Real-Time Scalable Cortical Computing at 46 Giga-Synaptic OPS/Watt with ~100× Speedup in Time-to-Solution and ~100,000× Reduction in Energy-to-Solution
Authors:
- Andrew S. CassidyACAndrew S. Cassidy
- Rodrigo Alvarez-IcazaRARodrigo Alvarez-Icaza
- Filipp AkopyanFAFilipp Akopyan
- Jun SawadaJSJun Sawada
- John V. ArthurJAJohn V. Arthur
- Paul A. MerollaPMPaul A. Merolla
- Pallab DattaPDPallab Datta
- Marc Gonzalez TalladaMTMarc Gonzalez Tallada
- Brian TabaBTBrian Taba
- Alexander AndreopoulosAAAlexander Andreopoulos
- Arnon AmirAAArnon Amir
- Steven K. EsserSESteven K. Esser
- 1 November 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21674329,p. 27-38
Abstract
Drawing on neuroscience, we have developed a parallel, event-driven kernel for neurosynaptic computation, that is efficient with respect to computation, memory, and communication. Building on the previously demonstrated highly optimized software expression of the kernel, here, we demonstrate True North, a co-designed silicon expression of the kernel. True North achieves five orders of magnitude reduction in energy to-solution and two orders of magnitude speedup in time-to solution, when running computer vision applications and complex recurrent neural network simulations. Breaking path with the von Neumann architecture, True North is a 4,096 core, 1 million neuron, and 256 million synapse brain-inspired neurosynaptic processor, that consumes 65mW of power running at real-time and delivers performance of 46 Giga-Synaptic OPS/Watt. We demonstrate seamless tiling of True North chips into arrays, forming a foundation for cortex-like scalability. True North's unprecedented time-to-solution, energy-to-solution, size, scalability, and performance combined with the underlying flexibility of the kernel enable a broad range of cognitive applications.Keywords
This publication has 51 references indexed in Scilit:
- 50 Years of object recognition: Directions forwardComputer Vision and Image Understanding, 2013
- The Geometric Structure of the Brain Fiber PathwaysScience, 2012
- Meeting the Memory Challenges of Brain-Scale Network SimulationFrontiers in Neuroinformatics, 2012
- Cognitive computingCommunications of the ACM, 2011
- Neuromorphic Silicon Neuron CircuitsFrontiers in Neuroscience, 2011
- Network architecture of the long-distance pathways in the macaque brainProceedings of the National Academy of Sciences, 2010
- A configurable simulation environment for the efficient simulation of large-scale spiking neural networks on graphics processorsNeural Networks, 2009
- Simulation of networks of spiking neurons: A review of tools and strategiesJournal of Computational Neuroscience, 2007
- NEST (NEural Simulation Tool)Scholarpedia, 2007
- OpenMP: an industry standard API for shared-memory programmingIEEE Computational Science and Engineering, 1998