papers.bib

@inproceedings{UniCore,
  title={UniCore: A Bit-Width Scalable GEMM Unit for Unified LLM Inference},
  author={Chen†*, Yonghao and Zou†*, Jiaxiang and Chen†, Xingyu and Xu†, Chenxi and Guo†, Jingyu and Chen, Xinyu},
  booktitle={International Symposium on Computer Architecture (ISCA)},
  year={2026},
  note={to appear},
  selected={true},

}

@inproceedings{DSTREE,
  author={Zeng†*, Bi and Wu†*, Zhenlin and Liu, Hongyuan and Chen, Xinyu},
  title={DSTREE: Data-Driven Synchronous Traversals for Decision Forests on GPUs},
  booktitle={IEEE International Parallel and Distributed Processing Symposium (IPDPS)},
  year={2026},
  selected={true}
}

@inproceedings{RidgeWalker,
  title={RidgeWalker: Perfectly Pipelined Graph Random Walks on FPGAs},
  author={Tan, Hongshi and Chen, Yao and  Chen, Xinyu and Zhang, Qizhen and Chen, Cheng and Wong, Weng-Fai and He, Bingsheng},
  booktitle={IEEE International Symposium on High Performance Computer Architecture (HPCA)},
  year={2026}
}

@inproceedings{AxCore,
  title={AxCore: A Quantization-Aware Approximate GEMM Unit for LLM Inference},
  author={Zou†*, Jiaxiang and Chen†*, Yonghao and Chen†, Xingyu and Xu†, Chenxi and Chen, Xinyu},
  booktitle={IEEE/ACM International Symposium on Microarchitecture (MICRO)},
  year={2025},
  selected={true},
  code={https://github.com/CLab-HKUST-GZ/micro58-axcore},
  pdf={axcore-micro25.pdf}
}

@inproceedings{X-SET,
  title={X-SET: An Efficient Graph Pattern Matching Accelerator With Order-Aware Parallel Intersection Units},
  author={Xu†, Chenxi and Shi, Tianhui and Sun, Shixuan and Zhai, Jidong and Chen, Xinyu},
  booktitle={IEEE/ACM International Symposium on Microarchitecture (MICRO)},
  year={2025},
  code={https://github.com/CLab-HKUST-GZ/micro58-xset},
  pdf={xset-micro25.pdf}
}

@inproceedings{OA-LAMA, 
author = {Chen†, Huangxu and Hao, Yingbo and Zou, Yi and Chen, Xinyu},
title = {OA-LAMA: An Outlier-Adaptive LLM Inference Accelerator with Memory-Aligned Mixed-Precision Group Quantization},
year = {2025},
booktitle = {IEEE/ACM International Conference on Computer-Aided Design (ICCAD)},
selected={true},
code={https://github.com/CLab-HKUST-GZ/ICCAD25_OA-LAMA},
pdf={OALAMA_ICCAD2025.pdf}
}


@inproceedings{Automata-taco, 
author = {Wu†, Zhenlin and Ge, Tianao and Li, Jiajia and Chen, Xinyu and Liu, Hongyuan},
title = {Advancing Matrix Operations for High-Performance and Memory-Efficient Automata Processing on GPUs},
year = {2025},
booktitle = {ACM Transactions on Architecture and Code Optimization (TACO)}
}

@inproceedings{Graphitron,
author = {Zhang, Xinmiao and Feng, Zheng and Liang, Shengwen and Chen, Xinyu and Zhang, Lei and Liu, Cheng},
title = {Graphitron: A Domain Specific Language for FPGA-Based Graph Processing Accelerator Generation},
year = {2025},
booktitle = {ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES)},
pdf={Graphitron-LCTES25.pdf}
}

@inproceedings{wu2025apnet,
  title={Rethinking Dynamic Networks and Heterogeneous Computing with Automatic Parallelization},
  author={WU, Ruilong and Li, Xinjiao and Wang, Yisu and Chen, Xinyu and Kutscher, Dirk},
  booktitle={The 9th Asia-Pacific Workshop on Networking (APNet)},
  year={2025},
  pdf={APNet-25.pdf}
}

@inproceedings{chen2025april,
  title={April: Accuracy-Improved Floating-Point Approximation For Neural Network Accelerators},
  author={Chen†, Yonghao and Zou†, Jiaxiang and Chen, Xinyu},
  booktitle={ACM/IEEE Design Automation Conference (DAC)},
  year={2025},
  organization={IEEE},
  pdf={April-DAC25.pdf},
  code={https://github.com/CLabGit/April}
}

@article{yu2025climenti,
  title={Clementi: Efficient Load Balancing and Communication Overlap for Multi-FPGA Graph Processing},
  author={Yu, Feng and Tan, Hongshi and Chen, Xinyu and Chen, Yao and He, Bingsheng and Wong, Weng-Fai},
  journal={Proceedings of the ACM on Management of Data (SIGMOD)},
  year={2025},
  publisher={ACM New York, NY, USA},
  code={https://github.com/Xtra-Computing/Clementi},
  pdf={clementi-sigmod25.pdf}
}

@inproceedings{cheng2019deploying,
  title={Deploying hash tables on die-stacked high bandwidth memory},
  author={Cheng, Xuntao and He, Bingsheng and Lo, Eric and Wang, Wei and Lu, Shengliang and Chen, Xinyu},
  booktitle={International Conference on Information and Knowledge Management (CIKM)},
  pages={239--248},
  year={2019},
  code={https://github.com/Xtra-Computing/HashJoin_HMA},
  pdf={cikm19.pdf}
}

@inproceedings{chen2019fly,
  title={On-the-fly parallel data shuffling for graph processing on OpenCL-based FPGAs},
  author={Chen, Xinyu and Bajaj, Ronak and Chen, Yao and He, Jiong and He, Bingsheng and Wong, Weng-Fai and Chen, Deming},
  booktitle={International Conference on Field Programmable Logic and Applications (FPL)},
  pages={67--73},
  year={2019},
  organization={IEEE},
  code={https://github.com/Xtra-Computing/On-the-fly-data-shuffling-for-OpenCL-based-FPGAs},
  pdf={FPL19.pdf}
}

@article{gui2019survey,
  title={A survey on graph processing accelerators: Challenges and opportunities},
  author={Gui, Chuang-Yi and Zheng, Long and He, Bingsheng and Liu, Cheng and Chen, Xinyu and Liao, Xiao-Fei and Jin, Hai},
  journal={Journal of Computer Science and Technology},
  volume={34},
  pages={339--371},
  year={2019},
  publisher={Springer US},
  pdf={JCST.pdf}
}

@inproceedings{liu2019obfs,
  title={OBFS: OpenCL based BFS optimizations on software programmable FPGAs},
  author={Liu, Cheng and Chen, Xinyu and He, Bingsheng and Liao, Xiaofei and Wang, Ying and Zhang, Lei},
  booktitle={International Conference on Field-Programmable Technology (FPT)},
  pages={315--318},
  year={2019},
  organization={IEEE},
  code={https://github.com/Liu-Cheng/bfs_with_Intel_OpenCL},
  pdf={OBFS.pdf}
}

@inproceedings{chen2020fpga,
  title={Is FPGA useful for hash joins?},
  author={Chen, Xinyu and Chen, Yao and Bajaj, Ronak and He, Jiong and He, Bingsheng and Wong, Weng-Fai and Chen, Deming},
  booktitle={Conference on Innovative Data Systems Research (CIDR)},
  year={2020},
  code={https://github.com/Xtra-Computing/HashjoinOnHARP},
  pdf={cidr20-join.pdf}
}

@article{liu2020g3,
  title={G3: when graph neural networks meet parallel graph processing systems on GPUs},
  author={Liu, Husong and Lu, Shengliang and Chen, Xinyu and He, Bingsheng},
  journal={Proceedings of the VLDB Endowment (VLDB)},
  volume={13}, 
  number={12},
  pages={2813--2816},
  year={2020},
  publisher={VLDB Endowment},
  code={https://github.com/Xtra-Computing/G3},
  pdf={vldb2020-G3.pdf}
}

@inproceedings{chen2021thundergp,
  title={ThunderGP: HLS-based graph processing framework on FPGAs},
  author={Chen, Xinyu and Tan, Hongshi and Chen, Yao and He, Bingsheng and Wong, Weng-Fai and Chen, Deming},
  booktitle={ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)},
  pages={69--80},
  year={2021},
  code={https://github.com/Xtra-Computing/ThunderGP},
  pdf={thundergp.pdf}
}

@inproceedings{chen2021skew,
  title={Skew-oblivious data routing for data intensive applications on FPGAs with HLS},
  author={Chen, Xinyu and Tan, Hongshi and Chen, Yao and He, Bingsheng and Wong, Weng-Fai and Chen, Deming},
  booktitle={ACM/IEEE Design Automation Conference (DAC)},
  pages={937--942},
  year={2021},
  organization={IEEE},
  pdf={dac.pdf}
}

@inproceedings{tan2021thundering,
  title={ThundeRiNG: generating multiple independent random number sequences on FPGAs},
  author={Tan, Hongshi and Chen, Xinyu and Chen, Yao and He, Bingsheng and Wong, Weng-Fai},
  booktitle={ACM International Conference on Supercomputing (SC)},
  pages={115--126},
  year={2021},
  code={https://github.com/Xtra-Computing/ThundeRiNG},
  pdf={thundering.pdf}
}

@inproceedings{chen2022regraph,
  title={ReGraph: Scaling Graph Processing on HBM-enabled FPGAs with Heterogeneous Pipelines},
  author={Chen, Xinyu and Chen, Yao and Cheng, Feng and Tan, Hongshi and He, Bingsheng and Wong, Weng-Fai},
  booktitle={IEEE/ACM International Symposium on Microarchitecture (MICRO)},
  pages={1342--1358},
  year={2022},
  organization={IEEE},
  code={https://github.com/Xtra-Computing/ReGraph},
  pdf={regraph.pdf}
}

@article{chen2022thundergp,
  title={ThunderGP: Resource-efficient graph processing framework on FPGAs with HLS},
  author={Chen, Xinyu and Cheng, Feng and Tan, Hongshi and Chen, Yao and He, Bingsheng and Wong, Weng-Fai and Chen, Deming},
  journal={ACM Transactions on Reconfigurable Technology and Systems (TRETS)},
  volume={15},
  number={4},
  pages={1--31},
  year={2022},
  publisher={ACM New York, NY},
  code={https://github.com/Xtra-Computing/ThunderGP/tree/v_HBM},
  pdf={trets22.pdf}
}


@article{tan2023lightrw,
  title={LightRW: FPGA Accelerated Graph Dynamic Random Walks},
  author={Tan, Hongshi and Chen, Xinyu and Chen, Yao and He, Bingsheng and Wong, Weng-Fai},
  journal={Proceedings of the ACM on Management of Data (SIGMOD)},
  volume={1},
  number={1},
  pages={1--27},
  year={2023},
  publisher={ACM New York, NY, USA},
  code={https://github.com/Xtra-Computing/LightRW},
  pdf={lightrw.pdf}
}