Home > Press > CEA-Leti & Stanford Target Edge-AI Apps with Breakthrough Memory Cell: Paper at ISSCC 2019 Presents Proof-of-Concept Multi-Bit Chip That Overcomes NVM’s Read/Write, Latency and Integration Challenges
Abstract:
Researchers at CEA-Leti and Stanford University have developed the world’s first circuit integrating multiple-bit non-volatile memory (NVM) technology called Resistive RAM (RRAM) with silicon computing units, as well as new memory resiliency features that provide 2.3-times the capacity of existing RRAM. Target applications include energy-efficient, smart-sensor nodes to support artificial intelligence on the Internet of Things, or “edge AI”.
The proof-of-concept chip has been validated for a wide variety of applications (machine learning, control, security). Designed by a Stanford team led by Professors Subhasish Mitra and H.-S. Philip Wong and realized in CEA-Leti’s cleanroom in Grenoble, France, the chip monolithically integrates two heterogeneous technologies: 18 kilobytes (KB) of on-chip RRAM on top of commercial 130nm silicon CMOS with a 16-bit general-purpose microcontroller core with 8KB of SRAM.
The new chip delivers 10-times better energy efficiency (at similar speed) versus standard embedded FLASH, thanks to its low operation energy, as well as ultra-fast and energy-efficient transitions from on mode to off mode and vice versa. To save energy, smart-sensor nodes must turn themselves off. Non-volatility, which enables memories to retain data when power is off, is thus becoming an essential on-chip memory characteristic for edge nodes. The design of 2.3 bits/cell RRAM enables higher memory density (NVM dense integration) yielding better application results: 2.3x better neural network inference accuracy, for example, compared to a 1-bit/cell equivalent memory.
The technology was presented on Feb. 19, at the International Solid-State Circuits Conference (ISSCC) 2019 in San Francisco in a paper titled, “A 43pJ/Cycle Non-Volatile Microcontroller with 4.7μs Shutdown/Wake-up Integrating 2.3-bit/Cell Resistive RAM and Resilience Techniques”.
But NVM technologies (RRAM and others) suffer from write failures. Such write failures have catastrophic impact at the application level and significantly diminish the usefulness of NVM such as RRAM. The CEA-Leti and Stanford team created a new technique called ENDURER that overcomes this major challenge. This gives the chip a 10-year functional lifetime when continuously running inference with the Modified National Institute of Standards and Technology (MNIST) database, for example.
“The Stanford/CEA-Leti team demonstrated a complete chip that stores multiple bits per on-chip RRAM cell. Stored information is correctly processed when compared with previous demonstrations using standalone RRAM or a few cells in a RAM array,” said Thomas Ernst, Leti’s chief scientist for silicon components and technologies. “This multi-bit storage improves the accuracy of neural network inference, a vital component of AI.”
Mitra said the chip demonstrates several industry firsts for RRAM technology. These include new algorithms that achieve multiple bits-per-cell RRAM at the full memory level, new techniques that exploit RRAM features as well as application characteristics to demonstrate the effectiveness of multiple bits-per-cell RRAM at the computing system level, and new resilience techniques that achieve a useful lifetime for RRAM-based computing systems.
“This is only possible with a unique team with end-to-end expertise across technology, circuits, architecture, and applications,” he said. “The Stanford SystemX Alliance and the Carnot Chair of Excellence in NanoSystems at CEA-Leti enabled such a unique collaboration.”
####
About Leti
Leti, a technology research institute at CEA Tech, is a global leader in miniaturization technologies enabling smart, energy-efficient and secure solutions for industry. Founded in 1967, Leti pioneers micro-& nanotechnologies, tailoring differentiating applicative solutions for global companies, SMEs and startups. CEA-Leti tackles critical challenges in healthcare; Leti’s multidisciplinary teams deliver solid expertise, leveraging world-class pre-industrialization facilities. With a staff of more than 1,900, a portfolio of 2,700 patents, 91,500 sq. ft. of cleanroom space and a clear IP policy, the institute is based in Grenoble, France, and has offices in Silicon Valley and Tokyo. CEA-Leti has launched 60 startups and is a member of the Carnot Institutes network. This year, the institute celebrates its 50th anniversary. Follow us on www.leti-cea.com and @CEA_Leti.
CEA Tech is the technology research branch of the French Alternative Energies and Atomic Energy Commission (CEA), a key player in innovative R&D, defence & security, nuclear energy, technological research for industry and fundamental science, identified by Thomson Reuters as the second most innovative research organization in the world. CEA Tech leverages a unique innovation-driven culture and unrivalled expertise to develop and disseminate new technologies for industry, helping to create high-end products and provide a competitive edge.
For more information, please click here
Contacts:
Press Contact
Agency
+33 6 74 93 23 47
Copyright © Leti
If you have a comment, please Contact us.Issuers of news releases, not 7th Wave, Inc. or Nanotechnology Now, are solely responsible for the accuracy of the content.
Related News Press |
News and information
Simulating magnetization in a Heisenberg quantum spin chain April 5th, 2024
NRL charters Navy’s quantum inertial navigation path to reduce drift April 5th, 2024
Discovery points path to flash-like memory for storing qubits: Rice find could hasten development of nonvolatile quantum memory April 5th, 2024
Internet-of-Things
New nanowire sensors are the next step in the Internet of Things January 6th, 2023
New chip ramps up AI computing efficiency August 19th, 2022
Lightening up the nanoscale long-wavelength optoelectronics May 13th, 2022
Thin-film, high-frequency antenna array offers new flexibility for wireless communications November 5th, 2021
Possible Futures
Discovery points path to flash-like memory for storing qubits: Rice find could hasten development of nonvolatile quantum memory April 5th, 2024
With VECSELs towards the quantum internet Fraunhofer: IAF achieves record output power with VECSEL for quantum frequency converters April 5th, 2024
Chip Technology
Discovery points path to flash-like memory for storing qubits: Rice find could hasten development of nonvolatile quantum memory April 5th, 2024
Utilizing palladium for addressing contact issues of buried oxide thin film transistors April 5th, 2024
HKUST researchers develop new integration technique for efficient coupling of III-V and silicon February 16th, 2024
Memory Technology
Utilizing palladium for addressing contact issues of buried oxide thin film transistors April 5th, 2024
Interdisciplinary: Rice team tackles the future of semiconductors Multiferroics could be the key to ultralow-energy computing October 6th, 2023
Researchers discover materials exhibiting huge magnetoresistance June 9th, 2023
Sensors
Announcements
NRL charters Navy’s quantum inertial navigation path to reduce drift April 5th, 2024
Discovery points path to flash-like memory for storing qubits: Rice find could hasten development of nonvolatile quantum memory April 5th, 2024
Artificial Intelligence
Simulating magnetization in a Heisenberg quantum spin chain April 5th, 2024
Researchers’ approach may protect quantum computers from attacks March 8th, 2024
New chip opens door to AI computing at light speed February 16th, 2024
HKUST researchers develop new integration technique for efficient coupling of III-V and silicon February 16th, 2024
Events/Classes
Researchers demonstrate co-propagation of quantum and classical signals: Study shows that quantum encryption can be implemented in existing fiber networks January 20th, 2023
Alliances/Trade associations/Partnerships/Distributorships
Chicago Quantum Exchange welcomes six new partners highlighting quantum technology solutions, from Chicago and beyond September 23rd, 2022
University of Illinois Chicago joins Brookhaven Lab's Quantum Center June 10th, 2022
Research partnerships
Discovery points path to flash-like memory for storing qubits: Rice find could hasten development of nonvolatile quantum memory April 5th, 2024
Researchers’ approach may protect quantum computers from attacks March 8th, 2024
'Sudden death' of quantum fluctuations defies current theories of superconductivity: Study challenges the conventional wisdom of superconducting quantum transitions January 12th, 2024
The latest news from around the world, FREE | ||
Premium Products | ||
Only the news you want to read!
Learn More |
||
Full-service, expert consulting
Learn More |
||