OpenMP in VASP: Threading and SIMD

Autor(en)

Florian Wende, Martijn Marsman, Jeongnim Kim, Fedor Vasilev, Zhengji Zhao, Thomas Steinke

Abstrakt

The Vienna Ab initio Simulation Package (VASP) is a widely used electronic structure code that originally exploits process-level parallelism through the Message Passing Interface (MPI) for work distribution within and across nodes. Architectural changes of modern parallel processors urge programmers to address thread- and data-level parallelism as well to benefit most from the available compute resources within a node. We describe for VASP how to approach for an MPI + OpenMP parallelization including data-level parallelism through OpenMP SIMD constructs together with a generic high-level vector coding scheme. We can demonstrate an improved scalability of VASP and more than 20% gain over the MPI-only version as well as a 2x increased performance of collective operations using the multiple-endpoint MPI feature. The high-level vector coding scheme applied to VASP's general gradient approximation routine gives up 9x performance gain on AVX512 platforms with the Intel compiler.

Organisation(en)

Computergestützte Materialphysik

Externe Organisation(en)

Intel Corporation (Intel Russia), Konrad-Zuse-Zentrum für Informationstechnik (ZIB), Intel Corporation, USA, Lawrence Berkeley National Laboratory

Journal

International Journal of Quantum Chemistry

Band

119

Anzahl der Seiten

17

ISSN

0020-7608

DOI

https://doi.org/10.1002/qua.25851

Publikationsdatum

12-2018

Peer-reviewed

Ja

ÖFOS 2012

102022 Softwareentwicklung, 102023 Supercomputing, 103018 Materialphysik, 102009 Computersimulation

Schlagwörter

ASJC Scopus Sachgebiete

Condensed Matter Physics, Atomic and Molecular Physics, and Optics, Physical and Theoretical Chemistry

Link zum Portal

https://ucrisportal.univie.ac.at/de/publications/63c02b3d-bfd3-4dc2-8f21-8eedff2b185c