kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Heterogeneous parallelization and acceleration of molecular dynamics simulations in GROMACS
KTH, Centres, SeRC - Swedish e-Science Research Centre. KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for High Performance Computing, PDC.ORCID iD: 0000-0003-0603-5514
KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for High Performance Computing, PDC. KTH, Centres, SeRC - Swedish e-Science Research Centre.
KTH, School of Engineering Sciences (SCI), Applied Physics, Biophysics. KTH, Centres, Science for Life Laboratory, SciLifeLab. KTH, Centres, SeRC - Swedish e-Science Research Centre.ORCID iD: 0000-0002-2268-0065
KTH, Centres, Science for Life Laboratory, SciLifeLab. KTH, Centres, SeRC - Swedish e-Science Research Centre. KTH, School of Engineering Sciences (SCI), Applied Physics, Biophysics.ORCID iD: 0000-0001-6363-2521
Show others and affiliations
2020 (English)In: Journal of Chemical Physics, ISSN 0021-9606, E-ISSN 1089-7690, Vol. 153, no 13, article id 134110Article in journal (Refereed) Published
Abstract [en]

The introduction of accelerator devices such as graphics processing units (GPUs) has had profound impact on molecular dynamics simulations and has enabled order-of-magnitude performance advances using commodity hardware. To fully reap these benefits, it has been necessary to reformulate some of the most fundamental algorithms, including the Verlet list, pair searching, and cutoffs. Here, we present the heterogeneous parallelization and acceleration design of molecular dynamics implemented in the GROMACS codebase over the last decade. The setup involves a general cluster-based approach to pair lists and non-bonded pair interactions that utilizes both GPU and central processing unit (CPU) single instruction, multiple data acceleration efficiently, including the ability to load-balance tasks between CPUs and GPUs. The algorithm work efficiency is tuned for each type of hardware, and to use accelerators more efficiently, we introduce dual pair lists with rolling pruning updates. Combined with new direct GPU-GPU communication and GPU integration, this enables excellent performance from single GPU simulations through strong scaling across multiple GPUs and efficient multi-node parallelization.

Place, publisher, year, edition, pages
AIP Publishing , 2020. Vol. 153, no 13, article id 134110
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-285625DOI: 10.1063/5.0018516ISI: 000578502400002PubMedID: 33032406Scopus ID: 2-s2.0-85092604813OAI: oai:DiVA.org:kth-285625DiVA, id: diva2:1499870
Note

QC 20201110

Available from: 2020-11-10 Created: 2020-11-10 Last updated: 2022-06-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Pall, SzilardZhmurov, ArtemBauer, PaulAbraham, Mark JamesHess, BerkLindahl, Erik

Search in DiVA

By author/editor
Pall, SzilardZhmurov, ArtemBauer, PaulAbraham, Mark JamesHess, BerkLindahl, Erik
By organisation
SeRC - Swedish e-Science Research CentreCentre for High Performance Computing, PDCBiophysicsScience for Life Laboratory, SciLifeLab
In the same journal
Journal of Chemical Physics
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 102 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf