Marc Willebeek-LeMair

Strategies for dynamic load balancing on highly parallel computers

Dynamic load balancing strategies for minimizing the execution time of single applications running in parallel on multicomputer systems are discussed. Dynamic load balancing (DLB) is essential for the efficient use of highly parallel systems when solving non-uniform problems with unpredictable load estimates. With the evolution of more highly parallel systems, centralized DLB approaches which make use of a high degree of knowledge become less feasible due to the load balancing communication overhead. Five DLB strategies are presented which illustrate the tradeoff between 1) knowledge - the accuracy of each balancing decision, and 2) overhead - the amount of added processing and communication incurred by the balancing process. All five strategies have been implemented on an Inter iPSC/2 hypercube. >

Videoconferencing over packet-based networks

The Internet explosion is driving the need for new collaboration tools which will enable two or more users to share data, audio, and video. The real-time packet-based solutions which are emerging differ considerably from the circuit-switch solutions which have existed for some time now. In this paper, we present one such packet-based approach, the Multimedia Multiparty Teleconferencing (MMT) system, which was fully implemented as a research prototype. Using MMT as an example, we address some of the fundamental issues related to videoconferencing systems in a packet-based environment, and discuss the differences with the traditional circuit-switch approaches, namely, the ITU H.320 standard. In particular, MMT is a distributed solution, while H.320 is centralized. The use of multicast and a novel video-mixing technique to facilitate the distributed solution are presented. Furthermore, MMT audio and video streams are susceptible to congestion and packet loss in the shared media packet-based environment, while H.320 streams use dedicated connections. As such, synchronization, error resilience, and dynamic rate control schemes for the packet-based system are presented.

On multipoint control units for videoconferencing

This paper examines the issues involved in the design of conference servers that support multiparty, multimedia conferences. These servers, called multipoint control units (MCUs) in the telephony world, coordinate the distribution of audio, video, and data streams amongst the multiple participants in a videoconference. The MCU is responsible for the processing of video and audio so that a conference participant can hear and see one or more of the other participants in the conference. It is also responsible for handling and forwarding the data streams from the participants. This paper presents different approaches to the design of an MCU to implement these functions. It also describes the design of a related device-a transcoding gateway that enables conferencing between participants using different video/audio equipment.<<ETX>>

Distributed video conferencing systems

The emergence of the Internet as a global communications infrastructure has enabled the development of new distributed multiparty video conferencing solutions. These distributed solutions differ considerably from the circuit-switched centralized approaches which preceded them. In this paper we discuss these differences from a general perspective and then describe an actual distributed multiparty solution. The multimedia multiparty teleconferencing (MMT) system implemented at the IBM T.J. Watson Research Center is a high quality video conferencing solution that runs over an IP network. The solution addresses multicast, synchronization, video mixing, error handling, and directory service issues. A detailed description of a solution for secure video conferencing through corporate firewalls is presented.

Bamba: audio and video streaming over the internet

The World Wide Web has become a primary means of disseminating information, which is being presented increasingly through multiple media. The ability to broadcast audio and video information is becoming a reality with the advent of new media-streaming technologies. Most of the emerging streaming systems require high-bandwidth connections in order to deliver audio and video of suitable quality. In this paper we present a media-streaming system, called Bamba, that delivers audio and video over low-bandwidth modem connections with the use of standard compression technologies. Bamba offers high-quality audio and video over low-bit-rate connections and can operate using a standard HTTP server. The Bamba video is enhanced with special provisions for reducing the effect of errors in a Iossy-network environment. Bamba adheres to existing standards wherever possible. Finally, Bamba has been fully implemented and deployed both internally at IBM and externally.

The sink tree paradigm: connectionless traffic support on ATM LAN's

Asynchronous transfer mode (ATM) is a connection-oriented technology in which all communication is based on virtual connections established prior to the transfer of data. It is expected that the bulk of traffic carried by the ATM network will be data traffic, e.g., local area network (LAN) internetwork traffic. Hence, a major issue regarding ATM is the support for connectionless (datagram) traffic. A scheme for the efficient support for connectionless traffic in ATM LANs based on trees of virtual connections is proposed. In this scheme, a sink tree is built for every switch in the LAN. Each tree provides an efficient means of routing connectionless traffic from any switch in the network to the sink switch (root) of the tree. The sink tree solution may also be used to broadcast connectionless messages in the reverse direction. The trees can easily be updated to adapt to topological changes or congestion in the network. A protocol for refreshing the tree structure using the ATM switch routing tables is described. An adaptive rate control solution, in conjunction with fast back pressure at the ATM layer, is presented. It is shown that this scheme achieves high utilization of available bandwidth for connectionless traffic, has low cell loss probability, and small overhead.

Efficient adaptive media scaling and streaming of layered multimedia in heterogeneous environment

The fast increasing network connectivities to a wider range of end-users and cheaper and diverse end-user devices further exacerbate the need for adaptive and scalable streaming solutions. Motivated by these streaming requirements, we introduce the notion of a layered multimedia presentation and outline a framework for the media scaling and streaming of such presentations across heterogeneous networks to different end-user devices. Layered multimedia is designed to handle heterogeneous and fluctuating resource conditions by trading-off the presentation quality. Based on the results of streaming buffer effects, an efficient on-demand media scaling technique is devised to deliver the highest quality presentation to the end-users, according to their specific network bandwidth and device constraints. Once a presentation is selected, an associated on-the-fly transmission scheduling and streaming technique is used for the streaming of multimedia with high efficiency. Efficient media scaling and streaming reduce startup and quality switch delays and facilitates scalable media server design under heavy loads.

Robust H.263 video coding for transmission over the Internet

The widely popular World Wide Web along with advances in desktop computers has brought the world into a new age of computing and communications. Low bit-rate video applications across the Internet are quickly emerging. The ITU-T H.263 standard was designed for low bit-rate video conferencing across phone lines and is an ideal candidate to be extended for Internet video applications. This paper focuses on the error robustness issue of compressed H.263 video streams when transmitted over the Internet. The traditional approach of inserting intra-coded frames increases the error resilience at the expense of bursty output traffic, lower picture quality, and uneven frame dropping. By extending the macroblock force update feature of the H.263 standard, we developed a scheme that complies with the standard and increases the robustness of the video stream. This macroblock updating scheme analyzes the temporal dependencies of macroblocks in successive frames and selectively updates the macroblocks which have the most impact on later frames. The performance evaluation of the proposed technique demonstrates that it achieves a good balance between error recovery speeds and video quality.

Approximating dependability measures of computer networks: an FDDI case study

An approximation technique is presented to evaluate the dependability of FDDI networks. This technique, based on the most likely paths to failure concept, is simple and practical. It may be applied easily to evaluate and compare the dependability of different FDDI network configurations. The effects of various network parameters on the network availability are examined. We conclude that, in order to guarantee high availability, an FDDI network backbone should be interconnected using dual-attachment concentrators. Furthermore, dual-homing configurations are required for high-availability paths between end stations and the backbone. For less stringent availability requirements, single-attachment concentrator trees with single attachment stations may suffice. We also discuss how the technique may be extended easily to more general heterogeneous networks including Token Ring and Ethernet.

A video conferencing testbed on ATM: design, implementation and optimizations

This paper describes our experiences with the design and implementation of a very high-end video conferencing testbed on an ATM network. Our system is built on an IBM RISC System/6000 equipped with prototype hardware for video and audio capture and compression, and an IBM 100 Mb/s ATM adapter. In our early experiments we used UDP/IP running over ATM Adaptation Layer 5 (AAL5) for data transfer between peers. Our initial experiences with the system indicated that the overall system performance did not match our expectations even though most of the video, audio, and network processing was performed in hardware. A thorough profiling of the system revealed that the protocol processing and data handling overheads in the end-host are responsible for the poor video/audio quality. Based on these observations, we have proposed and implemented changes to the protocol data path that can significantly improve the performance of the system. Although we discuss our solution in the context of a video conferencing application, our approach is general and can be applied to many other applications. It is particularly useful for applications that are required to handle large volumes of time-critical data, such as multimedia servers.