Towards High-Performance AI4NP Applications on Modern GPU Platforms

Conference · 06 May 2024 · EPJ Web of Conferences

DOI:https://doi.org/10.1051/epjconf/202429511023· OSTI ID:2406490

Mei, Xinxin ^[1]; Brei, Nathan ^[1]; Lawrence, David ^[1]

---

1. Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States)

The evolution of modern heterogeneous accelerators, such as GPUs, has significantly advanced the landscape of artificial intelligence (AI). There is a notable surge to adopt AI within the nuclear physics domain (AI4NP). While most AI4NP studies focus on feasibility analysis, our attention is directed towards evaluating their performance on contemporary GPUs that integrate tensor cores. We first benchmark the throughput of hyperparameterized multi-layer perceptron (MLP) models. We then examine the performance of an AI4NP application: Hydra. We assess the performance gain and accuracy loss caused by the tensor cores for low-precision floating-point operations. Our experiments encompass the PyTorch and TensorFlow Keras frameworks on NVIDIA’s T4 and A100 GPUs. We explore the behavior of different GPU hardware platforms and AI software tools. This study can be a valuable resource for guiding the performance optimization of larger-scale deployments of AI4NP applications.

• Research Organization: Thomas Jefferson National Accelerator Facility, Newport News, VA (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Nuclear Physics (NP)
• DOE Contract Number: AC05-06OR23177
• OSTI ID: 2406490
• Report Number(s): JLAB-CST-23-3917; DOE/OR/23177-7118
• Journal Information: EPJ Web of Conferences, Journal Name: EPJ Web of Conferences Vol. 295; ISSN 2100-014X
• Country of Publication: United States
• Language: English