About Me
I am Feng Yu, a Ph.D. student in the School of Computing at the National University of Singapore (NUS). I am fortunate to be supervised by Prof. Bingsheng He and Prof. Weng-fai Wong. My research focuses on high-performance computing and architecture design for next-generation accelerators. Currently, I am working on efficient LLM inference on TPUs, supported by a Google Research Award. Prior to my doctoral studies, I obtained both my Bachelor's and Master's degrees from Southeast University, China.
Publications
- [ATC 2026] Feng Yu, Hongshi Tan, Yao Chen, Gustavo Alonso, Weng-fai Wong, Bingsheng He. JetFire: Approximate-then-Correct Attention on Hybrid Memory for Long-Context LLM Inference.
- [MICRO 2026] Yao Chen, Feng Yu, Hongshi Tan, Xuanhua Shi, Weng-fai Wong, Bingsheng He, Hai Jin. HiCAM: Accelerating Parallel Triangle Counting via Bit-Efficient Content-Addressable Memory on FPGA.
- [ISCA 2026] Feng Yu, Hongshi Tan, Yao Chen, Weng-fai Wong, Bingsheng He. XtraMAC: An Efficient MAC Architecture for Mixed-Precision LLM Inference on FPGA.
- [SIGMOD 2025] Feng Yu, Hongshi Tan, Xinyu Chen, Yao Chen, Bingsheng He, Weng-fai Wong. Clementi: Efficient Load Balancing and Communication Overlap for Multi-FPGA Graph Processing.
- [DAC 2025] Yao Chen, Feng Yu, Di Wu, Bingsheng He, Weng-fai Wong. Configurable DSP-Based CAM Architecture for Data-Intensive Applications on FPGAs.
Honors & Awards
- NUS School of Computing Research Achievement Award ×2 (2025, 2026)
- Google TPU Builders Award ($50,000 credit) (2026)
- AMD HACC Outstanding Researcher Awards
- NUS Research Scholarship
- SEU Outstanding Master Graduate
- China National Scholarship