Communication and Architectural Support for Network-Based Parallel Computing

1. Front Matter

   PDF

2. Efficient communication mechanisms for cluster based parallel computing

   • Al Davis, Mark Swanson, Mike Parker

   Pages 1-15

3. Stream sockets on SHRIMP

   • Stefanos N. Damianakis, Cezary Dubnicki, Edward W. Felten

   Pages 16-30

4. A simple and efficient process and communication abstraction for network operating systems

   • David C. DiNucci

   Pages 31-45

5. Efficient adaptive routing in networks of workstations with irregular topology

   • F. Silla, M. P. Malumbres, A. Robles, P. López, J. Duato

   Pages 46-60

6. A deadlock avoidance method for computer networks

   • Bulent Abali

   Pages 61-72

7. Extending ATM networks for efficient reliable multicast

   • Jonathan S. Turner

   Pages 73-87

8. ATLAS I: A single-chip ATM switch for NOWs

   • Manolis G. H. Katevenis, Dimitrios Serpanos, Panagiota Vatsolaki, Evangelos Markatos

   Pages 88-101

9. Arachne: A portable threads library supporting migrant threads on heterogeneous network farms

   • Bozhidar Dimitrov, Vernon Rego

   Pages 102-114

10. Transparent treatment of remote pointers using IPC primitive in RPC systems

    • Shik Kim, Muyong Hyun, Sangjo Lee

    Pages 115-129

11. An Operating System support to low-overhead communications in NOW clusters

    • P. Marenzoni, G. Rimassa, M. Vignali, M. Bertozzi, G. Conte, P. Rossi

    Pages 130-143

12. Distributed hardware support for process synchronization in NSM workstation clusters

    • Jordan Bonney, Ranga Ramanujan, Atiq Ahamad, Siddhartha Takkella, Kenneth Thurber

    Pages 144-157

13. Synchronization support in I/O adapter based SCI clusters

    • Knut Omang

    Pages 158-172

14. Load balancing for regular data-parallel applications on workstation network

    • Maher Kaddoura

    Pages 173-183

15. A comparison of three high speed networks for parallel cluster computing

    • Henri Bal, Rutger Hofman, Kees Verstoep

    Pages 184-197

16. Understanding the performance of DSM applications

    • Wagner Meira Jr., Thomas J. LeBlanc, Nikolaos Hardavellas, Cláudio Amorim

    Pages 198-211

17. Performance metrics and measurement techniques of collective communication services

    • Natawut Nupairoj, Lionel M. Ni

    Pages 212-226

18. CLAM: Connection-less, Lightweight, and Multiway communication support for distributed computing

    • Juan Carlos Gomez, Vernon Rego, Vaidy Sunderam

    Pages 227-240

19. Network-wide cooperative computing architecture (NCCA)

    • Hiroyuki Yamashita, Toshihiko Suguri, Shingo Kinoshita, Yasushi Okada

    Pages 241-255

20. Data movement and control substrate for parallel scientific computing

    • Nikos Chrisochoides, Induprakas Kodukula, Keshav Pingali

    Pages 256-268

This book constitutes the refereed proceedings of the First International Workshop on Communication and Architectural Support for Network-Based Parallel Computing, CANPC'97, held in San Antonio, Texas, USA, in February 1997.
The 19 revised full papers presented were carefully selected from a total of 36 submissions. Among the topics addressed are processor/network interfaces, communication protocols, high-performance network technology, operating systems and architectural issues, and load balancing techniques. All in all, the papers competently describe the state-of-the-art for network-based computing systems.

• Kommunikationsprotokolle
• Lastenausgleich
• Netzwerkarchitektur
• Prozessor/Netzwerk-Schnittstelle
• Workstation-Clusters
• communication protocols
• load balancing
• network architecture
• operating system
• processor/network interface
• workstation clusters

Policies and ethics