This little electronic critter is able to process an amount of data that is equal to 16 million neurons and 4 billion synapses. It also takes in the energy equal to a hearing aid battery. That is merely 2.8 watts of power. This electronic brain of sorts can recognize patterns at the drop of a hat.
Also its integrated sensory processing power is far more efficient than ordinary microchips. This new device will be employed to gauge novel computing capabilities.
These in turn are of crucial importance to the NNSA (National Nuclear Security Administration). It is an organization that leads the way in cyber strategies, care of the nuclear weapons of the nation and nuclear deterrence.
The ASC program of this organization will judge machine learning schemes, algorithms and architectures in its quest to test feasibility standards. ASC is an important branch of the NNSA which ensures that weapons are graded without being tested. This is mainly to ensure peace in the global village.
Neuromorphic computing is the name of the game. It opens up exciting new avenues of research and development. Also the issue of national security connected with a nuclear weapons stockpile is solved via this method.
“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.”
The tools placed in the hands of scientists will enable the very paradigm of science to undergo a shift as we know it. The field of computer design that has been extant since the past 70 years is about to undergo a seismic shake-up.
Next generation supercomputers that perform at a speed that is 50 times that of current petaflop systems will be a likelihood soon.
Since all these latest systems of AI are built on the model of the human brain, they require comparatively little energy input. Exascale computing will be all about reducing power consumption since a lean and green future demands such a state of affairs.
A new eon may shine forth from the avalanche of time as mankind conducts its way forward into even more progressive paths. Breaking the barriers of the possible is what this is all about.
“The low power consumption of these brain-inspired processors reflects industry’s desire and a creative approach to reducing power consumption in all components for future systems as we set our sights on exascale computing,” said Michel McCoy, LLNL program director for Weapon Simulation and Computing.
“The delivery of this advanced computing platform represents a major milestone as we enter the next era of cognitive computing,” said Dharmendra Modha, IBM fellow and chief scientist of Brain-inspired Computing, IBM Research.
“We value our partnerships with the national labs. In fact, prior to design and fabrication, we simulated the IBM TrueNorth processor using LLNL’s Sequoia supercomputer. This collaboration will push the boundaries of brain-inspired computing to enable future systems that deliver unprecedented capability and throughput, while minimizing the capital, operating and programming costs – keeping our nation at the leading edge of science and technology.”
A single TrueNorth processor has 5.4 billion transistors in tandem in it. These go on to form 1 million digital neurons. As for power consumption, it is a measly 70 milliwatts.
i4u