Yuanbo Fan
Research Interests
Yuanbo Fan has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Nikhil Jain
Nvidia Corporation, Santa Clara, CA, USA
1 shared publication - Nirmal Saxena
NVIDIA, Santa Clara, CA, USA
1 shared publication - Rob Van der Wijngaart
Nvidia Corporation, Santa Clara, CA, USA
1 shared publication - Xu Liu
North Carolina State University, Raleigh, USA
1 shared publication - Yueming Hao
Meta, Menlo Park, USA
1 shared publication
Latest Publications
- Open Access
- 15 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 43-53
DrGPU: A Top-Down Profiler for GPU Applications
GPUs have become common in HPC systems to accelerate scientific computing and machine learning applications. Efficiently mapping these applications to rapid evolutions of GPU architectures for high performance is a well-known challenge. Various performance inefficiencies exist in GPU kernels that impede applications from obtaining bare-metal performance. While existing tools are able to measure these inefficiencies, they mostly focus on data collection and presentation, requiring significant manual efforts to understand the root causes for actionable optimization. Thus, we develop DrGPU, a novel profiler that performs top-down analysis to guide GPU code optimization. As its salient feature, DrGPU leverages hardware performance counters available in commodity GPUs to quantify stall cycles, decompose them into various stall reasons, pinpoint root causes, and provide intuitive optimization guidance. With the help of DrGPU, we are able to analyze important GPU benchmarks and applications and obtain nontrivial speedups --- up to 1.77X on V100 and 2.03X on GTX 1650.
- 15 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 43-53
Open AccessDrGPU: A Top-Down Profiler for GPU Applications
GPUs have become common in HPC systems to accelerate scientific computing and machine learning applications. Efficiently mapping these applications to rapid evolutions of GPU architectures for high performance is a well-known challenge. Various performance inefficiencies exist in GPU kernels that impede applications from obtaining bare-metal performance. While existing tools are able to measure these inefficiencies, they mostly focus on data collection and presentation, requiring significant manual efforts to understand the root causes for actionable optimization. Thus, we develop DrGPU, a novel profiler that performs top-down analysis to guide GPU code optimization. As its salient feature, DrGPU leverages hardware performance counters available in commodity GPUs to quantify stall cycles, decompose them into various stall reasons, pinpoint root causes, and provide intuitive optimization guidance. With the help of DrGPU, we are able to analyze important GPU benchmarks and applications and obtain nontrivial speedups --- up to 1.77X on V100 and 2.03X on GTX 1650.