Conference Proceedings of the 2001 IEEE International Performance, Computing, and Communications Conference (Cat. No.01CH37210)

4-6 April 2001

Filter Results

Displaying Results 1 - 25 of 50
  • Conference Proceedings of the 2001 IEEE International Performance, Computing, and Communications Conference (Cat. No.01CH37210)

    Publication Year: 2001
    Request permission for commercial reuse | PDF file iconPDF (414 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 2001, Page(s): 387
    Request permission for commercial reuse | PDF file iconPDF (73 KB)
    Freely Available from IEEE
  • Noah: low-cost file access prediction through pairs

    Publication Year: 2001, Page(s):27 - 33
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (584 KB) | HTML iconHTML

    Prediction is a powerful tool for performance and usability. It can reduce access latency for I/O systems, and can improve usability for mobile computing systems by automating the file hoarding process. We present recent research that has resulted in a file successor predictor that matches the performance of state-of-the-art context-modeling predictors, while requiring a small fraction of their sp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Increasing the accuracy of statistical simulation for modeling superscalar processors

    Publication Year: 2001, Page(s):196 - 204
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (832 KB) | HTML iconHTML

    Statistical simulation is known to be a useful technique to efficiently cull huge design spaces in limited time due to its fast simulation property. Statistical simulation consists of modeling the execution of a computer program by a statistical profile and generating a synthetic trace from it. Current statistical simulation techniques use simple cache statistics producing a flat cache miss behavi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards scalable VoD distribution on the Internet

    Publication Year: 2001, Page(s):71 - 76
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (476 KB) | HTML iconHTML

    Recent advances in the construction of broadcast schedules allow the bandwidth-efficient distribution of Variable Bit Rate (VBR) encoded video. Furthermore, most users are no longer severely limited by their local storage requirements, but are still limited in terms of available bandwidth. We examine an architecture that allows scalable video-on-demand (VoD) delivery, given bandwidth restrictions ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving call admission control in ATM networks using case-based reasoning

    Publication Year: 2001, Page(s):120 - 127
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (680 KB) | HTML iconHTML

    This paper presents a framework for call admission control (CAC) in ATM networks based on case-based reasoning (CBR). CBR is used to correct the error estimation of the required bandwidth computed by conventional call admission control schemes, which were shown to overestimate the required bandwidth. This leads to bandwidth wastage and increased call rejection. A CBR-based system is proposed to ch... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Universal self-stabilizing phase clock protocol with bounded memory

    Publication Year: 2001, Page(s):228 - 235
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB) | HTML iconHTML

    We propose a self-stabilizing K-phase clock protocol which works on uniform tree networks (i.e. without any root). The protocol is self-stabilizing because it guarantees that eventually all clock valve variables will be synchronized and advance in the same value, no matter what the initial state is. It requires (Degu+1)K states by processor u, where Degu is the degree of u; i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Packet marking strategies for Explicit Congestion Notification (ECN)

    Publication Year: 2001, Page(s):17 - 23
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (568 KB) | HTML iconHTML

    The Transmission Control Protocol (TCP) has congestion control mechanisms built into the protocol which reacts to congestion within the network by appropriately adjusting the sending rate of the TCP source. The congestion control mechanisms use packet drops as a means to detect congestion occurring in the network. Unnecessary packet drops lead to poor performance for low-bandwidth delay-sensitive ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TCP Reno with random losses: latency, throughput and sensitivity analysis

    Publication Year: 2001, Page(s):188 - 195
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (644 KB) | HTML iconHTML

    Current models for TCP performance focus mainly on the steady-state throughput of infinite flows, making them inappropriate for the short TCP flows which dominate the transfers over the Internet. We present a model for the latency of finite TCP Reno flows with independent losses for which currently no models exist. The proposed model can also estimate the steady-state throughput of long flows. We ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Configuration of distributed message converter systems using performance modeling

    Publication Year: 2001, Page(s):57 - 67
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (936 KB) | HTML iconHTML

    To find a configuration of a distributed system satisfying performance goals is a complex search problem that involves many design parameters, like hardware selection, job distribution and process configuration. Performance models are a powerful tool to analyse potential system configurations, however, their evaluation is expensive, such that only a limited number of possible configurations can be... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance of adaptive routing strategies in wavelength-routed networks

    Publication Year: 2001, Page(s):163 - 170
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (476 KB) | HTML iconHTML

    As the trend of increased reconfigurability emerges in wavelength division multiplexing (WDM) networks, lightpath establishment would be moved from static toward dynamic regimes. Therefore our interest is in real-time traffic where connection requests arrive dynamically and last for a random holding time if granted. We are concerned with the performance of adaptive routing algorithms in wavelength... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mamba-a programmable broadband multimedia interface board

    Publication Year: 2001, Page(s):281 - 286
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (452 KB) | HTML iconHTML

    The article describes a design approach and hardware implementation for a high speed interface card, capable of transmitting and receiving 216 MBit/sec raw DVB/ATSC data via an asynchronous serial or synchronous parallel interface (ASI/SPI). The local side interface is CompactPCI (CPCI). On-board performance bottlenecks will be largely avoided by utilising the new zero bus turnaround RAM technolog... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Message passing architectures for stochastic and dynamic distributed real time systems

    Publication Year: 2001, Page(s):367 - 372
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (452 KB) | HTML iconHTML

    Distributed real time systems have recently evolved that are based on commodity computers and networking technologies. In these systems, critical system resources and functionality are distributed over many different computers and networks. The operational modes of these systems include the integration of heterogeneous event driven information flows from multiple sensor platforms that dynamically ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real time TCP QoS monitoring in wireless ATM CDMA networks using aggregative large deviation principle

    Publication Year: 2001, Page(s):112 - 119
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (568 KB) | HTML iconHTML

    We present a buffer management scheme called dynamic resource allocation (DRA) that provides TCP traffic control guarantees to virtual channels (VCs) carrying multiple dynamic discard thresholds (MDT) over a wireless ATM network. A major task related to these systems addresses the call admission control and resource management. It is assumed that we have TCP wireless ATM networks integrating the c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TaBLA: a client-based scheduling algorithm for Web proxy clusters

    Publication Year: 2001, Page(s):217 - 227
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (944 KB) | HTML iconHTML

    As client populations in ISPs continue to rise, it becomes necessary far ISP proxy caches to efficiently handle large numbers of Web requests. We examine the performance of client-side load balancing schemes that help select a proxy from an array of proxies that are equidistant from the client. The current most popular solutions include choosing a random proxy based on either the URL requested, or... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cache design and exploration for low power embedded systems

    Publication Year: 2001, Page(s):135 - 139
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB) | HTML iconHTML

    This paper summarizes our work on memory design and exploration for low power data-dominated embedded systems. The memory sub-system consists of an instruction cache and a data cache on-chip, and a large memory off-chip. Our procedure consists of: reducing the power consumption due to memory traffic by applying memory-optimizing loop transformations; and using a memory exploration procedure to cho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • QoS-aware hierarchical multicast routing on next generation internetworks

    Publication Year: 2001, Page(s):9 - 16
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (568 KB) | HTML iconHTML

    Quality of service (QoS) based routing and scalability are two key features of multicast routing for next generation internetworks. The paper proposes a new protocol called QoS-aware hierarchical multicast routing protocol (QHMRP) that achieves scalability by organizing the network as a hierarchy of domains using the full-mesh aggregation technique. The protocol uses a novel reverse flooding appro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fair, efficient and scalable scheduling without per-flow state

    Publication Year: 2001, Page(s):181 - 187
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (584 KB) | HTML iconHTML

    In recent years, parallel computer systems are being increasingly used in multi-user environments, with several users sharing the interconnection network at the same time. As a result a large number frequently contend for link bandwidth at the core switches in the network. Traditional fair scheduling disciplines need to maintain per-flow states and perform packet scheduling on a per-flow basis, wh... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance analysis of dynamic soft real-time systems

    Publication Year: 2001, Page(s):379 - 386
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB) | HTML iconHTML

    Soft real-time processing is real-time processing in which some or all applications are allowed to miss deadlines, particularly in situations of system overload. Resource allocation decisions in such systems are often based in part on specifications of application utility or benefit and directly affect which applications will miss deadlines and by how much. A feedback mechanism is often provided t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Communication delay in circuit-switched interconnection networks

    Publication Year: 2001, Page(s):51 - 56
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (412 KB) | HTML iconHTML

    Interconnection network design plays a central role in the design of parallel systems. The paper presents an analytical model to predict communication delay in circuit-switched k-ary n-cube interconnection networks augmented with virtual channel support. The main feature of the proposed model is the use of Markov chains to compute the path set-up time and to capture the effects of using virtual ch... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Coded path routing: a new approach to broadcasting in 3-D meshes

    Publication Year: 2001, Page(s):155 - 162
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (628 KB) | HTML iconHTML

    Broadcast is an important collective communication operation required by many real-world parallel applications. This paper proposes the coded path routing (or CPR for short) as a new approach for designing efficient broadcast algorithms for wormhole-switched multicomputer networks. A unique feature of the CPR is that a message can be delivered to an arbitrary number of destination nodes with singl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A technique for managing mirrored disks

    Publication Year: 2001, Page(s):272 - 277
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB) | HTML iconHTML

    Disk mirroring is a highly effective technique for improving the fault tolerance and performance of storage systems. Mirroring requires that those disks holding the current data must be determined when recovering from total system failure. In a two disk system, this is only a minor problem since the operator can indicate which disk is current. The complexity increases when more disks are introduce... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Impact of CPU reservation on end-to-end media data transmission

    Publication Year: 2001, Page(s):354 - 361
    Cited by:  Papers (1)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (688 KB) | HTML iconHTML

    Current distributed multimedia applications usually use either best-effort or reservation-based network bandwidth allocation for media data transmission. We argue that end-system CPU reservation also plays an important role in media data transport. We present an analysis of the impact of CPU reservation on media data transmission tasks and its integration with the network bandwidth reservation mec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Traffic characteristics of bulk data transfer using TCP/IP over gigabit Ethernet

    Publication Year: 2001, Page(s):103 - 111
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (772 KB) | HTML iconHTML

    As network data rates scale-up, an understanding of how and why traffic characteristics change is needed. We study the characteristics of bulk data transfer TCP/IP flows in a fully-switched Gigabit Ethernet network. Both disk-to-disk and memory-to-memory transfers are studied. We investigate flow characteristics as a function of link speed, server load, operating system (Linux and WindowsNT), and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison of some numerical methods for QBD-M processes via analysis of an ATM concentrator

    Publication Year: 2001, Page(s):253 - 254
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (160 KB) | HTML iconHTML

    The paper focuses on the numerical efficiency of computational methods for solving QBD-M processes through a performance analysis for an ATM concentrator View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.