Conference paper Open Access

GPU Implementation of Neural-Network Simulations based on Adaptive-Exponential Models

Neofytou, Alexandros; Chatzikostantis, George; Magkanaris, Ioannis; Smaragdos, George; Strydis, Christos; Soudris, Dimitrios


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-12-26</subfield>
  </datafield>
  <controlfield tag="005">20200319202013.0</controlfield>
  <controlfield tag="001">3716318</controlfield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:3716318</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Detailed brain modeling has been presenting significant challenges to the world of high-performance computing (HPC), posing computational problems that can benefit from modern hardware-acceleration technologies. We explore the capacity of GPUs for simulating large-scale neuronal networks based on the Adaptive Exponential neuron-model, which is widely used in the neuroscientific community. Our GPU-powered simulator acts as a benchmark to evaluate the strengths and limitations of modern GPUs, as well as to explore their scaling properties when simulating large neural networks. This work presents an optimized GPU implementation that outperforms a reference multicore implementation by 50x, whereas utilizing a dual-GPU configuration can deliver a speedup of 90x for networks of 20,000 fully interconnected AdEx neurons.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">School of Electrical and Computer Engineering, National Technical University of Athens, Greece</subfield>
    <subfield code="a">Chatzikostantis, George</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">School of Electrical and Computer Engineering, National Technical University of Athens, Greece</subfield>
    <subfield code="a">Magkanaris, Ioannis</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Neuroscience dept., Erasmus Medical Center, The Netherlands</subfield>
    <subfield code="a">Smaragdos, George</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Neuroscience dept., Erasmus Medical Center, The Netherlands</subfield>
    <subfield code="a">Strydis, Christos</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">School of Electrical and Computer Engineering, National Technical University of Athens, Greece</subfield>
    <subfield code="a">Soudris, Dimitrios</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">629879</subfield>
    <subfield code="z">md5:9b39c4c2d60cdb8cd4726ae4ca6ac177</subfield>
    <subfield code="u">https://zenodo.org/record/3716318/files/12_GPU_acceleration.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">School of Electrical and Computer Engineering, National Technical University of Athens, Greece</subfield>
    <subfield code="a">Neofytou, Alexandros</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1109/BIBE.2019.00067</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">GPU Implementation of Neural-Network Simulations based on Adaptive-Exponential Models</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">801015</subfield>
    <subfield code="a">Enhancing Programmability and boosting Performance Portability for Exascale Computing Systems</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
</record>
37
71
views
downloads
Views 37
Downloads 71
Data volume 44.7 MB
Unique views 35
Unique downloads 68

Share

Cite as