IBM Research And LLNL Claim 1014 Synapse Simulation

Monday, November 19, 2012

Brain Simulation
IBM Research has presented the next milestone toward fulfilling the ultimate vision of the DARPA’s cognitive computing program, called Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) at the Supercomputing 2012 conference last week. According to the head of the research, Dharmendra Modha, “This fulfills a core vision of the DARPA SyNAPSE project to bring together nanotechnology, neuroscience, and supercomputing to lay the foundation of a novel cognitive computing architecture that complements today’s von Neumann machines.”
Inspired by the function, power, and volume of the organic brain, IBM is reportedly developing TrueNorth, a novel modular, scalable, non-von Neumann, ultra-low power, cognitive computing architecture.  The TrueNorth system consists of a scalable network of neurosynaptic cores, with each core containing neurons, dendrites, synapses, and axons. Also, to help the computation of TrueNorth, IBM has developed Compass, a multi-threaded, massively parallel functional simulator and a parallel compiler that maps a network of long-distance pathways in the macaque monkey brain to TrueNorth.

The research was recently presented at the Super Computing 2012 (SC12) confernence in Salt Lake City.  The paper, "Compass: A scalable simulator for an architecture for Cognitive Computing" is available online. of final paper.

IBM and Lawrence Livermore National Laboratory (LBNL) demonstrated near-perfect weak scaling on a 16 rack IBM Blue Gene/Q (262,144 processor cores, 256 TB memory), achieving an unprecedented scale of 256 million neurosynaptic cores containing 65 billion neurons and 16 trillion synapses running only 388× slower than real time with an average spiking rate of 8.1 Hz. By using emerging PGAS communication primitives, IBM also demonstrated 2× better real-time performance over MPI primitives on a 4 rack Blue Gene/P (16384 processor cores, 16 TB memory).

Also, since submitting the original paper, the work has continued using 96 Blue Gene/Q racks of the Lawrence Livermore National Lab Sequoia supercomputer (1,572,864 processor cores, 1.5 PB memory, 98,304 MPI processes, and 6,291,456 threads), IBM and LBNL achieved an unprecedented scale of 2.084 billion neurosynaptic cores containing 53x1010 neurons and 1.37x1014 synapses running only 1542× slower than real time. Here is PDF of IBM Research Report, RJ 10502.

As in the image above, A Network of Neurosynaptic Cores Derived from Long-distance Wiring in the Monkey Brain -Neuro-synaptic cores are locally clustered into brain-inspired regions, and each core is represented as an individual point along the ring. Arcs are drawn from a source core to a destination core with an edge color defined by the color assigned to the source core.

The ultimate vision of the DARPA SyNAPSE program is to build a cognitive computing architecture with 1010 neurons and 1014 synapses. “The vision for the Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) program is to develop electronic neuromorphic machine technology that scales to biological levels.”  This DARPA SyNAPSE metric was probably inspired by the following: Gordon Shepherd in The Synaptic Organization of the Brain that estimates the number of synapses in the human brain as 0.6x1014 and Christof Koch in Biophysics of Computation: Information Processing in Single Neurons estimates the number of synapses in the human brain as 2.4x1014.

The researchers, led by Dharmendra Modha, have not built a biologically realistic simulation of the complete human brain. Instead they have simulated a novel modular, scalable, non-von Neumann, ultra-low power, cognitive computing architecture at the scale of DARPA SyNAPSE metric of 1014 synapses that, in turn, is inspired by the number of synapses in the human brain.

Computation ("neurons"), memory ("synapses"), communication ("axons", "dendrites") are mathematically abstracted away from biological detail towards engineering goals of maximizing function (utility, applications) and minimizing cost (power, area, delay) and design complexity of hardware implementation claim the researchers.

Modha and his research team have used Compass to demonstrate numerous applications of the TrueNorth architecture, such as optic flow, attention mechanisms, image and audio classification, multi-modal image audio classification, character recognition, robotic navigation, and spatio-temporal feature extraction. These applications will be published separately.

SOURCE  Dharmendra Modha's Blog

By 33rd SquareSubscribe to 33rd Square