Li Lun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Li Lun has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Yi Zhong
Key Laboratory of Microelectronic Devices and Circuits, MPW Center, School of Integrated Circuits, Peking University, Beijing, China
2 shared publications - Chang Xue
School of Integrated Circuits and the Beijing Advanced Innovation Center for Integrated Circuits, Peking University, Beijing, China
1 shared publication - Cheng Zhao
School of Integrated Circuits, Peking University, Beijing, China
1 shared publication Jinhao Ruan
Peking University
1 shared publication- Tao Zhang
Key Laboratory of Microelectronic Devices and Circuits, MPW Center, School of Integrated Circuits, Peking University, Beijing, China
1 shared publication - Tingting Zhong
School of Integrated Circuits, Peking University, Beijing, China
1 shared publication
Latest Publications
- 26 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 72 (11) , 1750-1754
A Reconfigurable Digital Compute-in-Memory Architecture With 2:4 Compressed Weight Storage for Highly Sparse Fusion Neural Network
The fusion of convolutional neural network (CNN) and spiking neural network (SNN) harnesses their complementary strengths in edge video tasks. However, ongoing challenges remain in the low compatibility between two neural networks and the shortage of storage resources. In this brief, we propose a reconfigurable digital compute-in-memory (RDCIM) architecture featuring 2:4 structured weight pruning, tailored for the efficient fusion of CNN and SNN. Specifically, differential frame convolution (DFC) is adopted in place of conventional convolution. Therefore, the RDCIM fusion accelerator can operate in either DFC mode or SNN mode based on the sparsity of activations. First of all, fine-grained 2:4 structured sparsity enables compressed weight storage, thereby doubling the throughput. Secondly, a novel bitwise in-memory Booth multiplier is implemented to support both 4-bit and 8-bit activations, offering flexible computation. Thirdly, the high sparsity inherent in both differential frames and input spikes allows for the concurrent support of three sparse optimization strategies: coarse-grained zero skipping, medium-grained bank gating, and fine-grained precharge gating. Implemented by TSMC 28nm technology, our proposed architecture achieves the peak energy efficiency of 42.02 TOPS/W for DFC and 0.02 pJ/SOP for SNN.
- 26 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 72 (11) , 1750-1754
A Reconfigurable Digital Compute-in-Memory Architecture With 2:4 Compressed Weight Storage for Highly Sparse Fusion Neural Network
The fusion of convolutional neural network (CNN) and spiking neural network (SNN) harnesses their complementary strengths in edge video tasks. However, ongoing challenges remain in the low compatibility between two neural networks and the shortage of storage resources. In this brief, we propose a reconfigurable digital compute-in-memory (RDCIM) architecture featuring 2:4 structured weight pruning, tailored for the efficient fusion of CNN and SNN. Specifically, differential frame convolution (DFC) is adopted in place of conventional convolution. Therefore, the RDCIM fusion accelerator can operate in either DFC mode or SNN mode based on the sparsity of activations. First of all, fine-grained 2:4 structured sparsity enables compressed weight storage, thereby doubling the throughput. Secondly, a novel bitwise in-memory Booth multiplier is implemented to support both 4-bit and 8-bit activations, offering flexible computation. Thirdly, the high sparsity inherent in both differential frames and input spikes allows for the concurrent support of three sparse optimization strategies: coarse-grained zero skipping, medium-grained bank gating, and fine-grained precharge gating. Implemented by TSMC 28nm technology, our proposed architecture achieves the peak energy efficiency of 42.02 TOPS/W for DFC and 0.02 pJ/SOP for SNN.