System Maintenance:
There may be intermittent impact on performance while updates are in progress. We apologize for the inconvenience.
By Topic

Performance, Computing, and Communications Conference, 2000. IPCCC '00. Conference Proceeding of the IEEE International

Date 5-8 Feb. 2000

Filter Results

Displaying Results 1 - 25 of 77
  • Conference Proceedings of the 2000 IEEE International Performance, Computing, and Communications Conference (Cat. No.00CH37086)

    Publication Year: 2000
    Save to Project icon | Request Permissions | PDF file iconPDF (76 KB)  
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2000 , Page(s): ix - x
    Save to Project icon | Request Permissions | PDF file iconPDF (84 KB)  
    Freely Available from IEEE
  • Author index

    Publication Year: 2000 , Page(s): 0_3 - 0_4
    Save to Project icon | Request Permissions | PDF file iconPDF (130 KB)  
    Freely Available from IEEE
  • Constraint adaptive rate allocation scheme for QoS guarantee in packet-switched networks

    Publication Year: 2000 , Page(s): 561 - 566
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (472 KB)  

    Link sharing models and their implementations address various issues for QoS guarantee. As the service requirements of the network applications are diverse in the integrated service networks, it is required to provide differentiated services to the flows according to their flow characteristics, while guaranteeing the worst case performance of QoS. To meet such requirement, the adaptive rate allocation is essential and several researches have been done on that issue. However, in the research, to provide adaptive rates, the different rate allocation policies other than the links sharing policy are applied, which requires an additional runtime packet selection procedure in the system. In addition, the allocation policy uses the status of the flow at the instant, not the characteristics of the flow for the adaptive rate allocation. In this paper, we propose a new server capacity sharing scheme called Constraint Adaptive Rate Allocation (CARA) scheme. By decoupling the runtime rate and the worst case rate for a flow, the CARA scheme provides the differentiated services according to the traffic constraints, while guaranteeing the worst case QoS. As a consequence, the rates are adaptively allocated to the sharing flows according to their QoS constraints View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A model for representing wide area Internet packet behavior

    Publication Year: 2000 , Page(s): 167 - 173
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (520 KB)  

    In this paper an Internet cloud model is presented with the objective of representing Internet packet delay, loss, and out-of-sequence behavior in the wide area network. The main requirements of this model are to capture burstiness and long range dependence in packet delays burstiness of loss periods, and the correlation between network delay, packet loss ratio, and fraction of our-of-sequence packet deliveries. In representing these properties, the underlying assumption is that the dominant component of network traffic in determining delay, loss, and out-of-sequence delivery is FTP and Web traffic with a heavy-tailed file size distribution such as Pareto. Accordingly, in this paper the packet flow in the wide area Internet is modeled as a concatenation of U/Pareto/1 queues. The expected value of the end-to-end delay is obtained simply by an M/G/1 queueing analysis. The long range dependence in packet delays and is illustrated by analyzing the delay traces obtained by simulation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A flexible MAC protocol for all-optical WDM metropolitan area networks

    Publication Year: 2000 , Page(s): 567 - 573
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (484 KB)  

    In a metropolitan sized high-speed Wavelength Division Multiplexed optical network (WDM MAN), Media ACcess (MAC) protocols can only obtain low delay and high performance when reservation based protocols are used. However, reservation protocols limit the maximum number of network nodes. In existing solutions, this limit is either very tight, or the transmission delay is increased to allow more stations. In this paper, a new MAC protocol called Signal-Reservation-Decoupling (SRD) is proposed. SRD is capable of increasing the number of nodes considerably. Transmission delay is kept low by strictly avoiding signal-retransmissions. SRD is message-aware which faciliates transport of higher-level Protocol Data Units (PDUs) like IP datagrams. Directing subsequent packets of a message without interruption improves throughput when tuning times are not neglected View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Communication performance over a gigabit Ethernet network

    Publication Year: 2000 , Page(s): 181 - 189
    Cited by:  Papers (2)  |  Patents (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (736 KB)  

    Cluster computing imposes heavy demands on the communication network. Gigabit Ethernet technology can provide the required bandwidth to meet these demands. However, it has also shifted the communication bottleneck from network media to protocol processing. In this paper, we present an overview of Gigabit Ethernet technology and study the end-to-end Gigabit Ethernet communication bandwidth and latency. Performance graphs are collected using Net Pipe which clearly show the performance characteristics of TCP/IP over Gigabit Ethernet. These indicate the impact of a number of factors such as processor speeds, network adaptors, versions of the Linux Kernel and device drivers, and TCP/IP tuning on the performance of Gigabit Ethernet between two Pentium 11/350 PCs. Among the important conclusions are the marked superiority of the 2.1.121 and later development kernels and 2.2x production kernels of Linux and that the ability to increase the MTU beyond the Ethernet standard of 1500 could significantly enhance the throughput attainable View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Transport architecture for UMTS/IMT-2000 cellular networks

    Publication Year: 2000 , Page(s): 208 - 214
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (540 KB)  

    In this paper we discuss the transport architecture options for the UMTS/IMT-2000, or 3G (3rd Generation), cellular networks. The interfaces between access nodes in a cellular network and the changes incorporated to support packet data services are described. Challenges in selecting one transport technology over another are outlined with reasoning. Requirements to support mobile telephony as well as Internet services in a cellular network are explained. The new ATM standard, ATM Adaptation Layer type 2 (AAL2) and its applicability for transporting compressed speech in an ATM based cellular network is described. A similar approach in IF, multiplexing in Real-Time Transport Protocol (RTP) payload to transport compressed speech on selective interfaces of 3G network, is introduced. Transport network architecture evolution within four different scenarios is evaluated View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Power spectral analysis-based QoS evaluation of VBR video and its application to pricing model

    Publication Year: 2000 , Page(s): 463 - 468
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (756 KB)  

    Since so many potentials of QoS degradation, it is difficult to predict the QoS degradation of VBR MPEG video application under high-speed network environment. The general procedure of the call admission requires the QoS contract between the users and the network. But, various statistical properties of the source traffic and its hard estimation make it difficult to satisfy the QoS contract. In this paper, we propose the measurement-based cell-rate autocorrelation function as the criterion of estimation on QoS degradation. The analysis of the power spectrum of MPEG video with P-MMBBP traffic modeling is ventured. Simulation results show that QoS degradation of the input traffic, particularly delay is closely related to the power spectrum. Furthermore, a new method of the pricing scheme based on the power spectral analysis is proposed and analyzed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hint-based acceleration of Web proxy caches

    Publication Year: 2000 , Page(s): 30 - 37
    Cited by:  Papers (1)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (688 KB)  

    Numerous studies show that proxy cache miss ratios are typically at least 40%-50%. This paper proposes and evaluates a new approach for improving the throughput of proxy caches by reducing cache miss overheads. An embedded system able to achieve significantly better communications performance than a traditional proxy filters the requests directed to a proxy cache, forwarding the hits to the proxy and processing the misses itself. This system, called a Proxy Accelerator, uses hints of the proxy cache content and may include a main memory cache for the hottest objects. Scalability with the Web proxy cluster size is achieved by using several accelerators. We use analytical models and trace-based simulations to study the benefits and the implementation tradeoffs of this new approach. A single proxy accelerator node in front of a four-node Web proxy improves the cost-performance ratio by about 40%. Implementation choices that do not affect the overall hit ratio are available View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A MAC protocol supporting TCP in DS-CDMA PCNs

    Publication Year: 2000 , Page(s): 8 - 14
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (620 KB)  

    A MAC protocol for CDMA PCNs is proposed and studied which is shown to provide a better upper layer performance in the wireless applications. The protocol is based on Preamble Signaling Access which uses a Slotted-ALOHA-like scheme. Markovian chain models are used to analyze the performance of this protocol. Using the modeling, we have provided performance insight comparing the service received by individual user and the whole system under different system configurations. Several performance measures, such as the packet loss, data throughput and data transmission delay are investigated. From the analytical models and simulation results presented in this paper, one can gain interesting insight and useful guidance for incorporating TCP/IP protocol suite into Personal Communication Networks View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Features and utilization of Motorola's advanced INFOSEC machine, AIM, in embedded encryption applications

    Publication Year: 2000 , Page(s): 423 - 429
    Cited by:  Patents (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (676 KB)  

    AIM is a highly flexible, multi-processor Ultra-Large Scale Integration (ULSI) circuit, designed expressly for implementing programmable cryptographic algorithms. It offers a single, embeddable solution for encryption applications, from the most highly classified to commercial, and is exportable. AIM's ability to simultaneously run multiple algorithms on multiple channels enables the reduction of the size, weight and power in scenarios where formerly many discrete crypto devices were used. Features of the AIM ULSI and several current applications are discussed, along with description of other areas where programmable, embeddable cryptography can be used View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance analysis of application response measurement (ARM) version 2.0 measurement agent software implementations

    Publication Year: 2000 , Page(s): 190 - 198
    Cited by:  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (948 KB)  

    Effective distributed application performance management infrastructures are based upon the collection and management of key performance metrics including resource utilization, workload and service measurements. Without application oriented transaction service measurements, the viability and long term usability of the client/server paradigm for mission critical applications is in question. The Application Response Measurement (ARM) Application Programming Interface (API) addresses this requirement by enabling the measurement of transaction level metrics, notably response time, for distributed applications through application code instrumentation. Version 2.0 of the ARM API includes the ability to measure and correlate response time components on different processors (i.e., clients and sewers). ARM Agents encompass the software components responsible for interception and processing of the ARM API calls including support for response time measurement, collection and communication. This paper introduces alternatives for several important design aspects of ARM agent software that are not specified in the ARM standards documents. In particular, we consider the architecture of ARM Agent software, correlator generation and communication, and ARM data storage. We propose, implement and analyze the performance of several alternative designs. This work provides an assessment of ARM instrumentation impact on application response times as well as insights into the design issues involved. We first provide a general overview of the ARM 2.0 API and features. We then consider alternative ARM agent software designs. Next, we present measurements results for several design implementations that shed light on the overhead involved with instrumentation and the developed designs. Finally, we present conclusions and a description of future work View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Move-to-front and transpose hybrid parallel architectures for high-speed data compression

    Publication Year: 2000 , Page(s): 67 - 75
    Cited by:  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (620 KB)  

    We give linear systolic array architectures for self organising linear lists using two hybrids schemes of move-to-front and transpose heuristics, attempting to incorporate the best of both methodologies. The arrays provide input every clock cycle and have a number of processors equal to the length of the list n. This design is then implemented to build high-speed lossless data compression hardware for data communication and storage that have high compression ratio for both small and large files View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application aware scheduling for power management on IEEE 802.11

    Publication Year: 2000 , Page(s): 247 - 253
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (480 KB)  

    Asynchronous medium access protocols, like the MAC of IEEE 802.11, are inherently energy inefficient. Hosts have to continuously listen to the air waiting for packet arrivals. The power management mode of operation of IEEE 802.12 represents a significant improvement, however still has energy inefficiencies due to the one-fits-all policy and the medium access contention. To maximize energy efficiency and user satisfaction, the power management mechanism has to take into account application requirements. Traditional QoS specifications ignore energy consumption, and we argue that all service classes, including best effort, should be subdivided in energy consumption sublevels. We developed an application aware power management mechanism on top of the IEEE 802.12 power management which works on the trade-off between delay and power consumption, and allows per-flow customization View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient rollback recovery algorithm for distributed mobile computing systems

    Publication Year: 2000 , Page(s): 354 - 360
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (544 KB)  

    One major breakthrough on the communication society recently is the extension of networking from wired to wireless networks. This has made possible creating a mobile distributed computing environment and has brought us several new challenges in distributed protocol design. Obviously, wireless networks do have some fundamental differences from wired networks that need to be paid special attention of, such as lower communication bandwidth compared to wired networks, limited electrical power due to battery capacity, and mobility of processes. These new issues make traditional recovery algorithm unsuitable. In order to cope with these problems, the tasks of logging and recovery procedure are performed by the MSSs. In this paper, we propose an efficient algorithm with O(nr) message complexity where O(nr) is the total number of mobile hosts (MHs) related to the failed MH. In addition, these MHs only need to rollback once and can immediately resume its operation without waiting for any coordination message from other MHs. During normal operation, the application message needs O(1) additional information when it transmitted between MHs and mobile support stations (MSSs). Each MSS must keep an ntotal-h*ncell-h dependency matrix, where O(ntotal-h) is the total number of MHs in the system and n,,n h is the total number of MHs in its cell View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent browser initiated server pushing

    Publication Year: 2000 , Page(s): 17 - 23
    Cited by:  Papers (1)  |  Patents (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (644 KB)  

    This paper proposes enhanced browser initiated pushing (BIP) approaches to reduce the download latency for web pages and to improve web server resource utilization. In our BIP approaches, upon receiving a HTTP request, the server actively pushes embedded contents if the permission is given by the client. By means of the pushing mechanism, the HTML web page will be downloaded in one RTT if the embedded contents and the HTML web page are on the same server. The number of requests a web server receives may be reduced significantly and the percentage of HTML documents that may benefit from BIP is quite high. Using trace-driven simulation, this paper presents an evaluation of enhanced BIP approaches that vary in the manner that client cache information is conveyed to the server View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tighten the computation of worst-case execution-time by detecting feasible paths

    Publication Year: 2000 , Page(s): 430 - 436
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (456 KB)  

    The time to compute the Worst-Case Execution-Time (WCET) of a real-time program depends greatly on the technique used to generate paths. A method that is not able to distinguish between executable- and dead-paths could result in overestimation of the WCET. This paper addresses the issues of determining automatically the feasible paths. The algorithm targets the assembly code representation of a super-scalar processor program so that its hardware features can be accounted for during WCET estimation. The method attempts to identify constant values in a real-time program to reduce the amount of user provided information using the concept of partially-known variables View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experiments and evaluation in group work distance learning: the use of Internet collaboration system with `interactive image control' UNIVERSAL CANVAS

    Publication Year: 2000 , Page(s): 314 - 320
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (588 KB)  

    The paper describes: (1) an Internet collaboration system “UNIVERSAL CANVAS” which supports an efficient awareness by `interactive image control'even on narrow band networks; and (2) the experiments and evaluation in group work distance learning to exchange language and cross-cultural communication between Japanese and French students by using UNIVERSAL CANVAS. It explains how the unique features of this system could facilitate the effective use of shared Web pages in a multiparty environment from the view points of location, numbers of people, method of the lecture, and whether with or without interactive image control function View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Advanced generation tool of application's network traffic

    Publication Year: 2000 , Page(s): 471 - 477
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (556 KB)  

    We introduce a new traffic generation and monitoring tool which was developed for performance evaluation of TCP/IP networks. Our tool, called Agent-Ant, supports a number of TCP/IP applications and new applications of future can also be easily included. Agent-Ant supports multiple connections and can measure different traffic characteristics on the application level. The main concepts, the architecture and some performance results of the development of Agent-Ant are described in this paper View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experimental results and evaluation of the proactive application management system (PAMS)

    Publication Year: 2000 , Page(s): 76 - 82
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (676 KB)  

    Management of large-scale network-centric systems (NCS) and their applications is an extremely complex and challenging task due to factors such as centralized management architectures, lack of coordination and compatibility among heterogeneous network management systems, and the dynamic characteristics of networks and application bandwidth requirements, just to name a few. The goal of our research is to develop a hierarchical framework to achieve end-to-end intelligent proactive network management system that can be used to manage large scale network centric systems and their applications. This framework will provide the appropriate tools to write management programs to control and manage any function or property (performance, high assurance, fault, quality of service, etc.) of the network-centric systems and their applications during all the phases of their operations. In this paper, we present a framework to develop proactive and adaptive management services and an implementation of a Proactive Application Management System (PAMS) based on that framework. Our implementation approach utilizes delegated mobile agents to implement the management functions required by any network-centric system and/or application. We also present experimental results and evaluation of the management services offered by the PAMS prototype View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-preemptible locks for a distributed file system

    Publication Year: 2000 , Page(s): 397 - 404
    Cited by:  Patents (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (680 KB)  

    Many applications require the ability to obtain exclusive access to data, where an application is granted privileges to an object that cannot be preempted and limits the actions of other processes. Local file systems support exclusive access to files by maintaining information about the access rights of current open file instances, and checking subsequent opens for compatibility. Implementing exclusive access in this manner for distributed file systems degrades performance by requiring every open file to be registered with a server that maintains global open state. We introduce a distributed lock for managing file access, called a semi-preemptible lock, that avoids this performance limitation. Clients locally grant open requests for files that are consistent with a distributed semipreemptible lock that they hold. File system clients retain or cache distributed locks, even in the absence of open file instances. When a file access lock is already cached, a client services open requests. Without a server message, improving performance by exploiting locality, the affinity of files to clients View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Senddata: an agent for data processing systems using email

    Publication Year: 2000 , Page(s): 264 - 270
    Cited by:  Patents (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (588 KB)  

    People communicate with each other using email with great convenience, but there has been no research effort for utilizing email systems for Data Processing Systems (DPS). A certain class of DPS applications, such as order processing or sales reporting, do not require real-time response, so they may utilize email or protocols that allow delaying or relaying of messages. Lit this paper, we propose two models of DPS that utilize a MTA (Mail Transport Agent) to transport data and data processing commands. We introduce the concept of a DUA (Data User Agent), which we call Senddata, that interacts with a MTA, users, and applications. Our approach helps to reduce certain problems that can occur in DPS, such as overloaded server, heavy traffic on the Internet, and querying a database. We also discuss how these protocols can enhance security by utilizing a three-tier model View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative performance study of a fine-grain multi-threading model on distributed memory machines

    Publication Year: 2000 , Page(s): 590 - 596
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (516 KB)  

    We present a comparative study of the implementation of the Efficient Architecture for Running THreads (EARTH) on IBM SP-2, Beowulf, and the MANNA machine. EARTH is a programming, architecture, and execution model that implements fine grain multi-threading. Each platform presents different constraints on the interaction between the EARTH runtime system and the network. We characterize the performance in each implementation by measuring the cost of EARTH operations, such as the exchange of synchronization signals, the spawning of threads, and data transfers, and also by comparing speedup curves for a set of applications View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new protection model for component-based operating systems

    Publication Year: 2000 , Page(s): 537 - 543
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (672 KB)  

    This paper describes a new model of program protection particularly suited to component-based operating systems. Instead of the traditional separate user and kernel processor modes and paging, segmentation is combined with a simple software technique to avoid the use of separate processor modes while maintaining full protection. This new model offers dramatically improved performance, simplified and improved architectures and increased flexibility. A component-based OS (called Go!) has been implemented using such techniques and early experiences with it are described in this paper. In this paper we show that Go! offers fully protected round-trip RPC in just 85 cycles on the Pentium, and the single processor mode allows the Object Request Broker (Go's analogue of a kernel) to be responsible only for component management. We show that such a system allows multithreading, device management, and even interrupt handling to be provided by separate `application level' components without compromising protection View full abstract»

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