- Toshiba Demonstrates Deep Learning using Time-Domain Neural Network - Low-power memory arrays used for mixed analog-digital image processing with high energy-efficiency and compact circuity, suitable for IoT devices.
- Silicon Photonic Neurons Demonstrated - Researchers at Princeton University use lasers and integrated optical modulators to demonstrate neuron-like behavior that is scalable and faster than comparable electronic systems.
- Moving beyond Moore’s Law with New Research Center at Georgia Tech - “Center for Research into Novel Computer Hierarchies”
- New Standard for High-Performance Interconnects - Gen-Z Consortium sets new industry standard
- Record short transistor gate demonstrated at Berkeley - 1-nm gate length with MoS2 channel
- US National Nanotechnology Initiative issues new Strategic Plan - Includes “Nanotechnology-Inspired Grand Challenge for Future Computing”.
- Focus Shifting to Photonics - Silicon photonic lasers and detectors are now being incorporated into ICs, for high-bandwidth communication both between and within chips.
- GPU chip key to Low Power Image Recognition Challenge - Winners of recent RC-sponsored LPIRC contest used NVIDIA computing modules with graphics processing unit (GPU) chips.
- IRDS Featured in IEEE Institute - The International Roadmap for Devices and Systems (IRDS) is a new IEEE Standards Association initiative co-sponsored by Rebooting Computing.
Brain-Inspired Machines: What exactly are we looking for?
This feature article in IEEE Pulse Magazine addressed the subject of brain-inspired or neuromorphic computing. This is a broad concept that covers many different device and architectural approaches to computing. Researchers are not actually trying to design a human brain, which in any case we don’t fully understand. But unlike traditional computers, which follow the Von Neumann digital architecture, brains combine analog and digital, logic and memory, are massively parallel, energy efficient, tolerant of noise and defects, and are self-programming. Furthermore, they are optimized for problems (such as image and language processing) that can be difficult for traditional computers. We can expect that brain and computer research will continue to inspire each other for decades to come.
There are also many articles on brain-inspired or neuromorphic computing in the proceedings of the 1st IEEE International Conference on Rebooting Computing (ICRC 2016). See here for a list of papers.
Historical Impact of Government Investment in High Performance Computing
Dr. Robert Leland is the Chief Technology Officer of Sandia National Laboratories. He presented the opening talk of the 1st IEEE International Conference on Rebooting Computing (ICRC 2016, http://icrc.ieee.org/), held in San Diego, CA, Oct. 17-19, 2016. Dr. Leland reviewed the history of supercomputing, starting with the mainframe era in the 1950s. This was followed by the vector (parallel) era in the 1970s, the distributed memory (massively parallel) era in the 1990s, and the latest transition to a many-core era with heterogeneous nodes. In each case, US government investment was needed to make the transition from one era to the next. The National Strategic Computing Initiative (NSCI) is the latest effort to promote the development of a new generation of supercomputing hardware and software.
Other presentations from ICRC 2016 are available here.
- Rebooting Computing Video Overview
- Workshop on Neuromorphic Computing
- Workshop on Beyond CMOS Technology
- International Roadmap for Devices and Systems (IRDS)
- Update on National Strategic Computing Initiative (NSCI)
- RC White Paper on Nanocomputers
- IEEE Computer Magazine on Rebooting Computing
- Thinking Outside the Chip
- Berkeley Symposium on Energy Efficient Electronic Systems
- Low-Power Image Recognition Challenge
- RC-ITRS Report on the Foundation of the New Computer Industry Beyond 2020
- 3 Scenarios for Exascale Computing
- Electronics Butterfly Effect
- US Government Report on IT Research Funding
- New ITRS 2.0 Website