Zhaolin Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhaolin Li has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Mingyu Wang
School of Microelectronics Science and Technology, Sun Yat-sen University, Guangzhou, China
2 shared publications - Renhao Fan
Department of Computer Science and Technology, Tsinghua University, Beijing, China
2 shared publications - Yikai Cui
Department of Computer Science and Technology, Tsinghua University, Beijing, China
2 shared publications - Youhui Zhang
Tsinghua University, Beijing, China
2 shared publications - Meng Pang
Department of Computer Science and Technology, Tsinghua University, Beijing, China
1 shared publication - Peng Qu
Tsinghua University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 20 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1806-1818
MagiCache: A Virtual In-Cache Computing Engine
- 20 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1806-1818
Open AccessMagiCache: A Virtual In-Cache Computing Engine
- Open Access
- 20 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 377-389
A Row Decomposition-based Approach for Sparse Matrix Multiplication on GPUs
Sparse-Matrix Dense-Matrix Multiplication (SpMM) and Sampled Dense Dense Matrix Multiplication (SDDMM) are important sparse kernels in various computation domains. The uneven distribution of nonzeros in the sparse matrix and the tight data dependence between sparse and dense matrices make it a challenge to run sparse matrix multiplication efficiently on GPUs. By analyzing the aforementioned problems, we propose a row decomposition (RoDe)-based approach to optimize the two kernels on GPUs, using the standard Compressed Sparse Row (CSR) format. Specifically, RoDe divides the sparse matrix rows into regular parts and residual parts, to fully optimize their computations separately. We also devise the corresponding load balancing and finegrained pipelining technologies. Profiling results show that RoDe can achieve more efficient memory access and reduce warp stall cycles significantly. Compared to the state-of-the-art (SOTA) alternatives, RoDe achieves a speedup of up to 7.86× with a geometric mean of 1.45× for SpMM, and a speedup of up to 8.99× with a geometric mean of 1.49× for SDDMM; the dataset is SuiteSparse. RoDe also outperforms its counterpart in the deep learning dataset. Furthermore, its preprocessing overhead is significantly smaller, averaging only 16% of the SOTA.
- 20 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 377-389
Open AccessA Row Decomposition-based Approach for Sparse Matrix Multiplication on GPUs
Sparse-Matrix Dense-Matrix Multiplication (SpMM) and Sampled Dense Dense Matrix Multiplication (SDDMM) are important sparse kernels in various computation domains. The uneven distribution of nonzeros in the sparse matrix and the tight data dependence between sparse and dense matrices make it a challenge to run sparse matrix multiplication efficiently on GPUs. By analyzing the aforementioned problems, we propose a row decomposition (RoDe)-based approach to optimize the two kernels on GPUs, using the standard Compressed Sparse Row (CSR) format. Specifically, RoDe divides the sparse matrix rows into regular parts and residual parts, to fully optimize their computations separately. We also devise the corresponding load balancing and finegrained pipelining technologies. Profiling results show that RoDe can achieve more efficient memory access and reduce warp stall cycles significantly. Compared to the state-of-the-art (SOTA) alternatives, RoDe achieves a speedup of up to 7.86× with a geometric mean of 1.45× for SpMM, and a speedup of up to 8.99× with a geometric mean of 1.49× for SDDMM; the dataset is SuiteSparse. RoDe also outperforms its counterpart in the deep learning dataset. Furthermore, its preprocessing overhead is significantly smaller, averaging only 16% of the SOTA.
- Open Access
- 28 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 411-423
MAICC : A Lightweight Many-core Architecture with In-Cache Computing for Multi-DNN Parallel Inference
The growing complexity and diversity of neural networks in the fields of autonomous driving and intelligent robots have facilitated the research of many-core architectures, which can offer sufficient programming flexibility to simultaneously support multi-DNN parallel inference with different network structures and sizes compared to domain-specific architectures. However, due to the tight constraints of area and power consumption, many-core architectures typically use lightweight scalar cores without vector units and are almost unable to meet the high-performance computing needs of multi-DNN parallel inference. To solve the above problem, we design an area- and energy-efficient many-core architecture by integrating large amounts of lightweight processor cores with RV32IMA ISA. The architecture leverages the emerging SRAM-based computing-in-memory technology to implement vector instruction extensions by reusing memory cells in the data cache instead of conventional logic circuits. Thus, the data cache in each core can be reconfigured as the memory part and the computing part with the latter tightly coupled with the core pipeline, enabling parallel execution of the basic RISC-V instructions and the extended multi-cycle vector instructions. Furthermore, a corresponding execution framework is proposed to effectively map DNN models onto the many-core architecture by using intra-layer and inter-layer pipelining, which potentially supports multi-DNN parallel inference. Experimental results show that the proposed MAICC architecture obtains a 4.3 × throughput and 31.6 × energy efficiency over CPU (Intel i9-13900k). MAICC also achieves a 1.8 × energy efficiency over GPU (RTX 4090) with only 4MB on-chip memory and 28 mm2 area.
- 28 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 411-423
Open AccessMAICC : A Lightweight Many-core Architecture with In-Cache Computing for Multi-DNN Parallel Inference
The growing complexity and diversity of neural networks in the fields of autonomous driving and intelligent robots have facilitated the research of many-core architectures, which can offer sufficient programming flexibility to simultaneously support multi-DNN parallel inference with different network structures and sizes compared to domain-specific architectures. However, due to the tight constraints of area and power consumption, many-core architectures typically use lightweight scalar cores without vector units and are almost unable to meet the high-performance computing needs of multi-DNN parallel inference. To solve the above problem, we design an area- and energy-efficient many-core architecture by integrating large amounts of lightweight processor cores with RV32IMA ISA. The architecture leverages the emerging SRAM-based computing-in-memory technology to implement vector instruction extensions by reusing memory cells in the data cache instead of conventional logic circuits. Thus, the data cache in each core can be reconfigured as the memory part and the computing part with the latter tightly coupled with the core pipeline, enabling parallel execution of the basic RISC-V instructions and the extended multi-cycle vector instructions. Furthermore, a corresponding execution framework is proposed to effectively map DNN models onto the many-core architecture by using intra-layer and inter-layer pipelining, which potentially supports multi-DNN parallel inference. Experimental results show that the proposed MAICC architecture obtains a 4.3 × throughput and 31.6 × energy efficiency over CPU (Intel i9-13900k). MAICC also achieves a 1.8 × energy efficiency over GPU (RTX 4090) with only 4MB on-chip memory and 28 mm2 area.