• New MIT College of Computing - $1B commitment focuses on education and research toward future AI.
• IBM Identifies New Class of Problems for Quantum Computers - Can be implemented using present generation of noisy quantum computers.
• 3 Directions for Moore’s Law - Major companies are taking different approaches to continued scaling of transistors.
• Berkeley Quantum Computing Testbed - New Dept. of Energy project to design and test superconducting circuits for quantum computing.
• US National Cyber Strategy - New reports from White House and US Dept. of Defense on protecting cyber infrastructure.
• White House Summit on Quantum Information Science - US Agencies Plan Coordinated Efforts in Quantum Computing R&D
• IEEE Journal of Exploratory Solid-State Computational Devices and Circuits - Special Issue on Nonvolatile Memory for Efficient Implementation of Neuromorphic Computing
• National Quantum Initiative - US Congress considering bill promoting enhanced government support for R&D in quantum computing and quantum communication.

A Domain-Specific Architecture for Deep Neural Networks

N. Jouppi, et al., Google

Communications of the ACM, September 2018

Google engineers apply new Tensor Processing Unit (TPU) chips to neural network applications, up to 30 times faster and up to 80 times more energy efficient than competing chips.

Read the article here.

These improvements have been applied to real-time data center applications of deep neural networks, such as image recognition, language translation, and search. The applications are designed using open-source TensorFlow software.

A brief video of some of the authors discussing this work is also available here.

The Accelerator Age

At the recent DARPA ERI Summit, Bill Dally of NVIDIA spoke about machine learning applications of new GPU chips, enabling acceleration of performance based on computer architecture, rather than faster devices. See here for the video of his presentation here.

Slides for the talk are available here (PDF, 2 MB).

He provided an example whereby a speedup to 15,000 was enabled by co-design of algorithms and hardware (memory distribution) on a Volta GPU chip. He also described how DARPA sponsorship and teaming with university researchers is promoting the further development of this technology.

The agenda for the ERI Summit is available here, with links to many other presentations. Other videos from the Summit are available at DARPAtv.

• Rebooting Computing Video Overview
• IEEE Future Directions
• ICRC 2018 Call for Papers
• Computing in Science and Engineering on the End of Moore's Law
• IEEE Journal of Exploratory Solid-State Computational Devices and Circuits (JXCDC)
• Arch2030 Workshop Report
• TTM 2016 Videos
• Workshop on Neuromorphic Computing
• Workshop on Beyond CMOS Technology
• Update on National Strategic Computing Initiative (NSCI)
• RC White Paper on Nanocomputers
• IEEE Computer Magazine on Rebooting Computing
• RC-ITRS Report on the Foundation of the New Computer Industry Beyond 2020