Youwei Zhuo (卓有为) is a tenure-track assistant professor at the School of Integrated Circuits, Peking University. Before joining Peking University in 2024, he was a research scientist at Alibaba DAMO Academy. He received a BE degree in computer science and a BA degree in economics from Tsinghua University in 2016. He received his PhD degree in computer science from University of Southern California under the supervision of Prof. Xuehai Qian in 2021.

His research interest is computer architecture and system software, including novel memory architectures, heterogeneous parallel programming, and distributed systems for large-scale graph processing and machine learning. His research work has been published and presented in several top conferences, including PLDI, MICRO, HPCA, and ASPLOS.

I am actively looking for PhD students and undergraduate interns. If you are excited in cross-stack optimizations for hardware and software co-design, welcome to reach out to me!

Research Directions:

  1. 先进封装近存计算芯片
  2. 新器件存内计算芯片
  3. 并行编程语言与编译优化
  4. 分布式机器学习与图计算系统

Publications

Klotski: DNN Model Orchestration Framework for Dataflow Architecture Accelerators

2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD), 2023.
Distributed Graph Processing System and Processing-in-memory Architecture with Precise Loop-carried Dependency Guarantee

ACM Transactions on Computer Systems (TOCS), 2021.
AccPar: Tensor Partitioning for Heterogeneous Deep Learning Accelerators

2020 IEEE International Symposium on High Performance Computer Architecture (HPCA), 2020.
Prague: High-Performance Heterogeneity-Aware Asynchronous Decentralized Training

Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2020.
SympleGraph: distributed graph processing with precise loop-carried dependency guarantee

Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI), 2020.

Contact