dotlah! dotlah!
  • Cities
  • Technology
  • Business
  • Politics
  • Society
  • Science
  • About
Social Links
  • zedreviews.com
  • citi.io
  • aster.cloud
  • liwaiwai.com
  • guzz.co.uk
  • atinatin.com
0 Likes
0 Followers
0 Subscribers
dotlah!
  • Cities
  • Technology
  • Business
  • Politics
  • Society
  • Science
  • About
  • Technology

Enabling Battery-powered Silicon Chips To Work Faster And Longer

  • March 10, 2020
Total
0
Shares
0
0
0

A team of researchers from NUS have invented a novel class of reconfiguration techniques that adaptively extends both the minimum power consumption and the maximum performance of digital circuits, well beyond common voltage scaling. Such extended adaptation allows digital silicon chips to operate at lower power during normal use, and at higher performance level when necessary.

This extends the battery life under uncertain power availability in systems powered by harvesters (e.g. solar cell) or rechargeable batteries, while delivering higher peak performance to carry out on-chip data analytics upon the occurrence of events of interest. This is a key enabler for applications such as Internet of Things (IoT), artificial intelligence (AI), wearables and biomedical devices.

“Our reconfiguration techniques introduce unprecedented adaptability to fluctuating power availability and performance demand. Compared to the industry-standard voltage scaling technique, measurements on several test chips in our lab have shown that such adaptation extends the battery life of a mobile or wearable device by 1.5 times, while doubling peak performance. Our techniques can also be used to further miniaturise the battery by the same factor, while maintaining the same battery life,” explained Associate Professor Massimo Alioto, from NUS Engineering. He is the leader of the NUS Green IC Group that is behind this technological breakthrough.

He added, “As further benefit, the power-performance versatility of our circuit techniques allows semiconductor companies to simplify their chip portfolio and reduce the design cost, as the same digital design can be reused across a wide range of applications and markets.”

Assoc Prof Massimo Alioto (centre) and his team members Lin Longyang (left) and Saurabh Jain (right) showing off the prototyping boards for testing the silicon chips to demonstrate highly flexible power and performance, surpassing industry-standard voltage scaling.

The proposed techniques have led to the demonstration of accelerators and processors (for example, Fast Fourier Transform, ARM processors) with minimum energy consumption reported to date. The research behind the novel techniques has been supported by leading semiconductor companies (Intel, TSMC) as well as the Singapore Ministry of Education and the National Research Foundation of Singapore.

Data and clock path adaptation: Achieving both low minimum power consumption and higher peak performance

Most advanced mobile, IoT and AI applications require a flexible and wide trade-off between the average power (i.e. battery life), and the maximum performance that determines system responsiveness (e.g. when the screen is touched, or performing data analytics when a sensor produces data of interest).

Currently, dynamic voltage scaling is the gold standard in enabling such flexibility. Operating at voltages around 1 V leads to maximum performance and energy consumption, whereas reduction down to 0.4-0.5 V lowers energy consumption by four to five times and slows the operating speed by nearly 10 times. The drawback of this approach is that voltage scaling generally applies to a fixed digital architecture, although the optimal architecture for energy consumption and performance depends on the adopted voltage.

The NUS invention outperforms voltage scaling since its circuit reconfiguration enables better match between the architecture and the adopted voltage, and hence further reduction in energy consumption and improvements in performance at different voltages can be achieved.

figure960.jpg

The adaptive digital circuits demonstrated by the NUS team are able to extend the battery life of intelligent silicon chips by reducing the power consumption under normal use, while scaling up performance to quickly respond to occasional data events.

Assoc Prof Alioto said, “Our invention enables reconfiguration of both the “data path” where the actual processing is performed, and the “clock path” that distributes the clock signal to orchestrate the different processing tasks. In both cases, their fundamental building blocks are flexibly merged or split to create the data and clock path structure that improves either energy efficiency or performance at a given voltage.”

Compared to conventional voltage scaling, the approach proposed by the NUS Green IC group makes digital circuits more versatile and adaptive, allowing simultaneous optimisation at both ends of the power-performance spectrum.

Technical book and a complete toolchain publicly available 

To share the benefits of the team’s new technique with both industry and research groups worldwide, a technical book has recently been released to provide the background and details of the silicon chip implementation of processors, accelerators and on-chip memories. An automated design flow has also been created and publicly released over GitHub (Please visit http://www.green-ic.org/).

“In our book, we introduced and demonstrated design methodologies using solely commercial design tools, which are integrated into a cohesive design flow where clock and data path reconfiguration is incorporated in a plug-and-play fashion. We are delighted to share the software code in an open-source fashion to enable massive and rapid adoption of our novel techniques in the commercial sector and in academic research,” commented Assoc Prof Alioto.

Next steps

The NUS research team is now looking into developing new classes of intelligent silicon systems that allow ultra-wide power-performance adaptation in AI accelerators embedded in sensing silicon chips for IoT. This will lead to next-generation systems that are always available, while being able to promptly respond to external events with very significant computational performance.

In their work, the team endeavours to enable power-performance adaptation through drop-in techniques and design methodologies in existing system architectures. This allows the achievement of power-performance benefits without disrupting the design ecosystem, thus enabling a rapid and massive adoption of next-generation intelligent systems.

Total
0
Shares
Share
Tweet
Share
Share
Related Topics
  • AI
  • Battery-powered Silicon Chips
  • IoT
  • National University of Singapore
  • NUS
  • Research
dotlah.com

Previous Article
  • Technology

Investing In Deep Tech Is Akin To Investing In The Future

  • March 10, 2020
View Post
Next Article
  • Cities
  • People

Only Eight Countries Have Full Equal Rights For Women

  • March 10, 2020
View Post
You May Also Like
View Post
  • Gears
  • Technology

Apple Vision Pro upgraded with the powerful M5 chip and comfortable Dual Knit Band

  • Dean Marc
  • October 15, 2025
View Post
  • Gears
  • Technology

Meet Samsung Galaxy Tab S11 Series: Packing Everything You Expect From a Premium Tablet

  • Dean Marc
  • September 4, 2025
View Post
  • Technology

Malaysia’s ‘ASEAN Shenzhen’ needs some significant legal reform to take off — here’s how

  • dotlah.com
  • August 25, 2025
View Post
  • Gears
  • Technology

Samsung Electronics Debuts Odyssey G7 Monitors, Showcasing Top Games on Its Displays at Gamescom 2025

  • Dean Marc
  • August 20, 2025
View Post
  • Artificial Intelligence
  • Technology

Thoughts on America’s AI Action Plan

  • Dean Marc
  • July 24, 2025
View Post
  • Technology

ESWIN Computing launches the EBC77 Series Single Board Computer with Ubuntu

  • dotlah.com
  • July 17, 2025
View Post
  • Gears
  • Technology

Samsung Galaxy Z Fold7: Raising the Bar for Smartphones

  • Dean Marc
  • July 9, 2025
View Post
  • Cities
  • Technology

Meralco PowerGen’s PacificLight starts up 100 MW fast-response plant in Singapore

  • dotlah.com
  • June 20, 2025


Trending
  • 1
    • Technology
    Championing Personal Data Protection For Trust And Loyalty
    • May 24, 2020
  • CES 2025: Shaping the Future of Play 2
    • Gears
    • Technology
    CES 2025: Shaping the Future of Play
    • January 6, 2025
  • 3
    • Business
    • People
    Fast Loans With Bad Credit: 5 Best Companies To Go To
    • August 27, 2020
  • 4
    • Science
    Analysis Of Global Cancer Data Shines Light On Alternative Gene “Switches” In Tumours
    • September 6, 2019
  • 5
    • Lah!
    UOB Asset Management Launches First Sustainable Bond Fund Focused On Impact Investing And Stable Income For Retail Investors
    • March 29, 2020
  • electric vehicle electric charge 6
    • Cities
    5 Great Transportation Methods For The Environment
    • December 5, 2020
  • People wearing mask 7
    • Cities
    • People
    How worried should we be about the pneumonia outbreak in China?
    • November 30, 2023
  • 8
    • Cities
    Europe’s Worst Cities For Traffic Congestion
    • February 18, 2020
  • 9
    • Lah!
    Out And About—Events In February 2020
    • February 4, 2020
  • london-crowd-viktor-forgacs-6bMyJEvr-Cw-unsplash 10
    • Cities
    • Economy
    The World’s Next Megacities
    • January 20, 2023
  • 11
    • Artificial Intelligence
    • People
    AI Meets Climate: MIT Energy And Climate Hack 2023
    • December 18, 2023
  • 12
    • Technology
    United States-Singapore Joint Statement On Financial Services Data Connectivity
    • February 7, 2020
Trending
  • Bluetooth speakers 1
    Best Bluetooth Speakers Under $200 (2025 Edition)
    • October 16, 2025
  • 2
    Apple Vision Pro upgraded with the powerful M5 chip and comfortable Dual Knit Band
    • October 15, 2025
  • 3
    Apple unveils new 14‑inch MacBook Pro powered by the M5 chip, delivering the next big leap in AI for the Mac
    • October 15, 2025
  • 4
    Apple introduces the powerful new iPad Pro with the M5 chip
    • October 15, 2025
  • 5
    Singapore’s national identity excludes those who don’t look like a ‘regular family’
    • October 9, 2025
  • Smart Watch 6
    Best Smartwatches, Your Gateway to Health Monitoring and Everyday Use
    • October 5, 2025
  • Cooking pots and pans 7
    Best Pots and Pans 2025: All-Season, All-Purpose Picks for Every Kitchen
    • September 23, 2025
  • 8
    Politicians love comparing NZ’s economy to Singapore or Ireland – but it’s simplistic and misleading
    • September 21, 2025
  • Kitchen Knives - Best All-Around Picks in 2025 9
    Kitchen Knives : The Surgeons of Cooking – Best All-Around Picks in 2025
    • September 15, 2025
  • 10
    Apple unveils iPhone 17 Pro and iPhone 17 Pro Max, the most powerful and advanced Pro models ever
    • September 9, 2025
Social Links
dotlah! dotlah!
  • Cities
  • Technology
  • Business
  • Politics
  • Society
  • Science
  • About
Connecting Dots Across Asia's Tech and Urban Landscape

Input your search keywords and press Enter.