IBM Research And LLNL Claim 10¹⁴ Synapse Simulation

Inspired by the function, power, and volume of the organic brain, IBMis 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) conference in Salt Lake City.  The paper, “Compass: A scalable simulator for an architecture for Cognitive Computing" is available online.

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.