IBM’s brain-inspired supercomputer to Lawrence Livermore National Laboratory
31 March, 2016
The Platform is based on a neuro synaptic chip called TrueNorth. It will process the equivalent of 16 million neurons and 4 billion synapses and will be used for complex tasks
The Platform is based on a neuro synaptic chip called TrueNorth. It will process the equivalent of 16 million neurons and 4 billion synapses and will be used for complex tasks concerning national security
Lawrence Livermore National Laboratory (LLNL) today announced it has purchased a first-of-a-kind brain-inspired supercomputing platform for deep learning inference developed by IBM Research (NYSE: IBM). Based on a breakthrough neurosynaptic computer chip called IBM TrueNorth, the scalable platform will process the equivalent of 16 million neurons and 4 billion synapses and consume a mere 2.5 watts of power for the 16 TrueNorth chips.
The brain-like, neural network design of the IBM Neuromorphic System is able to infer complex cognitive tasks such as pattern recognition and integrated sensory processing far more efficiently than conventional chips. The newly acquired system will be used to explore computing capabilities important to the National Nuclear Security Administration, the federal agency in charge of US nuclear deterrent and non-proliferation.
“Neuromorphic computing opens very exciting new possibilities and is consistent with what we see as the future of the high performance computing and simulation at the heart of our national security missions,” said Jim Brase, LLNL deputy associate director for Data Science. “The potential capabilities neuromorphic computing represents and the machine intelligence that these will enable will change how we do science.”
According to IBM Research, TrueNorth represents a “fundamental departure from computer design” and is likely to play a part in the development of supercomputers 50-times faster than the most advanced systems today.
The True North chip has more than 5 billion transistors configured as a million neurons and 256 million synapses. It consumes only about 70 miliwatts, no more than a hearing aid. The platform delivered to the LLNL houses 16 such chips.
Speaking of the acquisition, Dharmendra S Modha, IBM Fellow, chief scientist, brain-inspired computing, IBM Research – Almaden, said: “This collaboration will push the boundaries of brain-inspired computing to enable future systems that deliver unprecedented capability and throughput, while helping to minimize the capital, operating and programming costs – keeping our nation at the leading edge of science and technology.”
The LLNL will also receive an end-to-end ecosystem that helps create and program energy-efficient machines that mimic the brain’s abilities for perception, action and cognition. LLNL scientists will collaborate with IBM Research and other partners to expand the frontiers of neurosynaptic architecture.