A decade ago, high-performance computing (HPC) was a relatively new concept for many users of engineering simulation — it was primarily available to those working in large companies that had resources to manage the substantial investments required to create and maintain technology infrastructure. Today, entry-level HPC is available on the typical desktop, and many organizations have embraced the enormous benefits of using multiple processors, or clusters of computers, to tackle their most sophisticated simulation challenges.
HPC adds tremendous value to engineering simulation by enabling the creation of large, high-fidelity models that yield accurate and detailed insight into the performance of a proposed design. High-fidelity simulations allow engineering teams to innovate with a high degree of confidence that their products will meet customer expectations — because their extremely accurate simulations are predicting the actual performance of the product under real-world conditions.
Loading Content. Please wait
High fidelity may refer to simulations using high mesh density for improved accuracy, those that include many geometric details, or those that include more-sophisticated treatment of physical phenomena. High fidelity also can encompass simulation models that go beyond consideration of a single component to include the interaction of multiple components or entire systems. HPC is a key strategic enabler of high-fidelity results, as it provides the resources required for very large and detailed simulations. HPC enables the work to be performed within the time required to impact engineering decisions.
HPC also adds value by enabling greater simulation throughput. Using HPC resources, engineering teams can analyze not just a single design idea, but many design variations. By simulating multiple design ideas concurrently, R&D teams can identify dramatic engineering improvements early in the design process, prior to and more effectively than physical prototyping alone.
The high throughput enabled by HPC also allows engineering teams to simulate the behavior of their product or process over a range of operating conditions. Companies are mindful of warranty promises and the increasing importance of customer satisfaction — especially in today’s world of social media — and HPC provides the capacity to use simulation to ensure that products will perform robustly and reliably once in the customer’s hands.
There is no doubt that users of ANSYS simulation software are ready to leverage the benefits of HPC. In a recent survey, ANSYS customers valued the fast turnaround and high fidelity offered by HPC-enabled simulations, as well as the ability to run more simulations. Accurate results, delivered with speed and certainty, have become mission critical.
The power of HPC is more vital than ever in today’s environment of intensified competition, shorter product life cycles, reduced time to market, sharply targeted product performance, and growing pressure to drive costs out of product development and testing. As businesses seek to minimize physical models and tests by using engineering simulation to study more-complicated multiphysics problems, conduct a larger range of analyses, and understand the interaction of system components, HPC has become a core strategic technology.
The computer industry continues to deliver enormous increases in computing speed and power at consistently lower costs. The average workstation that engineers use today is equivalent in power to the entry-level computer cluster of just a few years ago. Large-scale computing is now within the reach of more and more engineering teams, with the promise of new trends, like cloud computing, to make this access even more widespread.
However, today’s hardware paradigm has turned computational speed into a software development issue. For years, computer processors became faster with each new generation. Today, limited by thermal issues, individual processors are no longer getting faster. Rather, computing capacity is expanding through the addition of more processing units, or cores. The ability of software to scale effectively on a large number of computing cores is critical.
While hardware and software enhancements have enabled HPC to deliver significant value to users of engineering simulation, important challenges remain in ensuring that every organization is strategically deploying HPC to gain the greatest return on investment. Project requirements sometimes dictate the need for intermittent, elastic access to extremes of computational capacity.
For smaller enterprises, specifying, provisioning and managing HPC resources can represent a significant learning curve and require new skills. In medium- and large-sized enterprises, centralized HPC resources are often shared by geographically distributed users — creating a host of attendant issues such as file transfer, remote access and visualization, data management, collaboration, and security. ANSYS is committed to working with our customers to address these challenges related to HPC deployment. And we are also committed to partnering with industry leaders to collaborate on next-generation HPC solutions.
Many companies already leverage HPC resources strategically and successfully to achieve engineering insights that can result in innovation and a sustained market advantage. They are are combining HPC environments and ANSYS solutions to accomplish incredibly complex engineering simulations that would not have been possible even five years ago. Through strategic deployment, they are realizing a significant return on their HPC investment.
To meet the sometimes-conflicting demands of clients, the commercial aircraft industry is under intense pressure to reduce the cost of every flight, satisfy tightening environmental regulations, and transport passengers whose flight experience expectations are constantly increasing — all the while satisfying regulatory demands for airworthiness and safety mandated by regulators. When you couple this with the need to deliver a product to market as quickly as possible and to minimize ongoing operational and maintenance costs, it is clear to see why the industry is at the forefront, applying advanced engineering simulation technology and HPC. Parker Aerospace and Volvo Aero are two companies that have implemented HPC in innovative ways. Parker Aerospace has turned workstations into a virtual cluster and Volvo Aero has made ANSYS tools, including HPC, part of its Life Tracking System to determine the life of engine parts and to reduce maintenance costs for customers.
NVIDIA is not only an industry leader in enabling technology for HPC; the company employs simulation and high-performance computing in the design of its own products including 3-D glasses and PCBs. Consulting company EURO/CFD employs an HPC cluster, the largest among small- and medium-sized businesses in France, to solve complex problems for customers in a wide range of industries. This issue features these and many other case studies.
As customer examples demonstrate, ANSYS users today scale their largest simulations across thousands of processing cores, conducting simulations with more than a billion cells. They create incredibly dense meshes, model complex geometries, and consider complicated multiphysics phenomena. While the sophistication and scale of tomorrow’s simulations may dwarf today’s efforts — which is hard for any of us to fathom — one element will remain constant. ANSYS is committed to delivering HPC performance and capability to take customers to new heights of simulation fidelity, engineering insight and continuous innovation.