Add to ORKGThis work is devoted to the development of efficient parallel algorithms for the direct numerical simulation (DNS) of incompressible flows on modern supercomputers. A Poisson solver for problems with one uniform periodic direction is presented here. It is extended with a two-level hybrid MPI+OpenMP parallelization. Advantages and implementation details for the additional OpenMP parallelization are presented and discussed. This upgrade has allowed to significantly extend the range of efficient scalability. Here, the solver has been tested up to 12800 CPU cores for meshes with up to 10 9 nodes. However, estimations based on the presented results show that this range can be potentially stretched beyond 10 5 cores.Peer Reviewe
In this paper developed and realized absolutely new algorithm for solving three-dimensional Poisson ...
We present a multi-block finite-difference solver for massively parallel Direct Numerical Simulation...
Today most systems in high-performance computing (HPC) feature a hierarchical hardware design: share...
This work is devoted to the development of efficient parallel algorithms for the direct numerical si...
This work presents a parallel Navier-Stokes solver for the large-scale direct numerical simulation (...
This work presents a parallel Navier-Stokes solver for the large-scale direct numerical simulation (...
This work represents an experience in using the hybrid parallel model to perform large-scale DNS. Ad...
This work represents an experience in using the hybrid parallel model to perform large-scale DNS. Ad...
This article presents the development of a hybrid parallel algorithm for solving the Dirichlet probl...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Discon...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Disco...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Disco...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Disco...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Disco...
The solution of the pressure Poisson equation arising in the numerical solution of incompressible Na...
In this paper developed and realized absolutely new algorithm for solving three-dimensional Poisson ...
We present a multi-block finite-difference solver for massively parallel Direct Numerical Simulation...
Today most systems in high-performance computing (HPC) feature a hierarchical hardware design: share...
This work is devoted to the development of efficient parallel algorithms for the direct numerical si...
This work presents a parallel Navier-Stokes solver for the large-scale direct numerical simulation (...
This work presents a parallel Navier-Stokes solver for the large-scale direct numerical simulation (...
This work represents an experience in using the hybrid parallel model to perform large-scale DNS. Ad...
This work represents an experience in using the hybrid parallel model to perform large-scale DNS. Ad...
This article presents the development of a hybrid parallel algorithm for solving the Dirichlet probl...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Discon...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Disco...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Disco...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Disco...
This paper describes the implementation of an hybrid OpenMP/MPI parallelization strategy in a Disco...
The solution of the pressure Poisson equation arising in the numerical solution of incompressible Na...
In this paper developed and realized absolutely new algorithm for solving three-dimensional Poisson ...
We present a multi-block finite-difference solver for massively parallel Direct Numerical Simulation...
Today most systems in high-performance computing (HPC) feature a hierarchical hardware design: share...