Beyond von Neumann, Neuromorphic Computing Steadily Advances

By John Russell

March 21, 2016

Neuromorphic computing – brain inspired computing – has long been a tantalizing goal. The human brain does with around 20 watts what supercomputers do with megawatts. And power consumption isn’t the only difference. Fundamentally, brains ‘think differently’ than the von Neumann architecture-based computers. While neuromorphic computing progress has been intriguing, it has still not proven very practical.

This week neuromorphic computing takes another step forward with a workshop being offered to users from academia, industry and education interested in using two European neuromorphic systems that have been years in development and are coming online for broader use – the BrainScaleS system launching at the Kirchhoff Institute for Physics of Heidelberg University and SpiNNaker, a complementary approach and similarly sized system at the University of Manchester.

Ramping up BrainScaleS and SpiNNaker is an important milestone, strengthening Europe’s position in hardware development for alternative computing. Both projects are part of the European Human Brain Project, originally funded by the European Commission’s Future Emerging Technologies program (2005-2015). The webcast, which will be streamed live on Tuesday, will cover the architecture for both systems and approaches to application development.

BrainScaleS and SpiNNaker take different tacks for modeling neuron activity. One approach is to use traditional analog circuits — like the chips being developed by the BrainScaleS. Analog circuits can be fast and energy and efficient. Conversely, SpiNNaker’s architecture closely links a very large number of digital cores (also fast, and in this case, also energy efficient).

BrainScaleS post-processed wafer containing about 20 million plastic synapses.
BrainScaleS post-processed wafer containing about 20 million plastic synapses.

BrainScaleS’s neuromorphic hardware is based around wafer-scale analog, very large scale integration (VLSI). Each 20-cm-diameter silicon wafer contains 384 chips, each of which implements 128,000 synapses and up to 512 spiking neurons[i]. This gives a total of around 200,000 neurons and 49 million synapses per wafer. These VLSI models operate considerably faster than the biological originals and allow the emulated neural networks to evolve tens-of-thousands times quicker than real time. Put another way, a biological day of learning can be compressed to 100 seconds on the machine.

Leader of the BrainScaleS project, Prof. Dr. Karlheinz Meier (Heidelberg University) explains, “The BrainScaleS system goes beyond the paradigms of a Turing machine and the von Neumann architecture. It is neither executing a sequence of instructions nor is it constructed as a system of physically separated computing and memory units. It is rather a direct, silicon based image of the neuronal networks found in nature, realizing cells, connections and inter-cell communications by means of modern analogue and digital microelectronics.”

Learning – not external programming – is a key guiding principle. Unlike traditional computer architecture in which a structured program explicitly carries out an order of tasks, brains are fundamentally learning machines that turn patterns into programs.

Steve Furber, a professor at the University of Manchester and a co-designer of the ARM chip architecture, leads the SpiNNaker team. SpiNNaker is a contrived acronym derived from Spiking Neural Network Architecture. The machine consists of 57,600 identical 18-core processors, giving it 1,036,800 ARM968 cores in total. The die is fabricated by United Microelectronics Corporation (UMC) on a 130 nm CMOS process. Each System-in-Package (SiP) node has an on-board router to form links with its neighbors, as well as 128 Mbyte off-die SDRAM to hold synaptic weights.

SpiNNaker die 800xSpiNNaker, too, is built to mimic the brain’s biological structure and behavior. It will exhibit massive parallelism and resilience to failure of individual components. With more than one million cores, and one thousand simulated neurons per core, SpinNNaker should be capable of simulating one billion neurons in real-time. This equates to a little over one percent of the human brain’s estimated 85 billion neurons.

Rather than implement one particular algorithm, SpiNNaker will be a platform on which different algorithms can be tested. Various types of neural networks can be designed and run on the machine, thus simulating different kinds of neurons and connectivity patterns.

Both BrainScaleS and SpiNNaker architectures will be discussed during the Web-based workshop on March 22, scheduled from 3 pm to 6 pm CET. Together, the systems located in Heidelberg and Manchester comprise the “Neuromorphic Computing Platform” of the Human Brain Project.

Much of the early work on both machines will be basic research on self-organization in neural networks. Other potential applications, for example, are in energy and time efficiency optimization, broadly similar to deep learning technology developed by companies like Google and Facebook for the analysis of large data volumes using conventional high performance computers.

IBM’s Dharmendra Modha
IBM’s Dharmendra Modha

Europe, of course, is hardly alone in pursuing neuromorphic computing. Most prominent in the U.S. is IBM Research’s TrueNorth Chip effort. Dharmendra Modha, IBM fellow and chief scientist for brain-inspired computing, wrote an interesting commentary on the TrueNorth project that traces development of von Neumann architecture based computing and contrasts it with neuromorphic computing approaches: Introducing a Brain-inspired Computer. Though written in 2014, it remains relevant.

TrueNorth chip, introduced in August 2014, is a neuromorphic CMOS chip that consists of 4,096 hardware cores, each one simulating 256 programmable siliconneurons” for a total of just over a million neurons. Each neuron has 256 programmable “synapses” which convey the signals between them. Hence, the total number of programmable synapses is just over 268 million (228). In terms of basic building blocks, its transistor count is 5.4 billion.

Developed under the DARPA SyNAPSE (Systems of Neuromorphic Adaptive Plastic Scalable Electronics) project, TrueNorth’s computing power has been characterized as roughly equivalent to the brainpower of a rodent. It also circumvents the von-Neumann-architecture bottlenecks, is very energy-efficient, consumes merely 70 milliwatts, and is capable of 46 billion synaptic operations per second, per watt – literally a synaptic supercomputer in your palm.

BrainScaleS, SpiNNaker, and TrueNorth are just three examples of many ongoing neuromorphic computing projects. Turning them into commercial products or more general purpose computing machines remains a challenge.

Indeed, IBM put together a paper on cognitive computing commercialization and barriers[ii]. “New thinking, not only on the part of programmers and application developers, but also by organizational decision makers who seek to link technological possibilities to market opportunity. While incremental innovation can be achieved on the basis of existing knowledge in well-charted commercial territory, radical innovation entails far greater uncertainty.”

Among the barriers cited were: formulating business models and predicting future revenue to calibrate investment, defining strategy and structure to execute and finally, overcoming communicative and functional boundaries.

Much of the drive to push neuromorphic computing stems from the ongoing decline of Moore’s law, and this excerpt from a 2014 ACM article[iii] still sums circumstances today:

As the long-predicted end of Moore’s Law seems ever more imminent, researchers around the globe are seriously evaluating a profoundly different approach to large-scale computing inspired by biological principles. In the traditional von Neumann architecture, a powerful logic core (or several in parallel) operates sequentially on data fetched from memory. In contrast, “neuromorphic” computing distributes both computation and memory among an enormous number of relatively primitive “neurons,” each communicating with hundreds or thousands of other neurons through “synapses.” Ongoing projects are exploring this architecture at a vastly larger scale than ever before, rivaling mammalian nervous systems, and developing programming environments that take advantage of them. Still, the detailed implementation, such as the use of analog circuits, differs between the projects, and it may be several years before their relative merits can be assessed.

Researchers have long recognized the extraordinary energy stinginess of biological computing, most clearly in a visionary 1990 paper by the California Institute of Technology (Caltech)’s Carver Mead that established the term “neuromorphic.” Yet industry’s steady success in scaling traditional technology kept the pressure off.”

[i] “Spiking neural networks (SNNs) fall into the third generation of neural network models, increasing the level of realism in a neural simulation. In addition to neuronal and synaptic state, SNNs also incorporate the concept of time into their operating model. The idea is that neurons in the SNN do not fire at each propagation cycle (as it happens with typical multi-layer perceptron networks), but rather fire only when a membrane potential – an intrinsic quality of the neuron related to its membrane electrical charge – reaches a specific value. When a neuron fires, it generates a signal which travels to other neurons which, in turn, increase or decrease their potentials in accordance with this signal. In the context of spiking neural networks, the current activation level (modeled as some differential equation) is normally considered to be the neuron’s state, with incoming spikes pushing this value higher, and then either firing or decaying over time. Various coding methods exist for interpreting the outgoing spike train as a real-value number, either relying on the frequency of spikes, or the timing between spikes, to encode information.” From

[ii] For more on applications, see IBM paper, Cognitive Computing Commercialization: Boundary Objects for Communication,’13_boundary%20objects_3.4.pdf?cm_mc_uid=86343320971914489086046&cm_mc_sid_50200000=1458418853, Presented at 3rd INT. CONF. ON INTEGRATION OF DESIGN, ENGINEERING & MANAGEMENT FOR INNOVATION, Porto, Portugal, 4-6th September 2013

[iii] Communications of the ACM, Neuromorphic Computing Gets Ready for the (Really) Big Time,

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Mellanox Reacts to Activist Investor Pressures in Letter to Shareholders

March 16, 2018

Activist investor Starboard Value has been exerting pressure on Mellanox Technologies to increase its returns. In response, the high-performance networking company on Monday, March 12, published a letter to shareholders outlining its proposal for a May 2018 extraordinary general meeting (EGM) of shareholders and highlighting its long-term growth strategy and focus on operating margin improvement. Read more…

By Staff

Quantum Computing vs. Our ‘Caveman Newtonian Brain’: Why Quantum Is So Hard

March 15, 2018

Quantum is coming. Maybe not today, maybe not tomorrow, but soon enough. Within 10 to 12 years, we’re told, special-purpose quantum systems will enter the commercial realm. Assuming this happens, we can also assume that quantum will, over extended time, become increasingly general purpose as it delivers mind-blowing power. Read more…

By Doug Black

How the Cloud Is Falling Short for HPC

March 15, 2018

The last couple of years have seen cloud computing gradually build some legitimacy within the HPC world, but still the HPC industry lies far behind enterprise IT in its willingness to outsource computational power. The m Read more…

By Chris Downing

HPE Extreme Performance Solutions

Achieve Optimal Performance at Scale with High Performance Fabrics for HPC

High Performance Computing (HPC) is unlocking a new era of speed and productivity to fuel business transformation. Rapid advancements in HPC capabilities are helping organizations operate faster and more effectively than ever, but in today’s fast-paced marketplace, a new generation of technologies is required to reach greater scalability and cost-efficiency. Read more…

Stephen Hawking, Legendary Scientist, Dies at 76

March 14, 2018

Stephen Hawking passed away at his home in Cambridge, England, in the early morning of March 14; he was 76. Born on January 8, 1942, Hawking was an English theoretical physicist, cosmologist, author and director of resea Read more…

By Tiffany Trader

How the Cloud Is Falling Short for HPC

March 15, 2018

The last couple of years have seen cloud computing gradually build some legitimacy within the HPC world, but still the HPC industry lies far behind enterprise I Read more…

By Chris Downing

Stephen Hawking, Legendary Scientist, Dies at 76

March 14, 2018

Stephen Hawking passed away at his home in Cambridge, England, in the early morning of March 14; he was 76. Born on January 8, 1942, Hawking was an English theo Read more…

By Tiffany Trader

Hyperion Tackles Elusive Quantum Computing Landscape

March 13, 2018

Quantum computing - exciting and off-putting all at once - is a kaleidoscope of technology and market questions whose shapes and positions are far from settled. Read more…

By John Russell

Part Two: Navigating Life Sciences Choppy HPC Waters in 2018

March 8, 2018

2017 was not necessarily the best year to build a large HPC system for life sciences say Ari Berman, VP and GM of consulting services, and Aaron Gardner, direct Read more…

By John Russell

Google Chases Quantum Supremacy with 72-Qubit Processor

March 7, 2018

Google pulled ahead of the pack this week in the race toward "quantum supremacy," with the introduction of a new 72-qubit quantum processor called Bristlecone. Read more…

By Tiffany Trader

SciNet Launches Niagara, Canada’s Fastest Supercomputer

March 5, 2018

SciNet and the University of Toronto today unveiled "Niagara," Canada's most-powerful supercomputer, comprising 1,500 dense Lenovo ThinkSystem SD530 high-perfor Read more…

By Tiffany Trader

Part One: Deep Dive into 2018 Trends in Life Sciences HPC

March 1, 2018

Life sciences is an interesting lens through which to see HPC. It is perhaps not an obvious choice, given life sciences’ relative newness as a heavy user of H Read more…

By John Russell

Alibaba Cloud Launches ‘Bare Metal,’ HPC Instances in Europe

February 28, 2018

Alibaba, the e-commerce giant from China, is taking a run at AWS in the global public cloud computing market with new offerings aimed at the surging demand for Read more…

By Tiffany Trader

Inventor Claims to Have Solved Floating Point Error Problem

January 17, 2018

"The decades-old floating point error problem has been solved," proclaims a press release from inventor Alan Jorgensen. The computer scientist has filed for and Read more…

By Tiffany Trader

Japan Unveils Quantum Neural Network

November 22, 2017

The U.S. and China are leading the race toward productive quantum computing, but it's early enough that ultimate leadership is still something of an open questi Read more…

By Tiffany Trader

Researchers Measure Impact of ‘Meltdown’ and ‘Spectre’ Patches on HPC Workloads

January 17, 2018

Computer scientists from the Center for Computational Research, State University of New York (SUNY), University at Buffalo have examined the effect of Meltdown Read more…

By Tiffany Trader

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a Read more…

By Tiffany Trader

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

Russian Nuclear Engineers Caught Cryptomining on Lab Supercomputer

February 12, 2018

Nuclear scientists working at the All-Russian Research Institute of Experimental Physics (RFNC-VNIIEF) have been arrested for using lab supercomputing resources to mine crypto-currency, according to a report in Russia’s Interfax News Agency. Read more…

By Tiffany Trader

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

Leading Solution Providers

GlobalFoundries, Ayar Labs Team Up to Commercialize Optical I/O

December 4, 2017

GlobalFoundries (GF) and Ayar Labs, a startup focused on using light, instead of electricity, to transfer data between chips, today announced they've entered in Read more…

By Tiffany Trader

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

Perspective: What Really Happened at SC17?

November 22, 2017

SC is over. Now comes the myriad of follow-ups. Inboxes are filled with templated emails from vendors and other exhibitors hoping to win a place in the post-SC thinking of booth visitors. Attendees of tutorials, workshops and other technical sessions will be inundated with requests for feedback. Read more…

By Andrew Jones

V100 Good but not Great on Select Deep Learning Aps, Says Xcelerit

November 27, 2017

Wringing optimum performance from hardware to accelerate deep learning applications is a challenge that often depends on the specific application in use. A benc Read more…

By John Russell

Lenovo Unveils Warm Water Cooled ThinkSystem SD650 in Rampup to LRZ Install

February 22, 2018

This week Lenovo took the wraps off the ThinkSystem SD650 high-density server with third-generation direct water cooling technology developed in tandem with par Read more…

By Tiffany Trader

AMD Wins Another: Baidu to Deploy EPYC on Single Socket Servers

December 13, 2017

When AMD introduced its EPYC chip line in June, the company said a portion of the line was specifically designed to re-invigorate a single socket segment in wha Read more…

By John Russell

World Record: Quantum Computer with 46 Qubits Simulated

December 18, 2017

Scientists from the Jülich Supercomputing Centre have set a new world record. Together with researchers from Wuhan University and the University of Groningen, Read more…

New Blueprint for Converging HPC, Big Data

January 18, 2018

After five annual workshops on Big Data and Extreme-Scale Computing (BDEC), a group of international HPC heavyweights including Jack Dongarra (University of Te Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Share This