Siyu Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Siyu Wu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Hailong Yang
Beihang University
2 shared publications - Ruihao Gong
Beihang University, Beijing, China
2 shared publications - Depei Qian
School of Computer Science and Engineering, Beihang University, Beijing, China
1 shared publication - Shihao Bai
SenseTime, Shanghai, China
1 shared publication - Tao Sun
State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Wenming Liu
Departments of Biomedical Engineering and Pathology School of Basic Medical Science Central South University Changsha Hunan 410013 China
1 shared publication
Latest Publications
- Open Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 798-813
Past-Future Scheduler for LLM Serving under SLA Guarantees
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 798-813
Open AccessPast-Future Scheduler for LLM Serving under SLA Guarantees
- Open Access
- 12 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 822-832
PRoof: A Comprehensive Hierarchical Profiling Framework for Deep Neural Networks with Roofline Analysis
The increasing diversity of deep neural network (DNN) models and hardware platforms necessitates effective model profiling for high-performance inference deployment. Current DNN profiling tools suffer from either limited optimization insights due to the missing correlation between high-level DNN layer design and low-level hardware performance metrics, or prohibitive profiling overhead due to the large amount of performance measurement through hardware performance counters. Meanwhile, the roofline model has been widely used in the high-performance computing (HPC) domain for identifying performance bottlenecks and guiding optimizations. However, it lacks hierarchical (e.g., kernel/operator/layer), fine-grained, multi-platform support for profiling DNN models. To overcome the above limitations, we propose PRoof, a versatile DNN profiling framework, that can effectively attribute the hardware performance metrics back to the model design. In addition, PRoof does not require massive hardware profiling and thus mitigates the large profiling overhead. Specifically, our approach correlates the profiled result of each layer to their conceptual layer design by effectively handling layer fusion. Our approach also provides an analytical model to predict the floating-point operations (FLOP) and memory accesses of DNN models without massive profiling. We demonstrate the effectiveness of PRoof with representative DNN models across a wide range of hardware platforms. Derived from PRoof’s profiling results, we obtain several insights to provide useful guidance for model design and hardware tuning.
- 12 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 822-832
Open AccessPRoof: A Comprehensive Hierarchical Profiling Framework for Deep Neural Networks with Roofline Analysis
The increasing diversity of deep neural network (DNN) models and hardware platforms necessitates effective model profiling for high-performance inference deployment. Current DNN profiling tools suffer from either limited optimization insights due to the missing correlation between high-level DNN layer design and low-level hardware performance metrics, or prohibitive profiling overhead due to the large amount of performance measurement through hardware performance counters. Meanwhile, the roofline model has been widely used in the high-performance computing (HPC) domain for identifying performance bottlenecks and guiding optimizations. However, it lacks hierarchical (e.g., kernel/operator/layer), fine-grained, multi-platform support for profiling DNN models. To overcome the above limitations, we propose PRoof, a versatile DNN profiling framework, that can effectively attribute the hardware performance metrics back to the model design. In addition, PRoof does not require massive hardware profiling and thus mitigates the large profiling overhead. Specifically, our approach correlates the profiled result of each layer to their conceptual layer design by effectively handling layer fusion. Our approach also provides an analytical model to predict the floating-point operations (FLOP) and memory accesses of DNN models without massive profiling. We demonstrate the effectiveness of PRoof with representative DNN models across a wide range of hardware platforms. Derived from PRoof’s profiling results, we obtain several insights to provide useful guidance for model design and hardware tuning.
- 18 November 2019
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 105 (12) , 5203-5215
Influence of cooling water temperature on ME20M magnesium alloy submerged friction stir welding: a numerical and experimental study
- 18 November 2019
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 105 (12) , 5203-5215
Influence of cooling water temperature on ME20M magnesium alloy submerged friction stir welding: a numerical and experimental study