3 papers
cs.DC2025
CUTHERMO: Understanding GPU Memory Inefficiencies with Heat Map Profiling
Yanbo Zhao, Jinku Cui, Zecheng Li +3
GPUs have become indispensable in high-performance computing, machine learning, and many other domains. Efficiently utilizing the memory subsystem on GPUs is critical for maximizin…
cs.PF2024
DeepContext: A Context-aware, Cross-platform, and Cross-framework Tool for Performance Profiling and Analysis of Deep Learning Workloads
Qidong Zhao, Hao Wu, Yuming Hao +4
Effective performance profiling and analysis are essential for optimizing training and inference of deep learning models, especially given the growing complexity of heterogeneous c…
cs.SE2023
EasyView: Bringing Performance Profiles into Integrated Development Environments
Qidong Zhao, Milind Chabbi, Xu Liu
Dynamic program analysis (also known as profiling) is well-known for its powerful capabilities of identifying performance inefficiencies in software packages. Although a large numb…