Publications: PRIME paper selected for inclusion in ISCA@50 25-year Retrospective (1996-2020). Honors: Inducted into the Micro Hall of Fame in 2023. Two GNN papers to appear at Micro-23.
Research Experience
Alibaba DAMO Academy: Propose hardware innovations to address deep learning application challenges in Alibaba Cloud. Ongoing projects target improving foundation model training efficiency and reducing LLM serving cost. Previous work includes cloud FPGA solution (lead architect, ISCA-2022 prototype) and a 3D hybrid bonding near-data computing testchip (ISSCC-2022). At UCSB, worked on NVM and in-memory computing.
Education
Ph.D. (2014-2018): University of California, Santa Barbara (UCSB), supervised by Dr. Yuan Xie; M.S./B.S.: Tsinghua University.
Background
Research Interests: Memory system and domain-specific (especially AI) architecture. Brief: A Research Scientist at Compute Technology Lab, Alibaba DAMO Academy, since June 2019.