Google Team Develops AI Model To Design Chips Faster Than Humans

- Advertisement -

Google has used the model to design its next generation of tensor processing units (TPUs), which run in the company’s data centres to enhance the performance of various AI applications

In what could be dubbed as a new era of chip design, a team of Google researchers is designing next-generation artificial intelligence (AI) chips. As per reports, the team has created an AI model that allows chip design to be performed by artificial agents with more experience than any human designer.

- Advertisement -

To achieve this, the new AI method utilises past experience to become better and faster at solving new instances of the problem.

The model could generate a design that optimises the placement of different components on the chip in about six hours. For this, the Google team used a dataset of 10,000 chip layouts for a machine-learning model, which was then trained with reinforcement learning.

In a paper that appeared in the scientific journal Nature, the team wrote, “Our method was used to design the next generation of Google’s artificial intelligence (AI) accelerators, and has the potential to save thousands of hours of human effort for each new generation.”

“Finally, we believe that more powerful AI-designed hardware will fuel advances in AI, creating a symbiotic relationship between the two fields”, they added.

Google has used the model to design its next generation of tensor processing units (TPUs), which run in the company’s data centres to enhance the performance of various AI applications.

Despite five decades of research, chip floor planning has defied automation, requiring months of intense effort by physical design engineers to produce manufacturable layouts.

“Our RL (reinforcement learning) agent generates chip layouts in just a few hours, whereas human experts can take months,” Anna Goldie, Google Brain’s research scientist who took part in the research, said in a tweet.

“In under six hours, our method automatically generates chip floor plans that are superior or comparable to those produced by humans in all key metrics, including power consumption, performance and chip area,” according to the Google AI team.

- Advertisement -

Most Popular Articles

Automotive car sensor

ISRO Chairman Urges Association With Automotive Industry To Produce Sensors Locally

0
The space research organization is making significant strides in creating indigenous car sensors to empower the automotive industry. At the Bangalore Tech Summit on November...

U.S. Approves $1.5B Subsidy For GlobalFoundries Expansion

0
Winning the $1.5 billion US government subsidy, GlobalFoundries is looking to power industries like automotive, IoT, and defence with advanced chip manufacturing in New...

Trump’s Tariff Plan Could Derange Electronics Pricing

0
From disrupting global semiconductor supply chain to inflating iPhone prices, what can Donald Trump's proposed tariff raise on Chinese imports can cause? Donald Trump,...
Chip Manifacturing-NIvidia

New Blackwell Chip Will Propel Nvidia’s Unprecedented Market Growth In Coming Years

0
These chips have effectively dispelled concerns regarding potential pullbacks from tech giants investing heavily in AI processing and data centers. The global AI backed fabless...

David Goeckeler Appointed Chair Of SIA Board

0
Bringing 40 years of tech experience to lead the global semiconductor industry, David Goeckeler, CEO of Western Digital, joins to lead the SIA Board...
Abhishek Malik from Calcom Vision Limited

“India’s Electronics Sector Is Growing Rapidly, Making This The Decade For Investors To Engage”...

0
From the complexities of manufacturing and sourcing components to testing processes that drive innovation, know all the exciting dynamics shaping this ever-evolving industry in...
Sunit Kapur, CEO of Epsilon

“Epsilon Leads With Low-Carbon Graphite Manufacturing, Outpaces Chinese Competitors” – Sunit Kapur, CEO of...

0
Are LFP cathodes and silicon-graphite anodes the best for cost efficiency in EV batteries? Sunit Kapur, CEO of Epsilon Advanced Materials, discusses this with...
John W. Mitchell, President and CEO, IPC

“India’s Core Focus On 5G, IoT, AI Fosters Need For Advanced Electronics,Components, And Semiconductors”...

0
Will Industry 4.0 supercharge India’s progress in semiconductor and electronics manufacturing? IPC President and CEO John W. Mitchell shared more strategies on the country’s...
Raman M., Co-Founder and CEO, chargeMOD

“Our Goal Is To Achieve Complete Sustainability By 2025-2026” – Raman M. Of chargeMOD

0
In a conversation with Nitisha Dubey from EFY, Raman M. of chargeMOD, elaborated his goal of developing virtual power plants by decentralising power production. Q....

“Adoption Of IoT-Enabled SMT Machines Is Still In Early Phases” – Pradeep Tandon, Director...

0
While electronics are becoming smarter through the Internet of Things, is electronics manufacturing following suit? Pradeep Tandon, Director for India, Middle East, and SAARC...
Applied Materials Representational Image

Applied Materials Selects Six Startups For Deep-Tech Accelerator Programme

0
The selected deep-tech startups will be evaluated for investment by Applied Ventures and potential collaboration opportunities with Applied Materials. In collaboration with the company's India...

Space tech Startup Akash Secures $68M CHIPS Funding

0
Eyeing to power into AI, EVs, and more high-tech industries, Akash Systems lands $68 million CHIPS grant to boost its cooling tech facility, generating...

Wireless Light-Based Communication With Velmenni’s Technology

0
Velmenni is at the forefront of wireless communication innovation with its pioneering light-based technologies, Li-Fi and LC Link. Founded by Deepak Solanki in October 2014...

Harnessing AI Technology For Efficient Pest Management

0
AI-Genix, an agri-tech startup, is transforming pest management for farmers through advanced AI-enabled systems that precisely target harmful pests. In an industry where pesticides and...

One Charger To Charge All Your Devices

0
Now, there is no need to carry different chargers for different products. This Bhubaneswar startup has launched a universal 65W charger using GaN technology...

Industry's Buzz

Learn From Leaders

Startups