朱振华

朱振华，清华大学深圳国际研究生院助理教授，主要从事高能效AI芯片架构与系统研究，研究兴趣包括存算一体/近存计算、超节点智算系统、太空智算芯片与系统等方向，致力于为突破“存储墙”与“功耗墙”瓶颈提供架构设计方法与工具支撑。作为第一作者/通讯作者在IEEE TCAD、ISCA、MICRO、HPCA、DAC、ICCAD等会议期刊发表文章20余篇，谷歌学术引用2100余次。

朱振华在2024年和2018年于清华大学电子工程系获博士学位及本科学位。曾获中国计算机学会容错专委40周年优秀成果（第一完成人）、《电子与信息学报》2025年度“优秀论文奖”及“最具传播影响力论文奖”、计算机体系结构顶会HPCA 2025最佳论文荣誉提名奖、EDA会议DATE 2023最佳论文提名、清华大学优秀博士毕业生、优秀博士论文等荣誉。曾入选清华大学“水木学者”计划、清华大学电子系“传信学者”计划。主持国家自然科学基金青年（C类）项目。

2018.08-2024.01  清华大学  电子科学与技术  博士

2014.08-2018.08  清华大学  电子工程系   学士

2026.06-今    清华大学    助理教授

2024.03-2026.05   清华大学    博士后助理研究员

2024.07-2026.06   HKUST    Visiting Scholar

Asia and South Pacific Design Automation Conference 2025（ASP-DAC 2025）技术委员会秘书(Technical Program Committee Secretary)；

国际会议技术委员会委员(Technical Program Committee Member)：

IEEE/ACM International Conference on Computer-Aided Design（ICCAD）

International Conference on Compilers, Architecture, and Synthesis for Embedded Systems（CASES）

Great Lakes Symposium on VLSI（GLSVLSI）

IEEE Computer Society Annual Symposium on VLSI（ISVLSI）

国际期刊审稿人(Journal Reviewer)：

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems（IEEE TCAD）

ACM Transactions on Design Automation of Electronic Systems（ACM TODAES）

ACM Transactions on Embedded Computing Systems（ACM TECS）

主要研究方向为高能效AI芯片架构与系统研究，研究兴趣包括存算一体/近存计算、超节点智算系统、太空智算芯片与系统等方向，重点面向大模型与数据密集型应用，研究新型计算架构设计与系统优化方法。围绕存算一体、3D 堆叠近存计算、异构超节点智能计算系统、架构级性能建模、编译映射优化与设计空间探索开展一系列研究工作，旨在形成从器件/电路特性、计算架构、编译工具到系统部署的跨层协同优化方法，并进一步拓展至面向太空极端环境的高能效、高可靠智能计算芯片与系统。主持国家自然科学基金青年（C类）项目以及多项校企联合项目，参与国家自然科学基金重点项目、科技部重点研发计划等项目。成果多次获得重要期刊会议的最佳论文及提名。

1. Research on Processing-In-Memory Architecture and Scheduling Methods for Multimodal Self-Learning Embodied Intelligence, NSFC Youth Funding (Category-C) 国家自然科学基金青年科学基金项目（C类），2026.01-2028.12，30万元，项目负责人(PI)；
2. 面向AI智能体的HBF-DRAM存算一体协同架构的层次化存储管理与优化研究 (Hierarchical Memory Management and Optimization for an HBF-DRAM Processing-in-Memory Architecture Oriented to AI Agents), 清华大学-杭州知存算力科技有限公司“多模态智能感存算融合系统”产学研深度融合专项 (Tsinghua University-Hangzhou Witmem Computing Power Technology Co., Ltd. “Multimodal Intelligent Sensing-Computing Fusion System” Industry-Academia-Research Deep Integration Project), 2026.01-2026.12, 100万元，项目负责人(PI)；
3. 面向大模型的异构融合端侧存算一体芯片与系统 (Heterogeneous Integrated Edge-side Processing-in-Memory Chips and Systems for Large Models)，北京市自然科学基金 (Beijing Natural Science Foundation)，2025.07-2027.06，300万元，项目主要参与成员(Key Contributor)。

4. 存算一体高层次设计自动化工具 (High-Level Synthesis for Processing-In-Memory AI Chips and Architecture), 科技部重点研发计划 (National Key R&D Program of China), 2023-2027, 650万元，项目主要参与人员 (Key Contributor)。

[1] Tongxin Xie, Mingyu Gao, Zehao Wang, Zhihao Jia, Yuechen Xi, Bing Li, Mo Guang, Jiale Yan, Kaiwen Long, Xingcheng Zhang, Huazhong Yang, Yuan Xie, Zhenhua Zhu, and Yu Wang, Bringing Near Data Processing into the Low-Bit Floating-Point Era, in the 53rd Annual International Symposium on Computer Architecture, IEEE/ACM, 2026: 1383-1399.

[2] Tongxin Xie, Zhenhua Zhu, Bing Li, Yukai He, Cong Li, Guangyu Sun, Huazhong Yang, Yuan Xie, Yu Wang, UniNDP: A Unified Compilation and Simulation Tool for Near DRAM Processing Architectures, 2025 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 2025: 624-640.

[3] Hongyi Wang, Zhenhua Zhu, Tianchen Zhao, Yunfei Xiang, Zehao Wang, Jincheng Yu, Huazhong Yang, Yuan Xie and Yu Wang. REACT3D: Real-time Edge Accelerator for Incremental Training in 3D Gaussian Splatting based SLAM Systems, Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture. 2025: 1852-1866.

[4] Lidong Guo, Zhenhua Zhu, Qiushi Lin, Yuan Xie, Huazhong Yang, Wangyang Fu, and Yu Wang. How Do Errors Impact NN Accuracy on Non-Ideal Analog PIM? Fast Evaluation via an Error-Injected Robustness Metric, 2025 IEEE/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 2025: 1-9.

[5] Shuai Yuan, Angxin Cai, Qiushi Lin, Guoxing Wang, Yu Wang, Zhenhua Zhu, and Yanan Sun. HPIM-NoC: A Priori-Knowledge-Based Optimization Framework for Heterogeneous PIM-Based NoCs, 2025 62nd ACM/IEEE Design Automation Conference (DAC). IEEE, 2025: 1-7.

[6] Lidong Guo, Zhenhua Zhu, Tengxuan Liu, Xuefei Ning, Shiyao Li, Guohao Dai, Huazhong Yang, Wangyang Fu, and Yu Wang. Towards floating point-based attention-free LLM: Hybrid PIM with non-uniform data format and reduced multiplications, Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design. 2024: 1-9.

[7] Zhenhua Zhu, Hanbo Sun, Tongxin Xie, Yu Zhu, Guohao Dai, Lixue Xia, Dimin Niu, Xiaoming Chen, X. Sharon Hu, Yu Cao, Yuan Xie, Huazhong Yang, Yu Wang. MNSIM 2.0: A behavior-level modeling tool for processing-in-memory architectures. IEEE transactions on computer-aided design of integrated circuits and systems, 2023, 42(11): 4112-4125.

[8] Zhenhua Zhu, Jun Liu, Guohao Dai, Shulin Zeng, Bing Li, Huazhong Yang and Yu Wang. Processing-in-hierarchical-memory architecture for billion-scale approximate nearest neighbor search[C]//2023 60th ACM/IEEE Design Automation Conference (DAC). IEEE, 2023: 1-6.

[9] Zhenhua Zhu, Hanbo Sun, Yujun Lin, Guohao Dai, Lixue Xia, Song Han, Yu Wang, Huazhong Yang. A configurable multi-precision CNN computing framework based on single bit RRAM, Proceedings of the 56th Annual Design Automation Conference 2019. 2019: 1-6.

[10] Zhenhua Zhu, Jilan Lin, Ming Cheng, Lixue Xia, Hanbo Sun, Xiaoming Chen, Yu Wang and Huazhong Yang. Mixed size crossbar-based RRAM CNN accelerator with overlapped mapping method[C]//Proceedings of the International Conference on Computer-Aided Design. 2018: 1-8.

中国计算机学会容错专委40周年优秀成果

《电子与信息学报》2025年度“优秀论文奖”及“最具传播影响力论文奖”

计算机体系结构顶会HPCA 2025最佳论文荣誉提名奖

EDA会议DATE 2023最佳论文提名

清华大学优秀博士毕业生

清华大学优秀博士论文