Arbor — A Morphologically-Detailed Neural Network Simulation Library for Contemporary High-Performance Computing Architectures

Akar, Nora Abi; Yates, Stuart; Karakasis, Vasileios; Klijn, Wouter; Kusters, Anne; Peyser, Alexander; Cumming, Ben

doi:10.1109/EMPDP.2019.8671560

Contribution to a conference proceedings/Contribution to a book

FZJ-2019-02058

Arbor — A Morphologically-Detailed Neural Network Simulation Library for Contemporary High-Performance Computing Architectures

Akar, N. A. ; Cumming, B. (Corresponding author) ; Karakasis, V. ; Kusters, A.FZJ* ; Klijn, W.FZJ* ; Peyser, A. (Corresponding author)FZJ* ; Yates, S.

2019
IEEE
ISBN: 978-1-7281-1644-0

2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), Pavia, Italy, 13 Feb 2019 - 15 Feb 2019 IEEE 274-282 (2019) [10.1109/EMPDP.2019.8671560]

This record in other databases:

Please use a persistent id in citations: http://hdl.handle.net/2128/21897 doi:10.1109/EMPDP.2019.8671560

Abstract: We introduce Arbor, a performance portable library for simulation of large networks of multi-compartment neurons on HPC systems. Arbor is open source software, developed under the auspices of the HBP. The performance portability is by virtue of back-end specific optimizations for x86 multicore, Intel KNL, and NVIDIA GPUs. When coupled with low memory overheads, these optimizations make Arbor an order of magnitude faster than the most widely-used comparable simulation software. The single-node performance can be scaled out to run very large models at extreme scale with efficient weak scaling.Keywords: HPC;GPU;neuroscience;neuron;software

Contributing Institute(s):