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

Title: Acceleration of Time Integration

Abstract

We outline our strategies for accelerating time integration for long-running simulations, such as those for global climate modeling. The strategies target the Cray XT systems at the National Center for Computational Sciences at Oak Ridge National Laboratory. Our strategies include fully implicit, parallel-in-time, and curvelet methods.

Authors:
 [1];  [1];  [1];  [1];  [1];  [1]
  1. ORNL
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Center for Computational Sciences
Sponsoring Org.:
USDOE Laboratory Directed Research and Development (LDRD) Program
OSTI Identifier:
978809
DOE Contract Number:
DE-AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: CUG 2008, Helsinki, Finland, 20080505, 20080508
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICAL METHODS AND COMPUTING; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; SUPERCOMPUTERS; ORNL; COMPUTERIZED SIMULATION; OPERATION; PARALLEL PROCESSING; TIME DELAY

Citation Formats

White III, James B, Drake, John B, Worley, Patrick H, Archibald, Richard K, Evans, Katherine J, and Kothe, Douglas B. Acceleration of Time Integration. United States: N. p., 2007. Web.
White III, James B, Drake, John B, Worley, Patrick H, Archibald, Richard K, Evans, Katherine J, & Kothe, Douglas B. Acceleration of Time Integration. United States.
White III, James B, Drake, John B, Worley, Patrick H, Archibald, Richard K, Evans, Katherine J, and Kothe, Douglas B. Mon . "Acceleration of Time Integration". United States. doi:.
@article{osti_978809,
title = {Acceleration of Time Integration},
author = {White III, James B and Drake, John B and Worley, Patrick H and Archibald, Richard K and Evans, Katherine J and Kothe, Douglas B},
abstractNote = {We outline our strategies for accelerating time integration for long-running simulations, such as those for global climate modeling. The strategies target the Cray XT systems at the National Center for Computational Sciences at Oak Ridge National Laboratory. Our strategies include fully implicit, parallel-in-time, and curvelet methods.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Mon Jan 01 00:00:00 EST 2007},
month = {Mon Jan 01 00:00:00 EST 2007}
}

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:
  • In July 1996, the US Department of Energy (DOE) chartered a contractor-led effort to develop a suite of technically defensible, integrated alternatives which would allow the Environmental Management program to accomplish its mission objectives in an accelerated fashion and at a reduced cost. These alternatives, or opportunities, could then be evaluated by DOE and stakeholders for possible implementation, given precursor requirements (regulatory changes, etc.) could be met and benefits to the Complex realized. This contractor effort initially focused on six waste types, one of which was Mixed Low-Level Waste (MLLW). Many opportunities were identified by the contractor team for integratingmore » MLLW activities across the DOE Complex. These opportunities were further narrowed to six that had the most promise for implementation and savings to the DOE Complex. The opportunities include six items: (1) the consolidation of individual site analytical services procurement efforts, (2) the consolidation of individual site MLLW treatment services procurement efforts, (3) establishment of ``de minimus`` radioactivity levels, (4) standardization of characterization requirements, (5) increased utilization of existing DOE treatment facilities, and (6) using a combination of DOE and commercial MLLW disposal capacity. The results of the integration effort showed that by managing MLLW activities across the DOE Complex as a cohesive unit rather than as independent site efforts, the DOE could improve the rate of progress toward meeting its objectives and reduce its overall MLLW program costs. Savings potential for MLLW, if the identified opportunities could be implemented, could total $224 million or more. Implementation of the opportunities also could result in the acceleration of the MLLW ``work off schedule`` across the DOE Complex by five years.« less
  • Abstract—We demonstrate the systematic implementation of recently-developed fast explicit kinetic integration algorithms that solve efficiently N coupled ordinary differential equations (subject to initial conditions) on modern GPUs. We take representative test cases (Type Ia supernova explosions) and demonstrate two or more orders of magnitude increase in efficiency for solving such systems (of realistic thermonuclear networks coupled to fluid dynamics). This implies that important coupled, multiphysics problems in various scientific and technical disciplines that were intractable, or could be simulated only with highly schematic kinetic networks, are now computationally feasible. As examples of such applications we present the computational techniques developedmore » for our ongoing deployment of these new methods on modern GPU accelerators. We show that similarly to many other scientific applications, ranging from national security to medical advances, the computation can be split into many independent computational tasks, each of relatively small-size. As the size of each individual task does not provide sufficient parallelism for the underlying hardware, especially for accelerators, these tasks must be computed concurrently as a single routine, that we call batched routine, in order to saturate the hardware with enough work.« less
  • Abstract not provided.
  • Abstract not provided.
  • Abstract not provided.