Exploring Numba and CuPy for GPU-Accelerated Monte Carlo Radiation Transport-Reference-Cited by-同舟云学术

Exploring Numba and CuPy for GPU-Accelerated Monte Carlo Radiation Transport

Published:2024-03-20 Issue:3 Volume:12 Page:61
ISSN:2079-3197
Container-title:Computation
language:en
Short-container-title:Computation

Author:

Askar Tair¹²^ORCID,Yergaliyev Argyn³^ORCID,Shukirgaliyev Bekdaulet²⁴⁵⁶^ORCID,Abdikamalov Ernazar²³^ORCID

Affiliation:

1. School of Engineering and Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan

2. Energetic Cosmos Laboratory, Nazarbayev University, Astana 010000, Kazakhstan

3. Department of Physics, Nazarbayev University, Astana 010000, Kazakhstan

4. Heriot-Watt International Faculty, Zhubanov University, Aktobe 030000, Kazakhstan

5. Fesenkov Astrophysical Institute, Almaty 050020, Kazakhstan

6. Department of Computation and Data Science, Astana IT University, Astana 010000, Kazakhstan

Abstract

This paper examines the performance of two popular GPU programming platforms, Numba and CuPy, for Monte Carlo radiation transport calculations. We conducted tests involving random number generation and one-dimensional Monte Carlo radiation transport in plane-parallel geometry on three GPU cards: NVIDIA Tesla A100, Tesla V100, and GeForce RTX3080. We compared Numba and CuPy to each other and our CUDA C implementation. The results show that CUDA C, as expected, has the fastest performance and highest energy efficiency, while Numba offers comparable performance when data movement is minimal. While CuPy offers ease of implementation, it performs slower for compute-heavy tasks.

Funder

Science Committee of the Ministry of Science and Higher 268 Education of the Republic of Kazakhstan

Nazarbayev University Faculty Development Competitive Research Grant Program

Aerospace Committee of the Ministry of Digital Development, Innovations and Aerospace Industry of the Republic of Kazakhstan

Publisher

MDPI AG

Link

https://www.mdpi.com/2079-3197/12/3/61/pdf

Reference93 articles.

1. GPU algorithms for efficient exascale discretizations;Abdelfattah;Parallel Comput.,2021

2. End-to-end GPU acceleration of low-order-refined preconditioning for high-order finite element discretizations;Pazner;Int. J. High Perform. Comput. Appl.,2023

3. Hu, Y., Liu, Y., and Liu, Z. (2022, January 7–9). A Survey on Convolutional Neural Network Accelerators: GPU, FPGA and ASIC. Proceedings of the 2022 14th International Conference on Computer Research and Development (ICCRD), Shenzhen, China.

4. The transformational role of GPU computing and deep learning in drug discovery;Pandey;Nat. Mach. Intell.,2022

5. Myths and legends in high-performance computing;Matsuoka;Int. J. High Perform. Comput. Appl.,2023