Transnational R&D Consortium On AI Chip Design

smart city

The Hong Kong University of Science and Technology (HKUST) has formed Asia’s first transnational consortium to conduct AI chip design research and development, in order to help put Hong Kong on the global map of AI chip and hardware design and to nurture the talent required for a booming global AI chip market. The AI Chip Center for Emerging Smart Systems (ACCESS), which was founded by HKUST in collaboration on research with Stanford University, The University of Hong Kong, and The Chinese University of Hong Kong, with initial funding of HK$443.9 million from the Hong Kong government’s InnoHK Clusters initiative, sought to realize ubiquitous AI applications in society by developing AI chips that are 1,000 times faster and more energy-efficient than existing solutions.

 

ACCESS was founded in September of last year and has already begun 14 research projects, with more on the way. The Center’s goal is to not only profit from the fast-growing AI chip market, which is expected to reach a value of US$291.5 billion by 2026, but also to develop talent who can provide customized chip design and software-hardware co-designed solutions to tech start-ups and small businesses, ensuring that they are not stifled from development due to a lack of resources. The Center’s research is now overseen by 36 eminent professors, with more than 100 researchers from all of the partner universities. The team will continue to grow, with ACCESS aiming to hire and keep a full-time Center-based research staff of 60 to 80 people.

 

ACCESS is unique on numerous fronts, according to HKUST’s Dean of Engineering, Founding Director of ACCESS, and a globally recognized researcher in the fields of Electronic Design Automation (EDA), integrated circuit design, and computer architecture. Its combined research, development, and implementation strategy efficiently bridge the “Valley of Death” between scientific research and impact deployment. Meanwhile, he continued, the company’s teams of world-renowned professionals with complementary skills work well not only among themselves but also across institutions and industry, thanks to a well-established process.

 

He expressed confidence that the partnership will be a leader in AI chip design in terms of talent development, world-class research outputs, and successful technology transfer for societal impact. The Center is currently working on integrating silicon-compatible emerging memory and photonic technologies with scaled silicon chips, as well as developing new design methodologies and design automation tools dedicated to designing AI chips, as well as AI application-algorithm-and-hardware co-optimization aimed at achieving breakthroughs in both speed and energy efficiency. Two brand-new AI chip prototypes have already been created and are currently being evaluated and analyzed as a product.