From a Vector Computer to an SMP-Cluster Hybrid Parallelization of the CFD Code PANTA

نویسندگان

  • Dieter an Mey
  • Stephan Schmidt
چکیده

Transforming a well vectorized Fortran77 CFD code into a more flexible Fortran90 program using a hybrid parallelization model still is an adventure. Here we report on our experiences with PANTA, a 3D Navier-Stokes solver that is extensively used in the modeling of turbomachinery. During this ongoing process various software tools are employed: Hewlett Packard's, Silicon Garphics', Portland Group's, and SUN's autoparallelizing Fortran90 compilers, various serial runtime performance analyzers, Simulog's Foresys Fortran Engineering System in combination with AWK scripts, Etnus' TotalView parallel debugger, Kuck & Associates' KAP/Pro Toolset and Visual KAP for OpenMP preprocessor and Pallas' Vampir performance analysis tools for MPI programs. A few suggestions for an improved integration of automatic and explicit parallelization are made.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Hybrid Parallelization of a Turbomachinery Cfd Code: Peformance Enhancements on Multicore Architectures

The CFD code TRACE used to be parallelized by means of a domain decomposition and MPI for distributed cluster architectures. The roadmap for x86 processor development however shows that the single core performance will grow only very moderately in the future. Instead one processor will integrate more and more cores. For the traditionally parallelized code this means to further increase the numb...

متن کامل

Comparing the OpenMP, MPI, and Hybrid Programming Paradigm on an SMP Cluster

Clusters of SMP (Symmetric Multi-Processors) nodes provide support for a wide range of parallel programming paradigms. The shared address space within each node is suitable for OpenMP parallelization. Message passing can be employed within and across the nodes of a cluster. Multiple levels of parallelism can be achieved by combining message passing and OpenMP parallelization. Which programming ...

متن کامل

Comparing the OpenMP, MPI, and Hybrid Programming Paradigms on an SMP Cluster

Clusters of SMP (Symmetric Multi-Processors) nodes provide support for a wide range of parallel programming paradigms. The shared address space within each node is suitable for OpenMP parallelization. Message passing can be employed within and across the nodes of a cluster. Multiple levels of parallelism can be achieved by combining message passing and OpenMP parallelization. Which programming ...

متن کامل

Comparing the OpenMP, MPJ, and Hybrid Programming Paradigm on an SMP Cluster

Clusters of SMP (Symmetric Multi-Processors) nodes provide support for a wide range of parallel programming paradigms. The shared address space within each node is suitable for OpenMP parallelization. Message passing can be employed within and across the nodes of a cluster. Multiple levels of parallelism can be achieved by combining message passing and OpenMP parallelization. Which programming ...

متن کامل

Parallel Iterative Solvers for Unstructured Grids Using an OpenMP/MPI Hybrid Programming Model for the GeoFEM Platform on SMP Cluster Architectures

An efficient parallel iterative method for unstructured grids developed by the authors for SMP cluster architectures on the GeoFEM platform is presented. The method is based on a 3-level hybrid parallel programming model, including message passing for inter-SMP node communication, loop directives by OpenMP for intra-SMP node parallelization and vectorization for each processing element (PE). Si...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2000