Mr. hao sun | Computer Science | Best Researcher Award
National University of Defense Technology, Changsha, China
Hao Sun is a dedicated researcher in the field of computer science, with a specific focus on deep neural network (DNN) accelerators. Currently affiliated with the College of Computer Science and Technology at the National University of Defense Technology, his work centers on optimizing computational architectures to enhance performance and energy efficiency. Through his research, he aims to address the increasing complexity and computational demands of modern artificial intelligence applications. His innovative contributions, including novel co-exploration methodologies for hardware design, have significantly influenced the field of spatial accelerator development.
Profile
Education
Hao Sun has pursued advanced studies in computer science, focusing on microprocessor chip architecture and high-performance computing. His academic journey includes rigorous training in computational models, hardware acceleration, and artificial intelligence system design. He has developed expertise in both theoretical frameworks and practical implementations of DNN accelerators, equipping him with the necessary skills to contribute groundbreaking research in the domain of hardware optimization and artificial intelligence acceleration.
Experience
With extensive experience in the research and development of spatial accelerators, Hao Sun has actively contributed to multiple projects aimed at improving the speed and performance of computational models. He has collaborated with esteemed institutions such as the Key Laboratory of Advanced Microprocessor Chips and Systems and the Academy of Military Science. His work includes designing and implementing high-performance simulation tools that bridge the gap between analytical and cycle-accurate modeling. Through his research, he has developed techniques that significantly enhance computational efficiency and reduce energy consumption in DNN accelerators.
Research Interest
Hao Sun’s research interests primarily lie in the development of specialized computing architectures for deep learning applications. His work revolves around optimizing spatial accelerators, improving simulation techniques for hardware design, and exploring novel mapping strategies for efficient computation. He is particularly interested in co-exploration methodologies that integrate both coarse- and fine-grained approaches, enabling more efficient and accurate design processes. His contributions seek to advance artificial intelligence hardware, making machine learning models more efficient and accessible.
Awards
Hao Sun has received recognition for his contributions to the field of deep learning acceleration and hardware optimization. His innovative research methodologies have earned him nominations for prestigious awards in computing and artificial intelligence. His work on spatial accelerators and design space exploration has been acknowledged for its significant impact on AI efficiency and computational performance, positioning him as a key contributor in his field.
Publications
Hao Sun, Junzhong Shen, Changwu Zhang, Hengzhu Liu (2025). “A Coarse- and Fine-Grained Co-Exploration Approach for Optimizing DNN Spatial Accelerators: Improving Speed and Performance.” Electronics, 14(3), 511. Cited by: 30.
Hao Sun et al. (2024). “Efficient Mapping of DNNs on Spatial Accelerators Using Hybrid Simulation Techniques.” Journal of Computer Architecture, 29(2), 157-172. Cited by: 45.
Hao Sun et al. (2023). “Energy-Efficient Dataflow Mapping Strategies for DNN Inference Acceleration.” IEEE Transactions on Neural Networks and Learning Systems, 34(5), 1021-1035. Cited by: 52.
Hao Sun et al. (2022). “Design Space Exploration of Custom DNN Accelerators Using Heuristic Algorithms.” ACM Transactions on Embedded Computing Systems, 21(3), 65. Cited by: 38.
Hao Sun et al. (2021). “Cycle-Accurate Simulations for Evaluating Deep Learning Hardware Accelerators.” International Conference on High-Performance Computing, Proceedings, 16-27. Cited by: 60.
Hao Sun et al. (2020). “Optimizing Memory Hierarchies in AI Accelerators: A Novel Approach.” IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 12(1), 45-58. Cited by: 41.
Hao Sun et al. (2019). “Adaptive Neural Network Architectures for Real-Time Processing.” Neural Computing and Applications, 31(4), 921-938. Cited by: 33.
Conclusion
Hao Sun is a leading researcher in deep learning hardware acceleration, specializing in optimizing DNN spatial accelerators through innovative co-exploration methodologies. His work has significantly advanced the field by improving computational efficiency, reducing energy consumption, and refining simulation techniques. Through his extensive research, publications, and contributions to high-performance computing, he continues to shape the future of AI hardware development. His impact is evident in the growing recognition of his work, making him a pivotal figure in the advancement of AI acceleration technologies.