| Issue |
EPJ Web of Conf.
Volume 295, 2024
26th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2023)
|
|
|---|---|---|
| Article Number | 11022 | |
| Number of page(s) | 7 | |
| Section | Heterogeneous Computing and Accelerators | |
| DOI | https://doi.org/10.1051/epjconf/202429511022 | |
| Published online | 06 May 2024 | |
https://doi.org/10.1051/epjconf/202429511022
Running Qiskit on ROCm Platform
1 Institute of High Energy Physics, CAS, 100049 Beijing, China
2 Tianfu Cosmic Ray Research Center, 610213 Chengdu, China
3 Computer Network Information Center, CAS, 100083 Beijing, China
4 Beijing Academy of Quantum Information Sciences, 100193 Beijing, China
* e-mail: biyujiang@ihep.ac.cn
Published online: 6 May 2024
Qiskit is one of the common quantum computing frameworks and and the qiskit-aer package can accelerating quantum circuit simulation using NVIDIA GPU with the help of THRUST. AMD ROCm framework similar to CUDA, a heterogeneous computing framework supporting both the NVIDIA and AMD GPUs provides the possibility to porting Qiskit/Qiskit-Aer from CUDA platform to its own. We present the porting progress of Qiskit/QiskitAer and preliminary performance test on both NVIDA and AMD GPUs. Our results show that Qiskit/Qiskit-Aer cand work well on AMD GPUs with the help of ROCm/HIP, and has comparable performance on AMD platform.
© The Authors, published by EDP Sciences, 2024
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.