New computer architectures and the finite element method

2011/01/B/ST6/00674

Keywords

Descriptors

  • ST6_9: Obliczenia naukowe
  • ST6_12: Przetwarzanie równoległe i rozproszone
  • ST6_1: Architektura systemów komputerowych

Panel

ST6 – Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems

Host institution

Politechnika Krakowska im. Tadeusza Kościuszki, Wydział Fizyki, Matematyki i Informatyki

Voivodeship: małopolskie

Other projects carried out by the institution »

Principal investigator (from the host institution)

dr hab. Krzysztof Banaś

Number of co-investigators in the project: 9

Call

OPUS 1 – announced on 2011-03-15

Amount awarded
492 000 PLN
Project start date
2011-12-27
Project end date
2014-12-26
Project duration
36 months (the same as in the proposal)
Project status
Project settled

Equipment purchased [PL]

  1. Serwer/stacja robocza z procesorem AMD i kartą graficzna ATI. Cost: 15 000 PLN
  2. Serwer/stacja robocza z procesorem Intel Xeon i kartą akceleratora NVIDIA. Cost: 15 000 PLN
  3. Serwer/stacja robocza z procesorem Intel Xeon i kartą akceleratora Xeon Phi o architekturze Intel MIC. Cost: 15 000 PLN
  4. Serwer/stacja robocza z procesorem o architekturze Fusion firmy AMD. Cost: 2 167 PLN

Information in the final report

Publication in academic press/journals (16)

  1. DEVELOPMENT OF THREE-DIMENSIONAL ADAPTIVE MESH GENERATION FOR MULTISCALE APPLICATIONS

    Authors:
    Filip Krużel, Łukasz Madej, Konrad Perzyński, Krzysztof Banaś
    Academic press:
    International Journal for Multiscale Computational Engineering (year: 2014, volume: 12, pages: 257-269), Publisher: Begell House
    Status:
    Published
    DOI:
    10.1615/IntJMultCompEng.2014010702 – link to the publication
  2. Adaptive Projection-Based Interpolation as a preprocessing tool in the Finite Element workflow for elasticity simulations of the dual phase microstructures

    Authors:
    Marcin Sieniek, Maciej Paszyński, Łukasz Madej, Damian Goik
    Academic press:
    Steel Research International (year: 2014, volume: 85, pages: 1109-1119), Publisher: Wiley
    Status:
    Published
    DOI:
    10.1002/srin.201300168 – link to the publication
  3. A HYBRID ALGORITHM FOR SOLVING INVERSE PROBLEMS IN ELASTICITY

    Authors:
    BARBARA BARABASZ, EWA GAJDA-ZAGÓRSKA, STANISŁAW MIGÓRSKI, MACIEJ PASZYŃSKI, ROBERT SCHAEFER, MACIEJ SMOŁKA
    Academic press:
    International Journal of Applied Mathematics and Computer Science (year: 2014, volume: 24, pages: 865-886), Publisher: University of Zielona Góra
    Status:
    Published
    DOI:
    10.2478/amcs-2014-0064 – link to the publication
  4. Finite Element Method Computations of the Acoustics of the Human Head Based on the Projection Based Interpolation Data

    Authors:
    Marcin Sieniek, Piotr Gurgul, Maciej Paszyński
    Academic press:
    Journal of Applied Mathematics and Physics (year: 2014, volume: 2, pages: 1047-1052), Publisher: Scientific Research Publishing SCIRP
    Status:
    Published
    DOI:
    10.4236/jamp.2014.212119 – link to the publication
  5. Subtree Reuse in Multi-Frontal Solvers for Regular Grids in Step-and-Flash Imprint Nanolithography Modeling

    Authors:
    M. Sieniek, M. Paszyński
    Academic press:
    Advanced Engineering Materials (year: 2014, volume: 16, pages: 231-240), Publisher: Wiley
    Status:
    Published
    DOI:
    10.1002/adem.201300267 – link to the publication
  6. Minimizing the memory usage with parallel out-of-core multi-frontal direct solver

    Authors:
    M. Paszyński
    Academic press:
    Computer Assisted Methods in Engineering and Science (year: 2013, volume: 20, pages: 15-41), Publisher: Institute of Fundamental Technological Research, Polish Academy of Sciences
    Status:
    Published
  7. Iterative methods for solving large-scale problems of structural mechanics using multi-core computers

    Authors:
    S.Yu. Fialko
    Academic press:
    Archives of Civil and Mechanical Engineering (year: 2014, volume: 14, pages: 190-203), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.acme.2013.05.009 – link to the publication
  8. Graph Grammar-Based Multi-Frontal Parallel Direct Solver for Two-Dimensional Isogeometric Analysis

    Authors:
    Krzysztof Kuźnik, Maciej Paszyński, Victor Calo
    Academic press:
    Procedia Computer Science (year: 2012, volume: 9, pages: 1454-1463), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.procs.2012.04.160 – link to the publication
  9. About analysis of large problems of structural mechanics on multi-core computers.

    Authors:
    S.Yu. Fialko
    Academic press:
    Magazine of Civil Engineering (year: 2013, volume: 5 (40), pages: 116-124), Publisher: St-Petersburg State Polytechnical University
    Status:
    Published
    DOI:
    10.5862/MCE.40.13 – link to the publication
  10. Vectorized OpenCL implementation of numerical integration for higher order finite elements

    Authors:
    F. Krużel, K. Banaś
    Academic press:
    Computers and Mathematics with Applications (year: 2013, volume: 66, pages: 2030-2044), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.camwa.2013.08.026 – link to the publication
  11. Numerical integration on GPUs for higher order finite elements

    Authors:
    K. Banaś, P. Płaszewski, P. Macioł
    Academic press:
    Computers & Mathematics with Applications (year: 2014, volume: 67, pages: 1319-1344), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.camwa.2014.01.021 – link to the publication
  12. Modular FEM framework ModFem for generic scientific parallel simulations

    Authors:
    K. Michalik, K. Banaś, P. Płaszewski, P. Cybułka
    Academic press:
    Computer Science (year: 2013, volume: 14, pages: 513-528), Publisher: AGH University of Science and Technology, Krakow Poland
    Status:
    Published
    DOI:
    10.7494/csci.2013.14.3.513 – link to the publication
  13. Grammar-Based Multi-Frontal Solver for One Dimensional Isogeometric Analysis with Multiple Right-Hand-Sides

    Authors:
    K. Kuźnik, M. Paszyński, V. Calo
    Academic press:
    Procedia Computer Science (year: 2013, volume: 18, pages: 1574-1583), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.procs.2013.05.325 – link to the publication
  14. Performance analysis of iterative solvers of linear equations for hp-adaptive finite element method

    Authors:
    P. Płaszewski, K. Banaś
    Academic press:
    Procedia Computer Science (year: 2013, volume: 18, pages: 1584-1593), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.procs.2013.05.326 – link to the publication
  15. Computational cost estimates for parallel shared memory isogeometric multi-frontal solvers

    Authors:
    M. Woźniak, K. Kuźnik, M. Paszyński, V.M. Calo, D. Pardo
    Academic press:
    Computers and Mathematics with Applications (year: 2014, volume: 67, pages: 1864-1883), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.camwa.2014.03.017 – link to the publication
  16. Effective adaptation in hybrid finite element method using vectorization capabilities of modern processors during parallel numerical modeling.

    Authors:
    K. Michalik
    Status:
    Accepted for publication

Articles in post-conference publications (8)

  1. The natural vibration analysis of multistorey buildings on multi-core computers

    Authors:
    S. Yu. Fialko
    Conference:
    International Conference on Computer Methods in Mechanics (year: 2013, pages: TS02-7 - TS02-8), Publisher: Politechnika Poznańska
    Date:
    conference 27–31 August 2013
    Status:
    Published
    DOI:
    link to the publication
  2. Application of AVX (Advanced Vector Extensions) for Improved Performance of the PARFES – Finite Element Parallel Direct Solver

    Authors:
    S. Yu. Fialko
    Conference:
    Federated Conference on Computer Science and Information Systems (year: 2013, pages: 447-454), Publisher: IEEE
    Date:
    conference September 8–11, 2013
    Status:
    Published
    DOI:
    link to the publication
  3. Parallel Finite Element Solver for Multi-Core Computers

    Authors:
    Sergiy Fialko
    Conference:
    Federated Conference on Computer Science and Information Systems (year: 2012, pages: 525-532), Publisher: IEEE Xplore Digital Library
    Date:
    conference September 9–12, 2012
    Status:
    Published
  4. GRAPH GRAMMAR BASED PARALLEL DIRECT SOLVER FOR 1D AND 2D ISOGEOMETRIC FINITE ELEMENT METHOD

    Authors:
    Maciej R. Paszyński, Krzysztof M. Kuźnik, and Victor M. Calo
    Conference:
    European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS 2012) (year: 2012, pages: dokument elektroniczny), Publisher: Vienna University of Technology
    Date:
    conference September 10-14
    Status:
    Published
  5. Comparison of computational costs for two dimensional isogeometric collocation and finite element methods for parallel shared memory multi-frontal direct solver

    Authors:
    P. Lipski, P. Gurgul, M. Paszyński
    Conference:
    11th International Conference on Applied Computing (year: 2014, pages: 93-100), Publisher: International Association for Development of the Information Society
    Date:
    conference 25 – 27 October 2014
    Status:
    Published
  6. QUADRILATERAL FLAT SHELL FINITE ELEMENT FOR SIMULATION OF REINFORCED CONCRETE STRUCTURAL ELEMENTS

    Authors:
    S. Fialko
    Conference:
    39th Solid Mechanics Conference (year: 2014, pages: 221-222), Publisher: IPPT PAN
    Date:
    conference September 1–5, 2014
    Status:
    Published
  7. Finite element numerical integration on Xeon Phi coprocessor

    Authors:
    F. Krużel, K. Banaś
    Conference:
    Federated Conference on Computer Science and Information Systems (FedCSIS) (year: 2014, pages: 603-612), Publisher: IEEE
    Date:
    conference 7-10 Sept. 2014
    Status:
    Published
    DOI:
    link to the publication
  8. Comparison of Xeon Phi and Kepler GPU performance for finite element numerical integration

    Authors:
    K. Banaś, F. Krużel
    Conference:
    16th International Conference on High Performance Computing and Communications (year: 2014, pages: 145-148), Publisher: IEEE
    Status:
    Accepted for publication

Book publications / chapters in book publications (1)

  1. OpenCL Performance Portability for Xeon Phi Coprocessor and NVIDIA GPUs: A Case Study of Finite Element Numerical Integration

    Authors:
    K. Banaś, F. Krużel
    Book:
    Euro-Par 2014: Parallel Processing Workshops (year: 2014, volume: 8806, pages: 158-169), Publisher: Springer
    Status:
    Published
    DOI:
    link to the publication

« New search

Graphic design and implementation: Jakub Piotrowski