Since the final submission of our work on the Compass scalable simulator for the IBM TrueNorth Cognitive Computing architecture [1], we have simulated an unprecedented 2.084 billion neurosynaptic cores containing 53 x 1010 neurons and 1.37 x 1014 synapses running at only 1542x slower than real time. We attained this scale by using the Sequoia 96-rack IBM® Blue Gene®/Q supercomputer at Lawrence Livermore National Labs. By comparison, the ultimate vision of the DARPA SyNAPSE program is to build a cognitive computing architecture with 1010 neurons and 1014 synapses, inspired by the following: Shepherd [2] estimates the number of synapses in the human brain as 0.6 x 1014, and Koch [3] estimates the number of synapses in the human brain as 2.4 x 1014.

It is important to clarify that we have not built a biologically realistic simulation of the complete human brain. Rather, we have simulated a novel modular, scalable, non-von Neumann, ultra-low power, cognitive computing architecture at the DARPA SyNAPSE metric of 1014 synapses that itself is inspired by the number of synapses in the human brain. We mathematically abstract away computation (“neurons”), memory (“synapses”), and communication (“axons”, “dendrites”) from biological detail towards engineering goals of maximizing function (utility, applications) and minimizing hardware cost (power, area, delay) and design complexity.

By: Theodore M. Wong, Robert Preissl, Pallab Datta, Myron Flickner, Raghavendra Singh, Steven K. Esser, Emmett McQuinn, Rathinakumar Appuswamy, William P. Risk, Horst D. Simon, Dharmendra S. Modha

Published in: RJ10502 in 2012


Questions about this service can be mailed to .