Resume
PDF Resume
Download Here (outdated)
Education
- Junior High School Diploma, Beijing 101 Middle School, 2014
- Senior High School Diploma, The Affiliate High School of Peking University, 2017
- B.S. in Computer Science, Minor in Statistics, University of Michigan - Ann Arbor, 2021
- University Honors (Fall 2018, Winter&Fall 2019, Winter 2020)
- James B. Angell Scholar (2020, 2021)
- M.Eng. in Electronic Engineering and Computer Science, University of California - Berkeley, 2022
Work & Intern experience
- Architect @ NVIDIA Fast Kernel (Beijing) 2022.10 - present
- Develop kernels for latest GPU architecture for TensorRT,cuBLAS,cuDNN, and CUTLASS.
- High Performence Computing Intern @ YITU (Beijing) 2021.05 - 2021.09
- Use arm intrinsic (NEON) and NVIDIA CUDA to improve the speed and accuracy of general & customized operators (functions).
- Some common operators are 20-50% faster. Some uint8_t operators are nearly as accurate as double, with only 0.8% of values differing by 1.
Skills
- Proficient: C++, CUDA, Arm Intrinsic (NEON)
- Experienced: Python, PyTorch, x86 Intrinsic (AVX2 AVX512), OpenMP, MPI