EPJ Web Conf.
Volume 245, 202024th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2019)
|Number of page(s)||7|
|Section||9 - Exascale Science|
|Published online||16 November 2020|
Lattice QCD GPU Inverters on ROCm Platform
Institute of High Energy Physics, Chinese Academy of Science, Beijing 100049, China
2 The Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
3 Department of Physics, University of Warwick, Coventry, CV4 7AL, United Kingdom
4 School of Physics, University of Chinese Academy of Sciences, Beijing 100049, China
5 Nanjing Normal University, Nanjing, Jiangsu, 210023, China
6 Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
7 CAS Key Laboratory of Theoretical Physics, Institute of Theoretical Physics, Chinese Academy of Sciences, Beijing 100190, China
Published online: 16 November 2020
The open source ROCm/HIP platform for GPU computing provides a uniform framework to support both the NVIDIA and AMD GPUs, and also the possibility to porting the CUDA code to the HIP-compatible one. We present the porting progress on the Overlap fermion inverter (GWU-code) and also the general Lattice QCD inverter package - QUDA. The manual of using QUDA on HIP and also the tips of porting general CUDA code into the HIP framework are also provided.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.