University of North Carolina

Displaying 41-66 of 66 results

  • White Papers // Mar 2010

    Challenges in Genomic Data Processing I - Multiple Small Files

    Advances in the field of Genomics have made more data on the very building blocks of life available than ever before. When coupled with the burgeoning fields of Bioinformatics and Statistical Genomics, there is significant information that has been heretofore hidden in those simple chemical bonds. Unfortunately, bridging the divide...

    Provided By University of North Carolina

  • White Papers // Jan 2010

    A Performance Study of Loss Detection/Recovery in Real-World TCP Implementations

    TCP is the dominant transport protocol used in the Internet and its performance fundamentally governs the performance of Internet applications. It is well-known that packet losses can adversely affect the connection duration of TCP connections-however, what is not fully understood is how well does the TCP design deal with losses....

    Provided By University of North Carolina

  • White Papers // Dec 2009

    FloVis: Leveraging Visualization to Protect Sensitive Network Infrastructure

    Computer networks have become critical to NATO operations. Much of NATO's computer traffic runs over civilian networks, and NATO computers are accessible to a wide variety of malicious activities. The scale of the network traffic involved makes monitoring and analysis difficult, and the rapid deployment of computer systems to new...

    Provided By University of North Carolina

  • White Papers // Dec 2009

    Capacity of Data Collection in Arbitrary Wireless Sensor Networks

    How to efficiently collect sensing data from all sensor nodes is critical to the performance of wireless sensor networks. In this paper, the authors aim to understand the theoretical limitations of data collection in terms of possible and achievable maximum capacity. Previously, the study of data collection capacity has only...

    Provided By University of North Carolina

  • White Papers // Nov 2009

    Privacy Preserving Categorical Data Analysis With Unknown Distortion Parameters

    Randomized Response techniques have been investigated in privacy preserving categorical data analysis. However, the released distortion parameters can be exploited by attackers to breach privacy. In this paper, the authors investigate whether data mining or statistical analysis tasks can still be conducted on randomized data when distortion parameters are not...

    Provided By University of North Carolina

  • White Papers // Nov 2009

    TimeCapsule: Secure Recording of Accesses to a Protected Datastore

    The authors present an approach for transparently recording accesses to protected storage. In particular, they provide a framework for data monitoring in a virtualized environment using only the abstractions exposed by the hypervisor. To achieve their goals, they explore techniques for efficiently harvesting application code pages resident in memory at...

    Provided By University of North Carolina

  • White Papers // Oct 2009

    On the Development of an Internetwork-Centric Defense for Scanning Worms

    Studies of worm outbreaks have found that the speed of worm propagation makes manual intervention ineffective. Consequently, many automated containment mechanisms have been proposed to contain worm outbreaks before they grow out of control. These containment systems, however, only provide protection for hosts within networks that implement them. Such a...

    Provided By University of North Carolina

  • White Papers // Oct 2009

    The Causal Impact Of Media In Financial Markets

    It is challenging to disentangle the causal impact of media reporting from the impact of the events being reported. The authors solve this problem by comparing the behaviors of investors with access to different media coverage of the same information event. They use zip codes to identify 19 mutually exclusive...

    Provided By University of North Carolina

  • White Papers // Sep 2009

    Making Peer-Assisted Content Distribution Robust to Collusion Using Bandwidth Puzzles

    Many peer-assisted content-distribution systems reward a peer based on the amount of data that this peer serves to others. However, validating that a peer did so is, to the authors' knowledge, an open problem; e.g., a group of colluding attackers can earn rewards by claiming to have served content to...

    Provided By University of North Carolina

  • White Papers // Sep 2009

    A Hierarchical Multiprocessor Bandwidth Reservation Scheme with Timing Guarantees

    A multiprocessor scheduling scheme is presented for supporting hierarchical containers that encapsulate sporadic soft and hard real-time tasks. In this scheme, each container is allocated a specified bandwidth, which it uses to schedule its children (some of which may also be containers). This paper is novel in that, with only...

    Provided By University of North Carolina

  • White Papers // Sep 2009

    Generalized Tardiness Bounds for Global Multiprocessor Scheduling

    The authors consider the issue of deadline tardiness under global multiprocessor scheduling algorithms. They present a general tardiness-bound derivation that is applicable to a wide variety of such algorithms (including some whose tardiness behavior has not been analyzed before). Their derivation is very general: job priorities may change rather arbitrarily...

    Provided By University of North Carolina

  • White Papers // May 2009

    Supporting Sporadic Pipelined Tasks with Early-Releasing in Soft Real-Time Multiprocessor Systems

    With the advent of multicore technologies, it is important for programming frameworks for real-time applications to provide support for commonly-used multiprocessor programming techniques. One such technique is pipelined execution, which is used to increase throughput by leveraging the parallelism inherent on multiprocessor platforms. Soft real-time sporadic multiprocessor task systems are...

    Provided By University of North Carolina

  • White Papers // Apr 2009

    Did Structured Credit Fuel The LBO Boom?

    The authors demonstrate a link between the twin storms underlying the current financial crisis - the market for Collateralized Debt Obligations (CDOs) and the market for leveraged loans. The authors show that structural changes in credit markets that led to the explosion in CDOs created an increased supply of bank...

    Provided By University of North Carolina

  • White Papers // Apr 2009

    Supporting Pipelines in Soft Real-Time Multiprocessor Systems

    With the advent of multicore technologies, it is important that real-time scheduling theory be extended so that commonly-used multiprocessor programming techniques can be supported in systems with timing constraints. One technique of particular utility is pipelined execution, which is used to increase throughput by leveraging the parallelism inherent on multiprocessor...

    Provided By University of North Carolina

  • White Papers // Apr 2009

    What's The Use Of Arguing? European Union Strategies For The Promotion Of Human Rights In The United Nations

    This paper explores two themes raised by the recent ECFR Audit of European Power in the UN, where it is argued that a group of states constituting an 'Axis of Sovereignty' is frustrating European efforts to promote human rights in the multilateral framework of the UN. The first is the...

    Provided By University of North Carolina

  • White Papers // Mar 2009

    Improved Conditions for Bounded Tardiness Under EPDF Pfair Multiprocessor Scheduling

    The authors consider the scheduling of recurrent (i.e., periodic, sporadic, or rate-based) real-time task systems on multiprocessor platforms consisting of M identical, unit-capacity processors. Pfair scheduling, originally introduced by the research, is the only known way of optimally scheduling such multiprocessor task systems. The Earliest-Pseudo-Deadline-First (EPDF) Pfair algorithm is more...

    Provided By University of North Carolina

  • White Papers // May 2008

    A Unified Hard/Soft Real-Time Schedulability Test for Global EDF Multiprocessor Scheduling

    Most major chip manufacturers are investing in multicore technologies to continue performance improvements in their product lines in the face of fundamental limitations of single-core chip designs. This development is profound as it means that multiprocessors are now a \"Common-case\" platform. This realization has led to renewed recent interest in...

    Provided By University of North Carolina

  • White Papers // Nov 2007

    Examination of Infomediary Roles in B2C E-Commerce

    In this paper, the authors provide a parsimonious research model that assists in the study of infomediary roles in B2C E-commerce, their level of integration and sophistication, and their impact on infomediary performance and customers' satisfaction. After an extensive literature review, discovery, facilitation, and support roles were identified as the...

    Provided By University of North Carolina

  • White Papers // Nov 2007

    Tardiness Bounds Under Global EDF Scheduling on a Multiprocessor

    The authors consider the scheduling of a sporadic real-time task system on an identical multiprocessor. Though Pfair algorithms are theoretically optimal for such task systems, in practice, their runtime overheads can significantly reduce the amount of useful work that is accomplished. On the other hand, if all deadlines need to...

    Provided By University of North Carolina

  • White Papers // Oct 2007

    An EDF-Based Restricted-Migration Scheduling Algorithm for Multiprocessor Soft Real-Time Systems

    There has been much recent interest in the use of the Earliest-Deadline-First (EDF) algorithm for scheduling soft real-time sporadic task systems on identical multiprocessors. In hard real-time systems, a significant disparity exists between EDF-based schemes and Pfair scheduling: on M processors, the worst-case schedulable utilization for all known EDF variants...

    Provided By University of North Carolina

  • White Papers // Sep 2007

    Techniques for Multiprocessor Global Schedulability Analysis

    A real-time system is often modeled as a finite collection of independent recurring tasks, each of which generates a potentially infinite sequence of jobs. The scheduling of sporadic task systems upon multiprocessor platforms is considered, when inter-processor migration is permitted. It is known that current schedulability tests for such systems...

    Provided By University of North Carolina

  • White Papers // Aug 2007

    Efficient Synchronization Under Global EDF Scheduling on Multiprocessors

    The authors consider coordinating accesses to shared data structures in multiprocessor real-time systems scheduled under preemptive global EDF. To their knowledge, prior work on global EDF has focused only on systems of independent tasks. They take an initial step here towards a generic resource-sharing framework by considering simple shared objects,...

    Provided By University of North Carolina

  • White Papers // Mar 2007

    Task Reweighting Under Global Scheduling on Multiprocessors

    The authors consider schemes for enacting task share changes-a process called reweighting-on real-time multiprocessor platforms. Their particular focus is reweighting schemes that are deployed in environments in which tasks may frequently request significant share changes. This paper has shown that fair scheduling algorithms are capable of reweighting tasks with minimal...

    Provided By University of North Carolina

  • White Papers // Feb 2007

    Understanding the Adoption of Web-Enabled Transaction Processing by Small Businesses

    The promise of the Internet and e-commerce has led to the increasing use of the web for transaction processing. Many organizations have adopted web-enabled transaction processing for applications such as processing payments online, selling products online, making travel reservations to name a few. In spite of the trend in this...

    Provided By University of North Carolina

  • White Papers // Apr 2006

    The Partitioned Scheduling of Sporadic Tasks According to Static-Priorities

    A polynomial-time algorithm is presented for partitioning a collection of sporadic tasks among the processors of an identical multiprocessor platform with static-priority scheduling on each individual processor. Since the partitioning problem is easily seen to be NP-hard in the strong sense, this algorithm is not optimal. A quantitative characterization of...

    Provided By University of North Carolina

  • White Papers // Apr 2002

    How Representative Are Cross-Listed Firms? An Analysis of Firm Performance and Accounting Quality

    This article provides evidence on the characteristics of local-GAAP reported earnings for firms choosing to cross list in US markets relative to both a matched sample of foreign firms currently not cross listing in the US and a matched sample of US firms. The goal is to investigate the extent...

    Provided By University of North Carolina

  • White Papers // May 2008

    A Unified Hard/Soft Real-Time Schedulability Test for Global EDF Multiprocessor Scheduling

    Most major chip manufacturers are investing in multicore technologies to continue performance improvements in their product lines in the face of fundamental limitations of single-core chip designs. This development is profound as it means that multiprocessors are now a \"Common-case\" platform. This realization has led to renewed recent interest in...

    Provided By University of North Carolina

  • White Papers // Sep 2009

    Generalized Tardiness Bounds for Global Multiprocessor Scheduling

    The authors consider the issue of deadline tardiness under global multiprocessor scheduling algorithms. They present a general tardiness-bound derivation that is applicable to a wide variety of such algorithms (including some whose tardiness behavior has not been analyzed before). Their derivation is very general: job priorities may change rather arbitrarily...

    Provided By University of North Carolina

  • White Papers // Nov 2007

    Tardiness Bounds Under Global EDF Scheduling on a Multiprocessor

    The authors consider the scheduling of a sporadic real-time task system on an identical multiprocessor. Though Pfair algorithms are theoretically optimal for such task systems, in practice, their runtime overheads can significantly reduce the amount of useful work that is accomplished. On the other hand, if all deadlines need to...

    Provided By University of North Carolina

  • White Papers // Apr 2006

    The Partitioned Scheduling of Sporadic Tasks According to Static-Priorities

    A polynomial-time algorithm is presented for partitioning a collection of sporadic tasks among the processors of an identical multiprocessor platform with static-priority scheduling on each individual processor. Since the partitioning problem is easily seen to be NP-hard in the strong sense, this algorithm is not optimal. A quantitative characterization of...

    Provided By University of North Carolina

  • White Papers // Sep 2007

    Techniques for Multiprocessor Global Schedulability Analysis

    A real-time system is often modeled as a finite collection of independent recurring tasks, each of which generates a potentially infinite sequence of jobs. The scheduling of sporadic task systems upon multiprocessor platforms is considered, when inter-processor migration is permitted. It is known that current schedulability tests for such systems...

    Provided By University of North Carolina

  • White Papers // Jul 2010

    Spin-Based Reader-Writer Synchronization for Multiprocessor Real-Time Systems

    With the transition to multicore architectures by most major chip manufacturers, multiprocessors are now a standard deployment platform for (soft) real-time applications. Reader preference, writer preference, and task-fair reader-writer locks are shown to cause undue blocking in multiprocessor real-time systems. Phase-fair reader writer locks, a new class of reader-writer locks,...

    Provided By University of North Carolina

  • White Papers // Mar 2009

    Improved Conditions for Bounded Tardiness Under EPDF Pfair Multiprocessor Scheduling

    The authors consider the scheduling of recurrent (i.e., periodic, sporadic, or rate-based) real-time task systems on multiprocessor platforms consisting of M identical, unit-capacity processors. Pfair scheduling, originally introduced by the research, is the only known way of optimally scheduling such multiprocessor task systems. The Earliest-Pseudo-Deadline-First (EPDF) Pfair algorithm is more...

    Provided By University of North Carolina

  • White Papers // Mar 2007

    Task Reweighting Under Global Scheduling on Multiprocessors

    The authors consider schemes for enacting task share changes-a process called reweighting-on real-time multiprocessor platforms. Their particular focus is reweighting schemes that are deployed in environments in which tasks may frequently request significant share changes. This paper has shown that fair scheduling algorithms are capable of reweighting tasks with minimal...

    Provided By University of North Carolina

  • White Papers // Oct 2007

    An EDF-Based Restricted-Migration Scheduling Algorithm for Multiprocessor Soft Real-Time Systems

    There has been much recent interest in the use of the Earliest-Deadline-First (EDF) algorithm for scheduling soft real-time sporadic task systems on identical multiprocessors. In hard real-time systems, a significant disparity exists between EDF-based schemes and Pfair scheduling: on M processors, the worst-case schedulable utilization for all known EDF variants...

    Provided By University of North Carolina

  • White Papers // Jan 2014

    A Hybrid Real-Time Scheduling Approach for Large-Scale Multicore Platforms

    The authors propose a hybrid approach for scheduling real-time tasks on large-scale multicore platforms with hierarchical shared caches. In this approach, a multicore platform is partitioned into clusters. Tasks are statically assigned to these clusters, and scheduled within each cluster using the preemptive global EDF scheduling algorithm. They show that...

    Provided By University of North Carolina

  • White Papers // Apr 2013

    Supporting Soft Real-Time Parallel Applications on Multiprocessors

    The prevalence of multicore processors has resulted in the wider applicability of parallel programming models such as OpenMP and MapReduce. A common goal of running parallel applications implemented under such models is to guarantee bounded response times while maximizing system utilization. Unfortunately, little previous work has been done that can...

    Provided By University of North Carolina

  • White Papers // Aug 2007

    Efficient Synchronization Under Global EDF Scheduling on Multiprocessors

    The authors consider coordinating accesses to shared data structures in multiprocessor real-time systems scheduled under preemptive global EDF. To their knowledge, prior work on global EDF has focused only on systems of independent tasks. They take an initial step here towards a generic resource-sharing framework by considering simple shared objects,...

    Provided By University of North Carolina

  • White Papers // Jul 2013

    Fair Lateness Scheduling: Reducing Maximum Lateness in G-EDF-Like Scheduling

    In this paper, the authors discuss the Soft Real-Time (SRT) multiprocessor scheduling, tardiness bounds have been derived for a variety of scheduling algorithms, most notably, the Global Earliest-Deadline-First (G-EDF) algorithm. In this paper, the authors devise G-EDF-Like (GEL) schedulers, which have identical implementations to G-EDF and therefore the same overheads,...

    Provided By University of North Carolina

  • White Papers // Oct 2012

    An Optimal K-Exclusion Real-Time Locking Protocol Motivated by Multi-GPU Systems

    Graphics Processing Units (GPUs) are becoming increasingly important in today's platforms as their growing generality allows for them to be used as powerful co-processors. In previous work, the authors showed that GPUs may be integrated into real-time systems by treating GPUs as shared resources, allocated to real-time tasks through mutual...

    Provided By University of North Carolina

  • White Papers // Sep 2011

    Globally Scheduled Real-Time Multiprocessor Systems with GPUs

    Graphics Processing Units (GPUs) are powerful processors that can offer significant performance advantages over traditional CPUs. The last decade has seen rapid advancement in GPU computational power and generality. Recent technologies make it possible to use GPUs as coprocessors to CPUs. The performance advantages of GPUs can be great, often...

    Provided By University of North Carolina

  • White Papers // Apr 2011

    Multiprocessor Extensions to Real-Time Calculus

    Many embedded platforms consist of a heterogeneous collection of processing elements, memory modules, and communication subsystems. These components often implement different scheduling/arbitration policies, have different interfaces, and are supplied by different vendors. Hence, compositional techniques for modeling and analyzing such platforms are of interest. In this paper, the real-time calculus...

    Provided By University of North Carolina

  • White Papers // Apr 2009

    Supporting Pipelines in Soft Real-Time Multiprocessor Systems

    With the advent of multicore technologies, it is important that real-time scheduling theory be extended so that commonly-used multiprocessor programming techniques can be supported in systems with timing constraints. One technique of particular utility is pipelined execution, which is used to increase throughput by leveraging the parallelism inherent on multiprocessor...

    Provided By University of North Carolina

  • White Papers // Feb 2013

    Mixed-Criticality Scheduling Upon Unreliable Processors

    An unreliable processor is characterized by two execution speeds: a normal speed and a degraded speed. Under normal circumstances it will execute at its normal speed; unexpected conditions may occur during run-time that causes it to execute more slowly (but no slower than at its degraded speed). The problem of...

    Provided By University of North Carolina

  • White Papers // Jun 2011

    Supporting Graph-Based Real-Time Applications in Distributed Systems

    The Processing Graph Method (PGM) is a widely used framework for modeling applications with producer/ consumer precedence constraints. PGM was originally developed by the U.S. Navy to model signal-processing applications where data communications exist among connected tasks. Prior paper has shown how to schedule PGM-specified systems on uniprocessors and globally-scheduled...

    Provided By University of North Carolina

  • White Papers // Apr 2010

    Improving the Schedulability of Sporadic Self-Suspending Soft Real-Time Multiprocessor Task Systems

    In many real-time systems, tasks self-suspend due to interactions with external devices such as disks and network cards. The suspension delays introduced by such behaviors can quite negatively impact schedulability if deadline misses cannot be tolerated. In work on globally-scheduled soft real-time multiprocessor systems, analysis has been presented for dealing...

    Provided By University of North Carolina

  • White Papers // May 2009

    Supporting Sporadic Pipelined Tasks with Early-Releasing in Soft Real-Time Multiprocessor Systems

    With the advent of multicore technologies, it is important for programming frameworks for real-time applications to provide support for commonly-used multiprocessor programming techniques. One such technique is pipelined execution, which is used to increase throughput by leveraging the parallelism inherent on multiprocessor platforms. Soft real-time sporadic multiprocessor task systems are...

    Provided By University of North Carolina

  • White Papers // Nov 2007

    Examination of Infomediary Roles in B2C E-Commerce

    In this paper, the authors provide a parsimonious research model that assists in the study of infomediary roles in B2C E-commerce, their level of integration and sophistication, and their impact on infomediary performance and customers' satisfaction. After an extensive literature review, discovery, facilitation, and support roles were identified as the...

    Provided By University of North Carolina

  • White Papers // Aug 2012

    Effects of Dissatisfaction on Customer Repurchase Decisions in E-Commerce - An Emotion-Based Perspective

    Dissatisfaction is one of the factors that drive customers' decisions to reduce repurchase intention. Repurchase is crucial to the success of online stores. The present paper attempts to examine what coping behavior will be triggered by negative emotion in e-commerce and examines the potential influence of coping behavior on customer...

    Provided By University of North Carolina

  • White Papers // Feb 2007

    Understanding the Adoption of Web-Enabled Transaction Processing by Small Businesses

    The promise of the Internet and e-commerce has led to the increasing use of the web for transaction processing. Many organizations have adopted web-enabled transaction processing for applications such as processing payments online, selling products online, making travel reservations to name a few. In spite of the trend in this...

    Provided By University of North Carolina

  • White Papers // Nov 2009

    TimeCapsule: Secure Recording of Accesses to a Protected Datastore

    The authors present an approach for transparently recording accesses to protected storage. In particular, they provide a framework for data monitoring in a virtualized environment using only the abstractions exposed by the hypervisor. To achieve their goals, they explore techniques for efficiently harvesting application code pages resident in memory at...

    Provided By University of North Carolina

  • White Papers // Jan 2015

    Data Warehousing and Web Enablement: Opportunities, Issues, and Trends

    The Web is becoming the biggest contributor towards the growth of business intelligence and data warehousing. It is anticipated that 80% of all decision support queries will be across the Web in the near future. Using Internet/Intranet technologies to implement data warehouses is significantly reducing the cost associated deployment. Security...

    Provided By University of North Carolina