University of New Orleans Fund

Displaying 1-40 of 81 results

  • White Papers // Mar 2014

    Challenges in Practicing High Frequency Releases in Cloud Environments

    The continuous delivery trend is dramatically shortening release cycles from months into hours. Applications with high frequency releases often rely heavily on automated deployment tools using cloud infrastructure APIs. The authors report some results from experiments on reliability issues of cloud infrastructure and trade-offs between using heavily-baked and lightly-baked images....

    Provided By University of New Orleans Fund

  • White Papers // Mar 2014

    POD-Diagnosis: Error Diagnosis of Sporadic Operations on Cloud Applications

    Applications in the cloud are subject to sporadic changes due to operational activities such as upgrade, redeployment, and on-demand scaling. These operations are also subject to interferences from other simultaneous operations. Increasing the dependability of these sporadic operations is non-trivial, particularly since traditional anomaly-detection-based diagnosis techniques are less effective during...

    Provided By University of New Orleans Fund

  • White Papers // Mar 2014

    Recovery for Failures in Rolling Upgrade on Clouds

    When cloud consumers are performing rolling upgrade operations on cloud applications, they may encounter failures due to cloud uncertainty. For example, unreliable cloud API calls can make the rolling upgrade operation fail in unpredictable and subtle ways. This paper proposes two recovery strategies for recovering from rolling upgrade failures. The...

    Provided By University of New Orleans Fund

  • White Papers // Mar 2014

    Towards a Taxonomy of Cloud Recovery Strategies

    Dependability of cloud can be achieved by enabling cloud recoverability. Recovery for cloud from consumer's perspective is challenging because cloud platforms only provide consumers with limited visibility and control. One research on consumer-initiated cloud recovery is recovery for the errors occurring during sporadic operations on cloud applications. This research relies...

    Provided By University of New Orleans Fund

  • White Papers // Feb 2014

    A Recoverability-Oriented Analysis for Operations on Cloud Applications

    The consumer-initiated sporadic operations on cloud applications, such as deployment, upgrade and reconfiguration, may fail because of the inherent uncertainty of operating in a cloud environment. For example, if a VM is not able to start, operations dependent on that VM will fail. In this paper the authors propose an...

    Provided By University of New Orleans Fund

  • White Papers // Feb 2014

    Recovery for Sporadic Operations on Cloud Applications

    During sporadic operations (e.g. deployment, upgrade, and reconfiguration, etc.) on cloud applications, errors could happen and make the operations fail. This is due to several reasons such as cloud APIs uncertainty. One way to handle the errors is to recover from them. Some existing recovery approaches such as exceptions handling...

    Provided By University of New Orleans Fund

  • White Papers // Oct 2013

    FlaRe: Efficient Capability Semantics for Timely Processor Access

    In the seL4 microkernel and other capability-based OSs, the right to use resources is managed using abstract capabilities. Capability systems for fungible resources such as memory are well understood, but it has proven difficult to integrate time - i.e., real-time scheduling - into this model, since timeliness (i.e., system-wide schedulability)...

    Provided By University of New Orleans Fund

  • White Papers // Sep 2013

    Accelerating Inclusion-Based Pointer Analysis on Heterogeneous CPU-GPU Systems

    In this paper, the authors describe the first implementation of Andersen's inclusion-based pointer analysis for C programs on a heterogeneous CPU-GPU system, where both its CPU and GPU cores are used. As an important graph algorithm, Andersen's analysis is difficult to parallelize because it makes extensive modifications to the structure...

    Provided By University of New Orleans Fund

  • White Papers // Aug 2013

    Process-Oriented Recovery for Operations on Cloud Applications

    A large number of cloud application failures happen during sporadic operations such as upgrade, deployment reconfiguration, migration and scaling-out/in. Most of them are caused by operator and process errors. From a cloud consumer's perspective, recovery from these failures relies on the limited control and visibility provided by the cloud providers....

    Provided By University of New Orleans Fund

  • White Papers // Jul 2013

    Physical Layer Security in Downlink Multi-Antenna Cellular Networks

    In this paper, the authors study physical layer security for the downlink of cellular networks, where the confidential messages transmitted to each mobile user can be eavesdropped by both the other users in the same cell and the users in the other cells. The locations of base stations and mobile...

    Provided By University of New Orleans Fund

  • White Papers // Jul 2013

    Software-Hardware Cooperative DRAM Bank Partitioning for Chip Multiprocessors

    DRAM row buffer conflicts can increase the memory access latency significantly for single-threaded applications. In a chip multiprocessor system, multiple applications competing for DRAM will suffer additional row buffer conflicts due to interthread interference. This paper presents a new hardware and software cooperative DRAM bank partitioning method that combines page...

    Provided By University of New Orleans Fund

  • White Papers // Jul 2013

    Optimising Purely Functional GPU Programs

    Purely functional, embedded array programs are a good match for SIMD hardware, such as GPUs. However, the naive compilation of such programs quickly leads to both code explosion and an excessive use of intermediate data structures. The resulting slowdown is not acceptable on target hardware that is usually chosen to...

    Provided By University of New Orleans Fund

  • White Papers // Jun 2013

    A New Method to Mitigate the Impacts of Economical Denial of Sustainability Attacks Against the Cloud

    In the cloud era, security has become a renewed source of concerns. Distributed Denial of Service (DDoS) and the Economical Denial of Sustainability (EDoS) that can affect the pay-per-use model, which is one of the most valuable benefits of the cloud, can again become very relevant especially with the introduction...

    Provided By University of New Orleans Fund

  • White Papers // May 2013

    Managing the IT Integration of Acquisitions by Multi-Business Organizations

    Acquisitions are standard components of the growth strategies of many organizations. Frequently, acquisitions raise important questions concerning how and to what extent the acquisition's Information Technology (IT) needs to be integrated into the IT of the acquirer. The authors investigate how the initial conditions of business and IT alignment in...

    Provided By University of New Orleans Fund

  • White Papers // May 2013

    Patterned Interactions in Complex Systems: The Role of Information Technology for Reshaping Organizational Structures

    The complex relationships between organizational practices have been the focus of Information Technology Business Value (ITBV) research in recent years. There appears to be a discernible trend toward a more nuanced view in which the effects of Information Technology (IT), various organizational practices and their complex interactions are systematically investigated....

    Provided By University of New Orleans Fund

  • White Papers // May 2013

    Technoidentology: Towards an Explication of Individual Relationships With IS/IT

    This paper argues that IS theories should not ignore or background the relationship between individuals and technologies in explaining concepts such as adoption, innovation, diffusion, and practice. The relationships that individuals have with technologies should, arguably, be a core interest of IS because of the centrality of people and IT...

    Provided By University of New Orleans Fund

  • White Papers // May 2013

    Increasing the Trustworthiness of Commodity Hardware Through Software

    Advances in formal software verification have produced an operating system that is guaranteed mathematically to be correct and enforce access isolation. Such an operating system could potentially consolidate safety and security critical software on a single device where previously multiple devices were used. One of the barriers to consolidation on...

    Provided By University of New Orleans Fund

  • White Papers // May 2013

    Improving Availability of Cloud-Based Applications through Deployment Choices

    Deployment choices are critical in determining the availability of applications running in a cloud. But choosing good deployment for various software application components into virtual machines is a challenging task because of potential sharing of components among applications and potential interference from multi-tenancy. This paper presents an approach for improving...

    Provided By University of New Orleans Fund

  • White Papers // Apr 2013

    Attacks Via Record Multiplicity on Cancelable Biometrics Templates

    Various template protection techniques have been developed in the past few years, among which cancelable biometrics is a very popular and efficient one. It uses a noninvertible transformation to map an original template to a transformed domain to prevent the recovery of the original template from a compromised transformed template....

    Provided By University of New Orleans Fund

  • White Papers // Dec 2012

    Formal Verification, Engineering and Business Value

    How to apply automated verification technology such as model checking and static program analysis to millions of lines of embedded C/C++ code? How to package this technology in a way that it can be used by software developers and engineers, who might have no background in formal verification? And how...

    Provided By University of New Orleans Fund

  • White Papers // Nov 2012

    Verifying Probabilistic Correctness in Isabelle with pGCL

    This paper presents a formalization of pGCL in Isabelle/HOL. Using a shallow embedding, the authors demonstrate close integration with existing automation support. They demonstrate the facility with which the model can be extended to incorporate existing results, including those of the L4.verified project. They motivate the applicability of the formalism...

    Provided By University of New Orleans Fund

  • White Papers // Nov 2012

    Automatic Verification of Message-Based Device Drivers

    The authors develop a practical solution to the problem of automatic verification of the interface between device drivers and the OS. Their solution relies on a combination of improved driver architecture and verification tools. It supports drivers written in C and can be implemented in any existing OS, which sets...

    Provided By University of New Orleans Fund

  • White Papers // Oct 2012

    Assimilation of the Cloud: Benefits and Challenges to Acceptance, Routinization and Infusion of Cloud Computing

    This paper goes beyond a binary view of adoption and instead examines the more complex nature of cloud computing assimilation. It examines acceptance, the extent to which an organization's members are committed to the adoption, routinization, the extent to which the use of cloud becomes a normal activity, and infusion,...

    Provided By University of New Orleans Fund

  • White Papers // Oct 2012

    A Performance Model of Pedestrian Dead Reckoning With Activity-Based Location Updates

    Advanced computing and sensing capabilities of smartphones provide new opportunities for personal indoor positioning. A particular trend is to employ human activity recognition for autonomous calibration of pedestrian dead reckoning systems thereby achieving accurate indoor positioning even in the absence of any positioning infrastructure. The basic idea is that the...

    Provided By University of New Orleans Fund

  • White Papers // Sep 2012

    Ownership Types for Object Synchronisation

    In this paper, the authors have proposed the use of ownership types to enforce a structured synchronization discipline for safe execution of structured tasks. They use ownership effects to reason about interference between parallel tasks, and establish synchronization requirements that guarantee serialisability. Synchronization requirements can be inferred to simplify concurrent...

    Provided By University of New Orleans Fund

  • White Papers // Sep 2012

    Bringing Viability to Service-Oriented Enterprises in Cloud Ecosystems

    Cloud Computing is the next evolution of computing systems, which shifts the whole application infrastructure away from old monolithic architectural models to more open, interoperable, modular, reusable and agile building blocks. Many Enterprises realize the benefits of Cloud Computing and position it as the Information Technology (IT) outsourcing solution, which...

    Provided By University of New Orleans Fund

  • White Papers // Sep 2012

    Automatic Undo for Cloud Management via AI Planning

    The facility to rollback a collection of changes, i.e., reverting to a previous acceptable state, a checkpoint, is widely recognized as valuable support for dependability. This paper considers the particular needs of users of cloud computing resources, wishing to manage the resources. Cloud computing provides infrastructure programmatically managed through a...

    Provided By University of New Orleans Fund

  • White Papers // Aug 2012

    Application-Managed Replication Controller for Cloud-Hosted Databases

    Data replication is a well-known strategy to achieve the availability, scalability and performance improvement goals in the data management world. However, the cost of maintaining several database replicas always strongly consistent is very high. The CAP theorem shows that a shared-data system can choose at most two out of three...

    Provided By University of New Orleans Fund

  • White Papers // Aug 2012

    On the Spectrum of Web Scale Data Management

    Over the past decade, rapidly growing Internet-based services have substantially redefined the way of data persistence and retrieval. Relational DataBase Management Systems (RDBMS) have been considered as the one-size-fits-all solution for data persistence and retrieval for decades. However, ever-increasing needs for scalability and new application requirements have created high challenges...

    Provided By University of New Orleans Fund

  • White Papers // Aug 2012

    Extending Enterprise Service Design Knowledge using Clustering

    Automatically constructing or completing knowledge bases of SOA design knowledge puts traditional clustering approaches beyond their limits. The authors propose an approach to amend incomplete knowledge bases of Enterprise Service (ES) design knowledge, based on a set of ES signatures. The approach employs clustering, complemented with various filtering and ranking...

    Provided By University of New Orleans Fund

  • White Papers // Jul 2012

    Application of Business-Driven Decision Making to RESTful Business Processes

    Runtime adaptability is a desired quality attribute in business processes, particularly cross-organizational ones. Past work showed that designing and implementing business processes following the REpresentational State Transfer (REST) principles increases runtime adaptability. However, the past solutions for RESTful Business Processes (RESTfulBP) were limited to manual selection of process fragments to...

    Provided By University of New Orleans Fund

  • White Papers // Jul 2012

    To Preempt or Not to Preempt, That Is the Question

    Real-Time Operating Systems (RTOSes) are traditionally designed to be fully preemptible. This improves the average interrupt response time of the system but increases kernel complexity. An alternative design is to make the kernel mostly non-preemptible and only handle pending interrupts at specific preemption points within the kernel. While this potentially...

    Provided By University of New Orleans Fund

  • White Papers // Jun 2012

    Automatic Parallelization of Tiled Loop Nests with Enhanced Fine-Grained Parallelism on GPUs

    Automatically parallelizing loop nests into CUDA kernels must exploit the full potential of GPUs to obtain high performance. One state-of-the-art approach makes use of the polyhedral model to extract parallelism from a loop nest by applying a sequence of affine transformations to the loop nest. However, how to automate this...

    Provided By University of New Orleans Fund

  • White Papers // Jun 2012

    A Business Process-Driven Approach for Requirements Dependency Analysis

    Dependencies among software artifacts are very useful for various software development and maintenance activities such as change impact analysis and effort estimation. In the past, the focus on artifact dependencies has been at the design and code level rather than at the requirements level. This is due to the difficulties...

    Provided By University of New Orleans Fund

  • White Papers // Jun 2012

    Programming Cloud Resource Orchestration Framework: Operations and Research Challenges

    The emergence of cloud computing over the past five years is potentially one of the breakthrough advances in the history of computing. It delivers hardware and software resources as virtualization enabled services and in which administrators are free from the burden of worrying about the low level implementation or system...

    Provided By University of New Orleans Fund

  • White Papers // May 2012

    Relay Assisted Spectrum Sharing in Cognitive Radio Networks

    In this paper, the authors propose a Relay Assisted Spectrum Sharing (RASS) scheme based on the mixed sharing strategy in cognitive radio networks. Mixed sharing is a more general sharing strategy which provides a higher spectrum utilization efficiency than underlay sharing and interweave sharing. Compared to conventional mixed sharing, the...

    Provided By University of New Orleans Fund

  • White Papers // May 2012

    Optimal Spectrum Sensing Over Multipath Channels

    Wireless propagation phenomena including multipath pose significant challenges to reliable spectrum sensing which is a fundamental requirement for dynamic spectrum access and system coexistence. In this paper, an optimal detection technique along with two reduced-complexity alternatives, Modified Energy Detection (MED) and Equal Gain Detection (EGD), are proposed to improve the...

    Provided By University of New Orleans Fund

  • White Papers // May 2012

    Asymmetric Interference Alignment and Cancelation for 3-User MIMO Interference Channels

    The notion of Degree of Freedom (DoF) of a communication network, also known as the capacity pre-log/multiplexing gain/effective-bandwidth, etc., is a fundamental concept in communication and information theory. With recent focus on capacity approximation, the DoF characterization becomes especially significant as it provides a capacity approximation whose accuracy approaches 100%...

    Provided By University of New Orleans Fund

  • White Papers // May 2012

    Heterogeneous Secure Multi-Party Computation

    The increased processing power and storage capacity of in-home and mobile computing devices has motivated their inclusion in distributed and cloud computing systems. The resulting diverse environment creates a strong requirement for secure computations, which can be realized by secure Multi-Party Computation (MPC). However, MPC most commonly assumes that parties...

    Provided By University of New Orleans Fund

  • White Papers // May 2012

    A Framework for Consumer-Centric SLA Management of Cloud-Hosted Databases

    One of the main advantages of the cloud computing paradigm is that it simplifies the time-consuming processes of hardware provisioning, hardware purchasing and software deployment. Currently, the authors are witnessing a proliferation in the number of cloud-hosted applications with a tremendous increase in the scale of the data generated as...

    Provided By University of New Orleans Fund

  • White Papers // Mar 2012

    Large System Analysis of the Secrecy Sum-Rates With Regularized Channel Inversion Precoding

    Wireless networks are used more and more often to exchange sensitive data. Due to the broadcast nature of the medium, every node in the network is a potential eavesdropper, and securing the transmitted information is critical. Traditionally, security is ensured by network-layer cryptography techniques. These techniques are potentially vulnerable, since...

    Provided By University of New Orleans Fund

  • White Papers // Jun 2012

    Programming Cloud Resource Orchestration Framework: Operations and Research Challenges

    The emergence of cloud computing over the past five years is potentially one of the breakthrough advances in the history of computing. It delivers hardware and software resources as virtualization enabled services and in which administrators are free from the burden of worrying about the low level implementation or system...

    Provided By University of New Orleans Fund

  • White Papers // Nov 2012

    Verifying Probabilistic Correctness in Isabelle with pGCL

    This paper presents a formalization of pGCL in Isabelle/HOL. Using a shallow embedding, the authors demonstrate close integration with existing automation support. They demonstrate the facility with which the model can be extended to incorporate existing results, including those of the L4.verified project. They motivate the applicability of the formalism...

    Provided By University of New Orleans Fund

  • White Papers // Nov 2012

    Automatic Verification of Message-Based Device Drivers

    The authors develop a practical solution to the problem of automatic verification of the interface between device drivers and the OS. Their solution relies on a combination of improved driver architecture and verification tools. It supports drivers written in C and can be implemented in any existing OS, which sets...

    Provided By University of New Orleans Fund

  • White Papers // Sep 2012

    Automatic Undo for Cloud Management via AI Planning

    The facility to rollback a collection of changes, i.e., reverting to a previous acceptable state, a checkpoint, is widely recognized as valuable support for dependability. This paper considers the particular needs of users of cloud computing resources, wishing to manage the resources. Cloud computing provides infrastructure programmatically managed through a...

    Provided By University of New Orleans Fund

  • White Papers // Jul 2012

    To Preempt or Not to Preempt, That Is the Question

    Real-Time Operating Systems (RTOSes) are traditionally designed to be fully preemptible. This improves the average interrupt response time of the system but increases kernel complexity. An alternative design is to make the kernel mostly non-preemptible and only handle pending interrupts at specific preemption points within the kernel. While this potentially...

    Provided By University of New Orleans Fund

  • White Papers // Dec 2010

    Interband Mutual Information in Blind Audio Bandwidth Extension

    Bandwidth extension schemes have received considerable research attention for their ability to perceptually enhance band-limited audio. However, existing schemes do not exploit mutual information between bands or saliency of spectral features. A novel blind scheme is proposed, which preserves harmonicity in the extended spectrum and employs a trained band energy...

    Provided By University of New Orleans Fund

  • White Papers // Oct 2012

    A Performance Model of Pedestrian Dead Reckoning With Activity-Based Location Updates

    Advanced computing and sensing capabilities of smartphones provide new opportunities for personal indoor positioning. A particular trend is to employ human activity recognition for autonomous calibration of pedestrian dead reckoning systems thereby achieving accurate indoor positioning even in the absence of any positioning infrastructure. The basic idea is that the...

    Provided By University of New Orleans Fund

  • White Papers // Jul 2010

    Design of Rate-compatible Protograph-based LDPC Codes with Mixed Circulants

    Low-Density Parity-Check (LDPC) codes were initially proposed by Gallager in early 1960s. Their excellent performance with iterative decoding over various channels is overshadowed by the complexity of encoding and decoding. The authors propose a novel design of rate-compatible protograph-based low-density parity-check code families that can cover a wide range of...

    Provided By University of New Orleans Fund

  • White Papers // Oct 2012

    Assimilation of the Cloud: Benefits and Challenges to Acceptance, Routinization and Infusion of Cloud Computing

    This paper goes beyond a binary view of adoption and instead examines the more complex nature of cloud computing assimilation. It examines acceptance, the extent to which an organization's members are committed to the adoption, routinization, the extent to which the use of cloud becomes a normal activity, and infusion,...

    Provided By University of New Orleans Fund

  • White Papers // May 2013

    Patterned Interactions in Complex Systems: The Role of Information Technology for Reshaping Organizational Structures

    The complex relationships between organizational practices have been the focus of Information Technology Business Value (ITBV) research in recent years. There appears to be a discernible trend toward a more nuanced view in which the effects of Information Technology (IT), various organizational practices and their complex interactions are systematically investigated....

    Provided By University of New Orleans Fund

  • White Papers // May 2013

    Technoidentology: Towards an Explication of Individual Relationships With IS/IT

    This paper argues that IS theories should not ignore or background the relationship between individuals and technologies in explaining concepts such as adoption, innovation, diffusion, and practice. The relationships that individuals have with technologies should, arguably, be a core interest of IS because of the centrality of people and IT...

    Provided By University of New Orleans Fund

  • White Papers // May 2013

    Managing the IT Integration of Acquisitions by Multi-Business Organizations

    Acquisitions are standard components of the growth strategies of many organizations. Frequently, acquisitions raise important questions concerning how and to what extent the acquisition's Information Technology (IT) needs to be integrated into the IT of the acquirer. The authors investigate how the initial conditions of business and IT alignment in...

    Provided By University of New Orleans Fund

  • White Papers // Dec 2008

    Beyond Soundness: On the Verification of Semantic Business Process Models

    The verification of control-flow soundness is well understood as an important step before deploying business process models. However, the control flow does not capture what the process activities actually do when they are executed. Semantic annotations offer the opportunity to take this into account. Inspired by semantic Web service approaches...

    Provided By University of New Orleans Fund

  • White Papers // May 2012

    Relay Assisted Spectrum Sharing in Cognitive Radio Networks

    In this paper, the authors propose a Relay Assisted Spectrum Sharing (RASS) scheme based on the mixed sharing strategy in cognitive radio networks. Mixed sharing is a more general sharing strategy which provides a higher spectrum utilization efficiency than underlay sharing and interweave sharing. Compared to conventional mixed sharing, the...

    Provided By University of New Orleans Fund

  • White Papers // May 2012

    Optimal Spectrum Sensing Over Multipath Channels

    Wireless propagation phenomena including multipath pose significant challenges to reliable spectrum sensing which is a fundamental requirement for dynamic spectrum access and system coexistence. In this paper, an optimal detection technique along with two reduced-complexity alternatives, Modified Energy Detection (MED) and Equal Gain Detection (EGD), are proposed to improve the...

    Provided By University of New Orleans Fund

  • White Papers // May 2012

    Asymmetric Interference Alignment and Cancelation for 3-User MIMO Interference Channels

    The notion of Degree of Freedom (DoF) of a communication network, also known as the capacity pre-log/multiplexing gain/effective-bandwidth, etc., is a fundamental concept in communication and information theory. With recent focus on capacity approximation, the DoF characterization becomes especially significant as it provides a capacity approximation whose accuracy approaches 100%...

    Provided By University of New Orleans Fund

  • White Papers // Jul 2010

    Toward Harnessing DOACROSS Parallelism for Multi-GPGPUs

    To exploit the full potential of GPGPUs for general-purpose computing, DOACR parallelism abundant in scientific and engineering applications must be harnessed. However, the presence of cross-iteration data dependences in DOACR loops poses an obstacle to execute their computations concurrently using a massive number of fine-grained threads. In this paper, the...

    Provided By University of New Orleans Fund

  • White Papers // Jun 2012

    Automatic Parallelization of Tiled Loop Nests with Enhanced Fine-Grained Parallelism on GPUs

    Automatically parallelizing loop nests into CUDA kernels must exploit the full potential of GPUs to obtain high performance. One state-of-the-art approach makes use of the polyhedral model to extract parallelism from a loop nest by applying a sequence of affine transformations to the loop nest. However, how to automate this...

    Provided By University of New Orleans Fund

  • White Papers // Feb 2012

    A Highly Parallel Reuse Distance Analysis Algorithm on GPUs

    Reuse distance analysis is a runtime approach that has been widely used to accurately model the memory system behavior of applications. However, traditional reuse distance analysis algorithms use tree-based data structures and are hard to parallelize, missing the tremendous computing power of modern architectures such as the emerging GPUs. This...

    Provided By University of New Orleans Fund

  • White Papers // Jan 2012

    A Type and Effect System for Determinism in Multithreaded Programs

    There has been much recent interest in supporting deterministic parallelism in imperative programs. Structured parallel programming models have used type systems or static analysis to enforce determinism by constraining potential interference of lexically scoped tasks. But similar support for multithreaded programming, where threads may be ubiquitously spawned with arbitrary lifetimes,...

    Provided By University of New Orleans Fund

  • White Papers // May 2011

    Model-Driven Tile Size Selection for DOACROSS Loops on GPUs

    DOALL loops are tiled to exploit DOALL parallelism and data locality on GPUs. In contrast, due to loop-carried dependences, DOACROSS loops must be skewed first in order to make tiling legal and exploit wavefront parallelism across the tiles and within a tile. Thus, tile size selection, which is performance-critical, becomes...

    Provided By University of New Orleans Fund

  • White Papers // Sep 2013

    Accelerating Inclusion-Based Pointer Analysis on Heterogeneous CPU-GPU Systems

    In this paper, the authors describe the first implementation of Andersen's inclusion-based pointer analysis for C programs on a heterogeneous CPU-GPU system, where both its CPU and GPU cores are used. As an important graph algorithm, Andersen's analysis is difficult to parallelize because it makes extensive modifications to the structure...

    Provided By University of New Orleans Fund

  • White Papers // Sep 2006

    Instruction Scheduling with Release Times and Deadlines on ILP Processors

    The authors proposed a fast algorithm for scheduling instructions in a basic block with precedence-latency constraints, timing constraints in the form of individual integer release times and deadlines on an ILP processor. ILP (Instruction Level Parallelism) processors are being increasingly used in embedded systems. In embedded systems, instructions may be...

    Provided By University of New Orleans Fund

  • White Papers // Jul 2013

    Software-Hardware Cooperative DRAM Bank Partitioning for Chip Multiprocessors

    DRAM row buffer conflicts can increase the memory access latency significantly for single-threaded applications. In a chip multiprocessor system, multiple applications competing for DRAM will suffer additional row buffer conflicts due to interthread interference. This paper presents a new hardware and software cooperative DRAM bank partitioning method that combines page...

    Provided By University of New Orleans Fund

  • White Papers // Jan 2011

    Extendable Pattern-Oriented Optimization Directives

    Current programming models and compiler technologies for multi-core processors do not exploit well the performance benefits obtainable by applying algorithm-specific, i.e., semantic-specific optimizations to a particular application. In this paper, the authors propose a pattern-making methodology that allows algorithm-specific optimizations to be encapsulated into \"Optimization patterns\" that are expressed in...

    Provided By University of New Orleans Fund

  • White Papers // Sep 2012

    Ownership Types for Object Synchronisation

    In this paper, the authors have proposed the use of ownership types to enforce a structured synchronization discipline for safe execution of structured tasks. They use ownership effects to reason about interference between parallel tasks, and establish synchronization requirements that guarantee serialisability. Synchronization requirements can be inferred to simplify concurrent...

    Provided By University of New Orleans Fund

  • White Papers // Dec 2008

    Improving the Parallelism of Iterative Methods by Aggressive Loop Fusion

    Traditionally, loop nests are fused only when the data dependences in the loop nests are not violated. In this paper, the authors present a new loop fusion algorithm that is capable of fusing loop nests in the presence of fusion-preventing anti-dependences. All the violated anti-dependences are removed by automatic array...

    Provided By University of New Orleans Fund

  • White Papers // Aug 2011

    Comparability Graph Coloring for Optimizing Utilization of Software-Managed Stream Register Files for Stream Processors

    The stream processors represent a promising alternative to traditional cache-based general-purpose processors in achieving high performance in stream applications. In a stream programming model for stream processors, an application is decomposed into a sequence of kernels operating on streams of data. During the execution of a kernel on a stream...

    Provided By University of New Orleans Fund

  • White Papers // Jun 2010

    Evaluating Cloud Platform Architecture with the CARE Framework

    There is an emergence of cloud application platforms such as Microsoft's azure, Google's app engine and Amazon's EC2/SimpleDB/S3. Startups and enterprise alike, lured by the promise of 'Infinite Scalability', 'Ease of Development', 'Low Infrastructure Setup Cost' are increasingly using these cloud service building blocks to develop and deploy their web...

    Provided By University of New Orleans Fund

  • White Papers // Jun 2013

    A New Method to Mitigate the Impacts of Economical Denial of Sustainability Attacks Against the Cloud

    In the cloud era, security has become a renewed source of concerns. Distributed Denial of Service (DDoS) and the Economical Denial of Sustainability (EDoS) that can affect the pay-per-use model, which is one of the most valuable benefits of the cloud, can again become very relevant especially with the introduction...

    Provided By University of New Orleans Fund

  • White Papers // Feb 2014

    Recovery for Sporadic Operations on Cloud Applications

    During sporadic operations (e.g. deployment, upgrade, and reconfiguration, etc.) on cloud applications, errors could happen and make the operations fail. This is due to several reasons such as cloud APIs uncertainty. One way to handle the errors is to recover from them. Some existing recovery approaches such as exceptions handling...

    Provided By University of New Orleans Fund

  • White Papers // Feb 2014

    A Recoverability-Oriented Analysis for Operations on Cloud Applications

    The consumer-initiated sporadic operations on cloud applications, such as deployment, upgrade and reconfiguration, may fail because of the inherent uncertainty of operating in a cloud environment. For example, if a VM is not able to start, operations dependent on that VM will fail. In this paper the authors propose an...

    Provided By University of New Orleans Fund

  • White Papers // Mar 2014

    POD-Diagnosis: Error Diagnosis of Sporadic Operations on Cloud Applications

    Applications in the cloud are subject to sporadic changes due to operational activities such as upgrade, redeployment, and on-demand scaling. These operations are also subject to interferences from other simultaneous operations. Increasing the dependability of these sporadic operations is non-trivial, particularly since traditional anomaly-detection-based diagnosis techniques are less effective during...

    Provided By University of New Orleans Fund

  • White Papers // Mar 2014

    Challenges in Practicing High Frequency Releases in Cloud Environments

    The continuous delivery trend is dramatically shortening release cycles from months into hours. Applications with high frequency releases often rely heavily on automated deployment tools using cloud infrastructure APIs. The authors report some results from experiments on reliability issues of cloud infrastructure and trade-offs between using heavily-baked and lightly-baked images....

    Provided By University of New Orleans Fund

  • White Papers // May 2012

    A Framework for Consumer-Centric SLA Management of Cloud-Hosted Databases

    One of the main advantages of the cloud computing paradigm is that it simplifies the time-consuming processes of hardware provisioning, hardware purchasing and software deployment. Currently, the authors are witnessing a proliferation in the number of cloud-hosted applications with a tremendous increase in the scale of the data generated as...

    Provided By University of New Orleans Fund

  • White Papers // Aug 2012

    Extending Enterprise Service Design Knowledge using Clustering

    Automatically constructing or completing knowledge bases of SOA design knowledge puts traditional clustering approaches beyond their limits. The authors propose an approach to amend incomplete knowledge bases of Enterprise Service (ES) design knowledge, based on a set of ES signatures. The approach employs clustering, complemented with various filtering and ranking...

    Provided By University of New Orleans Fund

  • White Papers // Apr 2012

    The Clustered Multikernel: An Approach to Formal Verification of Multiprocessor OS Kernels

    Operating-system kernels are critical software components in computer systems. Building secure, safe and reliable computer systems is facilitated by having strong kernel correctness guarantees. Such guarantees can be obtained by formally verifying a kernel down to the implementation level. Kernel verification has attracted much research interest. For example, the L4.verified...

    Provided By University of New Orleans Fund

  • White Papers // Aug 2012

    Application-Managed Replication Controller for Cloud-Hosted Databases

    Data replication is a well-known strategy to achieve the availability, scalability and performance improvement goals in the data management world. However, the cost of maintaining several database replicas always strongly consistent is very high. The CAP theorem shows that a shared-data system can choose at most two out of three...

    Provided By University of New Orleans Fund

  • White Papers // Dec 2011

    On Understanding the Economics and Elasticity Challenges of Deploying Business Applications on Public Cloud Infrastructure

    The exposure of business applications to the web has considerably increased the variability of its workload patterns and volumes as the number of users/customers often grows and shrinks at various rates and times. Such application characteristics have increasingly demanded the need for flexible yet inexpensive computing infrastructure to accommodate variable...

    Provided By University of New Orleans Fund