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

Title: Methods, apparatus and system for selective duplication of subtasks

Abstract

A method for selective duplication of subtasks in a high-performance computing system includes: monitoring a health status of one or more nodes in a high-performance computing system, where one or more subtasks of a parallel task execute on the one or more nodes; identifying one or more nodes as having a likelihood of failure which exceeds a first prescribed threshold; selectively duplicating the one or more subtasks that execute on the one or more nodes having a likelihood of failure which exceeds the first prescribed threshold; and notifying a messaging library that one or more subtasks were duplicated.

Inventors:
; ; ; ;
Issue Date:
Research Org.:
International Business Machines Corp., Armonk, NY (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1244231
Patent Number(s):
9,298,553
Application Number:
14/176,083
Assignee:
International Business Machines Corporation (Armonk, NY)
DOE Contract Number:  
B599858
Resource Type:
Patent
Resource Relation:
Patent File Date: 2014 Feb 08
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; 99 GENERAL AND MISCELLANEOUS

Citation Formats

Andrade Costa, Carlos H., Cher, Chen-Yong, Park, Yoonho, Rosenburg, Bryan S., and Ryu, Kyung D. Methods, apparatus and system for selective duplication of subtasks. United States: N. p., 2016. Web.
Andrade Costa, Carlos H., Cher, Chen-Yong, Park, Yoonho, Rosenburg, Bryan S., & Ryu, Kyung D. Methods, apparatus and system for selective duplication of subtasks. United States.
Andrade Costa, Carlos H., Cher, Chen-Yong, Park, Yoonho, Rosenburg, Bryan S., and Ryu, Kyung D. Tue . "Methods, apparatus and system for selective duplication of subtasks". United States. https://www.osti.gov/servlets/purl/1244231.
@article{osti_1244231,
title = {Methods, apparatus and system for selective duplication of subtasks},
author = {Andrade Costa, Carlos H. and Cher, Chen-Yong and Park, Yoonho and Rosenburg, Bryan S. and Ryu, Kyung D.},
abstractNote = {A method for selective duplication of subtasks in a high-performance computing system includes: monitoring a health status of one or more nodes in a high-performance computing system, where one or more subtasks of a parallel task execute on the one or more nodes; identifying one or more nodes as having a likelihood of failure which exceeds a first prescribed threshold; selectively duplicating the one or more subtasks that execute on the one or more nodes having a likelihood of failure which exceeds the first prescribed threshold; and notifying a messaging library that one or more subtasks were duplicated.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2016},
month = {3}
}

Patent:

Save / Share: