Regarding high performance computing (HPC), there are numerous improvements introduced into ANSYS Mechanical APDL16.0. However, I would like to focus this post on a feature that demonstrates the technological leadership of our company. ANSYS Mechanical APDL 15.0 was the first commercial FEA software product to support the Intel® Xeon Phi™ coprocessor. In ANSYS Mechanical APDL 16.0, we extend support for Xeon Phi hardware to virtually all users. The Xeon Phi coprocessors can now be used on either Linux or Windows, as well as with shared-memory parallel (SMP) and distributed-memory parallel (DMP).
Intel Xeon Phi coprocessors are currently supported in a similar manner that NVIDIA GPUs are supported in Mechanical APDL. Once a user requests to use their Xeon Phi hardware, the sparse direct solver automatically offloads certain computationally intensive calculations from the CPU cores to the coprocessors. The coprocessor then quickly performs these calculations and provides the results back to the CPU cores involved in the simulation. This reduces the time to solution and ultimately accelerates the overall simulation. The amount of acceleration depends on several factors such as the model size, Xeon Phi model, CPU model, and the # of CPU cores involved. However, many engineers performing time-consuming FEA simulations will find that they can take advantage of the coprocessors to speed up their simulations. The chart above shows performance results for a standard benchmark of a turbine blade assembly. There is a significant gain achieved when using the Xeon Phi 7120A coprocessors in the Windows workstation.
To learn how you can accelerate your own simulations, attend our upcoming webinar on Tuesday, March 17th. And, as an extra bonus, Intel is offering a limited time (through June 27, 2015), limited volume special promotion for the Intel® Xeon Phi™ Coprocessor 3120A and 7120A. This offer is designed for ANSYS users to cost-effectively purchase and upgrade workstations or systems from your systems manufacturer to get greater levels of performance. Attend the webinar and find out more!
Editors note: If you can’t make the webinar on the 17th, we’re hosting a 2nd session on Thursday, March 19, 2015, 4 PM EST, 8 PM GMT – Register Here
The post Accelerate Mechanical Solutions with Intel® Xeon Phi™ appeared first on ANSYS Blog.