We arehappy to welcome you to the IFIP Protocols for High-Speed Networks '96 workshop hosted by INRIA Sophia Antipolis. This is the fifth event in a series initiated in Zurich in 1989 followed by Palo Alto (1990), Stockholm (1993), and Vancouver (1994). This workshop provides an international forum for the exchange of information on protocols for high-speed networks. The workshop focus on problems related to the e:fficient transmission of multimedia application data using high-speed networks and internetworks. Protocol for High-Speed Networks is a "working conference". That explains we have privileged high quality papers describing on-going research and novel ideas. The number of selected papers was kept low in order to leave room for discussion on each paper. Together with the technical sessions, working sessions were organized on hot topics. We would like to thank all the authors for their interest. We also thank the Program Committee members for the Ievel of effort in the reviewing process and in the workshop technical program organization. We finally thank INRIA and DRET for their financial support to the organization of the workshop.

1 This year marks the l0 h anniversary of the IFIP International Workshop on Protocols for High-Speed Networks (PfHSN). It began in May 1989, on a hillside overlooking Lake Zurich in Switzerland, and arrives now in Salem Massachusetts 6,000 kilometers away and 10 years later, in its sixth incarnation, but still with a waterfront view (the Atlantic Ocean). In between, it has visited some picturesque views of other lakes and bays of the world: Palo Alto (1990 - San Francisco Bay), Stockholm (1993 - Baltic Sea), Vancouver (1994- the Strait of Georgia and the Pacific Ocean), and Sophia Antipolis I Nice (1996- the Mediterranean Sea). PfHSN is a workshop providing an international forum for the exchange of information on high-speed networks. It is a relatively small workshop, limited to 80 participants or less, to encourage lively discussion and the active participation of all attendees. A significant component of the workshop is interactive in nature, with a long history of significant time reserved for discussions. This was enhanced in 1996 by Christophe Diot and W allid Dabbous with the institution of Working Sessions chaired by an "animator," who is a distinguished researcher focusing on topical issues of the day. These sessions are an audience participation event, and are one of the things that makes PfHSN a true "working conference.

Welcome to the fourth IFIP workshop on protocols for high speed networks in Vancouver. This workshop follows three very successful workshops held in Ziirich (1989), Palo Alto (1990) and Stockholm (1993) respectively. We received a large number of papers in response to our call for contributions. This year, forty papers were received of which sixteen were presented as full papers and four were presented as poster papers. Although we received many excellent papers the program committee decided to keep the number of full presentations low in order to accommodate more discussion in keeping with the format of a workshop. Many people have contributed to the success of this workshop including the members of the program committee who, with the additional reviewers, helped make the selection of the papers. We are thankful to all the authors of the papers that were submitted. We also thank several organizations which have contributed financially to this workshop, specially NSERC, ASI, CICSR, UBC, MPR Teltech and Newbridge Networks.

This workshop on “Protocols for High-Speed Networks” is the seventh in a s- cessful series of international workshops, well known for their small and focused target audience, that provide a sound basis for intensive discussions of hi- qualityand timelyresearch work. The location of the workshop has alternated between Europe and the United States, at venues not onlyworth visiting for the workshop, but also for the distinct impressions theyleave on the participants. The ?rst workshop was held in 1989 in Zurich. Subsequentlythe workshop was moved to Palo Alto (1990), Stockholm (1993), Vancouver (1994), Sophia-Antipolis/Nice (1996), and Salem (1999). In 2002, the workshop was hosted in Berlin, the capital of Germany. PfHSN is a workshop providing an international forum that focuses on issues related to high-speed networking, such as protocols, implementation techniques, router design, network processors and the like. Although the topics have shifted during the last couple of years, for example, from parallel protocol implemen- tions to network processors, it could be observed that high speed remains a very important issue with respect to future networking. Traditionally, PfHSN is a r- ativelyfocused and small workshop with an audience of about 60 participants.

TriComm '92 was the fifth in the series of Research Triangle conferences on Computer Communications. This series emerged from a need to provide a forum for the people who are actively involved in Research and Development in the Research Triangle area in which they could present and discuss new ideas in Computer Communications. TriComm '92 was dedicated to High Speed networks. In particular, the program was developed around the following themes: local ATM, preventive and reactive congestion control. routing. transport protocols. traffic measurements, software engineering for telecommunication systems. and standards. I would like to thank all the speakers who agreed to present a paper. and the members of the program committee who patiently refereed the papers despite their busy schedules. I would also like to thank Mr. Ed Bowen, IBM, Research Triangle Park, for covering the expenses for the preparation of the pre-conference proceedings. and Dr. Raif Onvural. IBM, Research Triangle Park, for overseeing the photocopying of the proceedings. I would also like to thank my "Guardian Angel" Ms. Margaret Hudacko. Center for Communications and Signal Processing. State University, who made all the local arrangements. North Carolina Without her help, this conference would have been a complete disaster. Many thanks also go to Norene Miller. Center for Communications and Signal Processing. North Carolina State University. Finally. I would like to thank Mr. Charles Lord, Eastern NC Chapter of the IEEE Communications SOCiety. for providing us with mailing lists.

As the speed of networks increase, users expect to deliver high bandwidth to their applications. There is much debate in the research community over the choice of protocols for these new networks. Discussion about new protocol architectures remains at center stage in the research community even as the user community continues to standardize protocols such as Asynchronous Transfer Mode (ATM). New transport protocols as well as resource management mechanisms are being designed to support real time multimedia applications on gigabit networks. This volume focuses on state-of-the-art protocol design and efficienct implementation techniques, interfacing high speed networks to high performance host computers and ATM as a protocol for high speed networks.

Leading authorities deliver the commandments for designing high-speed networks There are no end of books touting the virtues of one or another high-speed networking technology, but until now, there were none offering networking professionals a framework for choosing and integrating the best ones for their organization's networking needs. Written by two world-renowned experts in the field of high-speed network design, this book outlines a total strategy for designing high-bandwidth, low-latency systems. Using real-world implementation examples to illustrate their points, the authors cover all aspects of network design, including network components, network architectures, topologies, protocols, application interactions, and more.

In the last few years, the world of information networks has undergone significant changes that will revolutionize the future of communications. Data rates have reached the gigabit per second range. Optical fibers have become the transmission medium of choice. Standardization activities have very aggressively produced a set of well established standard for future LANs, MANs and WANs. It has become very difficult for computer and communications professionals to follow these rapidly evolving technologies and standards. High Performance Networks: Technology and Protocols provides a timely technical overview of the start-of-the-art in high performance networking. Chapters cover lightweight protocols, high performance protocol implementation techniques, high speed MAC protocols, optical networks, as well as emerging standards, including ATM, SMDS, B-ISDN, SONET, FCS and HIPPI. Professionals, engineers, and researchers in communications and computers, who need to understand the underlying technologies of high performance (gigabit) networks, will find this volume to be an invaluable reference. The book is also suitable for use as a text for advanced courses on the subject.

Multimedia data streams will form a major part of the new generation of applications in high-speed networks. Continuous media streams, however, require transmission with guaranteed performance. In addition, many multimedia applications will require peer-to-multipeer communication. Guaranteed performance can only be provided with resource reservation in the network, and efficient multipeer communication must be based on multicast support in the lower layers of the network. Architecture and Protocols for High-Speed Networks focuses on techniques for building the networks that will meet the needs of these multimedia applications. In particular two areas of current research interest in such communication systems are covered in depth. These are the protocol related aspects, such as switched networks, ATM, MAC layer, network and transport layer; and the services and applications. Architecture and Protocols for High-Speed Networks contains contributions from leading world experts, giving the most up-to-date research available. It is an essential reference for all professionals, engineers and researchers working in the area of high-speed networks.

Communication protocols form the operational basis of computer networks and telecommunication systems. They are behavior conventions that describe how communication systems interact with each other, defining the temporal order of the interactions and the formats of the data units exchanged – essentially they determine the efficiency and reliability of computer networks. Protocol Engineering is an important discipline covering the design, validation, and implementation of communication protocols. Part I of this book is devoted to the fundamentals of communication protocols, describing their working principles and implicitly also those of computer networks. The author introduces the concepts of service, protocol, layer, and layered architecture, and introduces the main elements required in the description of protocols using a model language. He then presents the most important protocol functions. Part II deals with the description of communication protocols, offering an overview of the various formal methods, the essence of Protocol Engineering. The author introduces the fundamental description methods, such as finite state machines, Petri nets, process calculi, and temporal logics, that are in part used as semantic models for formal description techniques. He then introduces one representative technique for each of the main description approaches, among others SDL and LOTOS, and surveys the use of UML for describing protocols. Part III covers the protocol life cycle and the most important development stages, presenting the reader with approaches for systematic protocol design, with various verification methods, with the main implementation techniques, and with strategies for their testing, in particular with conformance and interoperability tests, and the test description language TTCN. The author uses the simple data transfer example protocol XDT (eXample Data Transfer) throughout the book as a reference protocol to exemplify the various description techniques and to demonstrate important validation and implementation approaches. The book is an introduction to communication protocols and their development for undergraduate and graduate students of computer science and communication technology, and it is also a suitable reference for engineers and programmers. Most chapters contain exercises, and the author's accompanying website provides further online material including a complete formal description of the XDT protocol and an animated simulation visualizing its behavior.