, Volume 100, Issue 9, pp 907–926 | Cite as

Evaluation of the computational efficacy in GPU-accelerated simulations of spiking neurons

  • Kazuhisa Fujita
  • Shun Okuno
  • Yoshiki Kashimori


To understand the mechanism of information processing by a biological neural network, computer simulation of a large-scale spiking neural network is an important method. However, because of a high computation cost of the simulation of a large-scale spiking neural network, the simulation requires high performance computing implemented by a supercomputer or a computer cluster. Recently, hardware for parallel computing such as a multi-core CPU and a graphics card with a graphics processing unit (GPU) is built in a gaming computer and a workstation. Thus, parallel computing using this hardware is becoming widespread, allowing us to obtain powerful computing power for simulation of a large-scale spiking neural network. However, it is not clear how much increased performance the parallel computing method using a new GPU yields in the simulation of a large-scale spiking neural network. In this study, we compared computation time between the computing methods with CPUs and GPUs in a simulation of neuronal models. We developed computer programs of neuronal simulations for the computing systems that consist of a gaming graphics card with new architecture (the NVIDIA GTX 1080) and an accelerator board using a GPU (the NVIDIA Tesla K20C). Our results show that the computing systems can perform a simulation of a large number of neurons faster than CPU-based systems. Furthermore, we investigated the accuracy of a simulation using single precision floating point. We show that the simulation results of single precision were accurate enough compared with those of double precision, but chaotic neuronal response calculated by a GPU using single precision is prominently different from that calculated by a CPU using double precision. Furthermore, the difference in chaotic dynamics appeared even if we used double precision of a GPU. In conclusion, the GPU-based computing system exhibits a higher computing performance than the CPU-based system, even if the GPU system includes data transfer from a graphics card to host memory.


GPGPU CUDA Acceleration Spiking neural network Neuron model 

Mathematics Subject Classification

Simulation and numerical modeling Numerical chaos 



This work was supported by JSPS KAKENHI Grant No. 15K07146.


  1. 1.
    Aihara K, Matsumoto G, Ikegaya Y (1984) Periodic and non-periodic responses of a periodically forced Hodgkin–Huxley oscillator. J Theor Biol 109(2):249–269CrossRefGoogle Scholar
  2. 2.
    Ananthanarayanan R, Esser SK, Simon HD, Modha DS (2009) The cat is out of the bag: cortical simulations with \(10^9\) neurons, \(10^{13}\) synapses. In: IEEE computer society, pp. 1–12Google Scholar
  3. 3.
    Baladron J, Fasoli D, Faugeras O (2012) Three applications of GPU computing in neuroscience. Comput Sci Eng 14(3):40–47CrossRefGoogle Scholar
  4. 4.
    Bernhard F, Keriven R (2006) Spiking neurons on GPUs. In computational science ICCS 2006. Springer, Berlin, pp 236–243CrossRefGoogle Scholar
  5. 5.
    Beyeler M, Dutt ND, Krichmar JL (2013) Categorization and decision-making in a neurobiologically plausible spiking network using a STDP-like learning rule. Neural Netw 48:109–124CrossRefGoogle Scholar
  6. 6.
    Beyeler M, Oros N, Dutt N, Krichmar JL (2015) A GPU-accelerated cortical neural network model for visually guided robot navigation. Neural Netw 72:75–87CrossRefGoogle Scholar
  7. 7.
    Beyeler M, Richert M, Dutt ND, Krichmar JL (2014) Efficient spiking neural network model of pattern motion selectivity in visual cortex. Neuroinform 12(3):435–454CrossRefGoogle Scholar
  8. 8.
    Bray LCJ, Anumandla SR, Thibeault CM, Hoang RV, Goodman PH, Dascalu SM, Bryant BD, Harris FC (2012) Real-time human–robot interaction underlying neurorobotic trust and intent recognition. Neural Netw 32:130–137CrossRefGoogle Scholar
  9. 9.
    Brette R (2015) Philosophy of the spike: rate-based vs. spike-based theories of the brain. Front Syst Neurosci 9:151CrossRefGoogle Scholar
  10. 10.
    Carlson KD, Nageswaran JM, Dutt N, Krichmar JL (2014) An efficient automated parameter tuning framework for spiking neural networks. Front Neurosci 8:10CrossRefGoogle Scholar
  11. 11.
    Cheng J, Grossman M, McKercher T (2014) Professional CUDA C programming. Wrox, BirminghamGoogle Scholar
  12. 12.
    de Camargo RY, Rozante L, Song SW (2011) A multi-GPU algorithm for large-scale neuronal networks. Concurr Comput Pract Exp 23(6):556–572CrossRefGoogle Scholar
  13. 13.
    Dinkelbach HU, Vitay J, Beuth F, Hamker FH (2012) Comparison of GPU- and CPU-implementations of mean-firing rate neural networks on parallel hardware. Network 23(4):212–236CrossRefGoogle Scholar
  14. 14.
    Fidjeland AK, Shanahan MP (2010) Accelerated simulation of spiking neural networks using GPUs. In 2010 International joint conference on Neural networks (IJCNN), pp 1–8Google Scholar
  15. 15.
    Gangal H, Dar G (2014) Mode locking, chaos and bifurcations in Hodgkin–Huxley neuron forced by sinusoidal current. Chaot Simul Model 3:287–294Google Scholar
  16. 16.
    Gerstner W, Kistler WM (2002) Spiking neuron model, chapter noise in spiking neuron models. Cambridge University Press, New York, pp 157–209CrossRefzbMATHGoogle Scholar
  17. 17.
    Goodman DFM (2010) Code generation: a strategy for neural network simulators. Neuroinformatics 8(3):183–196CrossRefGoogle Scholar
  18. 18.
    Hoang RV, Tanna D, Bray JCL, Dascalu SM, Harris FCJ (2013) A novel CPU/GPU simulation environment for large-scale biologically realistic neural modeling. Front Neuroinform 7:19CrossRefGoogle Scholar
  19. 19.
    Hodgkin AL, Huxley AF (1952) A quantitative description of membrane current and its application to conduction and excitation in nerve. J Physiol 117(4):500–544CrossRefGoogle Scholar
  20. 20.
    Igarashi J, Shouno O, Fukai T, Tsujino H (2011) Real-time simulation of a spiking neural network model of the basal ganglia circuitry using general purpose computing on graphics processing units. Neural Netw 24(9):950–960CrossRefGoogle Scholar
  21. 21.
    Izhikevich EM (2003) Simple model of spiking neurons. IEEE Trans Neural Netw 14(6):1569–1572MathSciNetCrossRefGoogle Scholar
  22. 22.
    Izhikevich EM (2004) Which model to use for cortical spiking neurons? IEEE Trans Neural Netw 15(5):1063–1070CrossRefGoogle Scholar
  23. 23.
    Izhikevich EM, Edelman GM (2008) Large-scale model of mammalian thalamocortical systems. Proc Nat Acad Sci USA 105(9):3593–3598CrossRefGoogle Scholar
  24. 24.
    Liao S, Wang P (2014) On the mathematically reliable long-term simulation of chaotic solutions of Lorenz equation in the interval [0 10000]. Sci China Phys Mech Astron 57:330–335CrossRefGoogle Scholar
  25. 25.
    Morris C, Lecar H (1981) Voltage oscillations in the barnacle giant muscle fiber. Biophys J 35:193–213CrossRefGoogle Scholar
  26. 26.
    Nageswaran JM, Dutt N, Krichmar JL, Nicolau A, Veidenbaum A (2009) Efficient simulation of large-scale spiking neural networks using CUDA graphics processors. In: 2009 Proceedings of international joint conference on neural networks, pp 2145–2152Google Scholar
  27. 27.
    Nageswaran JM, Dutt N, Krichmar JL, Nicolau A, Veidenbaum AV (2009) A configurable simulation environment for the efficient simulation of large-scale spiking neural networks on graphics processors. Neural Netw 22(5–6):791–800CrossRefGoogle Scholar
  28. 28.
    Pallipuram VK, Bhuiyan MA, Smith MC (2011) Evaluation of GPU architectures using spiking neural networks. In: 2011 Symposium application accelerators in high-performance computing, pp. 93–102Google Scholar
  29. 29.
    Pallipuram VK, Bhuiyan M, Smith MC (2012) A comparative study of GPU programming models and architectures using neural networks. J Supercomput 61(3):673–718CrossRefGoogle Scholar
  30. 30.
    Pallipuram VK, Smith MC, Sarma N, Anand R, Weill E, Sapra K (2015) Subjective versus objective: classifying analytical models for productive heterogeneous performance prediction. J Supercomput 71:162–201CrossRefGoogle Scholar
  31. 31.
    Richert M, Nageswaran JM, Dutt N, Krichmar JL (2011) An efficient simulation environment for modeling large-scale cortical processing. Front Neuroinform 5:19CrossRefGoogle Scholar
  32. 32.
    Trappenberg T (2010) Fundamentals of computational neuroscience. OUP, OxfordzbMATHGoogle Scholar
  33. 33.
    Wang F (2015) Simulation tool for asynchronous cortical streams (STACS): interfacing with spiking neural networks. Proc Comput Sci 61:322–327CrossRefGoogle Scholar
  34. 34.
    Yamazaki T, Igarashi J (2013) Realtime cerebellum: a large-scale spiking network model of the cerebellum that runs in realtime using a graphics processing unit. Neural Netw 47:103–111CrossRefGoogle Scholar
  35. 35.
    Yavuz E, Turner J, Nowotny T (2016) GeNN: a code generation framework for accelerated brain simulations. Sci Rep 6:18854CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Austria, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Engineering ScienceUniversity of Electro-CommunicationsChofuJapan
  2. 2.Department of Integrated Science and TechnologyNational Institute of Technology, Tsuyama CollageTsuyamaJapan

Personalised recommendations