Accueil > Actualités > L'Actu des membres et partenaires > Numecas International

Actualités de Numeca International

Recent developments in NUMECA FINE™/Open have yielded impressive improvements in massively parallel performance. More than just improving the scalability of the solver iteration loop, these developments have affected all phases of a typical simulation: solver startup, iteration, and the solution writing. Taken together, these developments allow efficient performance with over 20,000 processes and have made rapid turnaround of high resolution time accurate simulations a reality.

In recent years there has been a shift in industrial turbomachinery design and analysis to higher fidelity, higher cost, time-accurate simulations in place of traditional steady state analysis. These simulations allow a deeper understanding of blade passing interaction and other time-varying phenomena which can negatively impact design efficiency. However, this type of simulation presents many significant software challenges:

• As opposed to steady state simulation which only require a single meshed blade passage, unsteady simulations require multiple blade passages or even a full 360 degree mesh. To maintain a sufficient mesh density this can lead to an order of magnitude or more increase in mesh size. To achieve a quick solution turnaround time a scalable parallel implementation is mandatory.
• A second problem appears in the form of poorly scaling solver input/output (IO). The famous saying by Ken Batcher applies:  “A supercomputer is a device for turning compute-bound problem into an I/O-bound problem”. At higher levels of parallelism a large percentage of computation time is spent on traditionally serial I/O. This is most apparent with unsteady simulations which require frequent solution writes.

Recent developments in the NUMECA FINE™/Open solver have addressed both of these problems. First, optimizations to the MPI-based parallel model have yielded efficient parallel performance with over 20,000 processes and a per-process load of less than 30K cells. Second, a comprehensive parallel I/O solution has been implemented with the CGNS-3 file format, allowing scalable initialization, check-pointing, and shutdown of the FINE™/Open solver at any scale.

Taken together, these developments have allowed massive unsteady simulations which would have been otherwise unfathomable. In collaboration with Dresser-Rand, high resolution turbomachinery DES simulations have been performed on the OLCF Titan supercomputer using mesh configurations with between 8e7 and 6e8 cells, the largest of which were solved on over 20,000 compute processes. Using the CPUBooster™ module for rapid convergence, and taking advantage of the efficient parallel performance of the FINE™/Open solver, it is now possible to complete each time step in less than 4 minutes including the solution write. This allows a complete solution turnaround time on the order of a few days.

Obtaining even the smallest increase in efficiency in turbomachinery design most often requires significant effort, but can result in largely diminished costs! Think about reduction of material, lower fuel consumption, increased performance, etc.

This typically implies evaluating the design not only from a component point of view, but also from a system level, bringing with it various uncertainties (geometrical related to manufacturing - input and boundary conditions, etc). 

NUMECA’s multiphysics CFD simulation and optimization environment for turbomachinery, combined with Concepts NREC preliminary design tools, is now offered as a unique state-of-the-art integrated & comprehensive end-to-end solution for any turbomachinery design applications: FINE/Agile™. During this seminar we will show you how this software solution can help you achieve those gains in efficiency in your design process as well.

Get the chance to learn first-hand about the latest advancements in CFD for turbomachinery. We will explain you the full capabilities of FINE/Agile™ and how it can improve your designs. Industry leaders, like Sebastien Le Martelot from the Centre National d'Études Spatiales​ (CNES) will be there to talk to you about their best practices and experiences with our software and Eric Zoppellari from AirREDIC who will share expertise about testing and prototyping of rotating machinery.

Specific topics:

• Introduction to FINE/Agile™: One environment from preliminary and detailed design to CFD simulation and optimization
• Overview of radial and axial preliminary and detailed design tools
• Structured and unstructured meshing solutions directly coupled with detailed design
• Optimization using the parametric blade modeler
• Get hands-on FINE/Agile™ experience

Products that will be covered during this workshop: FINE/Agile™, AutoGrid5™, HEXPRESS/Hybrid™, FINE™/Turbo, Axial™, Compal® and AxCent®

When: Wednesday October 11th 2017, 9:30 am to 5:00 pm 
Venue: École centrale de Lyon (ECL) - 36 Avenue Guy de Collongue, 69134 Écully, France

Don’t miss out! Registration is free but mandatory and places are limited.

Register here

AllScale is an innovative programming approach for ExaScale, decoupling program specification parallelism from management tasks during runtime. Their parallel programming model is based on the nested recursive parallelism, focusing on the following developments:

1. Automated applications porting from small- to extreme scale architectures.
2. Flexible tuning of program execution to fulfil trade-offs among execution time, energy and resource usage.
3. Efficient management of hardware resources and associated parameters (e.g. clock speed),
4. Seamless Integration of resilience management measures to compensate for isolated hardware failures.
5. Online performance monitoring and analysis.

The above mentioned developments will provide an application independent, reusable codes, taking advantage of combining sophisticated, modular and customizable compiler and runtime system based solutions.

As strategic partner within the Allscale project, NUMECA will develop and extend the usage of it's FINE/Open toolchain to exascale HPC.

The request from the industry towards higher fidelity CFD and increased simulation reliability is more and more pressing. The use of unsteady LES (Large Eddy Simulation) or DNS (Direct Numerical Simulation) provides an appropriate approach to fulfil such imposed industry demand.

However, when applied to industrial cases on complex geometries, such LES/DNS simulations imply very large meshes, ranging from 1 to 10 billion mesh points, yielding problems of 50-100 billions+ degrees of freedom as well as thousands of unsteady time steps. To fulfil those requirements, the cost, in terms of CPU time, needs to be significantly reduced, and the best way to do it, is to increase the number of processors, towards ExaScale HPC (High Performance Computing).

Fig1: Transient flow behind a triangular shaped body using FINE/Open.

AllScale will boost development productivity, portability and runtime efficiency. It will reduce energy needs, thus improving the resource efficiency utilisation of small to extreme scale parallel systems. The achieved outcomes are validated with applications from fluid dynamics, environmental hazard and space weather simulations; provided from industrial and academic consortium partners.

AllScale Objectives

1. Single Source to Any Scale
2. Facilitate Recursive Parallelism
3. Multi-Objective Optimization for time, energy and resource usage
4. Unified Runtime System
5. Mitigating Hardware Failures
6. Integrated Online/Offline Monitoring

Les prochains évènement de NUMECA International

Workshop FINE™/Agile in Toulouse, France

Seminar FINE™/Marine in Southhampton, UK

Seminar FINE™/Marine in Rotterdam, Netherlands

FINE™/Marine Workshop in Molde, Norway

NUMECA Germany Users' Meeting 2017

Mesh generation workshop AutoMesh™ in Paris

Workshop - Highly efficient RANS & Manifold modeling of industrial combustion processes 

Numeca will be exhibiting at the International Paris Air Show in June

36th International Conference on Ocean, Offshore & Arctic Engineering (OMAE)

Numeca International User Meeting 2017

10 mai 2016 - Concepts NREC et NUMECA International annoncent un partenariat stratégique pour le design et analyse de turbomachines

Entreprises dominantes en logiciels de design et analyse de turbomachines, Concepts NREC et NUMECA International ont annoncé un partenariat stratégique pour offrir ensemble leurs capabilités à l’industrie turbomachine. Concepts NREC est bien connu pour son logiciel Agile Engineering Design System®, incluant des modules de design préliminaire pour tout type de turbomachine. NUMECA International est mondialement renommé comme leader des logiciels de mécanique des fluides numériques (CFD) dédiés aux turbomachines. En combinant le meilleur de ces deux entreprises, les clients auront accès à la plus à la pointe des suites de logiciels de turbomachines. Cette solution intégrée ira du design préliminaire jusqu’à l’analyse 3D stationnaire et instationnaire.

“Nous travaillons depuis plus de 20 ans avec Concepts NREC et respectons leur compétences en design de turbomachines” déclare Dr. Charles Hirsch, PDG de NUMECA International. “Nous somme impatient de créer un partenariat formel grâce auquel nous pourrons offrir à nos clients les capacités de design préliminaire de Concepts NREC ainsi que celles de génération de géométrie de turbomachines rassemblées dans une même offre.”

Dr. David Japikse, PDG de Concepts NREC a déclaré : “Nous utilisons les outils CFD de NUMECA International depuis des décennies maintenant, et avons été impressionnés par les avancées réalisées au niveau vitesse, précision et fonctionnalités au fur et à mesure des années. Nous sommes très content de pouvoir combiner les fonctionnalités NUMECA International à notre Agile Engineering Design System de par ce nouveau partenariat."