CFD Direct

The Architects of OpenFOAM

Cloud

Remote CFD with OpenFOAM

Remote CFD with OpenFOAM

With restricted access to the workplace, a CFD engineer can be productive by quickly switching to remote CFD using CFD Direct From the Cloud™ (CFDDFC®) and by learning effective CFD. CFDDFC is a turnkey system with OpenFOAM and supporting software running in its native Linux environment on AWS. Engineers can launch remote instances (virtual machines) in 2 minutes providing remote desktop access to 48 core instances and scalable clusters of 100s of cores. At the same time the engineer can learn to be more productive by registering for our Live Virtual OpenFOAM Training, taken from the safety and comfort of their home using the CFDDFC system.

CFDDFC® v8 for Azure

CFDDFC® v8 for Azure

CFD Direct is pleased to announce the release of version 8 of CFD Direct From the Cloud™ (CFDDFC®) for Microsoft Azure. Available from the Azure Marketplace, CFDDFC v8 includes OpenFOAM v8, ParaView v5.6.0, OpenMPI v2.1.1 and FreeCAD v0.18.3, running on Ubuntu 18.04 LTS. Users can launch pay-as-you-go VMs from the image in minutes and connect via remote desktop or terminal login using SSH. Azure offers a wide range of VM types including the compute-optimised F-series with up to 36 physical cores (F72sv2) and the high performance computing H-series.

CFDDFC (Arm) for AWS C6g

CFDDFC (Arm) for AWS C6g

CFD Direct has launched CFDDFC® (Arm), a marketplace product on Amazon Web Services (AWS) for computational fluid dynamics (CFD) with OpenFOAM. CFDDFC (Arm) is a variant of CFD Direct From the Cloud™ for Amazon EC2 instances running Arm-based Graviton2 processors, in particular the C6g instances for compute-intensive workloads. CFDDFC (Arm) operates in server-mode without graphical applications and includes OpenFOAM 7 and OpenMPI 4.0.3 running on Ubuntu Server for Arm 20.04 LTS. For batch CFD jobs with guaranteed access on-demand, users can save 35% on their EC2 costs with C6g instances.

CFDDFC® v8 Released

CFDDFC® v8 Released

CFD Direct is pleased to announce the release of version 8 of CFD Direct From the Cloud™ (CFDDFC®), available on Amazon Web Services (AWS) Marketplace as the standard CFDDFC product and CFDDFC (Arm). Standard CFDDFC v8 includes OpenFOAM v8, ParaView v5.6.0, OpenMPI v3.1.4 and FreeCAD v0.18.3, running on Ubuntu 18.04 LTS. CFDDFC (Arm) is server-only including OpenFOAM v8 and OpenMPI v4.0.3, running on Ubuntu 18.04 LTS. CFDDFC runs on single instances with up to 48 C5 Intel cores (c5.24xlarge) or 64 C6 Arm-based cores (c6g.16xlarge) and in clusters with with good parallel scaling on clusters of instances up to 1000 cores.

OpenFOAM HPC with AWS EFA

External Aerodynamics of a Vehicle with OpenFOAM

In November 2018, Amazon Web Services (AWS) announed Elastic Fabric Adapter, a network interface for HPC applications running on EC2. We previewed the EFA technology, running benchmark CFD simulations with OpenFOAM, presented previously: (1) strong scaling – 97 m total cells, external aerodynamics around a car; (2) weak scaling – 100 k cells per core, flow over a weir. At 1008 cores, EFA delivered linear scaling in the strong scaling test and ~70% scaling in the weak scaling test. With linear strong scaling, EFA enables faster solutions for the same cost simply by running on more cores. The combination of open source software, C5n instances and EFA provides impressive HPC, at a price accessible to all.

OpenFOAM HPC with AWS C5n

Flow over a Weir with Hydraulic Jump

CFD Direct From the Cloud™ (CFDDFC) is a Marketplace Product for AWS EC2, that provides a complete platform with OpenFOAM and supporting software running on Ubuntu Linux. It enables simple, fast creation of a cluster of instances to run CFD with OpenFOAM. We tested Amazon EC2 C5n instances, launched in November 2018, on 2 cases of steady-state, external aerodynamics around a car and transient simulation of water flowing over a weir. With meshes of 50-100 million cells, results showed 70%-90% scaling at 504 cores. The cost of the simulations was in the order of $100, compared to $100,000+ to purchase on-premises hardware and licences of proprietary software.