OpenMP application experiences: Porting to accelerated nodes

As recent enhancements to the OpenMP specification become available in its implementations, there is a need to share the results of experimentation in order to better understand the OpenMP implementation’s behavior in practice, to identify pitfalls, and to learn how the implementations can be effect...

Full description

Saved in:
Bibliographic Details
Published in:Parallel computing 2022-03, Vol.109 (C), p.102856, Article 102856
Main Authors: Bak, Seonmyeong, Bertoni, Colleen, Boehm, Swen, Budiardja, Reuben, Chapman, Barbara M., Doerfert, Johannes, Eisenbach, Markus, Finkel, Hal, Hernandez, Oscar, Huber, Joseph, Iwasaki, Shintaro, Kale, Vivek, Kent, Paul R.C., Kwack, JaeHyuk, Lin, Meifeng, Luszczek, Piotr, Luo, Ye, Pham, Buu, Pophale, Swaroop, Ravikumar, Kiran, Sarkar, Vivek, Scogland, Thomas, Tian, Shilei, Yeung, P.K.
Format: Article
Language:English
Subjects:
Accelerators
Application porting experiences
GAMESS
GenASiS
GESTS
GridQCD
High performance computing
LSMS
OpenMP implementations
QMCPACK
RAJA
SLATE
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As recent enhancements to the OpenMP specification become available in its implementations, there is a need to share the results of experimentation in order to better understand the OpenMP implementation’s behavior in practice, to identify pitfalls, and to learn how the implementations can be effectively deployed in scientific codes. We report on experiences gained and practices adopted when using OpenMP to port a variety of ECP applications, mini-apps and libraries based on different computational motifs to accelerator-based leadership-class high-performance supercomputer systems at the United States Department of Energy. Additionally, we identify important challenges and open problems related to the deployment of OpenMP. Through our report of experiences, we find that OpenMP implementations are successful on current supercomputing platforms and that OpenMP is a promising programming model to use for applications to be run on emerging and future platforms with accelerated nodes.
ISSN:0167-8191
1872-7336
DOI:10.1016/j.parco.2021.102856