% 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”.
@ARTICLE{Heittmann:906315,
author = {Heittmann, Arne and Psychou, Georgia and Trensch, Guido and
Cox, Charles E. and Wilcke, Winfried W. and Diesmann, Markus
and Noll, Tobias G.},
title = {{S}imulating the {C}ortical {M}icrocircuit {S}ignificantly
{F}aster {T}han {R}eal {T}ime on the {IBM} {INC}-3000
{N}eural {S}upercomputer},
journal = {Frontiers in neuroscience},
volume = {15},
issn = {1662-453X},
address = {Lausanne},
publisher = {Frontiers Research Foundation},
reportid = {FZJ-2022-01365},
pages = {728460},
year = {2022},
abstract = {This article employs the new IBM INC-3000 prototype
FPGA-based neural supercomputer to implement a widely used
model of the cortical microcircuit. With approximately
80,000 neurons and 300 Million synapses this model has
become a benchmark network for comparing simulation
architectures with regard to performance. To the best of our
knowledge, the achieved speed-up factor is 2.4 times larger
than the highest speed-up factor reported in the literature
and four times larger than biological real time
demonstrating the potential of FPGA systems for neural
modeling. The work was performed at Jülich Research Centre
in Germany and the INC-3000 was built at the IBM Almaden
Research Center in San Jose, CA, United States. For the
simulation of the microcircuit only the programmable logic
part of the FPGA nodes are used. All arithmetic is
implemented with single-floating point precision. The
original microcircuit network with linear LIF neurons and
current-based exponential-decay-, alpha-function- as well as
beta-function-shaped synapses was simulated using exact
exponential integration as ODE solver method. In order to
demonstrate the flexibility of the approach, additionally
networks with non-linear neuron models (AdEx, Izhikevich)
and conductance-based synapses were simulated, applying
Runge–Kutta and Parker–Sochacki solver methods. In all
cases, the simulation-time speed-up factor did not decrease
by more than a very few percent. It finally turns out that
the speed-up factor is essentially limited by the latency of
the INC-3000 communication system.},
cin = {PGI-10 / INM-6 / INM-10 / IAS-6 / JSC},
ddc = {610},
cid = {I:(DE-Juel1)PGI-10-20170113 / I:(DE-Juel1)INM-6-20090406 /
I:(DE-Juel1)INM-10-20170113 / I:(DE-Juel1)IAS-6-20130828 /
I:(DE-Juel1)JSC-20090406},
pnm = {5234 - Emerging NC Architectures (POF4-523) / Advanced
Computing Architectures $(aca_20190115)$ / 5122 - Future
Computing $\&$ Big Data Systems (POF4-512) / 5111 -
Domain-Specific Simulation $\&$ Data Life Cycle Labs (SDLs)
and Research Groups (POF4-511)},
pid = {G:(DE-HGF)POF4-5234 / $G:(DE-Juel1)aca_20190115$ /
G:(DE-HGF)POF4-5122 / G:(DE-HGF)POF4-5111},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:35126034},
UT = {WOS:000750070900001},
doi = {10.3389/fnins.2021.728460},
url = {https://juser.fz-juelich.de/record/906315},
}