About

First Post:

Blog Link:
[site]

Introduction

I am a PhD candidate in the School of Computer Science at Peking University, advised by Prof. Yun Liang. My research interests include programming language, compiler design, high-performance computing, and system-level optimization for machine learning.

Education

  • 2021~　　　| PhD Candidate, School of Computer Science, Peking University, Beijing, China
  • 2017~2021 | Bachelor of Science, School of Computer Science, Peking University, Beijing, China

Awards

  • 　　　2024 | ByteDance Scholarship, ByteDance, China
  • 2022~2023 | Schlumberger Scholarship, School of Computer Science, Peking University, Beijing, China
  • 2019~2020 | PKU Second Class Scholarship, Peking University, Beijing, China
  • 2019~2020 | Merit Student, Peking University, Beijing, China
  • 2017~2018 | Merit Student, Peking University, Beijing, China

Publications

(“*” means equal contribution)

Venue Title & Links Author List
​
DAC’26 SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models Inference Shanghao Liu, Renze Chen, Size Zheng, Yuanqiang Liu, Yun Liang, Hailong Yang
​
DATE’26 LATIAS: A General Architecture-Operator Model for Spatial Accelerators with Complex Topology and Memory Hierarchy Chengrui Zhang, Liancheng Jia, Chu Wang, Tianqi Li, Renze Chen, Xiuping Cui, Size Zheng, Shengen Yan, Xiuhong Li, Yu Wang, Xiang Chen, Yun Liang
​
NIPS’24 ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction [site][code][paper][slides][poster] Renze Chen, Zhuofeng Wang, Beiquan Cao, Tong Wu, Size Zheng, Xiuhong Li, Xuechao Wei, Shengen Yan, Meng Li, Yun Liang
​
ICCAD’24 MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers [site][paper] Zebin Yang*, Renze Chen*, Taiqiang Wu, Ngai Wong, Yun Liang, Runsheng Wang, Ru Huang, Meng Li
​
ICCAD’24 FlexHE: a Flexible Kernel Generation Framework for Homomorphic Encryption-Based Private Inference [site][paper] Jiangrui Yu, Wenxuan Zeng, Tianshi Xu, Renze Chen, Yun Liang, Runsheng Wang, Ru Huang, Meng Li
​​
DAC’24 MoteNN: Memory Optimization via Fine-grained Scheduling for Deep Neural Networks on Tiny Devices [site][paper][slides][poster] Renze Chen, Zijian Ding, Size Zheng, Meng Li, Yun Liang
​
MLSys’24 vMCU: Coordinated Memory Management and Kernel Optimization for DNN Inference on MCUs [site][paper][slides] Size Zheng*, Renze Chen*, Meng Li, Zihao Ye, Luis Ceze, Yun Liang
​
ASPLOS’24 MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN [site][code][paper][slides][poster] Renze Chen, Zijian Ding, Size Zheng, Chengrui Zhang, Jingwen Leng, Xuanzhe Liu, Yun Liang
​
HPCA’23 Chimera: An Analytical Optimizing Framework for Effective Compute-intensive Operators Fusion [site][paper] Size Zheng, Siyuan Chen, Peidi Song, Renze Chen, Xiuhong Li, Shengen Yan, Dahua Lin, Jingwen Leng, Yun Liang
​
ISCA’22 AMOS: Enabling Automatic Mapping for Tensor Computations On Spatial Accelerators with Hardware Abstraction [site][code][paper] Size Zheng, Renze Chen, Anjiang Wei, Yicheng Jin, Qin Han, Liqiang Lu, Bingyang Wu, Xiuhong Li, Shengen Yan, Yun Liang
​
TPDS’22 NeoFlow: A Flexible Framework for Enabling Efficient Compilation for High Performance DNN Training [site][paper] Size Zheng, Renze Chen, Yicheng Jin, Anjiang Wei, Bingyang Wu, Xiuhong Li, Shengen Yan, Yun Liang
​
ASPLOS’20 FlexTensor: An Automatic Schedule Exploration and Optimization Framework for Tensor Computation on Heterogeneous System [site][code][paper] Size Zheng, Yun Liang, Shuo Wang, Renze Chen, Kaiwen Sheng

Projects

Name Description
​
Triton-Distributed Distributed Compiler based on Triton for Parallel Systems
​
ArkVale ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS’24).
​
MAGIS MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS’24).
​
AMOS AMOS: Enabling Automatic Mapping for Tensor Computations On Spatial Accelerators with Hardware Abstraction (ISCA’23).
​
FlexTensor FlexTensor: An Automatic Schedule Exploration and Optimization Framework for Tensor Computation on Heterogeneous System (ASPLOS’20).
​
CCTV CCTV: C++ Compile-Time EValuator for Scheme LISP. An interpreter for a tiny dialect of Scheme LISP language implemented with C++ template meta-programming.
​
CppyList A C++ library of python-like heterogeneous list.
​
CppFP A C++ library for “curry”, “partial” and some other functional programming combinators.
​
ECAIA Implementation of “Essentials of Compilation: An Incremental Approach” with Racket language.
​
AVL-Tree An AVL-Tree implementation with linear-time merging operation.
​
CoCo A simple symmetry coroutine library for POSIX C.

Coursework

Name Description
​
Rust-Linear Project of Design Principles of Programming Language (2022). Implementation of a flexible linear type system with Rust language.
​
Shift-Reset Project of Design Principles of Programming Language (2020). Implementation of paper “Selective CPS Transformation for shift and reset” with OCaml language.
​
MIT-JOS Lab. of Operating System (Honor Track). Implementation of a tiny micro-kernel OS.
​
MiniC Lab. of Practice for Compiler Design. Implementation of a C compiler from scratch.
≡