Established in 2020, AI Chip Center for Emerging Smart Systems (ACCESS) is a multi-disciplinary research center under the InnoHK initiative of the Hong Kong Special Administrative Region Government. Founded by The Hong Kong University of Science and Technology (HKUST) in collaboration on research with world-renowned local and overseas universities, ACCESS is dedicated to advancing integrated circuit (IC) design and design automation technologies to enable novel data-centric computing paradigms to support a wide range of AI applications.
ACCESS is wholly owned by The Hong Kong University of Science and Technology and Asia’s first transnational consortium to perform research and development on AI chip design. We aim to make remarkable contributions to the advancement of AI technologies for advanced chip/ hardware design and will advance Hong Kong as a driver for innovation in the global map of AI hardware as well to nurture the much-needed talent for a booming global AI chip market.
Vision
To realize ubiquitous artificial intelligence (AI) applications in society by:
(1) improving AI computing chip performance/ energy efficiency and
(2) accelerating AI chip design productivity and time-to-market.
Mission
To become a world-leading multidisciplinary innovation center for AI chips and systems, establishing design technologies for novel data-centric computing paradigms supporting a wide range of AI applications; and to elevate Hong Kong’s position as a major player on the world stage in AI chip and system design.
Tackling the most pressing challenges in AI hardware—energy efficiency, performance, and scalability—while harnessing the transformative potential of large-scale AI models. Our research drives innovation in Embodied AI platforms, edge-cloud collaborative systems, and efficient, scalable edge AI inference through localized learning, shaping the next generation of intelligent computing.
Guided by industry demands and technological evolution, our work spans four core research pillars:
Tackling the compute, memory, and memory bandwidth scaling problems, particularly focusing on advancing CIM-based chip architecture to enable the ultra-energy-efficient and scalable deployment of large-scale AI models.
ExploreAdvancing the field of algorithm-hardware co-design, addressing new challenges arising from the increasing complexity, scalability, energy efficiency, and latency requirements of embodied large-scale AI applications.
ExploreExploring new frontiers in EDA for AI chip and system design, with the primary focus placed on supporting the chiplet- and 3DIC-based designs, overcoming the limitations of existing EDA tools, and exploring the employment of foundation AI models in various design tasks to enable more agile chip design.
ExploreLeveraging the technologies developed in the above 3 research projects to perform cross-layer optimization and develop hardware-accelerated working systems for domain-specific, large-scale AI applications with revolutionary performance.
Explore
ACCESS pioneer AI chip innovation from fundamental research to commercial prototyping—enabling tech demos, industry transfers, and startups. By delivering commercial-ready prototypes, open-source tools, and collaborative testbeds, we bridge academia and industry, accelerating product development.
Based at Hong Kong Science Park, our team of 90+ experts— senior researchers, postdocs, and global collaborators — leads cutting-edge R&D in AI hardware. Through technology transfer and startup incubation, we foster a dynamic ecosystem, positioning Hong Kong as a leader in AI chip innovation.
Advancing innovation. Powering intelligence.
"We recognise that specialised AI chips will be a key factor driving the AI revolution. Our team of world-class experts are designing customised AI hardware that will support more innovative applications, and complement other AI research projects in the region."
Prof. Tim CHENG, Center Director of ACCESS and
Vice-President for Research and Development, HKUST