Latest from Simulation/IT

ABB Robotics
Messe Dusseldorf
Rösler Oberflächentechnik GmbH
Dragoscondrea | Dreamstime
Boxx Technologies
Boxx Technologies' APEXX S3 workstation featuring Intel® Core™ i7 and i9 14th gen processors.
A typical casting simulation run with FLOW3DMP showing a performance record for cores left and a contour plot of the filling velocity magnitude at t 05 sec

CFD Program, Distributed Memory Version

May 20, 2013
“… performance and scaling improvements” Fully synchronized physical models Compatible with v.10.1 GUI

FLOW SCIENCE INC. released an updated version of Flow-3D/MP, the distributed memory version of its flagship CFD software, Flow-3D. It allows engineers to take advantage of the scaling potential of the software on multi-core clusters. Flow-3D/MP v5.0 offers users substantial performance and scaling improvements compared to standard Flow-3D v10.1 for workstations and to the prior release of Flow-3D/MP, v4.2.

Flow-3D/MP, first released in 2006, uses a multi-block domain decomposition technique to distribute the simulation onto compute nodes in a cluster. Flow-3D/MP v5.0 was tested extensively and currently is supported on Linux systems (RHEL 5 & 6 and SUSE 11).

The new v5.0 was developed and optimized for the latest multi-core processing architecture. It develops physical models that are fully synchronized with Flow-3D v10.1. The parallelization process is based on the Hybrid MPI-OpenMP methodology.

Flow-3D/MP v5.0 has an ‘Automatic Decomposition Tool’ that allows directional decomposition, and also has ‘True Domain Decomposition’ capability.

The physical models in Flow-3D/MP v5.0 are based on Flow-3D v.10.1, released earlier this year, and new version is fully compatible with the Flow-3D v.10.1 graphical user interface (GUI) for post-processing results.

“Parallelization is the future of CFD. Users continue to simulate larger and more complex problems. By heavily investing in the development of our HPC infrastructure, we will allow our users to meet and even exceed their complex simulation needs,” according to Michael Barkhudarov, vice president of R&D.