Real-Time Scalable Cortical Computing at 46 Giga-Synaptic OPS/Watt with ~100x Speedup in Time-to-Solution and ~100,000x Reduction in Energy-to-Solution

Andrew S. Cassidy, Rodrigo Alvarez-Icaza, Filipp Akopyan, Jun Sawada, John V. Arthur, Paul A. Merolla, Pallab Datta, Marc Gonzalez Tallada, Brian Taba, Alexander Andreopoulos, Arnon Amir, Steven K. Esser, Jeff Kusnitz, Rathinakumar Appuswamy, Chuck Haymes, Bernard Brezzo, Roger Moussalli, Ralph Bellofatto, Christian Baks, Michael Mastro, Kai Schleupen, Charles E. Cox, Ken Inoue, Steve Millman, Nabil Imam, Emmett McQuinn, Yutaka T. Nakamura, Ivan Vo, Chen Guo, Don Nguyen, Scott Lekuch, Sameh Assad, Daniel Friedman, Bryan L. Jackson, Myron D. Flickner, William P. Risk, Rajit Manohar, Dharmendra S. Modha

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 TrueNorth, a co-designed silicon expression of the kernel. TrueNorth 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, TrueNorth 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 TrueNorth chips into arrays, forming a foundation for cortex-like scalability. TrueNorth'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.
 
  
Yale