Benchmark tests have seen large mechanical simulations solving three to six times faster.
Disclosure: Shawn Wasserman is a former employee of Ansys Inc. who owns minor Ansys company stock.
Over the past few years, Ansys has been paying close attention to the ability of graphics processing units (GPUs) to speed up the computations of simulations. In fact, they have a whole product centered around the concept with Ansys Discovery (formerly Discovery Live).
The industry has noticed and now a few solvers have at least some GPU functionality. Ansys is carrying on this tradition when last week it announced that Ansys Mechanical can run on AMD Instinct accelerators—one of the newest GPUs offered by data centers and supercomputers. This added compatibility offers engineers more high-performance computing (HPC) options to process their larger simulations. It also future proofs those simulations for the upcoming generation of supercomputers.
“Ansys’ collaboration with AMD will help enable mutual customers to leverage cutting-edge GPU hardware for Ansys Mechanical applications in the data center, both on-premises and in the cloud to reduce time to market and deliver more optimal solutions,” said Shane Emswiler, senior vice president of products at Ansys. “This work is well-aligned with our high-performance computing strategy to invest deeply in GPUs as an emerging, sustainable, powerful technology for Ansys simulations.”
To make Ansys software run on the new GPUs, Ansys developed an APDL code that can interface with AMD ROCm libraries on Linux. The software is designed to support the scaling of the Mechanical solvers on Instinct accelerators. According to some benchmarks with the sparse direct solver, this could translate to large structural mechanical models running three to six times faster.
“Today’s large, complex engineering challenges require quick, predictively accurate simulations that scale,” said Brad McCredie, corporate vice president, Data Center and Accelerated Business Unit at AMD. “The collaboration between Ansys and AMD can enable a speed boost for some applications, enabling our joint customers to run complex structural simulations that drive higher quality, more efficient designs for cars, planes, and a range of other products while meeting their deadlines.”
Clearly, GPU is becoming a big talking point when it comes to the computation of complex simulations. The dream of super-fast and accurate simulations on GPU is just beginning, for more on this topic, read: When Disruption Comes to Simulation, Will GPUs Take Victory?