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

Title: Optimized scalable network switch

Abstract

In a massively parallel computing system having a plurality of nodes configured in m multi-dimensions, each node including a computing device, a method for routing packets towards their destination nodes is provided which includes generating at least one of a 2m plurality of compact bit vectors containing information derived from downstream nodes. A multilevel arbitration process in which downstream information stored in the compact vectors, such as link status information and fullness of downstream buffers, is used to determine a preferred direction and virtual channel for packet transmission. Preferred direction ranges are encoded and virtual channels are selected by examining the plurality of compact bit vectors. This dynamic routing method eliminates the necessity of routing tables, thus enhancing scalability of the switch.

Inventors:
 [1];  [2];  [3]
  1. (Ridgefield, CT)
  2. (Croton on Hudson, NY)
  3. (Yorktown Heights, NY)
Publication Date:
Research Org.:
International Business Machines Corporation (Armonk, NY)
Sponsoring Org.:
USDOE
OSTI Identifier:
1014155
Patent Number(s):
7,668,970
Application Number:
US Patent Application 11/868,223
Assignee:
International Business Machines Corporation (Armonk, NY) OAK
DOE Contract Number:  
W-7405-ENG-48
Resource Type:
Patent
Country of Publication:
United States
Language:
English

Citation Formats

Blumrich, Matthias A., Chen, Dong, and Coteus, Paul W. Optimized scalable network switch. United States: N. p., 2010. Web.
Blumrich, Matthias A., Chen, Dong, & Coteus, Paul W. Optimized scalable network switch. United States.
Blumrich, Matthias A., Chen, Dong, and Coteus, Paul W. Tue . "Optimized scalable network switch". United States. https://www.osti.gov/servlets/purl/1014155.
@article{osti_1014155,
title = {Optimized scalable network switch},
author = {Blumrich, Matthias A. and Chen, Dong and Coteus, Paul W.},
abstractNote = {In a massively parallel computing system having a plurality of nodes configured in m multi-dimensions, each node including a computing device, a method for routing packets towards their destination nodes is provided which includes generating at least one of a 2m plurality of compact bit vectors containing information derived from downstream nodes. A multilevel arbitration process in which downstream information stored in the compact vectors, such as link status information and fullness of downstream buffers, is used to determine a preferred direction and virtual channel for packet transmission. Preferred direction ranges are encoded and virtual channels are selected by examining the plurality of compact bit vectors. This dynamic routing method eliminates the necessity of routing tables, thus enhancing scalability of the switch.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2010},
month = {2}
}

Patent:

Save / Share: