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

Title: Providing Runtime Clock Synchronization With Minimal Node-to-Node Time Deviation on XT4s and XT5s

Abstract

We present a new high precision clock synchronization algorithm designed for large XT4 and XT5 leadership-class machines. The algorithm, which is designed to support OS noise reduction through co-scheduling, is suitable for usage cases requiring low overhead and minimal time deviation between nodes. Unlike most high-precision algorithms which reach their precision in a post-mortem analysis after the application has completed, the new ORNL developed algorithm rapidly provides precise results during runtime. Previous to our work, the leading high-precision clock synchronization algorithms that made results available during runtime relied on probabilistic schemes that are not guaranteed to result in an answer.

Authors:
 [1];  [1]
  1. ORNL
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
1016620
DOE Contract Number:
DE-AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: CUG 2011, Fairbanks, AK, USA, 20110523, 20110526
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; ACCURACY; ALGORITHMS; ORNL; SYNCHRONIZATION; Time service; clock synchronization; MPI; supercomputing; system software; programming tools

Citation Formats

Jones, Terry R, and Koenig, Gregory A. Providing Runtime Clock Synchronization With Minimal Node-to-Node Time Deviation on XT4s and XT5s. United States: N. p., 2011. Web.
Jones, Terry R, & Koenig, Gregory A. Providing Runtime Clock Synchronization With Minimal Node-to-Node Time Deviation on XT4s and XT5s. United States.
Jones, Terry R, and Koenig, Gregory A. 2011. "Providing Runtime Clock Synchronization With Minimal Node-to-Node Time Deviation on XT4s and XT5s". United States. doi:.
@article{osti_1016620,
title = {Providing Runtime Clock Synchronization With Minimal Node-to-Node Time Deviation on XT4s and XT5s},
author = {Jones, Terry R and Koenig, Gregory A},
abstractNote = {We present a new high precision clock synchronization algorithm designed for large XT4 and XT5 leadership-class machines. The algorithm, which is designed to support OS noise reduction through co-scheduling, is suitable for usage cases requiring low overhead and minimal time deviation between nodes. Unlike most high-precision algorithms which reach their precision in a post-mortem analysis after the application has completed, the new ORNL developed algorithm rapidly provides precise results during runtime. Previous to our work, the leading high-precision clock synchronization algorithms that made results available during runtime relied on probabilistic schemes that are not guaranteed to result in an answer.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2011,
month = 1
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • We present a new software-based clock synchronization scheme designed to provide high precision time agreement among distributed memory nodes. The technique is designed to minimize variance from a reference chimer during runtime and with minimal time-request latency. Our scheme permits initial unbounded variations in time and corrects both slow and fast chimers (clock skew). An implementation developed within the context of the MPI message passing interface is described and time coordination measurements are presented. Among our results, the mean time variance among a set of nodes improved from 20.0 milliseconds under standard Network Time Protocol (NTP) to 2.29 secs undermore » our scheme.« less
  • From simulations, tracking of the impulse response is feasible. Potential to benefit other functions such as ranging between two nodes. Potential to combine the features of different protocols to create a new and more realistic clock-synchronization protocol.
  • We present a new software-based clock synchronization scheme that provides high precision time agreement among distributed memory nodes. The technique is designed to minimize variance from a reference chimer during runtime and with minimal time-request latency. Our scheme permits initial unbounded variations in time and corrects both slow and fast chimers (clock skew). An implementation developed within the context of the MPI message passing interface is described, and time coordination measurements are presented. Among our results, the mean time variance for a set of nodes improved from 20.0 milliseconds under standard Network Time Protocol (NTP) down to 2.29 secs undermore » our scheme.« less
  • Precise time is used by the Bonneville Power Administration (BPA) for on-line monitoring of the power system, to provide time synchronization for system monitoring equipment, and to assist in event analysis when a disturbance occurs on the transmission system. This paper presents results of this project and discusses research efforts that will result in further applications of voltage phase-angle measurement. Additional R and D is also needed for more accurate and reliable precise time equipment and the development of standards for disseminating time and frequency.
  • Reservoirs with a fluid bank, or a burning front, reservoirs with a reduced or an increased permeability region around the wellbore, and geothermal reservoirs are often modeled as composite reservoirs. Reservoirs with a fluid bank include reservoirs undergoing waterflood, chemical flood, polymer flood, CO/sub 2/ flood, and steam injection. Eight well tests reported in the literature exhibiting composite reservoir behavior have been analyzed using the deviation time method. The dimensionless deviation times obtained from pressure and pressure derivative responses for a well in a composite reservoir are used for analyzing the well tests. Analysis shows the estimate of discontinuity radiusmore » to be sensitive to both the real and the dimensionless deviation times used. The estimate discontinuity radius from the deviation time method may represent a lower bound for discontinuity radius, if the swept region is not cylindrical. Also, obtaining an accurate deviation time for small mobility contrasts may be difficult.« less