arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.08843physics.comp-ph
收藏

基于GPU的PyTorch增强型有限差分微磁仿真框架

magnum.np -- A PyTorch based GPU enhanced Finite Difference Micromagnetic Simulation Framework for High Level Development and Inverse Design

Florian Bruckner, Sabri Koraltan, Claas Abert, Dieter Suess

摘要:

magnum.np是一个完全基于张量库PyTorch的微磁有限差分库。这样一个高层次的库的使用导致高度可维护性和可扩展的代码库,这是新的算法和建模方法的调查的理想候选人。另一方面,magnum.np受益于PyTorch的设备抽象和优化,能够在包括GPU和潜在TPU系统在内的许多计算平台上有效执行微磁模拟。我们展示了一个有竞争力的性能,以国家的最先进的微磁代码,如mumax3,并显示我们的代码如何使新功能的快速实施。此外,通过使用PyTorch的autograd功能,可以处理逆问题。

英文摘要:

magnum.np is a micromagnetic finite-difference library completely based on the tensor library PyTorch. The use of such a high level library leads to a highly maintainable and extensible code base which is the ideal candidate for the investigation of novel algorithms and modeling approaches. On the other hand magnum.np benefits from the devices abstraction and optimizations of PyTorch enabling the efficient execution of micromagnetic simulations on a number of computational platforms including GPU and potentially TPU systems. We demonstrate a competitive performance to state-of-the art micromagnetic codes such a mumax3 and show how our code enables the rapid implementation of new functionality. Furthermore, handling inverse problems becomes possible by using PyTorch's autograd feature.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑