Mao Lin (林茂)

Mao Lin (林茂)

Graduate Student

I am currently a graduate student at UC Merced. Before this, I earned my M.S. degree in Software Engineering and my B.E. degree in Computer Science from Shandong University.

I am excited to delve into research topics related to machine learning systems and machine learning-oriented computer architecture. My research interests extend to heterogeneous computing, high-performance/parallel computing (CUDA), as well as static and dynamic program analysis and optimization.

💻 Experiences

  • 08/2023 - 11/2023, Research Intern, ByteDance, San Jose, CA, USA
    • Analyzing and optimizing the GPU memory wastage and fragmentation in large language model (LLM) training.
  • 05/2023 - 08/2023, Research Intern, ByteDance, Seattle, WA, USA
    • Analyzing and optimizing the GPU memory wastage and fragmentation in large language model (LLM) training.
  • 11/2022 - 02/2023, Part-time internship of software engineer, Uber, Sunnyvale, CA, USA
    • Detecting and fixing the data races in the Uber’s Golang code base.
  • 06/2022 - 08/2022, Research Intern, PNNL, Richland, WA, USA
    • Detecting floating-point data overflow of GPU-accelerated applications.

📝 Publications

[ASPLOS’23] “DrGPUM: Guiding Memory Optimization for GPU-accelerated Applications”, Mao Lin, Keren Zhou, and Pengfei Su. The 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Mar 25-29, 2023, Vancouver, BC, Canada. [Paper][Code][Kudos][PDF]

[PyTorch Conference’22] “Poster: Squeezing GPU Memory Usage in PyTorch”, Mao Lin, Keren Zhou, and Pengfei Su. Dec. 2022, New Orleans, LA, USA. [Poster]

[TCAD’22] “A comprehensive memory management framework for CPU-FPGA heterogenous SoCs”, Zelin Du, Qianling Zhang, Mao Lin, Shiqing Li, Xin Li, and Lei Ju. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2022). [Paper][PDF]

💬 Talks

  • 04/2023, Present DrGPUM at the 1st UC Merced EECS Research Symposium
  • 03/2023, Present paper DrGPUM at ASPLOS’23 [Slides]
  • 12/2022, Present a poster about squeezing GPU memory usage in PyTorch at PyTorch Conference’22

👔 Professional Services

  • Artifact Evaluation Committee: PPoPP’23, ASPLOS’24

📚 Teaching

  • Teaching Assistant of Intro to Programming Laboratory Skills/Techniques (CSE 022), 2023 Spring
  • Teaching Assistant of Data Structure (CSE 030), 2022 Spring
  • Teaching Assistant of Advanced Programming (CSE 024), 2021 Fall
  • Teaching Assistant of Intro to Object Orient Program (CSE 165), 2021 Fall

🧩 Skills

  • Languages:  C/C++; Python; CUDA; Go; Java; Shell; html; CSS; JSON
  • Platforms:  Linux; CPU-GPU HMPSoCs; CPU-FPGA HMPSoCs
  • Frameworks:  Pytorch; Darknet; Tensorflow
  • Toolchains:  Git; Nsight System; Linux perf; GDB; Xilinx Vivado Suite