主要从事高性能深度学习系统、人工智能编译器、神经网络模型压缩等方向的研究工作，作为负责人主持国家自然科学基金青年科学基金、中国博士后科学基金面上资助、CCF-腾讯犀牛鸟基金、CCF-百度松果基金、CCF-华为胡杨林基金等项目，在ASPLOS、CGO、TCAD、TACO等国际会议和期刊上发表论文30余篇。

2024年10月 — 今：中国科学院计算技术研究所，副研究员

2022年1月 — 2024年10月：中国科学院计算技术研究所，助理研究员

2018年9月 — 2022年1月：中国科学院计算技术研究所，博士生

2015年7月 — 2018年6月：吉林大学，计算机科学与技术学院，硕士生

2011年9月 — 2015年7月：吉林大学，计算机科学与技术学院，本科生

期刊文章：

[1] Xueying Wang, Guangli Li*, Zhen Jia, Xiaobing Feng, Yida Wang. Fast convolution meets low precision: Exploring efficient quantized Winograd convolution on modern CPUs. ACM Transactions on Architecture and Code Optimization, 2024: 1-26. (CCF-A)

[2] Xiaohui Wei, Nan Jiang, Hengshan Yue, Xiaonan Wang, Jianpeng Zhao, Guangli Li, Meikang Qiu. ApproxDup: Developing an approximate instruction duplication mechanism for efficient SDC detection in GPGPUs. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024: 1051-1064. (CCF-A)

[3] Guangli Li#, Xiu Ma#, Qiuchu Yu, Lei Liu, Huaxiao Liu, Xueying Wang. CoAxNN: Optimizing on-device deep learning with conditional approximate neural networks. Journal of Systems Architecture, 2023: 102978. (CCF-B)

[4] Xiaohui Wei, Xinyang Zheng, Chenyang Wang, Guangli Li, Hengshan Yue. FASS-pruner: Customizing a fine-grained CNN accelerator-aware pruning framework via intra-filter splitting and inter-filter shuffling. CCF Transactions on High Performance Computing, 2023: 1-12. (CCF-C)

[5] Xueying Wang, Guangli Li*, Xiu Ma, Xiaobing Feng. Facilitating hardware-aware neural architecture search with learning-based predictive models. Journal of Systems Architecture, 2023, 137: 102838. (CCF-B)

[6] Xiu Ma, Guangli Li*, Lei Liu, Huaxiao Liu, Xueying Wang. Accelerating deep neural network filter pruning with mask-aware convolutional computations on modern CPUs. Neurocomputing, 2022, 505: 375-387. (CCF-C)

[7] Jiansong Li, Xueying Wang, Xiaobing Chen, Guangli Li*, Xiao Dong, Peng Zhao, Xianzhi Yu, Yongxin Yang, Wei Cao, Lei Liu, Xiaobing Feng. An application-oblivious memory scheduling system for DNN accelerators. ACM Transactions on Architecture and Code Optimization, 2022: 1-26. (CCF-A)

[8] Guangli Li, Xiu Ma, Xueying Wang, Hengshan Yue, Jiansong Li, Lei Liu, Xiaobing Feng, Jingling Xue. Optimizing deep neural networks on intelligent edge accelerators via flexible-rate filter pruning. Journal of Systems Architecture, 2022, 124: 102431. (CCF-B)

[9] Lei Liu, Xiu Ma, Huaxiao Liu, Guangli Li, Lei Liu. FlexPDA: A flexible programming framework for deep learning accelerators. Journal of Computer Science and Technology, 2022, 37(5): 1200-1220. (CCF-B)

[10] Guangli Li, Xiu Ma, Xueying Wang, Lei Liu, Jingling Xue, Xiaobing Feng. Fusion-catalyzed pruning for optimizing deep learning on intelligent edge devices. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2020: 3614-3626. (CCF-A)

会议文章：

[1] Feng Yu, Guangli Li*, Jiacheng Zhao, Huimin Cui, Xiaobing Feng, Jingling Xue. Optimizing dynamic-shape neural networks on accelerators via on-the-fly micro-kernel polymerization. International Conference on Architectural Support for Programming Languages and Operating Systems, 2024: 797–812. (CCF-A)

[2] Guangli Li, Zhen Jia, Xiaobing Feng, Yida Wang. LoWino: Towards efficient low-precision Winograd convolutions on modern CPUs. International Conference on Parallel Processing, 2021: 1-11. (CCF-B)

[3] Guangli Li, Jingling Xue, Lei Liu, Xueying Wang, Xiu Ma, Xiao Dong, Jiansong Li, Xiaobing Feng. Unleashing the low-precision computation potential of Tensor Cores on GPUs. International Symposium on Code Generation and Optimization, 2021: 90-102. (CCF-B)

[4] Hengshan Yue, Xiaohui Wei, Guangli Li, Jianpeng Zhao, Nan Jiang, Jingweijia Tan. G-SEPM: Building an accurate and efficient soft error prediction model for GPGPUs. International Conference for High Performance Computing, Networking, Storage and Analysis, 2021: 1-15. (CCF-A)

[5] Xiu Ma, Guangli Li*, Lei Liu, Huaxiao Liu, Xiaobing Feng. Understanding the runtime overheads of deep learning inference on edge devices. International Symposium on Parallel and Distributed Processing with Applications, 2021: 390-397. (CCF-C)

[6] Guangli Li, Xueying Wang, Xiu Ma, Lei Liu, Xiaobing Feng. LANCE: Efficient low-precision quantized Winograd convolution for neural networks based on graphics processing units. IEEE International Conference on Acoustics, Speech and Signal Processing, 2020: 3842-3846. (CCF-B)

[7] Xueying Wang, Guangli Li, Xiao Dong, Jiansong Li, Lei Liu and Xiaobing Feng. Accelerating deep learning inference with cross-layer data reuse on GPUs. International European Conference on Parallel and Distributed Computing, 2020: 219-233. (CCF-B)

[8] Jiansong Li, Zihan Jiang, Fangxin Liu, Xiao Dong, Guangli Li, Xueying Wang, Wei Cao, Lei Liu, Yanzhi Wang, Tao Li, Xiaobing Feng. Characterizing the I/O pipeline in the deployment of CNNs on commercial accelerators. International Symposium on Parallel and Distributed Processing with Applications, 2020: 137-144. (CCF-C)

[9] Jiansong Li, Wei Cao, Xiao Dong, Guangli Li, Xueying Wang, Peng Zhao, Lei Liu, Xiaobing Feng. Compiler-assisted operator template library for DNN accelerators. International Conference on Network and Parallel Computing, 2020: 3-16. (CCF-C)

[10] Xiao Dong, Lei Liu, Peng Zhao, Guangli Li, Jiansong Li, Xueying Wang, Xiaobing Feng. Acorns: A framework for accelerating deep neural networks with input sparsity. International Conference on Parallel Architectures and Compilation Techniques, 2019: 178-191. (CCF-B)