October 25, 2010
Swift Engineering, Inc., a California-based designer and manufacturer of open-wheel race cars, developed key motorsports partnerships with industry-leading companies to further its bid to design and build the next generation of race car chassis for the 2010 IZOD IndyCar Series®.
In taking on this challenge, Swift Engineering looked at how the aerodynamics of a car, and the wake it creates, can be designed to enhance Indy car racing. To find the answer, Swift engineers began simulating everything: the motion of a race car on a track, the effect of the dampers on the suspension, the deformation of the tires, the behavior of the driver, the aerodynamic flow over the vehicle, and the overall structural loads.
To reach its objectives, Swift Engineering cemented a key alliance with Cray Inc. (The Supercomputer Company) to set new standards in innovative design, manufacturing and support. Swift Engineering is paving the way as the first Cray CX1000™ customer. In addition to the Cray CX1000 supercomputer, Swift is using a Cray CX1™ system to further enhance its capabilities in Computational Fluid Dynamics (CFD), a critical tool in the development of aerodynamic products.
“Cray’s CX1000 and CX1 systems will play a pivotal role in Swift’s continuing commitment to motorsport and will help Swift again re-set new industry standards in innovative design and manufacturing,” said Jan Wesley Refsdal, president of Swift Engineering. “The decision to use Cray supercomputers was the result of a focused effort to find the right resources to meet our significant and demanding design challenges. In the competitive world of motorsports, second place is the first loser and Cray’s system solution gives Swift an unfair advantage.”
Cray systems meet the variety of needs Swift faces during the conception, design and production lifecycle. The flexibility of configurations delivers the right kind of horsepower for both real world analysis and in situ modeling.
“Swift uses both physical wind tunnels and virtual modeling with CFD. Each of these methods has its advantages, depending on what you’re trying to do,” Mark Page, Swift’s chief scientist said. “We’ve been running CFD on a small cluster since 1997. We upgraded to a true HPC system earlier this year and increased our capability 10 to 100 times, depending on the problem. We aren’t just doing the same things faster; we’re doing way more things we haven’t had the ability to do before.”
These radical capability improvements apply more than just motorsports. Swift Engineering also does a substantial amount of work in unmanned aircraft for surveillance and emergency operations.
HPC Beyond Motorsports
Swift Engineering's Eclipse concept jet was conceived and developed, from paper designs to flight tests, in 200 days, setting a new benchmark for product development in the industry. These technologies require the fastest, most powerful computational cores to meet the design goals of good endurance and reliable system operation.
With the Cray CX1000 and CX1 systems, Swift Engineering receives the latest in HPC technology in a tightly integrated compute cluster. Both systems incorporate powerful Intel®Xeon® processors communicating over a very fast interconnect (QDR InfiniBand), allowing users to solve very large problems in small amounts of time. This level of performance is the new standard for HPC performance not only in motorsports or aviation, but any intensive CAE projects.
The New Economics of HPC
The current economic situation has reduced the amount of specialized in-house engineering projects within large companies. As a result, smaller companies like Swift Engineering face more and more opportunities for collaboration with these larger firms. With these opportunities comes increased need to provide next-generation, innovative solutions faster and better.
In more than just racing, speed-to-market is critical in any business. For any CAE team, speed and accuracy are crucial to project success. With the power of affordable, scalable HPC resources, engineers and designers working in SMBs have an opportunity to perform the testing and analysis that was out of reach just a few years ago.
By taking the first step in adopting the Cray CX1000 system for its small business enterprise, Swift Engineering is paving the way for other CAE firms looking for affordable, deployable and dependable HPC solutions to meet growing demands. Cray systems are now available in a full range of configurations. As a small business, Swift Engineering is proud to have Cray systems onboard. With no dedicated IT staff, Swift is able to deploy and manage the system without outside support and enjoy the time-to-market and financial benefits of using a Cray and HPC over wind-tunnel testing.
Flexibility for Scalable HPC
Swift Engineering was attracted to Cray for a variety of reasons with a top consideration being the flexibility of the Cray CX1000 system in delivering hybrid capabilities through a choice of chassis. While hybrid architectures often compromise individual capabilities in the quest for multi-purpose flexibility, the Cray CX1000 machine offers choice rather than restriction. Each of the Cray CX1000 technologies is best-of-class and can be mixed and matched in a single rack, creating a customized hybrid computing platform to meet a variety of scientific workloads.
At a time when design companies need faster design-cycle time and the addition of quality and regulatory requirements creates a highly competitive marketplace, organizations that rely on CAE are looking for ways to add capacity without adding complexity and support requirements to their computing environment. Swift Engineering found that the Cray CX1000 system offered the competitive advantage they need.
“If Swift were building computers, we would be building a Cray,” said Refsdal. “And Cray for me has been synonymous with high quality, high performance state-of-the-art technology for as long as I can remember... We are thrilled to be owners of Cray supercomputers.”
To find out more about how Cray helps Swift Engineering design and engineer tomorrow's race cars, view the interactive case study here (registration required).
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?