Computer simulation allows for testing of parts and assemblies without having to manufacture and physically manipulate them, which can save significant time and money in the product development process. Unfortunately, mainstream simulation software is incompatible with the data structures used for design models. Even today’s best methods for problems like simulating automotive crashes require millions of dollars of manual labor to prepare each simulation. And even after all this work, these approximated simulation models take up vast amounts of high-performance computing resources. While simulation has an important role in product development, these inefficiencies limit how much it can actually be used to perfect new designs.
“This award underscores the importance of new methods for computer simulation, which plays an important role in product development but has suffered from severe bottlenecks and limitations that have blunted its impact,” notes Chief Strategy Officer Matt Sederberg. “This funding will allow us to optimize our new technology for high performance computing and continue to unleash the power of simulation across industries.”
Coreform is developing a new technology that eliminates those approximations and inefficiencies, but is not yet configured to run on GPU-driven HPC systems. Coreform CEO Michael Scott says “This grant provides further support for our efforts to develop IGA for industry, and adding GPU capabilities will allow our code to handle even the most complex simulations.”
With an earlier, exploratory grant, Coreform collaborated with a national laboratory to partially integrate Coreform IGA with MFEM, a DOE-developed, GPU-enabled, finite element discretization library. The proof of concept they developed was highly successful, and led to the DOE’s decision to further fund the approach. When the project is completed, GPU-enabled Coreform IGA will be available for purchase at Coreform’s website.
