DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Asynchronous broadcast for ordered delivery between compute nodes in a parallel computing system where packet header space is limited

Abstract

Disclosed is a mechanism on receiving processors in a parallel computing system for providing order to data packets received from a broadcast call and to distinguish data packets received at nodes from several incoming asynchronous broadcast messages where header space is limited. In the present invention, processors at lower leafs of a tree do not need to obtain a broadcast message by directly accessing the data in a root processor's buffer. Instead, each subsequent intermediate node's rank id information is squeezed into the software header of packet headers. In turn, the entire broadcast message is not transferred from the root processor to each processor in a communicator but instead is replicated on several intermediate nodes which then replicated the message to nodes in lower leafs. Hence, the intermediate compute nodes become "virtual root compute nodes" for the purpose of replicating the broadcast message to lower levels of a tree.

Inventors:
Issue Date:
Research Org.:
International Business Machines Corp., Armonk, NY (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1176371
Patent Number(s):
7738443
Application Number:
11/768,619
Assignee:
International Business Machines Corporation (Armonk, NY)
Patent Classifications (CPCs):
H - ELECTRICITY H04 - ELECTRIC COMMUNICATION TECHNIQUE H04L - TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
DOE Contract Number:  
B554331
Resource Type:
Patent
Resource Relation:
Patent File Date: 2007 Jun 26
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Kumar, Sameer. Asynchronous broadcast for ordered delivery between compute nodes in a parallel computing system where packet header space is limited. United States: N. p., 2010. Web.
Kumar, Sameer. Asynchronous broadcast for ordered delivery between compute nodes in a parallel computing system where packet header space is limited. United States.
Kumar, Sameer. Tue . "Asynchronous broadcast for ordered delivery between compute nodes in a parallel computing system where packet header space is limited". United States. https://www.osti.gov/servlets/purl/1176371.
@article{osti_1176371,
title = {Asynchronous broadcast for ordered delivery between compute nodes in a parallel computing system where packet header space is limited},
author = {Kumar, Sameer},
abstractNote = {Disclosed is a mechanism on receiving processors in a parallel computing system for providing order to data packets received from a broadcast call and to distinguish data packets received at nodes from several incoming asynchronous broadcast messages where header space is limited. In the present invention, processors at lower leafs of a tree do not need to obtain a broadcast message by directly accessing the data in a root processor's buffer. Instead, each subsequent intermediate node's rank id information is squeezed into the software header of packet headers. In turn, the entire broadcast message is not transferred from the root processor to each processor in a communicator but instead is replicated on several intermediate nodes which then replicated the message to nodes in lower leafs. Hence, the intermediate compute nodes become "virtual root compute nodes" for the purpose of replicating the broadcast message to lower levels of a tree.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2010},
month = {6}
}

Works referenced in this record:

Performance evaluation of adaptive MPI
conference, January 2006

  • Huang, Chao; Zheng, Gengbin; Kalé, Laxmikant
  • Proceedings of the eleventh ACM SIGPLAN symposium on Principles and practice of parallel programming - PPoPP '06
  • https://doi.org/10.1145/1122971.1122976

Overview of the Blue Gene/L system architecture
journal, March 2005


Optimization of MPI collective communication on BlueGene/L systems
conference, January 2005