Efficient Solutions Advancing Simulation

Siemens has partnered with Nvidia to advance the concept of computational fluid dynamics simulation. With Siemens’ Simcenter Star-CCM+ 2022.1 software one is able to accelerate CUDA-enabled GPU which ensures faster turnaround times and lower hardware investment costs.

Related Vendors

EDL Anlagenbau Gesellschaft mbH

Angst+Pfister AG

Anton Paar GmbH

Siemens AG

Siemens Digital Industries Software has collaborated with Nvidia to open the door to a new era of Computational Fluid Dynamics (CFD) simulation. Part of the Xcelerator portfolio of software and services, Simcenter STAR-CCM+ 2022.1 software brings CUDA-enabled GPU acceleration to deliver faster turnaround times at lower hardware investment costs to CFD simulation within design and engineering organizations of every size, states the company.

This technology will enable engineers working on external aerodynamics, aerospace, building and infrastructure / civil engineering applications, etc. to massively improve their simulation throughput at equivalent hardware investments with an increased per-dollar performance of GPUs compared to CPUs, adds the firm.

Running a set of industrial-grade external vehicle aerodynamics simulations, the engineers at Siemens and Nvidia were able to demonstrate how usage of GPUs could reduce required hardware compute investments by up to 40 % and the power consumption down to 10 % of the CPU equivalent, while maintaining identical simulation turnaround times.

While CPU-based high-performance computing in conjunction with highly scalable CFD parallelization allows for massive speed-ups in absolute times to solution, it comes at the cost of high hardware or cloud computing investments.

Siemens' software is giving an incredible boost to CFD simulations by using the GPU technology via the CUDA platform and accelerated libraries. Leveraging the GPU architecture, the software users can now run more simulations, faster, and can gain critical insights for their design and operation workflows without compromising on accuracy, mentions Nvidia.

(ID:48033113)