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

Title: Performing an allreduce operation on a plurality of compute nodes of a parallel computer

Abstract

Methods, apparatus, and products are disclosed for performing an allreduce operation on a plurality of compute nodes of a parallel computer. Each compute node includes at least two processing cores. Each processing core has contribution data for the allreduce operation. Performing an allreduce operation on a plurality of compute nodes of a parallel computer includes: establishing one or more logical rings among the compute nodes, each logical ring including at least one processing core from each compute node; performing, for each logical ring, a global allreduce operation using the contribution data for the processing cores included in that logical ring, yielding a global allreduce result for each processing core included in that logical ring; and performing, for each compute node, a local allreduce operation using the global allreduce results for each processing core on that compute node.

Inventors:
 [1]
  1. Rochester, MN
Publication Date:
Research Org.:
International Business Machines Corporation (Armonk, NY)
Sponsoring Org.:
USDOE
OSTI Identifier:
1040781
Patent Number(s):
8,161,268
Application Number:
12/124,756
Assignee:
International Business Machines Corporation (Armonk, NY) OSTI
DOE Contract Number:  
B554331
Resource Type:
Patent
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Faraj, Ahmad. Performing an allreduce operation on a plurality of compute nodes of a parallel computer. United States: N. p., 2012. Web.
Faraj, Ahmad. Performing an allreduce operation on a plurality of compute nodes of a parallel computer. United States.
Faraj, Ahmad. Tue . "Performing an allreduce operation on a plurality of compute nodes of a parallel computer". United States. https://www.osti.gov/servlets/purl/1040781.
@article{osti_1040781,
title = {Performing an allreduce operation on a plurality of compute nodes of a parallel computer},
author = {Faraj, Ahmad},
abstractNote = {Methods, apparatus, and products are disclosed for performing an allreduce operation on a plurality of compute nodes of a parallel computer. Each compute node includes at least two processing cores. Each processing core has contribution data for the allreduce operation. Performing an allreduce operation on a plurality of compute nodes of a parallel computer includes: establishing one or more logical rings among the compute nodes, each logical ring including at least one processing core from each compute node; performing, for each logical ring, a global allreduce operation using the contribution data for the processing cores included in that logical ring, yielding a global allreduce result for each processing core included in that logical ring; and performing, for each compute node, a local allreduce operation using the global allreduce results for each processing core on that compute node.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2012},
month = {4}
}

Patent:

Save / Share: