Employing graphics processing unit technology, alternating direction implicit method and domain decomposition to speed up the numerical diffusion solver for the biomedical engineering research

Beini Jiang, Allan Struthers, Zhe Sun, Zhuo Feng, Xuqian Zhao, Kaiyong Zhao, Weizhong Dai, Xiaobo Zhou, Michael E. Berens, Le Zhang

Research output: Contribution to journalArticlepeer-review

19 Scopus citations

Abstract

Diffusion of biological compounds, including nutrients, oxygen, and chemoattractants, is a common component of biomedical engineering models. Conventional numerical schemes, such as alternating direction implicit (ADI) for diffusion, are frequently the computational bottleneck. Our study employs graphics processing unit (GPU) technology to accelerate the diffusion model simulation. We tailor, implement, analyze, and test several parallel ADI algorithms on the highly parallel computational and data architecture of the GPU. Our study confirms that the proposed algorithms provide fast, high-quality simulation results suitable for inclusion in numerous bioengineering simulations.

Original languageEnglish
Pages (from-to)1829-1849
Number of pages21
JournalInternational Journal for Numerical Methods in Biomedical Engineering
Volume27
Issue number11
DOIs
StatePublished - Nov 2011

Keywords

  • Alternating direction implicit method (ADI)
  • Domain decomposition
  • Graphics processing unit (GPU)
  • Parallel computing

Fingerprint

Dive into the research topics of 'Employing graphics processing unit technology, alternating direction implicit method and domain decomposition to speed up the numerical diffusion solver for the biomedical engineering research'. Together they form a unique fingerprint.

Cite this