Abstract
Real-time simulation of a large-scale biologically representative spiking neural network is presented, through the use of a heterogeneous parallelization scheme and SpiNNaker neuromorphic hardware. A published cortical microcircuit model is used as a benchmark test case, representing ≈1 mm2 of early sensory cortex, containing 77 k neurons and 0.3 billion synapses. This is the first hard real-time simulation of this model, with 10 s of biological simulation time executed in 10 s wall-clock time. This surpasses best-published efforts on HPC neural simulators (3 × slowdown) and GPUs running optimized spiking neural network (SNN) libraries (2 × slowdown). Furthermore, the presented approach indicates that real-time processing can be maintained with increasing SNN size, breaking the communication barrier incurred by traditional computing machinery. Model results are compared to an established HPC simulator baseline to verify simulation correctness, comparing well across a range of statistical measures. Energy to solution and energy per synaptic event are also reported, demonstrating that the relatively low-tech SpiNNaker processors achieve a 10 × reduction in energy relative to modern HPC systems, and comparable energy consumption to modern GPUs. Finally, system robustness is demonstrated through multiple 12 h simulations of the cortical microcircuit, each simulating 12 h of biological time, and demonstrating the potential of neuromorphic hardware as a neuroscience research tool for studying complex spiking neural networks over extended time periods.This article is part of the theme issue ‘Harmonizing energy-autonomous computing and intelligence’.
Highlights
Neural networks provide brains with the ability to perform cognitive tasks, motor control, and learn and memorize information
The cortical microcircuit model was executed for 10 s of biological simulation time, with each 0.1 ms time step evaluated in 0.1 ms CPU time, resulting in a wall-clock simulation time of 10 s, and hard real-time execution
This work presents the first real-time execution of a published large-scale cortical microcircuit model. This result surpasses previously published results in terms of processing speed, with optimal performance relative to real time reported at 3× slow-down for an HPC-based simulator [7], and 2× slow-down for GPUs running optimized spiking neural networks (SNNs) libraries [8]
Summary
Neural networks provide brains with the ability to perform cognitive tasks, motor control, and learn and memorize information. These circuits are robust, fault-tolerant and extremely efficient, with the human cerebral cortex consuming approximately 12 W [1]. Understanding these systems is a complex task requiring consideration of cellular and circuit level behaviours. While experimental measurements are readily taken at the cellular scale, gathering data from large-scale circuits is more challenging This has led to the use of computational models to simulate the response of circuit-scale spiking neural networks (SNNs) representing brain activity. Communication costs dominate performance, and scale nonlinearly with neural network size, slowing down simulations and increasing energy consumption of the underlying simulator
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
