Fault tolerance in a supercomputer through dynamic repartitioning

Chen, Dong; Coteus, Paul W; Gara, Alan G; Takken, Todd E

Title: Fault tolerance in a supercomputer through dynamic repartitioning

Full Record
Other Related Research

Abstract

A multiprocessor, parallel computer is made tolerant to hardware failures by providing extra groups of redundant standby processors and by designing the system so that these extra groups of processors can be swapped with any group which experiences a hardware failure. This swapping can be under software control, thereby permitting the entire computer to sustain a hardware failure but, after swapping in the standby processors, to still appear to software as a pristine, fully functioning system.

Inventors:

Chen, Dong ^[1]; Coteus, Paul W ^[2]; Gara, Alan G ^[3]; Takken, Todd E ^[3]

Croton On Hudson, NY
Yorktown Heights, NY
Mount Kisco, NY

Issue Date:: 2007-02-27

Research Org.:: Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); International Business Machines Corp., Armonk, NY (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 949199

Patent Number(s):: 7185226

Application Number:: 10/469,002

Assignee:: International Business Machines Corporation (Armonk, NY)

Patent Classifications (CPCs):: H - ELECTRICITY H05 - ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR H05K - PRINTED CIRCUITS

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING

Show more

H - ELECTRICITY H05 - ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR H05K - PRINTED CIRCUITS
H05K7/20836 - {Thermal management, e.g. server temperature control}

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
G06F9/52 - Program synchronisation
G06F17/142 - {Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm}

H - ELECTRICITY H04 - ELECTRIC COMMUNICATION TECHNIQUE H04L - TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
H04L7/0338 - {the correction of the phase error being performed by a feed forward loop}

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
G06F15/17381 - {Two dimensional, e.g. mesh, torus}

Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y02 - TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE Y02B - CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
Y02B30/70 - Efficient control or regulation technologies

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
G06F11/2051 - {in regular structures}
G06F11/2028 - {eliminating a faulty processor or activating a spare}

F - MECHANICAL ENGINEERING F04 - POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS F04D - NON-POSITIVE-DISPLACEMENT PUMPS
F04D27/004 - {by varying driving speed}

F - MECHANICAL ENGINEERING F24 - HEATING F24F - AIR-CONDITIONING
F24F11/77 - by controlling the speed of ventilators

F - MECHANICAL ENGINEERING F04 - POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS F04D - NON-POSITIVE-DISPLACEMENT PUMPS
F04D25/166 - {using fans}

G - PHYSICS G09 - EDUCATION G09G - ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
G09G5/008 - {Clock recovery}

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
G06F11/2041 - {with more than one idle spare processing component}
G06F9/526 - {Mutual exclusion algorithms}

Show less

DOE Contract Number:: W-7405-ENG-48

Resource Type:: Patent

Country of Publication:: United States

Language:: English

Citation Formats


                    Chen, Dong, Coteus, Paul W, Gara, Alan G, and Takken, Todd E. Fault tolerance in a supercomputer through dynamic repartitioning.  United States: N. p., 2007. 
        Web.

Copy to clipboard


                    Chen, Dong, Coteus, Paul W, Gara, Alan G, & Takken, Todd E. Fault tolerance in a supercomputer through dynamic repartitioning.  United States.

Copy to clipboard


                    Chen, Dong, Coteus, Paul W, Gara, Alan G, and Takken, Todd E. Tue .  
        "Fault tolerance in a supercomputer through dynamic repartitioning".  United States.  https://www.osti.gov/servlets/purl/949199.

Copy to clipboard


                    
@article{osti_949199,

  title        = {Fault tolerance in a supercomputer through dynamic repartitioning},

  author       = {Chen, Dong and Coteus, Paul W and Gara, Alan G and Takken, Todd E},

  abstractNote = {A multiprocessor, parallel computer is made tolerant to hardware failures by providing extra groups of redundant standby processors and by designing the system so that these extra groups of processors can be swapped with any group which experiences a hardware failure. This swapping can be under software control, thereby permitting the entire computer to sustain a hardware failure but, after swapping in the standby processors, to still appear to software as a pristine, fully functioning system.},

  doi          = {},

  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2007},

  month        = {2}

}

Copy to clipboard

Patent:

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE Patents and OSTI.GOV collections:

Methods and apparatuses for self-generating fault-tolerant keys in spread-spectrum systems

Patent Moradi, Hussein; Farhang, Behrouz; Subramanian, Vijayarangam

Self-generating fault-tolerant keys for use in spread-spectrum systems are disclosed. At a communication device, beacon signals are received from another communication device and impulse responses are determined from the beacon signals. The impulse responses are circularly shifted to place a largest sample at a predefined position. The impulse responses are converted to a set of frequency responses in a frequency domain. The frequency responses are shuffled with a predetermined shuffle scheme to develop a set of shuffled frequency responses. A set of phase differences is determined as a difference between an angle of the frequency response and an angle ofmore » « less
Full Text Available
Fault-tolerant rotary actuator

Patent Tesar, Delbert

A fault-tolerant actuator module, in a single containment shell, containing two actuator subsystems that are either asymmetrically or symmetrically laid out is provided. Fault tolerance in the actuators of the present invention is achieved by the employment of dual sets of equal resources. Dual resources are integrated into single modules, with each having the external appearance and functionality of a single set of resources.
Full Text Available
Fault-tolerant three-level inverter

Patent Edwards, John; Xu, Longya; Bhargava, Brij B.

A method for driving a neutral point clamped three-level inverter is provided. In one exemplary embodiment, DC current is received at a neutral point-clamped three-level inverter. The inverter has a plurality of nodes including first, second and third output nodes. The inverter also has a plurality of switches. Faults are checked for in the inverter and predetermined switches are automatically activated responsive to a detected fault such that three-phase electrical power is provided at the output nodes.
Full Text Available
Fault tolerant linear actuator

Patent Tesar, Delbert

In varying embodiments, the fault tolerant linear actuator of the present invention is a new and improved linear actuator with fault tolerance and positional control that may incorporate velocity summing, force summing, or a combination of the two. In one embodiment, the invention offers a velocity summing arrangement with a differential gear between two prime movers driving a cage, which then drives a linear spindle screw transmission. Other embodiments feature two prime movers driving separate linear spindle screw transmissions, one internal and one external, in a totally concentric and compact integrated module.
Full Text Available
Fault-tolerant controller for modular multi-level converters

Patent Azidehak, Ali; Bhattacharya, Subhashish

Various examples are provided related to fault-tolerant controller architectures for multi-level converters. In one example, a multi-level converter includes an array of power modules. The power modules can include a controller communicatively coupled to controllers of adjacent power modules in the array of power modules. Circuitry of the controllers can receive operational data from the adjacent power modules; identify a fault condition in an adjacent power module using the operational data; and initiate reconfiguration of the array of power modules in response to an indication of the fault condition, where the reconfiguration bypasses the adjacent power module. In another example,more » « less
Full Text Available

Similar Records