skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: H-network-a high speed distributed packet switching local computer network

Abstract

The h-network is a high-speed distributed local computer network designed to facilitate user interaction and control of the homogeneous multiprocessor. The topology of the network and its access protocol are discussed. Performance measures based on analysis of the protocol and the hardware used are presented. 3 references.

Authors:
;
Publication Date:
OSTI Identifier:
5198201
Alternate Identifier(s):
OSTI ID: 5198201
Resource Type:
Conference
Resource Relation:
Conference: Sponsored by IEEE, Athens, Greece, 24 May 1983
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; COMPUTER NETWORKS; ARCHITECTURE; PERFORMANCE; ARRAY PROCESSORS; DISTRIBUTED DATA PROCESSING; TOPOLOGY; DATA PROCESSING; MATHEMATICS; PROCESSING 990200* -- Mathematics & Computers

Citation Formats

Dimopoulos, N., and Kehayas, D. H-network-a high speed distributed packet switching local computer network. United States: N. p., 1983. Web.
Dimopoulos, N., & Kehayas, D. H-network-a high speed distributed packet switching local computer network. United States.
Dimopoulos, N., and Kehayas, D. Sat . "H-network-a high speed distributed packet switching local computer network". United States. doi:.
@article{osti_5198201,
title = {H-network-a high speed distributed packet switching local computer network},
author = {Dimopoulos, N. and Kehayas, D.},
abstractNote = {The h-network is a high-speed distributed local computer network designed to facilitate user interaction and control of the homogeneous multiprocessor. The topology of the network and its access protocol are discussed. Performance measures based on analysis of the protocol and the hardware used are presented. 3 references.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sat Jan 01 00:00:00 EST 1983},
month = {Sat Jan 01 00:00:00 EST 1983}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • This paper proposes a high throughput packet switching network with bypass queues based on a MIN. We improve the switch throughput by partitioning the input buffers into disjoint buffer sets and multiplexing several sets of nonblocking packets within a time slot. A neural network model is presented as a controller for packet scheduling and multiplexing in the switch.
  • The paper describes a concept for implementing a combined data collecting, control and trigger system for Large Hadron Collider experiments at CERN. The system, called SWIPP, is based on a flexible interconnection of fast crossbar switches, interfaced to various transducer, storage and computer nodes by Protocol Engines. This infrastructure offers a common framework for various kinds of information, being programmable and scalable in an easy way. It endeavors to solve the extremely demanding instrumentation needs of these experiments in particle physics.
  • As network bandwidth continues to grow and longer paths are used to exchange large scientific data between storage systems and GRID computation, it has become increasingly obvious that there is a need to deploy a packet drop avoidance mechanism into network transmission protocols. Current end-to-end congestion avoidance mechanisms used in Transmission Control Protocol (TCP) have worked well on low bandwidth delay product networks, but with newer high-bandwidth delay networks they have shown to be inefficient and prone to unstable. This is largely due to increased network bandwidth coupled with changes in internet traffic patterns. These changes come from a varietymore » of new network applications that are being developed to take advantage of the increased network bandwidth. This paper will examine the end-to-end congestion avoidance mechanism and perform a step-by-step analysis of its theory. In addition we will propose an alternative approach developed as part of a new network transmission protocol. Our alternative protocol uses a packet drop avoidance (PDA) mechanism built on top of the maximum burst size (MBS) theory combined with a real-time available bandwidth algorithm.« less
  • The Multiple Crossbar Network (MCN) is a prototype High-Speed Local Network at the Los Alamos National Laboratory. It will interconnect supercomputers, network servers and workstations from various commercial vendors. The MCN can also serve as a backbone for message traffic between local area networks. The MCN is a switched local network of switching nodes called Cross-Point Stars (CPs). Hosts and CPs are connected by 800-Mbit/s (100-Mbyte/s) point-to-point ANSI High-Speed Channels. CPs include RISC-based network protocol processors called Crossbar Interfaces and a switching core called the Crossbar Switch. Protocols include physical, data link, intranet, and network access functionality. Various internet andmore » transport protocols are intended to run above the MCN protocol suite. A network management and simple naming service is also included within the Los Alamos Network Architecture. Immediate applications include visualization. The MCN is intended to also serve as a framework for multicomputer applications. 36 refs., 10 figs.« less
  • Visapult is a prototype application and framework for remote visualization of large scientific datasets. We approach the technical challenges of tera-scale visualization with a unique architecture that employs high speed WANs and network data caches for data staging and transmission. This architecture allows for the use of available cache and compute resources at arbitrary locations on the network. High data throughput rates and network utilization are achieved by parallelizing I/O at each stage in the application, and by pipe-lining the visualization process. On the desktop, the graphics interactivity is effectively decoupled from the latency inherent in network applications. We presentmore » a detailed performance analysis of the application, and improvements resulting from field-test analysis conducted as part of the DOE Combustion Corridor project.« less