Ohio State University

Displaying 1-40 of 163 results

  • White Papers // Dec 2009

    Leveraged Buyouts Of Private Companies

    Over the last two decades, the number (Enterprise value) of leveraged buyout transactions involving privately held targets totals 10,013 ($855 billion), accounting for 46% (21%) of the worldwide leveraged buyout market. Yet the vast majority of academic studies focus on the buyouts of publicly held targets. This paper investigates the...

    Provided By Ohio State University

  • White Papers // May 2010

    Evaluating Caching and Storage Options on the Amazon Web Services Cloud

    With the availability of on-demand compute and storage infrastructures, many users are deploying data-intensive scientific applications onto Clouds. To accelerate these applications, the prospect of caching intermediate data using the Cloud's elastic compute and storage framework has been promising. To this end, the authors believe that an in-depth study of...

    Provided By Ohio State University

  • White Papers // Jan 2011

    Applying MPI Derived Datatypes to the NAS Benchmarks: A Case Study

    MPI derived datatypes are a powerful method to define arbitrary collections of non-contiguous data in memory and to enable non-contiguous data communication in a single MPI function call. In this paper, the authors employs MPI datatypes in four NAS benchmarks (MG, LU, BT, and SP) to transfer non-contiguous data. Comprehensive...

    Provided By Ohio State University

  • White Papers // Aug 2010

    In-Flight Camera Platform Geometric Calibration of the Aerial Multi-Head Camera System

    This paper describes an in-flight camera platform geometric calibration method for aerial multi-head camera systems. The platform calibration parameters express the geometric relationship between camera heads and are estimated by means of a temporal geometric constraint in consecutive frames. The constraint used here is the relative geometry between camera heads...

    Provided By Ohio State University

  • White Papers // May 2010

    3D Reconstruction Using Photo Consistency From Uncalibrated Multiple Views

    This paper presents a new 3D object shape reconstruction approach, which exploits the homography transform and photo consistency between multiple images. The proposed method eliminates the requirement for dense feature correspondences, camera calibration, and pose estimation. Using planar homography, the authors generate a set of planes slicing the object to...

    Provided By Ohio State University

  • White Papers // Jan 2010

    Secure Communications Over Wireless Channels

    This paper presents new techniques that leverage the wireless medium in facilitating secure communications in the presence of eavesdroppers. First, this paper considers the secure transmission of information over an ergodic fading channel with long coherence intervals. The secrecy capacity of such a system is characterized under different assumptions on...

    Provided By Ohio State University

  • White Papers // Oct 2010

    Competitive Nonlinear Pricing And Contract Variety

    The authors analyze markets with both horizontally and vertically differentiated products under both monopoly and duopoly. In the base model with two consumer types, the authors identify conditions under which entry prompts an incumbent to expand or contract its product line. The analysis offers a novel explanation for the widespread...

    Provided By Ohio State University

  • White Papers // Jan 2011

    Advanced RDMA-Based Admission Control for Modern Data-Centers

    Current data-centers employ admission control mechanism to maintain low response time and high throughput under overloaded scenarios. Existing mechanisms use internal (On the overloaded server) or external (On the frontend proxies) admission control approaches. The external admission control is preferred since it can be performed transparently without any modifications to...

    Provided By Ohio State University

  • White Papers // Jul 2009

    An Efficient Hardware-Software Approach to Network Fault Tolerance With InfiniBand

    In the last decade or so, clusters have observed a tremendous rise in popularity due to excellent price to performance ratio. A variety of Interconnects have been proposed during this period, with InfiniBand leading the way due to its high performance and open standard. Increasing size of the InfiniBand clusters...

    Provided By Ohio State University

  • White Papers // Jan 2011

    A Software Based Approach for Providing Network Fault Tolerance in Clusters With UDAPL Interface: MPI Level Design and Performance Evaluation

    In the arena of cluster computing, MPI has emerged as the de facto standard for writing parallel applications. At the same time, introduction of high speed RDMA-enabled interconnects like InfiniBand, Myrinet, Quadrics, RDMA-enabled Ethernet has escalated the trends in cluster computing. Network APIs like uDAPL (user Direct Access Provider Library)...

    Provided By Ohio State University

  • White Papers // Jan 2011

    DDSS: A Low-Overhead Distributed Data Sharing Substrate for Cluster-Based Data-Centers Over Modern Interconnects

    Information-sharing is a key aspect of distributed applications such as database servers and web servers. Information-sharing also assists services such as caching, reconfiguration, etc. In the past, information-sharing has been implemented using ad-hoc messaging protocols which often incur high overheads and are not very scalable. This paper presents a new...

    Provided By Ohio State University

  • White Papers // Jan 2011

    Secret Instantiation in Ad-Hoc Networks

    Security is typically an important issue in wireless ad-hoc networks, including sensor networks, where the communication medium is broadcast in nature and, hence, an adversary can overhear all messages sent by any user. For this reason, a sender must authenticate the receiver and encrypt any messages it sends. One way...

    Provided By Ohio State University

  • White Papers // Jan 2011

    Performance Limits of Greedy Maximal Matching in Multi-Hop Wireless Networks

    In this paper, the authors characterize the performance limits of an important class of scheduling schemes, called Greedy Maximal Matching (GMM), for multi-hop wireless networks. For simplicity, they focus on the well-established node-exclusive interference model, although many of the stated results can be readily extended to more general interference models....

    Provided By Ohio State University

  • White Papers // Jan 2011

    Rate Quantization and the Speedup Required to Achieve 100% Throughput for Multicast Over Crossbar Switches

    The problem of providing quality of service guarantees for multicast traffic over crossbar switches has received a limited attention, despite the popularity of its counterpart for unicast traffic. Providing a 100% throughput to all admissible multicast traffic has been shown to be very difficult task and it requires a very...

    Provided By Ohio State University

  • White Papers // Feb 2010

    Energy Optimal Transmission Scheduling in Wireless Sensor Networks

    One of the main issues in the design of sensor networks is energy efficient communication of time-critical data. Energy wastage can be caused by failed packet transmission attempts at each node due to channel dynamics and interference. Therefore transmission control techniques that are unaware of the channel dynamics can lead...

    Provided By Ohio State University

  • White Papers // Dec 2009

    A Greedy Link Scheduler for Wireless Networks With Gaussian Multiple Access and Broadcast Channels

    Information theoretic Broadcast Channels (BC) and Multiple Access Channels (MAC) enable a single node to transmit data simultaneously to multiple nodes, and multiple nodes to transmit data simultaneously to a single node respectively. In this paper, the authors address the problem of link scheduling in multihop wireless networks containing nodes...

    Provided By Ohio State University

  • White Papers // Jan 2011

    MAGNET: A Tool for Debugging, Analyzing and Adapting Computing Systems

    As computing systems grow in complexity, the cluster and grid communities require more sophisticated tools to diagnose, debug and analyze such systems. The authors have developed a toolkit called MAGNET (Monitoring Apparatus for General kerNel-Event Tracing) that provides a detailed look at operating-system kernel events with very low overhead. Using...

    Provided By Ohio State University

  • White Papers // Jan 2011

    Monitoring Protocol Traffic With a MAGNeT

    Network researchers have traditionally focused on monitoring, measuring, and characterizing traffic in the network to gain insight into building critical network components (e.g., protocol stacks, routers, switches, and network interface cards). Recent research suggests that additional insight can be obtained by monitoring traffic at the application level (i.e., before traffic...

    Provided By Ohio State University

  • White Papers // Aug 2010

    Power-Aware Consolidation of Scientific Workflows in Virtualized Environments

    Use of virtualization technologies is becoming prevalent, including, but not limited to, the current commercial cloud environments. At the same time, besides resources costs and application performance, energy efficiency is becoming a dominant consideration while designing systems and executing applications on them. The premise of the work is that consolidation...

    Provided By Ohio State University

  • White Papers // Aug 2009

    Distributed Cross-Layer Algorithms for the Optimal Control of Multi-hop Wireless Networks

    In this paper, the authors provide and study a general framework that facilitates the development of distributed mechanisms to achieve full utilization of multi-hop wireless networks. In particular, they describe a generic randomized routing, scheduling and flow control scheme that allows for a set of imperfections in the operation of...

    Provided By Ohio State University

  • White Papers // Aug 2009

    A Wireless Security Framework Without Shared Secrets

    This paper develops a framework for wireless security that provides confidentiality, identity authentication, message authentication, integrity, sender non-repudiation, receiver non-repudiation and anonymity. The framework is based on two physical primitives: collaborative jamming and spatial signature enforcement. Notably, it eschews the use of shared secrets, while providing a cryptosystem that is...

    Provided By Ohio State University

  • White Papers // Jul 2010

    RDMA-Based Job Migration Framework for MPI Over InfiniBand

    Coordinated checkpoint and recovery is a common approach to achieve fault tolerance on large-scale systems. The traditional mechanism dumps the process image to a local disk or a central storage area of all the processes involved in the parallel job. When a failure occurs, the processes are restarted and restored...

    Provided By Ohio State University

  • White Papers // Jun 2010

    Improving Application Performance and Predictability Using Multiple Virtual Lanes in Modern Multi-Core InfiniBand Clusters

    Network congestion is an important factor affecting the performance of large scale jobs in supercomputing clusters, especially with the wide deployment of multi-core processors. The blocking nature of current day collectives makes such congestion a critical factor in their performance. On the other hand, modern interconnects like InfiniBand provide one...

    Provided By Ohio State University

  • White Papers // Jul 2010

    High Performance Design and Implementation of Nemesis Communication Layer for Two-Sided and One-Sided MPI Semantics in MVAPICH2

    High End Computing (HEC) systems are being deployed with eight to sixteen compute cores, with 64 to 128 cores/node being envisioned for exascale systems. MVAPICH2 is a popular implementation of MPI-2 specifically designed and optimized for InfiniBand, iWARP and RDMA over Converged Ethernet (RoCE). MVAPICH2 is based on MPICH2 from...

    Provided By Ohio State University

  • White Papers // Aug 2010

    Design and Evaluation of Generalized Collective Communication Primitives With Overlap Using ConnectX-2 Offload Engine

    Collective communication operations provided by the Message Passing Interface (MPI) are heavily used by scientific applications at large scale. The current MPI standard, MPI-2.2, only defines blocking collective communication calls and it is expected that MPI-3 will allow for non-blocking collective communication. While it is possible to allow simultaneous computation...

    Provided By Ohio State University

  • White Papers // Mar 2010

    High Performance Data Transfer in Grid Environment Using GridFTP Over InfiniBand

    GridFTP, designed by using the Globus XIO framework, is one of the most popular methods for performing data transfers in the Grid environment. But the performance of GridFTP in WAN is limited by the relatively low communication bandwidth offered by existing network protocols. On the other hand, modern interconnects such...

    Provided By Ohio State University

  • White Papers // Feb 2010

    An MPI-Stream Hybrid Programming Model for Computational Clusters

    The MPI programming model hides network type and topology from developers, but also allows them to seamlessly distribute a computational job across multiple cores in both an intra and inter node fashion. This provides for high locality performance when the cores are either on the same node or on nodes...

    Provided By Ohio State University

  • White Papers // Mar 2010

    Designing Topology-Aware Collective Communication Algorithms for Large Scale InfiniBand Clusters: Case Studies With Scatter and Gather

    Modern high performance computing systems are being increasingly deployed in a hierarchical fashion with multi-core computing platforms forming the base of the hierarchy. These systems are usually comprised of multiple racks, with each rack consisting of a finite number of chassis, and each chassis having multiple compute nodes or blades,...

    Provided By Ohio State University

  • White Papers // Feb 2010

    Designing High-Performance and Resilient Message Passing on InfiniBand

    Clusters featuring the InfiniBand interconnect are continuing to scale. As an example, the "Ranger" system at the Texas Advanced Computing Center (TACC) includes over 60,000 cores with nearly 4,000 InfiniBand ports. The latest Top500 list shows 30% of systems and over 50% of the top 100 are now using InfiniBand...

    Provided By Ohio State University

  • White Papers // Dec 2009

    Fast Checkpointing by Write Aggregation With Dynamic Buffer and Interleaving on Multicore Architecture

    Large scale compute clusters continue to grow to ever-increasing proportions. However, as clusters and applications continue to grow, the Mean Time Between Failures (MTBF) has reduced from days to hours. As a result, fault tolerance within the cluster has become imperative. MPI, the de-facto standard for parallel programming, is widely...

    Provided By Ohio State University

  • White Papers // Jun 2009

    Designing Efficient FTP Mechanisms for High Performance Data-Transfer Over InfiniBand

    The rapid growth of InfiniBand, 10 Gigabit Ethernet/ iWARP and IB WAN extensions is increasingly gaining momentum for designing high end computing clusters and data-centers. For typical applications such as data staging, content replication and remote site backup etc., FTP has been the most popular method to transfer bulk data...

    Provided By Ohio State University

  • White Papers // Jul 2009

    Designing and Evaluating MPI-2 Dynamic Process Management Support for InfiniBand

    Dynamic process management is a feature of MPI-2 that allows an MPI process to create new processes and manage communication with these processes. The dynamic creation of processes allows application writers to develop multiscale applications or master/worker based programs. Although several MPI implementations support this feature the authors are not...

    Provided By Ohio State University

  • White Papers // Aug 2009

    Design Alternatives for Implementing Fence Synchronization in MPI-2 One-Sided Communication for InfiniBand Clusters

    Scientific computing has seen an immense growth in recent years. The Message Passing Interface (MPI) has become the de-facto standard for parallel programming model for distributed memory systems. As the system scale increases, application writers often try to increase the overlap of computation and communication. The MPI-2 standard expanded MPI...

    Provided By Ohio State University

  • White Papers // Aug 2009

    Reducing Network Contention With Mixed Workloads on Modern Multicore Clusters

    Multi-core systems are now extremely common in modern clusters. In the past commodity systems may have had up to two or four CPUs per compute node. In modern clusters, these systems still have the same number of CPUs, however, these CPUs have moved from single-core to quad-core and further advances...

    Provided By Ohio State University

  • White Papers // Aug 2009

    Designing Next Generation Clusters: Evaluation of InfiniBand DDR/QDR on Intel Computing Platforms

    Clusters based on commodity components continue to be very popular for High-Performance Computing (HPC). These clusters must be careful to balance both computational as well as I/O requirements of applications. This I/O requirement is generally fulfilled by a high-speed interconnect such as InfiniBand. The balance of computational and I/O performance...

    Provided By Ohio State University

  • White Papers // Jan 2011

    Designing NFS With RDMA for Security, Performance and Scalability

    NFS has traditionally used TCP or UDP as the underlying transport. However, the overhead of these stacks has limited both the performance and scalability of NFS. Recently, high-performance network such as InfiniBand have been deployed. These networks provide low latency of a few microseconds and high bandwidth for large messages...

    Provided By Ohio State University

  • White Papers // Jan 2011

    IMCa: A High Performance Caching Front-End for GlusterFS on InfiniBand

    With the rapid advances in computing technology, there is an explosion in media that needs to collected, cataloged, stored and accessed. With the speed of disks not keeping pace with the improvements in processor and network speed, the ability of network file systems to provide data to demanding applications at...

    Provided By Ohio State University

  • White Papers // Jan 2011

    Enhancing the Performance of NFSv4 With RDMA

    NFS is a widely deployed storage technology. It has gone through several revisions. One of the latest revisions, v4 has started to become deployed. NFSv4 on OpenSolaris uses TCP as the underlying transport. This has limited its performance. In this paper, the authors take on the challenge of designing an...

    Provided By Ohio State University

  • White Papers // Jan 2011

    High Performance Virtual Machine Migration With RDMA Over Modern Interconnects

    One of the most useful features provided by Virtual Machine (VM) technologies is the ability to migrate running OS instances across distinct physical nodes. As a basis for many administration tools in modern clusters and data-centers, VM migration is desired to be extremely efficient to reduce both migration time and...

    Provided By Ohio State University

  • White Papers // Mar 2011

    Control of Wireless Networks With Secrecy

    The authors consider the problem of cross-layer resource allocation in time-varying cellular wireless networks, and incorporate information theoretic secrecy as a Quality of Service constraint. Specifically, each node in the network injects two types of traffic, private and open, at rates chosen in order to maximize a global utility function,...

    Provided By Ohio State University