STEllAR-GROUP/hpx: HPX V1.4.1: The C++ Standards Library for Parallelism and Concurrency

Kaiser, Hartmut; wash, Bryce Adelstein Lelbach aka; Heller, Thomas; Simberg, Mikael; Bergé, Agustín; Biddiscombe, John; aurianer,; Bikineev, Anton; Mercer, Grant; Schäfer, Andreas; Huck, Kevin; Lemoine, Adrian S.; Kwon, Taeguk; Habraken, Jeroen; Anderson, Matthew; Copik, Marcin; Brandt, Steven R.; Stumpf, Martin; Bourgeois, Daniel; Blank, Denis; Jakobovits, Shoshana; Amatya, Vinay; rstobaugh,; Viklund, Lars; Khatami, Zahra; Diehl, Patrick; Pathak, Tapasweni; Bacharwar, Devang; Yang, Shuangyang; Schnetter, Erik

doi:10.5281/zenodo.3675272

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The developed numerical model has been implemented in a software framework written in C++ programming language with the use of open source scientific computing libraries, such as Eigen [41], Blaze [42], and PETSc [43]. The software has been parallelized for shared and distributed memory systems with the use of a hybrid OpenMP+MPI programming, and HPX [44]. Performance comparison between the hybrid programming and HPX has been performed by Bremer et al in [21].…”

Section: Numerical Experiments and Discussionmentioning

confidence: 99%

Discontinuous Galerkin methods for a dispersive wave hydro-morphodynamic model with bed-load transport

Kazhyken,

Videman,

Dawson

2020

Preprint

View full text Add to dashboard Cite

A dispersive wave hydro-morphodynamic model coupling the Green-Naghdi equations (the hydrodynamic part) with the sediment continuity Exner equation (the morphodynamic part) is presented. Numerical solution algorithms based on discontinuous Galerkin finite element discretizations of the model are proposed. The algorithms include both coupled and decoupled approaches for solving the hydrodynamic and morphodynamic parts simultaneously and separately from each other, respectively. The Strang operator splitting technique is employed to treat the dispersive terms separately, and it provides the ability to ignore the dispersive terms in specified regions, such as surf zones. Algorithms that can handle wetting-drying and detect wave breaking are presented. The numerical methods are verified and validated with two numerical experiments:(1) a simulation of water waves in the vicinity of the Faro-Olhão inlet of the Ria Formosa lagoon in Portugal, (2) an experiment that measures the flow and bed morphology induced by a solitary wave over a sloping beach. The results indicate that the model has the potential to be used in studies of coastal morphodynamics driven by dispersive water waves, given that the hydrodynamic part resolves the water motion and dispersive wave effects with sufficient accuracy up to swash zones, and the morphodynamic model can capture the major features of bed erosion and deposition.

show abstract

Section: Numerical Experiments and Discussionmentioning

confidence: 99%

Discontinuous Galerkin methods for a dispersive wave hydro-morphodynamic model with bed-load transport

Kazhyken,

Videman,

Dawson

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The developed numerical model has been implemented in a software framework written in C++ programming language with the use of open source scientific computing libraries, such as Eigen [57], Blaze [58], and PETSc [59]. The software has been parallelized for shared and distributed memory systems with the use of a hybrid OpenMP+MPI programming, and HPX [60]. Performance comparison between the hybrid programming and HPX has been performed by Bremer et al in [36].…”

Section: Numerical Experiments and Discussionmentioning

confidence: 99%

Discontinuous Galerkin methods for a dispersive wave hydro-sediment-morphodynamic model

Kazhyken,

Videman,

Dawson

2020

Preprint

View full text Add to dashboard Cite

A dispersive wave hydro-sediment-morphodynamic model developed by complementing the shallow water hydro-sediment-morphodynamic (SHSM) equations with the dispersive term from the Green-Naghdi equations is presented. A numerical solution algorithm for the model based on the second-order Strang operator splitting is presented. The model is partitioned into two parts, (1) the SHSM equations and (2) the dispersive correction part, which are discretized using discontinuous Galerkin finite element methods. This splitting technique provides a facility to select dynamically regions of a problem domain where the dispersive term is not applied, e.g. wave breaking regions where the dispersive wave model is no longer valid. Algorithms that can handle wetting-drying and detect wave breaking are provided and a number of numerical examples are presented to validate the developed numerical solution algorithm. The results of the simulations indicate that the model is capable of predicting sediment transport and bed morphodynamic processes correctly provided that the empirical models for the suspended and bed load transport are properly calibrated. Moreover, the developed model is able to accurately capture hydrodynamics and wave dispersion effects up to swash zones, and its application is justified for simulations where dispersive wave effects are prevalent.

show abstract

“…Existing task-based libraries, such as HPX [11], Legion [2], StarPU [1] or Charm++ [12], target performance at any scale from fine-grained parallelism to distributed parallel computing. HPX uses an API compatible with the C ++ 14 standard and is based on message-driven computations and asynchronous calls.…”

Section: Background/state Of the Artmentioning

confidence: 99%

Hedgehog: Understandable Scheduler-Free Heterogeneous Asynchronous Multithreaded Data-Flow Graphs

Bardakoff¹,

Bachelet²,

Blattner³

et al. 2020

2020 IEEE/ACM 3rd Annual Parallel Applications Workshop: Alternatives to MPI+X (PAW-ATM)

View full text Add to dashboard Cite

Getting performance on high-end heterogeneous nodes is challenging. This is due to the large semantic gap between a computation's specification-possibly mathematical formulas or an abstract sequential algorithm-and its parallel implementation; this gap obscures the program's parallel structures and how it gains or loses performance. We present Hedgehog, a library aimed at coarse-grain parallelism. It explicitly embeds a data-flow graph in a program and uses this graph at runtime to drive the program's execution so it takes advantage of hardware parallelism (multicore CPUs and multiple accelerators). Hedgehog has asynchronicity built in. It statically binds individual threads to graph nodes, which are ready to fire when any of their inputs are available. This allows Hedgehog to avoid using a global scheduler and the loss of performance associated with global synchronizations and managing of thread pools. Hedgehog provides a separation of concerns and distinguishes between compute and state maintenance tasks. Its API reflects this separation and allows a developer to gain a better understanding of performance when executing the graph. Hedgehog is implemented as a C ++ 17 headers-only library. One feature of the framework is its low overhead; it transfers control of data between two nodes in ≈ 1 µs. This low overhead combines with Hedgehog's API to provide essentially cost-free profiling of the graph, thereby enabling experimentation for performance, which enhances a developer's insight into a program's performance.Hedgehog's asynchronous data-flow graph supports a data streaming programming model both within and between graphs. We demonstrate the effectiveness of this approach by highlighting the performance of streaming implementations of two numerical linear algebra routines, which are comparable to existing libraries: matrix multiplication achieves >95 % of the theoretical peak of 4 GPUs; LU decomposition with partial pivoting starts streaming partial final result blocks 40× earlier than waiting for the full result. The relative ease and understandability of obtaining performance with Hedgehog promises to enable non-specialists to target performance on high-end single nodes.

show abstract

STEllAR-GROUP/hpx: HPX V1.4.1: The C++ Standards Library for Parallelism and Concurrency

Cited by 3 publications

References 0 publications

Discontinuous Galerkin methods for a dispersive wave hydro-morphodynamic model with bed-load transport

Discontinuous Galerkin methods for a dispersive wave hydro-morphodynamic model with bed-load transport

Discontinuous Galerkin methods for a dispersive wave hydro-sediment-morphodynamic model

Hedgehog: Understandable Scheduler-Free Heterogeneous Asynchronous Multithreaded Data-Flow Graphs

Contact Info

Product

Resources

About