- Lawrence Livermore National Laboratory has purchased a new brain-inspired supercomputing platform from IBM, powered by IBM's TrueNorth neuromorphic chips.
- Neuromorphic chips are optimized for very high performance at very low power, and suitable for AI and Machine Learning applications.
- IBM is ahead in the race towards next-generation computing hardware for both supercomputers and mobile devices.
Lawrence Livermore National Laboratory (LLNL) has purchased a new brain-inspired supercomputing platform developed by International Business Machines Corp (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 while consuming only the energy equivalent of a tablet computer. The brain-like, neural network design of the IBM neuromorphic system is able to run complex cognitive tasks such as pattern recognition and integrated sensory processing far more efficiently than conventional chips.
“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.”
LLNL will receive a 16-chip TrueNorth system representing a total of 16 million neurons and 4 billion synapses. The new system will be used to explore new computing capabilities important to the National Nuclear Security Administration (NNSA) missions in cybersecurity, stewardship of the nation’s nuclear weapons stockpile and nonproliferation.
“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.”
Neuromorphic - or neurosynaptic - computing tries to achieve more efficient computation by emulating how neurons and synapses process information in the brain, very efficiently at low power. The "TrueNorth" chip, a neuromorphic chip with 1,000,000 neurons and 256 million programmable synapses unveiled in August 2014, developed by IBM with funding from the Defense Advanced Research Projects Agency, is one of the first neuromorphic chips on the market.
Neuromorphic computing represents a fundamental departure from current computers and could lead to next-generation supercomputers able to perform at "exascale" speeds (quintillion floating point operations per second), 50 times (or two orders of magnitude) faster than today’s most advanced petaflop (quadrillion floating point operations per second) supercomputers.
Another important consideration is that, like the human brain, neurosynaptic systems require significantly less electrical power and volume. In fact, there is a huge gap in power consumption between today's supercomputers, which may require dedicated power plants, and the brain, which is a light, portable and efficient computer powered by three meals a day. It appears that the brain's efficiency, small size and weight, and low power consumption, can be emulated by neuromorphic computing. Therefore, neuromorphic hardware could enable next-generation mobile devices.
The Wall Street Journal notes that the 16-processor Lawrence Livermore machine is an important test of IBM’s TrueNorth technology. Neuromorphic chips such as TrueNorth are better suited to the Artificial Intelligence (AI) technique known as deep learning, which also is based loosely on how the brain operates, and in the future could power everything - from large data centers to cars - as companies look for ways to accelerate the performance of their Machine Learning (ML) algorithms.
Alphabet Inc (NASDAQ:GOOGL) is convinced that AI is rapidly becoming a mature technology with a potential for world-changing applications. The recent AlphaGo AI breakthrough indicates that AI is becoming adept at more and more high-level cognitive tasks that used to be considered as too complex for automation, and Alphabet plans to leverage its machine learning technology to power its commercial cloud computing services.
Other companies are trying to develop hardware optimized for ML. For example, Qualcomm (NASDAQ:QCOM) is working on a chip called Zeroth, and Microsoft (NASDAQ:MSFT) researchers are experimenting with programmable processors designed to work with the company’s Bing search engine.
But at this moment, IBM seems ahead of the competition. Modha's personal website has detailed information on this significant milestone in the history of IBM's neuromorphic computing project. “The race to get to the new architecture of this era is on,” said Modha to The Wall Street Journal. “And, frankly, we’re leading.” IBM's leadership in the race toward next-generation computing hardware for both supercomputers and mobile devices is very good news for investors who hold International Business Machines Corp. stock.