Massively parallel fast elliptic equation solver for three dimensional hydrodynamics and relativity

Sholl, P L; Wilson, J R; Mathews, G J; Avila, J H

doi:10.2172/34202

Title: Massively parallel fast elliptic equation solver for three dimensional hydrodynamics and relativity

Full Record
Other Related Research

Abstract

Through the work proposed in this document we expect to advance the forefront of large scale computational efforts on massively parallel distributed-memory multiprocessors. We will develop tools for effective conversion to a parallel implementation of sequential numerical methods used to solve large systems of partial differential equations. The research supported by this work will involve conversion of a program which does state of the art modeling of multi-dimensional hydrodynamics, general relativity and particle transport in energetic astrophysical environments. The proposed parallel algorithm development, particularly the study and development of fast elliptic equation solvers, could significantly benefit this program and other applications involving solutions to systems of differential equations. We shall develop a data communication manager for distributed memory computers as an aid in program conversions to a parallel environment and implement it in the three dimensional relativistic hydrodynamics program discussed below; develop a concurrent system/concurrent subgrid multigrid method. Currently, five systems are approximated sequentially using multigrid successive overrelaxation. Results from an iteration cycle of one multigrid system are used in following multigrid systems iterations. We shall develop a multigrid algorithm for simultaneous computation of the sets of equations. In addition, we shall implement a method for concurrent processing of themore »« less

Authors:

Sholl, P L; Wilson, J R; Mathews, G J ^[1]; Avila, J H ^[2]

Lawrence Livermore National Lab., CA (United States)
San Jose State Univ., CA (United States). Dept. of Mathematics and Computer Science

Publication Date:: 1995-01-01

Research Org.:: Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

Sponsoring Org.:: USDOE, Washington, DC (United States)

OSTI Identifier:: 34202

Report Number(s):: UCRL-ID-119803
ON: DE95009385

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

Resource Type:: Technical Report

Resource Relation:: Other Information: PBD: Jan 1995

Country of Publication:: United States

Language:: English

Subject:: 66 PHYSICS; 99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS; PARTIAL DIFFERENTIAL EQUATIONS; PARALLEL PROCESSING; NUMERICAL SOLUTION; ARRAY PROCESSORS; THREE-DIMENSIONAL CALCULATIONS; DISTRIBUTED DATA PROCESSING; RELATIVITY THEORY; ALGORITHMS; ITERATIVE METHODS; ELLIPTICAL CONFIGURATION; NEUTRON STARS

Citation Formats


                    Sholl, P L, Wilson, J R, Mathews, G J, and Avila, J H. Massively parallel fast elliptic equation solver for three dimensional hydrodynamics and relativity.  United States: N. p., 1995. 
        Web.  doi:10.2172/34202.

Copy to clipboard


                    Sholl, P L, Wilson, J R, Mathews, G J, & Avila, J H. Massively parallel fast elliptic equation solver for three dimensional hydrodynamics and relativity.  United States.  https://doi.org/10.2172/34202

Copy to clipboard


                    Sholl, P L, Wilson, J R, Mathews, G J, and Avila, J H. 1995.  
        "Massively parallel fast elliptic equation solver for three dimensional hydrodynamics and relativity".  United States.  https://doi.org/10.2172/34202.  https://www.osti.gov/servlets/purl/34202.

Copy to clipboard


                    
@article{osti_34202,

  title        = {Massively parallel fast elliptic equation solver for three dimensional hydrodynamics and relativity},

  author       = {Sholl, P L and Wilson, J R and Mathews, G J and Avila, J H},

  abstractNote = {Through the work proposed in this document we expect to advance the forefront of large scale computational efforts on massively parallel distributed-memory multiprocessors. We will develop tools for effective conversion to a parallel implementation of sequential numerical methods used to solve large systems of partial differential equations. The research supported by this work will involve conversion of a program which does state of the art modeling of multi-dimensional hydrodynamics, general relativity and particle transport in energetic astrophysical environments. The proposed parallel algorithm development, particularly the study and development of fast elliptic equation solvers, could significantly benefit this program and other applications involving solutions to systems of differential equations. We shall develop a data communication manager for distributed memory computers as an aid in program conversions to a parallel environment and implement it in the three dimensional relativistic hydrodynamics program discussed below; develop a concurrent system/concurrent subgrid multigrid method. Currently, five systems are approximated sequentially using multigrid successive overrelaxation. Results from an iteration cycle of one multigrid system are used in following multigrid systems iterations. We shall develop a multigrid algorithm for simultaneous computation of the sets of equations. In addition, we shall implement a method for concurrent processing of the subgrids in each of the multigrid computations. The conditions for convergence of the method will be examined. We`ll compare this technique to other parallel multigrid techniques, such as distributed data/sequential subgrids and the Parallel Superconvergent Multigrid of Frederickson and McBryan. We expect the results of these studies to offer insight and tools both for the selection of new algorithms as well as for conversion of existing large codes for massively parallel architectures.},

  doi          = {10.2172/34202},

  url          = {https://www.osti.gov/biblio/34202},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {1995},

  month        = {1}

}

Copy to clipboard

Technical Report:

View Technical Report (1.93 MB)

https://doi.org/10.2172/34202

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

LDRD final report on massively-parallel linear programming : the parPCx system.

Technical Report Parekh, Ojas; Phillips, Cynthia; Boman, Erik

This report summarizes the research and development performed from October 2002 to September 2004 at Sandia National Laboratories under the Laboratory-Directed Research and Development (LDRD) project ''Massively-Parallel Linear Programming''. We developed a linear programming (LP) solver designed to use a large number of processors. LP is the optimization of a linear objective function subject to linear constraints. Companies and universities have expended huge efforts over decades to produce fast, stable serial LP solvers. Previous parallel codes run on shared-memory systems and have little or no distribution of the constraint matrix. We have seen no reports of general LP solver runsmore »« less
https://doi.org/10.2172/921147

Full Text Available
Parallel linear solvers for reservoir simulation: A generic approach for existing and emerging computer architectures

Journal Article Bhogeswara, R; Killough, J - SPE Computer Applications (Society of Petroleum Engineers); (United States)

Recent architectural advances in the computer industry focus on the numerical solution of intensive flows, such as in oil reservoirs, on several processors simultaneously. Different computer architectures evolved from connection of these processors: shared memory with a few processors, distributed memory with up to a few hundred processors, and massively parallel with several thousand processors. Oil industry researchers are developing efficient techniques to improve hydrocarbon recovery in reservoirs by use of these computers. In this work, a generic approach is developed to solve the large system of sparse linear equations that arises in reservoir simulation. This approach uses a combinationmore »« less
https://doi.org/10.2118/25240-PA
An iterative algorithm for solving the multidimensional neutron diffusion nodal method equations on parallel computers

Journal Article Kirk, B; Azmy, Y - Nuclear Science and Engineering; (United States)

In this paper the one-group, steady-state neutron diffusion equation in two-dimensional Cartesian geometry is solved using the nodal integral method. The discrete variable equations comprise loosely coupled sets of equations representing the nodal balance of neutrons, as well as neutron current continuity along rows or columns of computational cells. An iterative algorithm that is more suitable for solving large problems concurrently is derived based on the decomposition of the spatial domain and is accelerated using successive overrelaxation. This algorithm is very well suited for parallel computers, especially since the spatial domain decomposition occurs naturally, so that the number of iterationsmore »« less
Enabling Computational Technologies for Terascale Scientific Simulations

Technical Report Ashby, S

We develop scalable algorithms and object-oriented code frameworks for terascale scientific simulations on massively parallel processors (MPPs). Our research in multigrid-based linear solvers and adaptive mesh refinement enables Laboratory programs to use MPPs to explore important physical phenomena. For example, our research aids stockpile stewardship by making practical detailed 3D simulations of radiation transport. The need to solve large linear systems arises in many applications, including radiation transport, structural dynamics, combustion, and flow in porous media. These systems result from discretizations of partial differential equations on computational meshes. Our first research objective is to develop multigrid preconditioned iterative methods formore »« less
https://doi.org/10.2172/802085

Full Text Available
Time-parallel iterative methods for parabolic PDES: Multigrid waveform relaxation and time-parallel multigrid

Conference Vandewalle, S

Time-stepping methods for parabolic partial differential equations are essentially sequential. This prohibits the use of massively parallel computers unless the problem on each time-level is very large. This observation has led to the development of algorithms that operate on more than one time-level simultaneously; that is to say, on grids extending in space and in time. The so-called parabolic multigrid methods solve the time-dependent parabolic PDE as if it were a stationary PDE discretized on a space-time grid. The author has investigated the use of multigrid waveform relaxation, an algorithm developed by Lubich and Ostermann. The algorithm is based onmore »« less
Full Text Available

Similar Records