article

Free access

The VMP network adapter board (NAB): high-performance network communication for multiprocessors

Authors:

D. CheritonAuthors Info & Claims

ACM SIGCOMM Computer Communication Review, Volume 18, Issue 4

Pages 175 - 187

https://doi.org/10.1145/52325.52343

Published: 01 August 1988 Publication History

Abstract

High performance computer communication between multiprocessor nodes requires significant improvements over conventional host-to-network adapters. Current host-to-network adapter interfaces impose excessive processing, system bus and interrupt overhead on a multiprocessor host. Current network adapters are either limited in function, wasting key host resources such as the system bus and the processors, or else intelligent but too slow, because of complex transport protocols and because of an inadequate internal memory architecture. Conventional transport protocols are too complex for hardware implementation and too slow without it.

In this paper, we describe the design of a network adapter board for the VMP multiprocessor machine that addresses these issues. The adapter uses a host interface that is designed for minimal latency, minimal interrupt processing overhead and minimal system bus and memory access overhead. The network adapter itself has a novel internal memory and processing architecture that implements some of the key performance-critical transport layer functions in hardware. This design is integrated with VMTP, a new transport protocol specifically designed for efficient implementation on an intelligent high-performance network adapter. Although targeted for the VMP system, the design is applicable to other multiprocessors as well as uni-processors.

References

[1]

D. R. Cheriton. VMTP: A Versatile Message Transaction Protocol. Technical Report RFC 1045, Defense Advanced Research Projects Agency, February 1988.]]

Digital Library

[2]

D. R. Cheriton and S.E. Deering. Host groups: A multicast Extension for Datagram Intemetworks. In 9th Data Cotmnunication Symposium, IEEE Computer Society and ACM $1GCOMM, September 1985.]]

Digital Library

[3]

D. R. Cheriton, Gert Slavenberg, and Patrick Boyle. Software-Controlled Caches in the VMP Multiprocessor. Technical Report STAN-CS-86-1105, Computer Science Dept., Stanford University, 1986.]]

Digital Library

[4]

D. R. Cheriton and C. L. Williamson. Network Measuxement of the VMTP Request-Response Protocol in the V Distributed System. In ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems, pages 216-225, May 1987.]]

Digital Library

[5]

D. R. Cheriton and W. Zwaenepoel. The Distributed V Kernel and its Performance for Diskless Workstations. In Proceedings of 9th Symposium on Operating Systems Principles, pages 129-140, ACM, October 1983.]]

Digital Library

[6]

G. Chesson Protocol Engine project. Silicon Graphics Incorporated. A talk given at Stanford University, November 12, 1987.]]

[7]

A special issue on computer bus standards. IEEE Micro. IEEE Computer Society, August 1984.]]

[8]

Connection Oriented Transport Protocol. International Standards Organization, 1983. DP 8073.]]

[9]

W. Crowther, J. Goodhue, E. Start, R. Thomas, W. Milkiken, and T. Blakadar. Performance measuxements on a 128-node butterfly paraUel processor. In Proceedings of the 1985 International Conference on Parallel Processing, IEEE Computer Society, August 1985.]]

[10]

W. Daley et al. Architecture of a Message-Driven Processor. In Proceedings of the 14th Annual Intl. Sympositan on Computer Architecture, Pittsburg, PA. June 2-5, 1987.]]

Digital Library

[11]

Draft Proposed American National Standard, FDDI Token Ring Media Access Control - ANSC X3T9.5, 1986.]]

[12]

S, Fraser Universal Receiver Protocol. Internal memorandum. Bell Laboratories, Murray Hill.]]

[13]

Z. Haas and D. R. Cheriton. A Case for Packet-Switching in High-Performance Wide-Area Networks. in Proceedings of SIGCOMM 87 Workshop, Stowe VT, Aug 11-13, 1987.]]

Digital Library

[14]

J. L. Hennessy, N. Jouppi, F. Baskett and J. Gill. MIPS: A VLSI Processor Architecture. In Proc. CMU Conference on VLSI Systems and Computations, October 1981.]]

[15]

H. Kanakia and F. Tobagi. Performance Measurements of a Data Link Protocol. In International Conference on Communications, IEEE, June 22-25 1986.]]

[16]

F.A. Tobagi, F. Borgonova and L. Fratta Express-net: A High-performance Integrated-services Local Area Network. IEEE J. on Selected Areas in Comm., Vol SAC-l, No. 5, Nov. 1983, pp. 898-912.]]

[17]

J. Ousterhout, H. Da Costa, D. Harrison, I. Kunze, M. Kupfer, and J. Thompson. A Trace-driven Analysis of the UNIX 4.2 bscl File System. In Proceedings of the Tenth Symposium on Operating Systems Principles, pages 15-24, December 1985.]]

Digital Library

[18]

A. Spector Multiprocessing Architectures for Local Computer Networks. Technical Report STAN-CS-81-874, Cornpurer Science Dept., Stanford University, 1981.]]

[19]

3C400 Multibus Ethernet Controller: A Reference Manual. 3Corn Corporation, 1985.]]

[20]

DEUNA: User's Guide. Digital Equipment Corp., 1983.]]

[21]

Ethernet Interface: User's Guide. Communications Machinery Corp., 1985.]]

[22]

Excelan 1020: Network Interface- User's Guide. Excelan Corp., Mountain View, Calif., 1985.]]

[23]

SUN-3 Architecture: A Sun Technical Report. SUN Microsystems, Corp., 1985.]]

Cited By

Ishizaka MTsuchida MIdeguchi T(2007)Parallel processing scheme of the received data based on OSI protocolsElectronics and Communications in Japan (Part I: Communications)10.1002/ecja.441074110374:11(26-41)Online publication date: 23-Mar-2007
https://doi.org/10.1002/ecja.4410741103
Houh HAdam JIsmert MLindblad CTennenhouse D(2006)The VuNet desk area networkIEEE Journal on Selected Areas in Communications10.1109/49.38216113:4(710-721)Online publication date: 1-Sep-2006
https://dl.acm.org/doi/10.1109/49.382161
Hariri SPark JParashar MFox G(2006)Communication system for high‐performance distributed computingConcurrency: Practice and Experience10.1002/cpe.43300604046:4(251-270)Online publication date: 25-Oct-2006
https://doi.org/10.1002/cpe.4330060404
Show More Cited By

Index Terms

The VMP network adapter board (NAB): high-performance network communication for multiprocessors

Recommendations

The VMP network adapter board (NAB): high-performance network communication for multiprocessors
SIGCOMM '88: Symposium proceedings on Communications architectures and protocols

High performance computer communication between multiprocessor nodes requires significant improvements over conventional host-to-network adapters. Current host-to-network adapter interfaces impose excessive processing, system bus and interrupt overhead ...
A high performance Inter-VM network communication mechanism
ICA3PP'10: Proceedings of the 10th international conference on Algorithms and Architectures for Parallel Processing - Volume Part I

In virtualization technology domain, researches mainly focus on strengthening the isolation barrier between virtual machines (VMs) that are co-resident within a single physical machine At the same time, there are many kinds of communication intensive ...
High performance network virtualization with SR-IOV

Virtualization poses new challenges to I/O performance. The single-root I/O virtualization (SR-IOV) standard allows an I/O device to be shared by multiple Virtual Machines (VMs), without losing performance. We propose a generic virtualization ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM SIGCOMM Computer Communication Review

ACM SIGCOMM Computer Communication Review Volume 18, Issue 4

August 1988

338 pages

ISSN:0146-4833

DOI:10.1145/52325

Editor:
J. C. Burruss
Bolt Beranek & Newman Inc., Cambridge, MA

Issue’s Table of Contents

SIGCOMM '88: Symposium proceedings on Communications architectures and protocols
August 1988
339 pages
ISBN:0897912799
DOI:10.1145/52324
Editor:
Vinton Cerf
Corporation for National Research Initiatives, Washington, DC

Copyright © 1988 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 August 1988

Published in SIGCOMM-CCR Volume 18, Issue 4

Check for updates

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

124
Total Citations
View Citations
955
Total Downloads

Downloads (Last 12 months)177
Downloads (Last 6 weeks)19

Reflects downloads up to 13 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Ishizaka MTsuchida MIdeguchi T(2007)Parallel processing scheme of the received data based on OSI protocolsElectronics and Communications in Japan (Part I: Communications)10.1002/ecja.441074110374:11(26-41)Online publication date: 23-Mar-2007
https://doi.org/10.1002/ecja.4410741103
Houh HAdam JIsmert MLindblad CTennenhouse D(2006)The VuNet desk area networkIEEE Journal on Selected Areas in Communications10.1109/49.38216113:4(710-721)Online publication date: 1-Sep-2006
https://dl.acm.org/doi/10.1109/49.382161
Hariri SPark JParashar MFox G(2006)Communication system for high‐performance distributed computingConcurrency: Practice and Experience10.1002/cpe.43300604046:4(251-270)Online publication date: 25-Oct-2006
https://doi.org/10.1002/cpe.4330060404
Zeadally SGheorghiu GLevi A(1998)Improving End System Performance for Multimedia Applications over High Bandwidth NetworksMultimedia Technologies and Applications for the 21st Century10.1007/978-0-585-28767-6_10(241-255)Online publication date: 1998
https://doi.org/10.1007/978-0-585-28767-6_10
Zeadally SGheorghiu GLevi A(1997)Throughput optimization for multimedia applications over high speed networksHigh Performance Networking VII10.1007/978-0-387-35279-4_7(101-114)Online publication date: 1997
https://doi.org/10.1007/978-0-387-35279-4_7
Heinrichs BHeinrichs B(1996)LiteraturMultimedia im Netz10.1007/978-3-642-79203-8_8(233-248)Online publication date: 1996
https://doi.org/10.1007/978-3-642-79203-8_8
Dittia ZCox JParulkar G(1995)Design of the APIC: A high performance ATM host-network interface chipProceedings of INFOCOM'9510.1109/INFCOM.1995.515875(179-187)Online publication date: 1995
https://doi.org/10.1109/INFCOM.1995.515875
Morales FAbu-Amara H(1994)Design of a header processor for the PSi implementation of the logical link control protocol in LANsProceedings of 3rd IEEE International Symposium on High Performance Distributed Computing10.1109/HPDC.1994.340235(270-277)Online publication date: 1994
https://doi.org/10.1109/HPDC.1994.340235
Asthana ADelph CJagadish HKrzyzanowski P(1992)Towards a Gigabit IP RouterJournal of High Speed Networks10.5555/2659452.26594531:4(281-288)Online publication date: 1-Oct-1992
https://dl.acm.org/doi/10.5555/2659452.2659453
Alsafadi YMcNeill KMartinez R(1992)Very High Speed Lans for Medical ImagingIEEE Workshop on the Architecture and Implementation of High Performance Communication Subsystems10.1109/HPCS.1992.759213(1-5)Online publication date: 1992
https://doi.org/10.1109/HPCS.1992.759213
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents