering, financial analysis, physics simulations, and biomedical analysis. These massively parallel systems are exposed to programmers through in- terfaces such as NVIDIAs CUDA, OpenCL, and Microsofts C++ AMP. These frame- works expose functionality using primarily either C or C++. In order to use these massively parallel frameworks, programs being implemented must be run on machines equipped with massively parallel hardware. These requirements limit the flexibility of new massively parallel systems. This paper explores the possibility that massively parallel systems can be exposed through web services in order to facilitate using these architectures from remote systems written in other languages. To explore this possi- bility, an architecture is put forth with requirements and high level design for building a web service that can overcome limitations of existing tools and frameworks. The CUDA Web API is built using Python, PyCUDA, NumPy, JSON, and Django to meet the requirements set forth. Additionaly, a client application, CUDA Cloud, is built and serves as an example web service client. The CUDA Web API’s performance and its functionality is validated using a common matrix multiplication algorithm implemented using different languages and tools. Performance tests show runtime improvements for larger datasets using the CUDA Web API for remote CUDA kernel execution over serial implementations. This paper concludes that existing limitations associated with GPGPU usage can be overcome with the specified architecture.

Document retrieval systems recover documents from a dataset and order them according to their perceived relevance to a user’s search query. This is a difficult task for machines to accomplish because there exists a semantic gap between the meaning of the terms in a user’s literal query and a user’s true intentions. Even with this ambiguity that arises with a lack of context, users still expect that the set of documents returned by a search engine is both highly relevant to their query and properly ordered. The focus of this thesis is on document retrieval systems that explore methods of ordering documents from unstructured, textual corpora using text queries. The main goal of this study is to enhance the Okapi BM25 document retrieval model. In doing so, this research hypothesizes that the structure of text inside documents and queries hold valuable semantic information that can be incorporated into the Okapi BM25 model to increase its performance. Modifications that account for a term’s part of speech, the proximity between a pair of related terms, the proximity of a term with respect to its location in a document, and query expansion are used to augment Okapi BM25 to increase the model’s performance. The study resulted in 87 modifications which were all validated using open source corpora. The top scoring modification from the validation phase was then tested under the Lisa corpus and the model performed 10.25% better than Okapi BM25 when evaluated under mean average precision. When compared against two industry standard search engines, Lucene and Solr, the top scoring modification largely outperforms these systems by upwards to 21.78% and 23.01%, respectively.

<p>In this thesis we consider the need to generate efficient solvers for inverse imaging problems in a way that supports both quality and performance in software, as well as flexibility in the underlying mathematical models. Many problem domains involve large data sizes and rates, and changes in mathematical modelling are limited only by researcher ingenuity and driven by the value of the application. We use a problem in Magnetic Resonance Imaging to illustrate this situation, motivate the need for better software tools and test the tools we develop. The problem is the determination of velocity profiles, think blood-flow patterns, using Phase Contrast Angiography. Despite the name, this method is completely noninvasive, not requiring the injection of contrast agents, but it is too time-consuming with present imaging and computing technology.</p> <p>Our approach is to separate the specification, the mathematical model, from the implementation details required for performance, using a custom language. The Domain Specific Language (DSL) provided to scientists allows for a complete abstraction from the highly optimized generated code. The mathematical DSL is converted to an internal representation we refer to as the Coconut Expression Library. Our expression library uses the directed acyclic graphs as an underlying data structure, which lends itself nicely to our automatic simplifications, differentiation and subexpression elimination. We show how parallelization and other optimizations are encoded as rules which are applied automatically rather than schemes that need to be implemented by the programmer in the low-level implementation. Finally, we present results, both in terms of numerical results and computational performance.</p> / Master of Science (MSc)

Elliptic curve cryptography (ECC) is extensively used in various multifactor authentication protocols. In this work, various recent ECC based authentication and key exchange protocols are subjected to threat modeling and static analysis to detect vulnerabilities, and to enhance them to be more secure against threats. This work demonstrates how currently used ECC based protocols are vulnerable to attacks. If protocols are vulnerable, damages could include critical data loss and elevated privacy concerns. The protocols considered in thiswork differ in their usage of security factors (e.g. passwords, pins, and biometrics), encryption and timestamps. The threatmodel considers various kinds of attacks including denial of service, man in the middle, weak authentication and SQL injection. Countermeasures to reduce or prevent such attacks are suggested. Beyond cryptanalysis of current schemes and proposal of new schemes, the proposed adversary model and criteria set forth provide a benchmark for the systematic evaluation of future two-factor authentication proposals.

Maintaining closeness between data sources and data consumers is crucial for workload I/O performance. In cloud environments, this kind of closeness can be violated by system administrative events and storage architecture barriers. VM migration events are frequent in cloud environments. VM migration changes VM runtime inter-connection or cache contexts, significantly degrading VM I/O performance. Virtualization is the backbone of cloud platforms. I/O virtualization adds additional hops to workload data access path, prolonging I/O latencies. I/O virtualization overheads cap the throughput of high-speed storage devices and imposes high CPU utilizations and energy consumptions to cloud infrastructures. To maintain the closeness between data sources and workloads during VM migration, we propose Clique, an affinity-aware migration scheduling policy, to minimize the aggregate wide area communication traffic during storage migration in virtual cluster contexts. In host-side caching contexts, we propose Successor to recognize warm pages and prefetch them into caches of destination hosts before migration completion. To bypass the I/O virtualization barriers, we propose VIP, an adaptive I/O prefetching framework, which utilizes a virtual I/O front-end buffer for prefetching so as to avoid the on-demand involvement of I/O virtualization stacks and accelerate the I/O response. Analysis on the traffic trace of a virtual cluster containing 68 VMs demonstrates that Clique can reduce inter-cloud traffic by up to 40%. Tests of MPI Reduce_scatter benchmark show that Clique can keep VM performance during migration up to 75% of the non-migration scenario, which is more than 3 times of the Random VM choosing policy. In host-side caching environments, Successor performs better than existing cache warm-up solutions and achieves zero VM-perceived cache warm-up time with low resource costs. At system level, we conducted comprehensive quantitative analysis on I/O virtualization overheads. Our trace replay based simulation demonstrates the effectiveness of VIP for data prefetching with ignorable additional cache resource costs.

In this modern rather interconnected era, an organization’s top priority is to protect itself from major security breaches occurring frequently within a communicational environment. But, it seems, as if they quite fail in doing so. Every week there are new headlines relating to information being forged, funds being stolen and corrupt usage of credit card and so on. Personal computers are turned into “zombie machines” by hackers to steal confidential and financial information from sources without disclosing hacker’s true identity. These identity thieves rob private data and ruin the very purpose of privacy. The purpose of this project is to identify suspicious user activity by analyzing a log file which then later can help an investigation agency like FBI to track and monitor anonymous user(s) who seek for weaknesses to attack vulnerable parts of a system to have access of it. The project also emphasizes the potential damage that a malicious activity could have on the system. This project uses Hadoop framework to search and store log files for logging activities and then performs a ‘Map Reduce’ programming code to finally compute and analyze the results.

Cloud computing is one important direction of current advanced technology trends, which is dominating the industry in many aspects. These days Cloud computing has become an intense battlefield of many big technology companies, whoever can win this war can have a very high potential to rule the next generation of technologies. From a technical point of view, Cloud computing is classified into three different categories, each can provide different crucial services to users: Infrastructure (Hardware) as a Service (IaaS), Software as a Service (SaaS), and Platform as a Service (PaaS). Normally, the standard measurements for cloud computing reliability level is based on two approaches: Service Level Agreements (SLAs) and Quality of Service (QoS). This thesis will focus on IaaS cloud systems’ Error Event Logs as an aspect of QoS in IaaS cloud reliability. To have a better view, basically, IaaS is a derivation of the traditional virtualization system where multiple virtual machines (VMs) with different Operating System (OS) platforms, are run solely on one physical machine (PM) that has enough computational power. The PM will play the role of the host machine in cloud computing, and the VMs will play the role as the guest machines in cloud computing. Due to the lack of fully access to the complete real cloud system, this thesis will investigate the technical reliability level of IaaS cloud through simulated virtualization system. By collecting and analyzing the event logs generated from the virtualization system, we can have a general overview of the system’s technical reliability level based on number of error events occur in the system. Then, these events will be used on neural network time series model to detect the system failure events’ pattern, as well as predict the next error event that is going to occur in the virtualization system.

Modern operating systems have been designed around the hypotheses that (a) memory is both byte-addressable and volatile and (b) storage is block addressable and persistent. The arrival of new Persistent Memory (PM) technologies, has made these assumptions obsolete. Despite much of the recent work in this space, the need for consistently sharing PM data across multiple applications remains an urgent, unsolved problem. Furthermore, the availability of simple yet powerful operating system support remains elusive. In this dissertation, we propose and build The Region System – a high-performance operating system stack for PM that implements usable consistency and persistence for application data. The region system provides support for consistently mapping and sharing data resident in PM across user application address spaces. The region system creates a novel IPI based PMSYNC operation, which ensures atomic persistence of mapped pages across multiple address spaces. This allows applications to consume PM using the well understood and much desired memory like model with an easy-to-use interface. Next, we propose a metadata structure without any redundant metadata to reduce CPU cache flushes. The high-performance design minimizes the expensive PM ordering and durability operations by embracing a minimalistic approach to metadata construction and management. To strengthen the case for the region system, in this dissertation, we analyze different types of applications to identify their dependence on memory mapped data usage, and propose user level libraries LIBPM-R and LIBPMEMOBJ-R to support shared persistent containers. The user level libraries along with the region system demonstrate a comprehensive end-to-end software stack for consuming the PM devices.

Structured Light Illumination (SLI) is the process where spatially varied patterns are projected onto a 3-D surface and based on the distortion by the surface topology, phase information can be calculated and a 3D model constructed. Phase Measuring Profilometry (PMP) is a particular type of SLI that requires three or more patterns temporarily multiplexed. High speed PMP attempts to scan moving objects whose motion is small so as to have little impact on the 3-D model. Given that practically all machine vision cameras and high speed cameras employ a Field Programmable Gate Array (FPGA) interface directly to the image sensors, the opportunity exists to do the processing on camera. This thesis focuses on the design, implementation, testing, and evaluation of a camera-projector system to implement a PMP dual-frequency scheme for 3-D shape measurement on a single FPGA chip. The processor architecture is implemented and tested using the Xilinx Spartan 3 FPGA chip on an Opal Kelly development board. The hardware is described using VHDL and Verilog Hardware Description Languages (HDLs).

Insecure cyber behavior of end users may expose their computers to cyber-attack. A first step to improve their cyber behavior is to identify their tendency toward insecure cyber behavior. Unfortunately, not much work has been done in this area. In particular, the relationship between end users cyber behavior and their personality traits is much less explored. This paper presents a comprehensive review of a newly developed, easily configurable, and flexible software SPICE for psychologist and cognitive scientists to study personality traits and insecure cyber behavior of end users. The software utilizes well-established cognitive methods (such as dot-probe) to identify number of personality traits, and further allows researchers to design and conduct experiments and detailed quantitative study on the cyber behavior of end users. The software collects fine-grained data on users for analysis.