magnum.np.distributed: accelerating finite difference micromagnetic simulations with multiple GPUs
- 1Graduate School of Information Science and Electrical Engineering, Kyushu University
Abstract
Micromagnetic simulations are essential tools in nanomagnetism and spintronics research. Although widely adopted solvers like Mumax3 and the Python-native magnum.np use GPU acceleration to improve performance, these tools are limited to single-device computation. In this work, we present, to our knowledge, the first Python-native multi-GPU micromagnetic framework by extending magnum.np with PyTorch Distributed. This leverages high-speed communication and computation across multiple GPUs while retaining the benefits of ease of installation, platform-agnostic design, and compatibility with Python. For computationally intensive demagnetisation effective-field calculations, we achieve a 7.0x speedup on a synthetic benchmark with 42.8M cells across 8 GPUs connected via NVLink, whereas the Halo exchange required for Heisenberg exchange shows limited scalability due to kernel dispatch latency. We also demonstrated the framework’s versatility by achieving a 6.8x speedup in demagnetisation field computation on the CPU with NUMA pinning via the MPI backend of PyTorch Distributed, using a 1M-cell synthetic benchmark. Faster turnaround times will enable researchers to explore larger, more complex systems and accelerate the design cycle for novel spintronic devices. Source code: https://gitlab.com/jedcheng/magnum-np-distributed .
Related
- A fullwave model of the nonlinear wave equation with multiple relaxations and relaxing perfectly matched layers for high-order numerical finite difference solutions
- Accelerating cardiovascular digital twin creation using precomputed virtual populations as Bayesian priors
- Accelerating research to keep pace with the rising incidence of coccidioidomycosis
- Accelerating equitable cancer genomics and precision oncology in health care and research: a Lancet Oncology Commission
- Cannabis legalisation and cardiovascular hospitalisations in the United States: nationwide difference-in-differences analysis, 2012–2018
BibTeX
@article{cheng2026magnumnpdistributed,
title = {{magnum.np.distributed: accelerating finite difference micromagnetic simulations with multiple GPUs}},
author = {Tsz Chung Cheng and Yuichiro Kurokawa and Hiromi Yuasa},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-62507-1},
url = {https://doi.org/10.1038/s41598-026-62507-1},
note = {CC BY},
}
RIS
TY - JOUR
TI - magnum.np.distributed: accelerating finite difference micromagnetic simulations with multiple GPUs
AU - Tsz Chung Cheng
AU - Yuichiro Kurokawa
AU - Hiromi Yuasa
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-62507-1
UR - https://doi.org/10.1038/s41598-026-62507-1
AB - Micromagnetic simulations are essential tools in nanomagnetism and spintronics research. Although widely adopted solvers like Mumax3 and the Python-native magnum.np use GPU acceleration to improve performance, these tools are limited to single-device computation. In this work, we present, to our knowledge, the first Python-native multi-GPU micromagnetic framework by extending magnum.np with PyTorch Distributed. This leverages high-speed communication and computation across multiple GPUs while retaining the benefits of ease of installation, platform-agnostic design, and compatibility with Python. For computationally intensive demagnetisation effective-field calculations, we achieve a 7.0x speedup on a synthetic benchmark with 42.8M cells across 8 GPUs connected via NVLink, whereas the Halo exchange required for Heisenberg exchange shows limited scalability due to kernel dispatch latency. We also demonstrated the framework’s versatility by achieving a 6.8x speedup in demagnetisation field computation on the CPU with NUMA pinning via the MPI backend of PyTorch Distributed, using a 1M-cell synthetic benchmark. Faster turnaround times will enable researchers to explore larger, more complex systems and accelerate the design cycle for novel spintronic devices. Source code: https://gitlab.com/jedcheng/magnum-np-distributed .
SN - 2045-2322
ER -