% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Villamar:1030589,
      author       = {Villamar, Jose and Golosio, Bruno and Tiddia, Gianmarco and
                      Sergi, Luca and Pontisso, Luca and Simula, Francesco and
                      Lonardo, Alessandro and Pastorelli, Elena and Paolucci, Pier
                      Stanislao and Diesmann, Markus and Morrison, Abigail and
                      Senk, Johanna},
      title        = {{P}reparing for exascale computing: {L}arge-scale neuronal
                      network construction through parallel {GPU} memory
                      instantiation},
      reportid     = {FZJ-2024-05342},
      year         = {2024},
      abstract     = {Efficient simulation of large-scale spiking neuronal
                      networks is important for neuroscientific research, and both
                      the simulation speed and the time it takes to instantiate
                      the network in computer memory are key factors. NEST GPU
                      demonstrates high simulation speeds with models of various
                      network sizes on single-GPU and multi-GPU systems[1,2].
                      Using a single GPU, networks on the order of $10^5$ neurons
                      and $10^9$ synapses can already be instantiated in less than
                      a second[3]. On the path toward models of the whole brain,
                      neuroscientists show an increasing interest in studying
                      networks that are larger by several orders of magnitude.
                      However, the time needed to construct such large network
                      models was so far a restrictive factor for simulating them.
                      With the aim to fully exploit available and upcoming
                      computing resources for computational neuroscience, we here
                      propose a novel method to efficiently instantiate large
                      networks on multiple GPUs in parallel. Our approach relies
                      on the determinism dependent on the initial state of
                      pseudo-random number generators (PRNGs). Starting from a
                      unique common master RNG seed, a two-dimensional array of
                      seeds is generated, with one seed for each possible pair of
                      source-target MPI processes. These seeds are used to
                      generate the connectivity between each of such pairs. The
                      connections are stored only in the GPU memory of the target
                      MPI process. By synchronising the construction directives,
                      each MPI process does not need to share information on the
                      obtained connectivity after each instruction but can
                      construct its relevant connections by generating the same
                      sequence of random states as the other MPI processes. The
                      method is evaluated through a two-population recurrently
                      connected network designed for benchmarking a variety of
                      commonly used high-level connection rules[4]. Furthermore,
                      we validate the simulation performance with a multi-area
                      model of macaque vision-related cortex[2,5], made up of
                      about 4 million neurons and 24 billion synapses. Lastly we
                      compare our results with other state-of-the-art simulation
                      technologies across varying network sizes using a highly
                      scalable network model[6].[1] Golosio et al. Front. Comput.
                      Neurosci. 15:627620, 2021.[2] Tiddia et al. Front.
                      Neuroinform. 16:883333, 2022.[3] Golosio et al. Appl. Sci.
                      13, 9598, 2023.[4] Senk et al. PLoS Comput Biol. 18(9):
                      e1010086. 2022.[5] Schmidt et al. PLoS Comput Biol. 14(10):
                      e1006359, 2018.[6] Kunkel et al. Front. Neuroinform. 8:78,
                      2014.},
      month         = {Jun},
      date          = {2024-06-03},
      organization  = {International Conceference on
                       Neuromorphic Computing and Engineering,
                       Aachen (Germany), 3 Jun 2024 - 6 Jun
                       2024},
      subtyp        = {After Call},
      cin          = {IAS-6 / INM-10},
      cid          = {I:(DE-Juel1)IAS-6-20130828 / I:(DE-Juel1)INM-10-20170113},
      pnm          = {5232 - Computational Principles (POF4-523) / MetaMoSim -
                      Generic metadata management for reproducible
                      high-performance-computing simulation workflows - MetaMoSim
                      (ZT-I-PF-3-026) / Brain-Scale Simulations
                      $(jinb33_20220812)$ / ICEI - Interactive Computing
                      E-Infrastructure for the Human Brain Project (800858) /
                      Helmholtz Platform for Research Software Engineering -
                      Preparatory Study $(HiRSE_PS-20220812)$},
      pid          = {G:(DE-HGF)POF4-5232 / G:(DE-Juel-1)ZT-I-PF-3-026 /
                      $G:(DE-Juel1)jinb33_20220812$ / G:(EU-Grant)800858 /
                      $G:(DE-Juel-1)HiRSE_PS-20220812$},
      typ          = {PUB:(DE-HGF)24},
      doi          = {10.34734/FZJ-2024-05342},
      url          = {https://juser.fz-juelich.de/record/1030589},
}