Application-Algorithm-Hardware Co-design AI Accelerator
Overview
ACCESS is creating new design methodologies and tools by considering co-design and co-optimisation of applications, algorithms, and hardware for ultra-high-efficiency AI chips. A new generation of AI accelerator co-designed for compressed neural networks was developed and the manufacturing of ultra-low-power chips will be completed in 2023.
Technical name of innovation
Application-Algorithm-Hardware Co-design AI Accelerator
Commercialisation opportunities
Technology licensing
Problem addressed
1. Huge gap between the full potential of AI and what the hardware technologies can offer in terms of performance and energy efficiency; 2. AI chip design needs huge manpower investment and has very long development time.
Innovation
- Applications-algorithms-hardware co-design workflow and toolchain using design automation technologies;
- Co-optimization of compressed neural network, compilation, and hardware architecture of AI chips;
- Intelligence camera with ultra-low power embedded AI accelerator for people counting and broader vision applications.
Key impact
- Enable ubiquitous intelligence by high-performance and low-power AI chips;
- Accelerating AI chip design productivity and time-to-market
- The co-design method and tool are usable for a broad range of smart applications based on text, image, audio, video, and time-series data, etc.
Application
- Various intelligent cameras for people counting, object recognition, facial analysis, etc.
- AI accelerator sticks for vision and broad smart applications.
- Embedded into various AI SoC chip products
Specialized AI chips will be a key factor driving the AI revolution. To cope with this emerging demand on hardware, the AI Chip Center for Emerging Smart Systems (ACCESS) is putting Hong Kong on the global map of AI chip and hardware design. ACCESS is a tightly coordinated, multi-disciplinary center for advancing integrated circuit (IC) design technologies to enable novel data-centric computing paradigms supporting a wide range of AI applications. Putting together world-class experts, the Center is focus on the research theme of designing customised AI chips to realise ubiquitous AI applications used throughout society.
The research agenda in ACCESS is organised into four programmes:
- Enabling Technology for Emerging Computing Systems addresses memory and data bandwidth problems to alleviate the bottlenecks of AI hardware by exploring integration of silicon-compatible emerging technologies with scaled silicon chips.
- Architecture and Heterogeneous System Integration focuses on exploring different new architectural and system integration solutions for efficient neuromorphic computing on platforms ranging from cloud to smart Internet of Things.
- AI-Assisted EDA (Electronic Design Automation) for AI Hardware hopes to develop new design methodologies and design automation tools for AI chips.
- Hardware-Accelerated AI Applications emphasise selected emerging applications for hardware acceleration, exploring system architecture and new design tools specific to the target applications to achieve breakthroughs in AI hardware in speeds and energy efficiency.
For more inforamtion, please check: https://inno-access.hk/
Enquiry
