Modeling and management of correlation between performance and energy consumption in parallel computing platforms

2015/17/D/ST6/04059

Keywords

Descriptors

  • ST6_2: Systemy komputerowe, systemy równoległe i rozproszone, sieci sensorów, systemy wbudowane, systemy cybernetyczne
  • ST6_1: Architektura systemów komputerowych, przetwarzanie wszechobecne
  • ST6_6: Algorytmika, algorytmy równoległe, rozproszone i sieciowe, algorytmiczna teoria gier

Panel

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

Host institution

Politechnika Częstochowska, Wydział Inżynierii Mechanicznej i Informatyki

Voivodeship: śląskie

Other projects carried out by the institution »

Principal investigator (from the host institution)

dr Krzysztof Rojek

Number of co-investigators in the project: 3

Call

SONATA 9 – announced on 2015-03-16

Amount awarded
228 000 PLN
Project start date
2016-01-21
Project end date
2019-06-20
Project duration
41 months (the same as in the proposal)
Project status
Project settled

Project description

Download the project description in a pdf file

Note — project descriptions were prepared by the authors of the applications themselves and placed in the system in an unchanged form.

Equipment purchased [PL]

  1. Komputer przenośny. Cost: 18 000 PLN

Information in the final report

Publication in academic press/journals (8)

  1. Energy-aware mechanism for stencil-based MPDATA algorithm with constraints

    Authors:
    K. Rojek, A. Ilic, R. Wyrzykowski, L. Sousa
    Academic press:
    Concurrency Computat.: Pract. Exper. (year: 2017, volume: 29 (8), pages: 46041), Publisher: John Wiley & Sons Ltd
    Status:
    Published
    DOI:
    10.1002/cpe.4016 – link to the publication
  2. Modeling power consumption of 3D MPDATA and the CG method on ARM and Intel multicore architectures

    Authors:
    Krzysztof Rojek, Enrique S. Quintana-Ort, Roman Wyrzykowski
    Academic press:
    The Journal of Supercomputing (year: 2017, volume: 73 (10), pages: 4373-4389), Publisher: Springer US
    Status:
    Published
    DOI:
    10.1007/s11227-017-2020-z – link to the publication
  3. An Study of the Effect of Process Malleability in the Energy Efficiency on GPU-based Clusters

    Authors:
    Sergio Iserte, Krzysztof Rojek
    Academic press:
    The Journal of Supercomputing (year: 2020, volume: 76, pages: 255-274), Publisher: Springer US
    Status:
    Published
    DOI:
    10.1007/s11227-019-03034-x – link to the publication
  4. Machine learning method for energy reduction by utilizing dynamic mixed precision on GPU-based supercomputers

    Authors:
    Krzysztof Rojek
    Academic press:
    Concurrency Computat.: Pract. Exper. (year: 2019, volume: 31 (6), pages: 46034), Publisher: John Wiley & Sons Ltd
    Status:
    Published
    DOI:
    10.1002/cpe.4644 – link to the publication
  5. Model-based optimization of EULAG kernel on Intel Xeon Phi through load imbalancing

    Authors:
    A. Lastovetsky, L. Szustak, R. Wyrzykowski
    Academic press:
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS (year: 2017, volume: 28 (3), pages: 787-797), Publisher: IEEE Press Piscataway
    Status:
    Published
    DOI:
    10.1109/TPDS.2016.2599527 – link to the publication
  6. Systematic adaptation of stencil-based 3D MPDATA to GPU architectures

    Authors:
    K. Rojek, R. Wyrzykowski, L. Kuczynski
    Academic press:
    Concurrency Computat.: Pract. Exper. (year: 2017, volume: 29, pages: 46042), Publisher: John Wiley & Sons Ltd
    Status:
    Published
    DOI:
    10.1002/cpe.3970 – link to the publication
  7. Performance modeling of 3D MPDATA simulations on GPU cluster

    Authors:
    K. Rojek, R. Wyrzykowski
    Academic press:
    The Journal of Supercomputing (year: 2017, volume: 73 (2), pages: 664-675), Publisher: Springer US
    Status:
    Published
    DOI:
    10.1007/s11227-016-1774-z – link to the publication
  8. Porting and optimization of solidification application for CPU–MIC hybrid platforms

    Authors:
    Lukasz Szustak, Kamil Halbiniak, Lukasz Kuczynski, Joanna Wrobel, Adam Kulawik
    Status:
    Accepted for publication

Articles in post-conference publications (3)

  1. Islands-of-Cores Approach for Harnessing SMP/NUMA Architectures in Heterogeneous Stencil Computations

    Authors:
    Lukasz Szustak, Roman Wyrzykowski, Ondřej Jakl
    Conference:
    International Conference on Parallel Computing Technologies (year: 2017, pages: 351-364), Publisher: Springer, Cham
    Date:
    conference 4-8 September
    Status:
    Published
  2. Energy Consumption of Stencil-Based MPDATA Algorithm

    Authors:
    K. Rojek, M. Barreda, E.S. Quintana-Ort, R. Wyrzykowski
    Conference:
    Proceedings of the 16th International Conference on Computational and Mathematical Methods in Science and Engineering, CMMSE 2016 (year: 2016, pages: 1104-1107), Publisher: -
    Date:
    conference 4-8 July, 2016
    Status:
    Published
    DOI:
    link to the publication
  3. Network-Aware Optimization of MPDATA on Homogeneous Multi-core Clusters with Heterogeneous Network

    Authors:
    T. Malik, L. Szustak, R. Wyrzykowski, A. Lastovetsky
    Conference:
    International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2016) (year: 2016, pages: 30-42), Publisher: Lecture Notes in Computer Science, vol 10049. Springer, Cham
    Date:
    conference 14-16 December 2016
    Status:
    Published
    DOI:
    link to the publication

« New search

Graphic design and implementation: Jakub Piotrowski