Treffer: TorchCor: High-Performance Cardiac Electrophysiology Simulations with the Finite Element Method on GPUs

Title:
TorchCor: High-Performance Cardiac Electrophysiology Simulations with the Finite Element Method on GPUs
Authors:
Zhou, Bei, Balmus, Maximilian, Corrado, Cesare, Cicci, Ludovica, Qian, Shuang, Niederer, Steven A.
Publication Year:
2025
Collection:
ArXiv.org (Cornell University Library)
Subject Terms:
Software Engineering
Document Type:
Fachzeitschrift text
Language:
unknown
Relation:
http://arxiv.org/abs/2510.12011
Availability:
http://arxiv.org/abs/2510.12011
Accession Number:
edsbas.A80CA8C7
Database:
BASE

Weitere Informationen

Cardiac electrophysiology (CEP) simulations are increasingly used for understanding cardiac arrhythmias and guiding clinical decisions. However, these simulations typically require high-performance computing resources with numerous CPU cores, which are often inaccessible to many research groups and clinicians. To address this, we present TorchCor, a high-performance Python library for CEP simulations using the finite element method on general-purpose GPUs. Built on PyTorch, TorchCor significantly accelerates CEP simulations, particularly for large 3D meshes. The accuracy of the solver is verified against manufactured analytical solutions and the $N$-version benchmark problem. TorchCor is freely available for both academic and commercial use without restrictions.