Experiences with the OpenMP Parallelization of DROPS, a Navier-Stokes Solver Written in C++

Terboven, Christian; Spiegel, Alexander; Mey, Dieter an; Groß, Sven; Reichelt, Volker

doi:10.1007/978-3-540-68555-5_8

Cited by 11 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For being able to handle such big computational problems in an acceptable time, the computations must be done on a high performance computer. A shared memory parallelization with OpenMP has been implemented, see Terboven et al (2005) for results. Another strategy is to use multiple processes, where ''process'' means a computing unit with its own memory (called ''distributed memory'').…”

Section: Parallelizationmentioning

confidence: 99%

Validated simulation of droplet sedimentation with finite-element and level-set methods

Bertakis

Groß

Grande

et al. 2010

Chemical Engineering Science

View full text Add to dashboard Cite

Section: Parallelizationmentioning

confidence: 99%

Validated simulation of droplet sedimentation with finite-element and level-set methods

Bertakis

Groß

Grande

et al. 2010

Chemical Engineering Science

View full text Add to dashboard Cite

“…in [14], [16]). After finishing the cell loop, the contributions are merged into the destination vector.…”

Section: A Overview Of Possible Strategiesmentioning

confidence: 91%

Parallel Finite Element Operator Application: Graph Partitioning and Coloring

Kormann

Kronbichler

2011

2011 IEEE Seventh International Conference on eScience

View full text Add to dashboard Cite

We present an efficient implementation of parallel finite element operator application for hexahedral elements. The implementation is tailored to data structures for adaptively refined meshes and exploits parallelism on modern computer systems. The evaluation of local shape functions and gradients is performed with sum-factorization that makes use of the tensorproduct form. For shared memory parallelization, we propose a novel two-level partitioning/coloring approach that avoids race conditions when writing into the result vector. We give evidence for the good performance of our implementation. We employ the optimized operator implementation on a problem in quantum dynamics described by the time-dependent Schrödinger equation. We obtain a speedup of more than a factor four over conventional solvers based on sparse matrices for a moderate polynomial order of four in three dimensions.

show abstract

“…This work precisely aims at filling this gap, providing a practical but generic enough methodology for loop parallelization of typical scientific code. Even though some examples of the application of OpenMP to serial scientific codes can be found in literature [27,28], the discussion is usually focused on the analyzed case, making it di cult for researchers without parallel programming experience to generalize concepts and apply them to a similar but di↵erent problem.…”

Section: Related Workmentioning

confidence: 99%

Practical parallelization of scientific applications with OpenMP, OpenACC and MPI

Aldinucci

Cesare

Colonnelli

et al. 2021

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

This work aims at distilling a systematic methodology to modernize existing sequential scientific codes with a little re-designing e↵ort, turning an old codebase into modern code, i.e., parallel and robust code. We propose a semi-automatic methodology to parallelize scientific applications designed with a purely sequential programming mindset, possibly using global variables, aliasing, random number generators, and stateful functions. We demonstrate that the same methodology works for the parallelization in the shared memory model (via OpenMP), message passing model (via MPI), and General Purpose Computing on GPU model (via OpenACC). The method is demonstrated parallelizing four real-world sequential codes in the domain of physics and material science. The methodology itself has been distilled in collaboration with MSc students of the Parallel Computing course at the University of Torino, that applied it for the first time to the project works that they presented for the final exam of the course. Every year the course hosts some special lectures from industry representatives, who present how they use parallel computing and o↵er codes to be parallelized.

show abstract

Experiences with the OpenMP Parallelization of DROPS, a Navier-Stokes Solver Written in C++

Cited by 11 publications

References 0 publications

Validated simulation of droplet sedimentation with finite-element and level-set methods

Validated simulation of droplet sedimentation with finite-element and level-set methods

Parallel Finite Element Operator Application: Graph Partitioning and Coloring

Practical parallelization of scientific applications with OpenMP, OpenACC and MPI

Contact Info

Product

Resources

About