T2 News

Lawrence Livermore Partners With IBM to Build New Frontiers of Supercomputing

Livermore IBM

Lawrence Livermore National Laboratory (LLNL) recently announced that it will receive a brain-inspired supercomputing platform for deep learning developed by IBM Research. This neurosynaptic computer chip, called IBM TrueNorth, is the first of its kind and will process the equivalent of 16 million neurons and 4 billion synapses, and consume the energy equivalent of a hearing aid battery—just 2.5 watts of power.

IBM TrueNorth’s structure is based on the neural network design of the IBM Neuromorphic System, which can interpret complex cognitive tasks similar to that of the human brain and is far more efficient than conventional computer chips.

TrueNorth was originally developed under the support of the Defense Advanced Research Project Agency’s (DARPA) Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) program in collaboration with Cornell University. Now the technology will now lend itself to assisting in Department of Energy (DOE) laboratory supercomputing research and development projects for national nuclear security. Tasks such as pattern recognition and integrated sensory processing of the new system will be used to explore new computing capabilities important to the National Nuclear Security Administration (NNSA) cybersecurity mission of safeguarding the nation’s nuclear weapons stockpile and nonproliferation. The NNSA’s Advanced Simulation and Computing (ASC) program, located at LLNL, will also use the technology to evaluate machine-learning applications, deep-learning algorithms, and architectures, as well as conduct general computing feasibility studies.

“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.”

TrueNorth’s technology represents a major shift from computer design that has been prevalent for the past 70 years, and could prove to be a powerful complement in the development of next-generation supercomputers that are able to perform at exascale speeds. Neurosynaptic systems like TrueNorth also require significantly less electrical power and volume to operate, much like the human brain.

“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 consists of 5.4 billion transistors wired together to create an array of 1 million digital neurons that communicate with one another via 256 million electrical synapses. It consumes 70 milliwatts of power running in real time and delivers 46 giga synaptic operations per second—orders of magnitude lower energy than a conventional computer running on the same neural network.

Under terms of the $1 million contract, LLNL will receive a 16-chip TrueNorth system representing a total of 16 million neurons and 4 billion synapses. LLNL also will receive an end-to-end ecosystem to create and program energy-efficient machines that mimic the brain’s abilities for perception, action, and cognition. The ecosystem consists of a simulator, a programming language, an integrated programming environment, a library of algorithms as well as applications, firmware, tools for composing neural networks for deep learning, a teaching curriculum, and cloud enablement. 

LLNL computer scientists will collaborate with IBM Research, partners across the Department of Energy complex, and universities to expand the frontiers of neurosynaptic architecture, system design, algorithms, and software ecosystem.

For more information about the recent collaboration and partnership between LLNL and IBM Research to utilize TrueNorth, LLNL breaks down the details in this video.

To learn more about Lawrence Livermore National Laboratory, visit www.llnl.gov.

To learn more about IBM Research, visit www.research.ibm.com.

Click here to view the original LLNL article.

T2 News
Far West