Back to Table of contents

Primeur weekly 2018-10-08

Special

Where did the first 500 million euro invested by the European Horizon 2020 programme go? ...

Focus

World's first ARM-based supercomputer Isambard is ready for science ...

Exascale supercomputing

New European project ESCAPE-2 on exascale computing for numerical weather prediction gets under way ...

Berkeley Lab, Oak Ridge, and NVIDIA team breaks exaop barrier with deep learning application ...

Coming soon to exascale computing: Software for chemistry of catalysis ...

Quantum computing

ORNL researchers advance quantum computing, science through six DOE awards ...

Berkeley Lab to build an advanced quantum computing testbed ...

Berkeley Lab to push quantum information frontiers with new programmes in computing, physics, materials, and chemistry ...

Berkeley Quantum to accelerate innovation in quantum information science ...

Quantum software company Zapata Computing adds Clark Golestani to Board ...

Defects promise quantum communication through standard optical fiber ...

Focus on Europe

Atos and the University of Reims launch ROMEO, one of the most powerful supercomputers in the world, under the sponsorship of Cedric Villani ...

Special Edition of Open e-IRG Workshop under the Austrian EU Presidency will focus on relationship between Open Science, FAIR data and EOSC ...

Goethe University to develop green supercomputer for science ...

Calling on HPC experts and enthusiasts to propose tutorials and workshops for ISC 2019 ...

ISC 2019 calls for research paper submission by December 12, 2018 ...

Middleware

USC ISI to pilot Cyberinfrastructure Center of Excellence for National Science Foundation ...

Hardware

Tintri co-founder Mark Gritter joins Tintri by DDN as CTO to lead analytics and server virtualization vision ...

DDN simplifies the AI data centre with NVIDIA ...

New research could lead to more energy-efficient computing ...

Applications

New simulation sheds light on spiraling supermassive black holes ...

DNA unzipped, turned around, and rezipped ...

Dark Energy Survey releases first year value-added data products ...

A quantum leap toward expanding the search for dark matter ...

HP-CONCORD paves the way for scalable machine learning in HPC ...

In disaster's wake, novel computing techniques support emergency responders ...

Transition metal dichalcogenides could increase computer speed, memory by a million times ...

A new brain-inspired architecture could improve how computers handle data and advance AI ...

Rochester Institute of Technology leads multi-university collaboration to simulate neutron star mergers ...

The Cloud

Oracle rolls out Autonomous NoSQL Database service ...

Quanta Cloud Technology showcases AI portfolio options at GTC Europe ...

ZeroStack delivers GPU-as-a-Service via NVIDIA hardware ...

A new brain-inspired architecture could improve how computers handle data and advance AI

Brain-inspired computing using phase change memory. Credit: Nature Nanotechnology/IBM Research.3 Oct 2018 Washington, D.C. - IBM researchers are developing a new computer architecture, better equipped to handle increased data loads from artificial intelligence. Their designs draw on concepts from the human brain and significantly outperform conventional computers in comparative studies. They report on their recent findings in theJournal of Applied Physics.

Today's computers are built on the von Neumann architecture, developed in the 1940s. Von Neumann computing systems feature a central processer that executes logic and arithmetic, a memory unit, storage, and input and output devices. Unlike the stovepipe components in conventional computers, the authors propose that brain-inspired computers could have coexisting processing and memory units.

Abu Sebastian, an author on the paper, explained that executing certain computational tasks in the computer's memory would increase the system's efficiency and save energy.

"If you look at human beings, we compute with 20 to 30 watts of power, whereas AI today is based on supercomputers which run on kilowatts or megawatts of power", Abu Sebastian stated. "In the brain, synapses are both computing and storing information. In a new architecture, going beyond von Neumann, memory has to play a more active role in computing."

The IBM team drew on three different levels of inspiration from the brain. The first level exploits a memory device's state dynamics to perform computational tasks in the memory itself, similar to how the brain's memory and processing are co-located. The second level draws on the brain's synaptic network structures as inspiration for arrays of phase change memory (PCM) devices to accelerate training for deep neural networks. Lastly, the dynamic and stochastic nature of neurons and synapses inspired the team to create a powerful computational substrate for spiking neural networks.

Phase change memory is a nanoscale memory device built from compounds of Ge, Te and Sb sandwiched between electrodes. These compounds exhibit different electrical properties depending on their atomic arrangement. For example, in a disordered phase, these materials exhibit high resistivity, whereas in a crystalline phase they show low resistivity.

By applying electrical pulses, the researchers modulated the ratio of material in the crystalline and the amorphous phases so the phase change memory devices could support a continuum of electrical resistance or conductance. This analog storage better resembles nonbinary, biological synapses and enables more information to be stored in a single nanoscale device.

Abu Sebastian and his IBM colleagues have encountered surprising results in their comparative studies on the efficiency of these proposed systems. "We always expected these systems to be much better than conventional computing systems in some tasks, but we were surprised how much more efficient some of these approaches were."

Last year, they ran an unsupervised machine learning algorithm on a conventional computer and a prototype computational memory platform based on phase change memory devices. "We could achieve 200 times faster performance in the phase change memory computing systems as opposed to conventional computing systems", Abu Sebastian stated. "We always knew they would be efficient, but we didn't expect them to outperform by this much." The team continues to build prototype chips and systems based on brain-inspired concepts.

The article titled " Tutorial: Brain-inspired computing using phase-change memory devices ", is authored by Abu Sebastian, Manuel Le Gallo, Geoffrey W. Burr, Sangbum Kim, Matthew BrightSky and Evangelos Eleftheriou. The article appeared in theJournal of Applied Physicson September 18, 2018 - DOI: 10.1063/1.5036538.
Source: American Institute of Physics

Back to Table of contents

Primeur weekly 2018-10-08

Special

Where did the first 500 million euro invested by the European Horizon 2020 programme go? ...

Focus

World's first ARM-based supercomputer Isambard is ready for science ...

Exascale supercomputing

New European project ESCAPE-2 on exascale computing for numerical weather prediction gets under way ...

Berkeley Lab, Oak Ridge, and NVIDIA team breaks exaop barrier with deep learning application ...

Coming soon to exascale computing: Software for chemistry of catalysis ...

Quantum computing

ORNL researchers advance quantum computing, science through six DOE awards ...

Berkeley Lab to build an advanced quantum computing testbed ...

Berkeley Lab to push quantum information frontiers with new programmes in computing, physics, materials, and chemistry ...

Berkeley Quantum to accelerate innovation in quantum information science ...

Quantum software company Zapata Computing adds Clark Golestani to Board ...

Defects promise quantum communication through standard optical fiber ...

Focus on Europe

Atos and the University of Reims launch ROMEO, one of the most powerful supercomputers in the world, under the sponsorship of Cedric Villani ...

Special Edition of Open e-IRG Workshop under the Austrian EU Presidency will focus on relationship between Open Science, FAIR data and EOSC ...

Goethe University to develop green supercomputer for science ...

Calling on HPC experts and enthusiasts to propose tutorials and workshops for ISC 2019 ...

ISC 2019 calls for research paper submission by December 12, 2018 ...

Middleware

USC ISI to pilot Cyberinfrastructure Center of Excellence for National Science Foundation ...

Hardware

Tintri co-founder Mark Gritter joins Tintri by DDN as CTO to lead analytics and server virtualization vision ...

DDN simplifies the AI data centre with NVIDIA ...

New research could lead to more energy-efficient computing ...

Applications

New simulation sheds light on spiraling supermassive black holes ...

DNA unzipped, turned around, and rezipped ...

Dark Energy Survey releases first year value-added data products ...

A quantum leap toward expanding the search for dark matter ...

HP-CONCORD paves the way for scalable machine learning in HPC ...

In disaster's wake, novel computing techniques support emergency responders ...

Transition metal dichalcogenides could increase computer speed, memory by a million times ...

A new brain-inspired architecture could improve how computers handle data and advance AI ...

Rochester Institute of Technology leads multi-university collaboration to simulate neutron star mergers ...

The Cloud

Oracle rolls out Autonomous NoSQL Database service ...

Quanta Cloud Technology showcases AI portfolio options at GTC Europe ...

ZeroStack delivers GPU-as-a-Service via NVIDIA hardware ...