Gast ::
| Hauptseite > Publikationsdatenbank > Exploiting network topology in brain-scale simulations of spiking neural networks |
| Hauptseite > Publikationsdatenbank > Exploiting network topology in brain-scale simulations of spiking neural networks |
| Journal Article | FZJ-2026-04460 |
; ;
2026
IOP Publishing Ltd.
Bristol
This record in other databases:
Please use a persistent id in citations: doi:10.1088/2634-4386/ae762e doi:10.34734/FZJ-2026-04460
Abstract: Simulation code for conventional supercomputers serves as a reference for neuromorphic computing systems. The present bottleneck of distributed large-scale spiking neuronal network simulations is the collective communication between compute nodes. Communication speed seems limited by the interconnect between the nodes and the software library orchestrating the transfer of data packets. Profiling reveals, however, that the variability of the time required by the compute nodes between communication calls is large. The bottleneck is in fact the waiting time for the slowest node. A statistical model explains total simulation time on the basis of the collective distribution of computation times between communication calls. A fundamental cure is to avoid communication calls because this requires fewer synchronizations and reduces the relative variability of computation times across compute nodes. The spatial organization of the mammalian brain into areas lends itself to such an optimization strategy. The connections between neurons within an area have short delays, but the delays of the long-range connections across areas are an order of magnitude longer. This suggests a structure-aware mapping of areas to compute nodes allowing for a partition into more frequent communication between nodes simulating a particular area and less frequent global communication. We demonstrate a substantial performance gain on a real-world example. Our study proposes a local-global hybrid communication architecture for large-scale neuronal network simulations as a first step in mapping the structure of the brain to the structure of a supercomputer. We challenge the long-standing belief that the bottleneck of simulation is the synchronization inherent in the collective calls of standard communication libraries. The work provides guidelines for the energy efficient simulation of neuronal networks on conventional computing systems and raises the bar for neuromorphic systems.
; 
; 
; 
; Article Processing Charges ; Clarivate Analytics Master Journal List ; DOAJ Seal ; Emerging Sources Citation Index ; Fees ; SCOPUS ; Web of Science Core Collection
|
The record appears in these collections: |
PDF