Design and Analysis of a Task-based Parallelization over a Runtime System of an Explicit Finite-Volume CFD Code with Adaptive Time Stepping

Abstract FLUSEPA (registered trademark in France No. 134009261) is an advanced simulation tool which performs a large panel of aerodynamic studies. It is the unstructured finite-volume solver developed by Airbus Safran Launchers company to calculate compressible, multidimensional, unsteady, viscous and reactive flows around bodies in relative motion. The time integration in FLUSEPA is done using an explicit temporal adaptive method. The current production version of the code is based on MPI and OpenMP. This implementation leads to important synchronizations that must be reduced. To tackle this problem, we present the study of a task-based parallelization of the aerodynamic solver of FLUSEPA using the runtime system StarPU and combining up to three levels of parallelism. We validate our solution by the simulation (using a finite-volume mesh with 80 million cells) of a take-off blast wave propagation for Ariane 5 launcher.

• Publication year

  2017

• Venue

  Journal of Computer Science

• Publication date

  2017-03-01

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1016/j.jocs.2017.03.008arXiv 1704.01144
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Towards an Efficient Task-Based Parallelization over a Runtime System of an Explicit Finite-Volume CFD Code with Adaptive Time Stepping

  2016cited by this paper
• Bridging the gap between OpenMP 4.0 and native runtime systems for the fast multipole method

  2016cited by this paper
• Faithful performance prediction of a dynamic task‐based runtime system for heterogeneous multi‐core architectures

  2015cited by this paper
• Exploiting two-level parallelism by aggregating computing resources in task-based applications over accelerator-based machines

  2015influential reference
• Legion: programming distributed heterogeneous architectures with logical regions

  2014cited by this paper
• Taking Advantage of Hybrid Systems for Sparse Direct Solvers via Task-Based Runtimes

  2014cited by this paper
• Task-Based FMM for Multicore Architectures

  2014influential reference
• PaRSEC : A programming paradigm exploiting heterogeneity for enhancing scalability

  2013cited by this paper
• Composing multiple StarPU applications over heterogeneous machines: A supervised approach

  2013cited by this paper
• Flexible Development of Dense Linear Algebra Algorithms on Massively Parallel Architectures with DPLASMA

  2011cited by this paper
• StarPU: a unified platform for task scheduling on heterogeneous multicore architectures

  2011influential reference
• Concurrent Collections

  2010cited by this paper
• Extending the OpenMP Tasking Model to Allow Dependent Tasks

  2008cited by this paper
• An introduction to computational fluid dynamics - the finite volume method

  2007cited by this paper
• Supermatrix out-of-order scheduling of matrix operations for SMP and multi-core architectures

  2007cited by this paper
• Optimizing Compilers for Modern Architectures

  2004cited by this paper
• Optimizing Compilers for Modern Architectures: A Dependence-based Approach

  2001cited by this paper
• From RANS to DNS: Towards a Bridging Model

  1999cited by this paper
• OpenMP: an industry standard API for shared-memory programming

  1998cited by this paper
• An Arbitrary Lagrangian-Eulerian Computing Method for All Flow Speeds

  1997cited by this paper
• SCOTCH: A Software Package for Static Mapping by Dual Recursive Bipartitioning of Process and Architecture Graphs

  1996cited by this paper
• Automatic task graph generation techniques

  1995cited by this paper
• Two new chimera methods - Application to missile separation

  1995cited by this paper
• MPI: A Message-Passing Interface Standard

  1994cited by this paper
• Grid adaptation using chimera composite overlapping meshes

  1993cited by this paper
• Temporal adaptive Euler/Navier-Stokes algorithm involving unstructured dynamic meshes

  1992cited by this paper
• Three-dimensional aerodynamics with moving bodies applied to solid propellant

  1991influential reference
• Temporal and spatial adaptive algorithm for reacting flows

  1988cited by this paper
• Finite element methods for high speed flows

  1985influential reference

• A Granularity Characterization of Task Scheduling Effectiveness

  2026cites this paper
• Improving energy efficiency of HPC applications using unbalanced GPU power capping

  2025cites this paper
• Scalable and Portable LU Factorization with Partial Pivoting on Top of Runtime Systems

  2025cites this paper
• RSCHED: An Effective Heterogeneous Resource Management for Simultaneous Execution of Task-Based Applications

  2025cites this paper
• Multi-Criteria Mesh Partitioning for an Explicit Temporal Adaptive Task-Distributed Finite-Volume Solver

  2024cites this paper
• Dynamic Tasks Scheduling with Multiple Priorities on Heterogeneous Computing Systems

  2024cites this paper
• Assessing Saiph, a task-based DSL for high-performance computational fluid dynamics

  2023cites this paper
• Automated Generation of High-Performance Computational Fluid Dynamics Codes

  2022cites this paper
• Automated prioritizing heuristics for parallel task graph scheduling in heterogeneous computing

  2022cites this paper
• MulTreePrio: Scheduling task-based applications for heterogeneous computing systems

  2022cites this paper
• Asynchronous task based Eulerian-Lagrangian parallel solver for combustion applications

  2022cites this paper
• Providing In-depth Performance Analysis for Heterogeneous Task-based Applications with StarVZ

  2021cites this paper
• Automatic task-based parallelization of C++ applications by source-to-source transformations

  2021cites this paper
• Improving parallel executions by increasing task granularity in task-based runtime systems using acyclic DAG clustering

  2020cites this paper
• Task‐based parallel strategies for computational fluid dynamic application in heterogeneous CPU/GPU resources

  2020cites this paper
• A Tool for Translating Sequential Source Code to Parallel Code Written in C++ and OpenACC

  2019cites this paper
• Impact study of data locality on task-based applications through the Heteroprio scheduler

  2019cites this paper
• Impact study of data locality on task-based applications through the Heteroprio scheduler

  2019cites this paper
• Mathematical analysis of the spatial coupling of an explicit temporal adaptive integration scheme with an implicit time integration scheme

  2019cites this paper
• A coupled implicit-explicit time integration method for compressible unsteady flows

  2019cites this paper
• Hybrid CPU–GPU execution support in the skeleton programming framework SkePU

  2019cites this paper
• Resource aggregation for task-based Cholesky Factorization on top of modern architectures

  2019cites this paper
• Design, Implementation and Performance Analysis of a CFD Task-Based Application for Heterogeneous CPU/GPU Resources

  2018cites this paper
• High-Performance Computing: Dos and Don’ts

  2018cites this paper
• A visual performance analysis framework for task‐based parallel applications running on hybrid clusters

  2018cites this paper
• Performance Analysis Strategies for Task-based Applications on Hybrid Platforms. (Stratégies d'analyse de performance pour les applications basées sur tâches sur plates-formes hybrides)

  2018cites this paper
• Distributed Task-Based Runtime Systems - Current State and Micro-Benchmark Performance

  2018cites this paper
• A Survey of Distributed Asynchronous Many-Task Models and Their Applications

  year unknowncites this paper
• Improving energy efficiency of HPC applications using unbalanced GPU power capping

  year unknowncites this paper
• Conditional Random Field Approach Combining FFT Filtering and Co-Kriging for Reliability Assessment of Slopes

  year unknowncites this paper