% 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{Kurth:894269,
      author       = {Kurth, Anno and Finnerty, Justin and Terhorst, Dennis and
                      Pronold, Jari and Senk, Johanna and Diesmann, Markus},
      title        = {{S}ub {R}ealtime {S}imulation of a {F}ull {D}ensity
                      {C}ortical {M}icrocircuit {M}odel on a {S}ingle {C}ompute
                      {N}ode},
      reportid     = {FZJ-2021-03144},
      year         = {2021},
      abstract     = {The cortical microcircuit is a building block of the
                      mammalian brain. In a model of the network below a 1 mm2
                      patch of cortical surface [1] the spatial structure is
                      replaced by cell-type specific random connectivity. Each
                      layer is represented by an excitatory and an inhibitory
                      population of integrate-and-fire model neurons. The network
                      model is a benchmark for neuromorphic systems [2, 3, 4].This
                      contribution shows performance data for the microcircuit
                      model on two AMD EPYC Rome 128 core compute nodes coupled by
                      a direct Infiniband interconnect and running NEST 2.14 [5]
                      (with fix 726f9b04bbd47c). On a single node we observe sub
                      realtime performance, on two the simulation is 1.7 times
                      faster than realtime. Our study of the aged 4g kernel serves
                      as a reference for present optimizations, exposes
                      bottlenecks, and guides the design of future computing
                      systems.For the single node the energy per synaptic event is
                      0.26 μJ, and for the fastest configuration using two nodes
                      0.39 μJ. These values are in the same order of magnitude as
                      the lowest reported so far. The findings confirm a
                      non-trivial relationship [2] between the resources in use
                      and the energy required. At the poster we demonstrate how
                      power measurements with a contemporary PDU can be aligned
                      with benchmark timers to obtain a reliable time course of
                      power consumption.AcknowledgementsPartially supported by EU
                      Horizon 2020 945539 (HBP SGA3) and Helmholtz IVF SO-092
                      (ACA).References 1. Potjans TC $\&$ Diesmann M (2014) The
                      cell-type specific cortical microcircuit: relating structure
                      and activity in a full-scale spiking network model. Cerebral
                      Cortex 24:785–806. doi: 10.1093/cercor/bhs358 2. van
                      Albada SJ, et al. (2018) Performance comparison of the
                      digital neuromorphic hardware SpiNNaker and the neural
                      network simulation software NEST for a full-scale cortical
                      microcircuit model. Front Neurosci 12:291. doi:
                      10.3389/fnins.2018.00291 3. Knight JC $\&$ Nowotny T (2018)
                      GPUs outperform current HPC and neuromorphic solutions in
                      terms of speed and energy when simulating a highly-connected
                      cortical model. Front Neurosci 12:941. doi:
                      10.3389/fnins.2018.00941},
      month         = {Jun},
      date          = {2021-06-28},
      organization  = {NEST Conference 2021, Aas (Norway), 28
                       Jun 2021 - 29 Jun 2021},
      subtyp        = {After Call},
      cin          = {INM-6 / IAS-6 / INM-10},
      cid          = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)IAS-6-20130828 /
                      I:(DE-Juel1)INM-10-20170113},
      pnm          = {5234 - Emerging NC Architectures (POF4-523) / Advanced
                      Computing Architectures $(aca_20190115)$ / HBP SGA3 - Human
                      Brain Project Specific Grant Agreement 3 (945539)},
      pid          = {G:(DE-HGF)POF4-5234 / $G:(DE-Juel1)aca_20190115$ /
                      G:(EU-Grant)945539},
      typ          = {PUB:(DE-HGF)6},
      url          = {https://juser.fz-juelich.de/record/894269},
}