FLOW-3D/MP enables engineers to take advantage of the power of FLOW-3D on high-performance compute clusters to tackle problems with very large domains or long runtimes. Hybrid parallelization of the FLOW-3D solver uses both Message Passing Interface (MPI) and OpenMP to achieve maximum parallelization and utilization of the underlying multi-core cluster architecture. FLOW-3D/MP offers significant performance advantage and reduced runtimes which results in shorter design cycles and an opportunity to do a comprehensive parametric study within their design cycles. All this can be achieved while retaining the accuracy offered by FLOW-3D. The physical models and numerical methods of FLOW-3D/MP v6 are based on FLOW-3D v11.
Highlights of FLOW-3D/MP v6.0
- Developed and optimized for the latest multi-core architecture
- Parallelization based on the Hybrid MPI-OpenMP methodology
- True Domain Decomposition
- Automatic Decomposition Tool allows directional decomposition
- Optimized MPI communication and memory management in the pre-processor
- Full compatibility with the FLOW-3D v11 GUI and FlowSight for post-processing results
- Remote solving capability enabled
High performance clusters offer significant performance gains over typical desktop computers but can be quite complex to configure. There are many choices for operating systems, middleware, interconnects, memory, and storage. Intel Corporation operates the Intel Cluster Ready certification program to assure users that hardware and software will work correctly together. Hardware that displays the Intel Cluster Ready logo is assured to run software which is also certified as Cluster Ready. FLOW-3D/MP v6.0 is certified Cluster Ready.