Open Access. Powered by Scholars. Published by Universities.®

Computer Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 14 of 14

Full-Text Articles in Computer Engineering

Spatiotemporal Capacity Management For The Last Level Caches Of Chip Multiprocessors, Dongyuan Zhan Dec 2012

Spatiotemporal Capacity Management For The Last Level Caches Of Chip Multiprocessors, Dongyuan Zhan

Computer Science and Engineering: Theses, Dissertations, and Student Research

Judicious management of on-chip last-level caches (LLC) is critical to alleviating the memory wall of chip multiprocessors (CMP). Although there already exist many LLC management proposals, belonging to either the spatial or temporal dimension, they fail to capture and utilize the inherent interplays between the two dimensions in capacity management. Therefore, this dissertation is targeted at exploring and exploiting the spatiotemporal interactions in LLC capacity management to improve CMPs' performance. Based on this general idea, we address four specific research problems in the dissertation.

For the private LLC organization, prior-art proposals can improve the efficacy of inter-core cooperative caching at ...


A Unifying Approach To Behavioral Coverage, Elena Sherman Dec 2012

A Unifying Approach To Behavioral Coverage, Elena Sherman

Computer Science and Engineering: Theses, Dissertations, and Student Research

Developing methods for validating that a program works as intended is one of the key research areas in software engineering. Ideally a program P must exhibit its expected be- havior, or property, φ on all of its inputs, i.e., P |= φ. The software engineering community has developed various program analysis approaches to assess whether P |= φ. In general, these approaches can be partitioned into dynamic and static program analysis. The former execute P on a particular input and checks that the execution conforms to φ. The latter in- terprets the code of P and check that on all possible ...


Modeling Of Yeast Pheromone Pathway Using Petri Nets, Abhishek Majumdar Dec 2012

Modeling Of Yeast Pheromone Pathway Using Petri Nets, Abhishek Majumdar

Computer Science and Engineering: Theses, Dissertations, and Student Research

Yeast (Saccharomyces cerevisiae) is one of the most widely studied single celled organisms. Mating of yeast cells occur between cells of opposite mating types a and alpha. Pheromone secretion by a cell alerts the corresponding opposite type cell about its presence and eventually facilitates the process of mating between them. The details of how pheromones affect cells can be studied from the pheromone response pathway in a yeast cell. A response pathway typically depicts the chain of interactions that happens between the different proteins in the cells in response to the pheromone. In this thesis we model the yeast pheromone ...


Improving Performance Of Solid State Drives In Enterprise Environment, Jian Hu Oct 2012

Improving Performance Of Solid State Drives In Enterprise Environment, Jian Hu

Computer Science and Engineering: Theses, Dissertations, and Student Research

Flash memory, in the form of Solid State Drive (SSD), is being increasingly employed in mobile and enterprise-level storage systems due to its superior features such as high energy efficiency, high random read performance and small form factor. However, SSD suffers from the erase-before-write and endurance problems, which limit the direct deployment of SSD in enterprise environment. Existing studies either develop SSD-friendly on-board buffer management algorithms, or design sophisticated Flash Translation Layers (FTL) to ease the erase-before-write problem. This dissertation addresses the two issues and consists of two parts.

The first part focuses on the white-box approaches that optimize the ...


Automation Of Landmark Selection For Rodent Brain Mri-Histology Registration Using Thin-Plate Splines, Ayan Sengupta Aug 2012

Automation Of Landmark Selection For Rodent Brain Mri-Histology Registration Using Thin-Plate Splines, Ayan Sengupta

Computer Science and Engineering: Theses, Dissertations, and Student Research

Image registration is the process of aligning two different images of the same object taken at different times, at different orientations or using different instruments. This is common in medical applications since multiple modalities are used to image different parts of the body. This is an important early step in many diagnostic procedures such as change detection, monitoring tumor or quantifying spread of a disease. The widely used landmark based registration approach is tedious, time consuming, inconsistent and error prone. Furthermore, the standard schemes based on rigid and affine transformation can only describe global geometric differences between the objects of ...


Routing Over The Interplanetary Internet, Joyeeta Mukherjee Aug 2012

Routing Over The Interplanetary Internet, Joyeeta Mukherjee

Computer Science and Engineering: Theses, Dissertations, and Student Research

Future space exploration demands a Space Network that will be able to connect spacecrafts with one another and in turn with Earth's terrestrial Internet and hence efficiently transfer data back and forth. The feasibility of this technology would enable common people to directly access telemetric data from distant planets and satellites. The concept of an Interplanetary Internet (IPN) is only in its incubation stage and considerable amount of common standards and research is required before widespread deployment can occur to make IPN feasible.

We provide a comprehensive survey that presents a picture of the current space networking technologies and ...


Statistical Software Properties: Definition, Inference And Monitoring, Javier A. Darsie Aug 2012

Statistical Software Properties: Definition, Inference And Monitoring, Javier A. Darsie

Computer Science and Engineering: Theses, Dissertations, and Student Research

Software properties define how software systems should operate. Specifying correct properties, however, can be difficult and expensive as it requires deep knowledge of the system's expected behavior and the environment in which it operates. Automated analysis techniques to infer properties from code or code executions can mitigate that cost, but are still unable to go beyond state properties and the simplest patterns of temporal properties. This limitation renders properties that sacrifice fault detection power.

To address this problem, we introduce a new type of software properties called \textit{statistical properties}, which characterize significant statistical relationships among the values of ...


Simulation, Development And Deployment Of Mobile Wireless Sensor Networks For Migratory Bird Tracking, William P. Bennett Jr Aug 2012

Simulation, Development And Deployment Of Mobile Wireless Sensor Networks For Migratory Bird Tracking, William P. Bennett Jr

Computer Science and Engineering: Theses, Dissertations, and Student Research

This thesis presents CraneTracker, a multi-modal sensing and communication system for monitoring migratory species at the continental level. By exploiting the robust and extensive cellular infrastructure across the continent, traditional mobile wireless sensor networks can be extended to enable reliable, low-cost monitoring of migratory species. The developed multi-tier architecture yields ecologists with unconventional behavior information not furnished by alternative tracking systems at such a large scale and for a low-cost. The simulation, development and implementation of the CraneTracker software system is presented. The system is shown effective through multiple proxy deployments on wildlife and has been operational for 10 months ...


Data Mining Of Protein Databases, Christopher Assi Jul 2012

Data Mining Of Protein Databases, Christopher Assi

Computer Science and Engineering: Theses, Dissertations, and Student Research

Data mining of protein databases poses special challenges because many protein databases are non-relational whereas most data mining and machine learning algorithms assume the input data to be a relational database. Protein databases are non-relational mainly because they often contain set data types. We developed new data mining algorithms that can restructure non-relational protein databases so that they become relational and amenable for various data mining and machine learning tools. We applied the new restructuring algorithms to a pancreatic protein database. After the restructuring, we also applied two classification methods, such as decision tree and SVM classifiers and compared their ...


On Heterogeneous User Demands In Peer-To-Peer Video Streaming Systems, Zhipeng Ouyang Jul 2012

On Heterogeneous User Demands In Peer-To-Peer Video Streaming Systems, Zhipeng Ouyang

Computer Science and Engineering: Theses, Dissertations, and Student Research

A Peer-to-Peer (P2P) video streaming system usually consists of a large number of peers, which have heterogeneous physical properties. Orthogonal to the physical heterogeneity, there is another type of heterogeneity called demand heterogeneity. Namely, peers have their own demands on the quality and type of the streaming service. The problem of demand heterogeneity has received little attention and as a result current P2P video streaming systems cannot achieve satisfactory performance due to demand heterogeneity. In this dissertation, we study how to design efficient P2P video streaming systems with heterogeneous user demands.

First, we study the problem of heterogeneous user demands ...


An Enhanced Self-Adaptive Mapreduce Scheduling Algorithm, Xiaoyu Sun May 2012

An Enhanced Self-Adaptive Mapreduce Scheduling Algorithm, Xiaoyu Sun

Computer Science and Engineering: Theses, Dissertations, and Student Research

MapReduce is a framework for processing huge amounts of data in a distributed environment and Hadoop is Apache’s open source implementation of MapReduce, which is widely used. However, Hadoop’s performance is currently limited by its default task scheduler, which assumes that cluster nodes are homogeneous when estimating the task progress and choosing slow tasks for re-execution. In practice, the homogeneity assumption does not always hold. Longest Approximate Time to End (LATE) is a scheduling algorithm that takes heterogeneity into account. It, however, still depends on a static method to estimate the task execution time. As a result, neither ...


Probabilistic Qos Analysis In Wireless Sensor Networks, Yunbo Wang May 2012

Probabilistic Qos Analysis In Wireless Sensor Networks, Yunbo Wang

Computer Science and Engineering: Theses, Dissertations, and Student Research

Emerging applications of wireless sensor networks (WSNs) require real-time quality of service (QoS) guarantees to be provided by the network. Traditional analysis work only focuses on the first-order statistics, such as the mean and the variance of the QoS performance. However, due to unique characteristics of WSNs, a cross-layer probabilistic analysis of QoS performance is essential. In this dissertation, a comprehensive cross-layer probabilistic analysis framework is developed to investigate the probabilistic evaluation and optimization of QoS performance provided by WSNs. In this framework, the distributions of QoS performance metrics are derived, which are natural tools to discover the probabilities to ...


Supporting Developer-Onboarding With Enhanced Resource Finding And Visual Exploration, Jianguo Wang Apr 2012

Supporting Developer-Onboarding With Enhanced Resource Finding And Visual Exploration, Jianguo Wang

Computer Science and Engineering: Theses, Dissertations, and Student Research

Understanding the basic structure of a code base and a development team are essential to get new developers up to speed in a software development project. Developers do so through the process of early experimentation with code and the creation of mental models of technical and social structures in a project. However, getting up-to-speed in a new project can be challenging due to difficulties in: finding the right place to begin explorations, expanding the focus to determine relevant resources for tasks, and identifying dependencies across project elements to gain a high-level overview of project structures. In this thesis, I first ...


Improving Backup And Restore Performance For Deduplication-Based Cloud Backup Services, Stephen Mkandawire Apr 2012

Improving Backup And Restore Performance For Deduplication-Based Cloud Backup Services, Stephen Mkandawire

Computer Science and Engineering: Theses, Dissertations, and Student Research

The benefits provided by cloud computing and the space savings offered by data deduplication make it attractive to host data storage services like backup in the cloud. Data deduplication relies on comparing fingerprints of data chunks, and store them in the chunk index, to identify and remove redundant data, with an ultimate goal of saving storage space and network bandwidth.

However, the chunk index presents a bottleneck to the throughput of the backup operation. While several solutions to address deduplication throughput have been proposed, the chunk index is still a centralized resource and limits the scalability of both storage capacity ...