Publications
[Google scholar] | [DBLP] |
Recent papers in top-tier conferences/journals
- Zhongkai Yu, Shengwen Liang, Tianyun Ma, Yunke Cai, Ziyuan Nan, Di Huang, Xinkai Song, Yifan Hao, Jie Zhang, Tian Zhi, Yongwei Zhao, Zidong Du, Xing Hu, Qi Guo, and Tianshi Chen. Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM, 2024 57th IEEE/ACM International Symposium on Microarchitecture (MICRO), Austin, TX, USA, 2024, pp.1474-1488.
- Xiurui Pan, Yuda An, Shengwen Liang, Bo Mao, Mingzhe Zhang, Qiao Li, Myoungsoo Jung, and Jie Zhang. Flagger: Cooperative acceleration for large-scale cross-silo federated learning aggregation, 2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA). IEEE, 2024, pp.915-930.
Papers
2025
- APoX-M: Accelerate deep point cloud analysis via adaptive graph constructionIntegration, the VLSI Journal, 2025
2024
- AGC: A Unified Architecture for Accelerating K-Nearest Neighbor Graph Construction in Vector SearchIn 2024 IEEE/ACM International Conference on Computer Aided Design (ICCAD), New Jersey, USA, Oct 2024
- Flagger: Cooperative acceleration for large-scale cross-silo federated learning aggregationIn 2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA), Buenos Aires, Argentina, Oct 2024
- Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLMIn 2024 57th IEEE/ACM International Symposium on Microarchitecture (MICRO), Austin, TX, USA, Oct 2024
- Chiplever: Towards Effortless Extension of Chiplet-based System for FHEIn 61st ACM/IEEE Design Automation Conference (DAC), San Francisco CA USA, Jun 2024
- Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation frameworkIn 61st ACM/IEEE Design Automation Conference (DAC), San Francisco CA USA, Jun 2024
- Alchemist: A Unified Accelerator Architecture for Cross-Scheme Fully Homomorphic EncryptionIn 61st ACM/IEEE Design Automation Conference (DAC), San Francisco CA USA, Jun 2024
- SmartATPG: Learning-based Automatic Test Pattern Generation with Graph Convolutional Network and Reinforcement LearningIn 61st ACM/IEEE Design Automation Conference (DAC), San Francisco CA USA, Jun 2024
- HyQA: Hybrid Near-Data Processing Platform for Embedding Based Question Answering SystemIn 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), Valencia, Spain, Mar 2024
- GPACE: An Energy-Efficient PQ-Based GCN Accelerator with Redundancy ReductionIn 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), Valencia, Spain, Mar 2024
- APoX: Accelerate Graph-Based Deep Point Cloud Analysis via Adaptive Graph ConstructionIn 29th Asia and South Pacific Design Automation Conference (ASP-DAC), Songdo Convention Center, Incheon, Korea., Jan 2024
2023
- Intelligent Automatic Test Pattern Generation for Digital Circuits Based on Reinforcement LearningIn IEEE 32nd Asian Test Symposium (ATS), Beijing, China, Oct 2023
- PANG: A Pattern-Aware GCN Accelerator for Universal GraphsIn IEEE 41st International Conference on Computer Design (ICCD), Washington, DC, USA, Nov 2023
- Energy-efficient NTT design with one-bank SRAM and 2-D PE arrayIn 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE), Antwerp, Belgium, Apr 2023
2022
- VStore: In-storage graph based vector search acceleratorIn 59th ACM/IEEE Design Automation Conference (DAC), San Francisco California, Apr 2022
- Cognitive SSD+: a deep learning engine for energy-efficient unstructured data retrievalCCF Transactions on High Performance Computing (CCF-THPC), Apr 2022
2021
- GLIST: Towards In-Storage Graph LearningIn 2021 USENIX Annual Technical Conference (ATC), Virtual Event, Apr 2021
- GCiM: A Near-Data Processing Accelerator for Graph ConstructionIn 58th ACM/IEEE Design Automation Conference (DAC), San Francisco, CA, USA, Jun 2021
- EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural NetworksIEEE Transactions on Computers (TC), Jun 2021
2020
- DeepBurning-GL: an Automated Framework for Generating Graph Neural Network AcceleratorsIn 2020 IEEE/ACM International Conference On Computer Aided Design (ICCAD), San Diego, CA, USA, Jun 2020
2019
- InS-DLA: an In-SSD Deep Learning Accelerator for Near-Data Processing.In 29th International Conference on Field Programmable Logic and Applications (FPL), Barcelona, Spain, Sep 2019
- Cognitive SSD: A Deep Learning Engine for In-Storage Data Retrieval.In 2019 USENIX Conference on Usenix Annual Technical Conference (ATC), Renton, WA, USA, Sep 2019
- A None-Sparse Deep Learning Accelerator that Explores the Computation Redundancy in Neural Networks.In IEEE/ACM Proceedings of Design, Automation Conference (DAC), Las Vegas, NV, USA, Jun 2019