Multilevel parallelization for simulating compressible turbulent flows on most kinds of hybrid supercomputers

DOI10.1016/J.COMPFLUID.2018.03.011MaRDI QIDQ1615500zbMATH OpenOpenAlexWikidataFDO

Authors A. Gorobets, S. A. Soukov, P. B. Bogdanov

Publication date 31 October 2018

Published in Computers and Fluids (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.compfluid.2018.03.011

zbMATH Keywords

GPUheterogeneous computingparallel CFDturbulent flowsunstructured mesh

Mathematics Subject Classification ID

Finite volume methods for initial value and initial-boundary value problems involving PDEs (65M08) Numerical algorithms for specific classes of architectures (65Y10) Compressibility effects in turbulence (76F50) Finite volume methods applied to problems in fluid mechanics (76M12)

Recommendations

• Heterogeneous CPU+GPU parallelization for high-accuracy scale-resolving simulations of compressible turbulent flows on hybrid supercomputers
• GPU-accelerated DNS of compressible turbulent flows
• A parallel MPI+OpenMP+OpenCL algorithm for hybrid supercomputations of incompressible flows
• A hierarchical parallel implementation for heterogeneous computing. Application to algebra-based CFD simulations on hybrid supercomputers
• Adaptation and optimization of basic operations for an unstructured mesh CFD algorithm, for computation on massively parallel accelerators

Cites work

• A parallel MPI+OpenMP+OpenCL algorithm for hybrid supercomputations of incompressible flows
• A portable OpenCL-based unstructured edge-based finite element Navier-Stokes solver on graphics hardware
• Adaptation and optimization of basic operations for an unstructured mesh CFD algorithm, for computation on massively parallel accelerators
• Collaborating CPU and GPU for large-scale high-order CFD simulations with complex grids on the TianHe-1A supercomputer
• Heterogeneous computing on mixed unstructured grids with pyfr
• Riemann Solvers and Numerical Methods for Fluid Dynamics
• Two-level parallelization of a fluid mechanics algorithm exploiting hardware heterogeneity

Cited in

(16)

• Parallel computation of super-/hypersonic flows on workstation network and Transputer arrays
• A parallel MPI+OpenMP+OpenCL algorithm for hybrid supercomputations of incompressible flows
• Parallelizing and optimizing a detonation combustion simulation application on heterogeneous platform
• Heterogeneous computing in resource-intensive CFD simulations
• A hierarchical parallel implementation for heterogeneous computing. Application to algebra-based CFD simulations on hybrid supercomputers
• Parallel performance analysis of coupled heat and fluid flow in parallel plate channel using CUDA
• Adaptive mesh refinement simulations of gas dynamic flows on hybrid meshes
• Productivity, performance, and portability for computational fluid dynamics applications
• Performance of a new CFD flow solver using a hybrid programming paradigm
• Parallelization for unstructured adaptive mesh CFD algorithm
• scientific article; zbMATH DE number 956669 (Why is no real title available?)
• Load balancing method for heterogeneous CFD algorithms
• Методы повышения и оценки производительности алгоритмов моделирования газодинамических течений на неструктурированных сетках
• Scale-resolving simulation of a low-pressure turbine on hybrid supercomputers
• On the implementation of flux limiters in algebraic frameworks
• Heterogeneous CPU+GPU parallelization for high-accuracy scale-resolving simulations of compressible turbulent flows on hybrid supercomputers

Describes a project that uses

Uses Software

• MPI
• OpenCL
• PyFR

This page was built for publication: Multilevel parallelization for simulating compressible turbulent flows on most kinds of hybrid supercomputers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1615500)