% 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:1044380,
      author       = {Villamar, Jose and Tiddia, Gianmarco and Sergi, Luca and
                      Babu, Pooja and Pontisso, Luca and Simula, Francesco and
                      Lonardo, Alessandro and Pastorelli, Elena and Paolucci, Pier
                      Stanislao and Golosio, Bruno and Senk, Johanna},
      title        = {{NEST} {GPU} simulations scale up to networks of billions
                      of spiking neurons and trillions of synapses},
      school       = {RWTH Aachen},
      reportid     = {FZJ-2025-03154},
      year         = {2025},
      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 is
                      a GPU-based simulator under the NEST Initiative written in
                      CUDA-C++ that demonstrates high simulation speeds with
                      models of various network sizes on single-GPU and multi-GPU
                      systems [1,2,3]. 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. Here, we show the performance of our simulation
                      technology with a scalable network model across multiple
                      network sizes approaching human cortex magnitudes.For this,
                      we propose a novel method to efficiently instantiate large
                      networks on multiple GPUs in parallel. Our approach relies
                      on the deterministic initial state of pseudo-random number
                      generators (PRNGs). While requiring synchronization of
                      network construction directives between MPI processes and a
                      small memory overhead, this approach enables dynamical
                      neuron creation and connection at runtime. The method is
                      evaluated through a two-population recurrently connected
                      network model designed for benchmarking an arbitrary number
                      of GPUs while maintaining first-order network statistics
                      across scales.The benchmarking model was tested during an
                      exclusive reservation of the LEONARDO Booster cluster. While
                      keeping constant the number of neurons and incoming synapses
                      to each neuron per GPU, we performed several simulation runs
                      exploiting in parallel from 400 to 12,000 (full system)
                      GPUs. Each GPU device contained approximately 281 thousand
                      neurons and 3.1 billion synapses. Our results show network
                      construction times of less than a second using the full
                      system and stable dynamics across scales. At full system
                      scale, the network model was composed of approximately 3.37
                      billion neurons and 37.96 trillion synapses $(~25\%$ human
                      cortex).To conclude, our novel approach enabled network
                      model instantiation of magnitudes nearing human cortex scale
                      while keeping fast construction times, on average of 0.5s
                      across trials. The stability of dynamics and performance
                      across scales obtained in our model is a proof of
                      feasibility paving the way for biologically more plausible
                      and detailed brain scale models. [1]
                      https://doi.org/10.3389/fncom.2021.627620 . [2]
                      https://doi.org/10.3389/fninf.2022.883333 . [3]
                      https://doi.org/10.3390/app13179598},
      month         = {Jul},
      date          = {2025-07-05},
      organization  = {34th Annual Computational Neuroscience
                       Meeting, Florence (Italy), 5 Jul 2025 -
                       9 Jul 2025},
      subtyp        = {After Call},
      cin          = {IAS-6 / JSC},
      cid          = {I:(DE-Juel1)IAS-6-20130828 / I:(DE-Juel1)JSC-20090406},
      pnm          = {5232 - Computational Principles (POF4-523) / 5235 -
                      Digitization of Neuroscience and User-Community Building
                      (POF4-523) / HiRSE - Helmholtz Platform for Research
                      Software Engineering (HiRSE-20250220) / JL SMHB - Joint Lab
                      Supercomputing and Modeling for the Human Brain (JL
                      SMHB-2021-2027)},
      pid          = {G:(DE-HGF)POF4-5232 / G:(DE-HGF)POF4-5235 /
                      G:(DE-Juel-1)HiRSE-20250220 / G:(DE-Juel1)JL SMHB-2021-2027},
      typ          = {PUB:(DE-HGF)24},
      doi          = {10.34734/FZJ-2025-03154},
      url          = {https://juser.fz-juelich.de/record/1044380},
}