Tools to support mesh adaptation on massively parallel computers

Zhou, Min; Xie, Ting; Seol, Seegyoung; Shephard, Mark S.; Sahni, Onkar; Jansen, Kenneth E.

doi:10.1007/s00366-011-0218-x

Cited by 11 publications

(3 citation statements)

References 29 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such simulations make use of unstructured meshes which are being adapted as the simulation is run on a supercomputer [20,12,21]. The mesh is partitioned, giving a subset of its elements to each thread [12,22,23].…”

Section: Migration Use Casementioning

confidence: 99%

See 1 more Smart Citation

Hybrid MPI-thread parallelization of adaptive mesh operations

2016

Self Cite

View full text Add to dashboard Cite

Many of the world's leading supercomputer architectures are a hybrid of shared memory and network-distributed memory. Such an architecture lends itself to a hybrid MPI-thread programming model. We first present an implementation of inter-thread message passing based on the MPI and pthread libraries. In addition, we present an efficient implementation of termination detection for communication rounds. We use the term phased message passing to denote the communication interface based on this termination detection. This interface is then used to implement parallel operations for adaptive unstructured meshes, and the performance of resulting applications is compared to pure MPI operation. We also present new workflows enabled by the ability to vary the number of threads during runtime.

show abstract

Section: Migration Use Casementioning

confidence: 99%

“…move elements from one thread to another. This operation, called mesh migration [24,25,23], arises in many scenarios. When described in terms of threads, this operation includes the following types of operations:…”

Section: Migration Use Casementioning

confidence: 99%

Hybrid MPI-thread parallelization of adaptive mesh operations

2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…As the adapted grid size is continually evolving during the application, careful attention must be given to load balancing. [58][59][60] Also, adaptation of the surface grid requires distributed access to the geometry model, a capability that is rarely incorporated in existing adaptation tools. Several published grid adaptation methods incorporate parallel execution on small-to moderately-sized systems of thousands of cores.…”

Section: Geometry Denion Coarse Mesh Adapted Meshmentioning

confidence: 99%

Unstructured Grid Adaptation: Status, Potential Impacts, and Recommended Investments Towards CFD 2030

Park

Krakos

Michal

et al. 2016

46th AIAA Fluid Dynamics Conference

View full text Add to dashboard Cite

Unstructured grid adaptation is a powerful tool to control Computational Fluid Dynamics (CFD) discretization error. It has enabled key increases in the accuracy, automation, and capacity of some fluid simulation applications. Slotnick et al. provide a number of case studies in the CFD Vision 2030 Study: A Path to Revolutionary Computational Aerosciences to illustrate the current state of CFD capability and capacity. The study authors forecast the potential impact of emerging High Performance Computing (HPC) environments forecast in the year 2030 and identify that mesh generation and adaptivity will continue to be significant bottlenecks in the CFD workflow. These bottlenecks may persist because very little government investment has been targeted in these areas. To motivate investment, the impacts of improved grid adaptation technologies are identified. The CFD Vision 2030 Study roadmap and anticipated capabilities in complementary disciplines are quoted to provide context for the progress made in grid adaptation in the past fifteen years, current status, and a forecast for the next fifteen years with recommended investments. These investments are specific to mesh adaptation and impact other aspects of the CFD process. Finally, a strategy is identified to di↵use grid adaptation technology into production CFD work flows.

show abstract