For companies focused on manufacturing areas that require heavy engineering simulation, unlimited computing power, or managing data-intensive applications and workflows, the challenges will multiply. up quickly. They needed a simulation platform that effectively addressed these challenges, providing an avenue for accessing HPC in the cloud to stimulate innovation.
In the last few years, the cloud has evolved to be more responsive to engineering workloads thanks to the increasing computing power available through faster and cheaper hardware and the maturation of manufacturing software solutions. Early adopters implemented a cloud-first strategy on the enterprise side of the business, leaving HPC behind. Today, the benefits of the cloud enjoyed by the enterprise are finally available to production applications.
For HPC in the cloud to work well, there are a number of challenges that stand in the way.
The acquisition costs associated with owning and operating an HPC system in place are often too burdensome for companies, costing millions of dollars. Navigating through a complex process, companies can wait six months or more before selecting a system, which must be shipped and installed. All previous systems and application software must be migrated to the new system. Setting up and running the simulation requires moving the latest release to the new system (usually three times a year), which takes several days for each version.
Consider the total cost of ownership (TCO). Costs include hardware and software running on it, hardware storage space, energy usage, staffing, and more. TCO calculations must also take into account organizational, operational, and logistical costs, which require ongoing effort and investment to keep a system up and running.
Another challenge — a company buys an HPC system today, only to find out tomorrow, it’s old. Running expensive simulation software on an outdated system can take longer, further increasing TCO.
Enter UberCloud: HPC seamlessly integrates into the cloud
UberCloud’s automated, self-service, multi-cloud engineering simulation platform and standard simulation workflow containers enable manufacturing businesses to seamlessly integrate HPC into a “priority cloud” or hybrid cloud strategy. Adopting the latest apps — and resource agnostic IT technologies like containers and Kubernetes — UberCloud enables performance without compromise. Engineers can run their complex simulation workflows from anywhere, including their home office, quickly and with familiarity, always using the latest technology.
Widely applicable to many complex jobs including multiphysics simulation, construction, AI/machine learning, digital twin, data analysis, autonomous driving and edge computing, platform UberCloud and its application containers provide the computing power, flexibility, and agility demanded by the most data-intensive and computing applications in many industries. Because of its ability to make accessing and using HPC transparent, the UberCloud platform accelerates the recent trend of “democratizing HPC” — it enables more engineers to adopt HPC to solve challenging problems. .
UberCloud and Rimac . Technology
Running computer simulations in the cloud accelerates high-quality, innovative development, optimizes agility, and accelerates time to market.
For Rimac Technologies, accelerating their research and development process to design and deliver the latest powertrain, battery and electric vehicle technology will make them more competitive, more innovative and more cost-effective. The first step requires an assessment of the legacy on-premises HPC Cluster and the ability to move engineering simulation workloads to the cloud. UberCloud and the Microsoft Azure project team worked with Rimac experts to design and configure their Azure cloud environment to run a variety of computer-aided engineering (CAE) software calculations to evaluate applications. applications, analyze TCO for the cloud versus on-premises, and gain insight into the engineering simulation usage of cloud HPC resources and related workflows.
The UberCloud engineering simulation platform and container technology, running in Microsoft Azure and using 3rd Gen AMD EPYC™ processors, integrates easily with existing IT, allowing engineers to run full simulations challenge, test larger batches of prototypes faster than ever, and do so safely, driving innovation. Rimac engineers now have on-demand access to additional and more powerful compute resources in the cloud without having to leave their workstations on demand. They achieve agility through shorter product design cycles, a direct result of shorter simulation times. They achieve a superior level of quality by simulating more complex geometries and physics, and by simply running more iterations. Because it’s the cloud, Rimac only pays for what it uses, further enabling rapid innovation.
UberCloud has created a flexible global HPC architecture that can handle a wide variety of workloads, can be easily scaled to other sites, and offers maximum flexibility and cost-effectiveness. using on-demand, pre-order, and spot versions. Knowing that one of Rimac’s key technologies was a high-performance battery pack, the UberCloud team helped Rimac engineers optimize the design with numerical simulations that analyze mechanical integrity, thermal behavior, and analysis. current distribution. Finally, HPC on Azure with UberCloud has allowed Rimac to dramatically improve their overall design workflow and increase simulation throughput.
Rimac engineering processes have been analyzed to provide the best cloud environment for engineering processes, reducing IT management costs. Engineers can utilize simulation applications and a wide range of on-demand resources, allowing for faster results and turnaround times, while providing total control and management to the team. With Azure, engineering simulations get a scalable infrastructure, while data is stored in Azure’s secure data centers eliminating any delays in data transmission.
What’s Next: UberCloud and the Manufacturing Industry
UberCloud and Microsoft’s work with Rimac and other partners can be applied to any production design scenario. From machine learning to experimental design, parametric spatial evaluation, optimization algorithms, and more, UberCloud’s technology is horizontal — it’s all about engineering, scientific simulation, and data processing. Together, these resources enable organizations to move from running 10 to 50 simulations per hour on-premises to running thousands of simulations per hour in the cloud.
UberCloud’s engineering simulation platform for producing CAE applications, running in Microsoft Azure with the latest 3rd Gen AMD EPYC processors, is key to achieving a competitive advantage. You can bring better, more innovative products to market faster, shorten product development times, increase the productivity and agility of engineers, and reduce equipment costs. design and development.
Learn more about how UberCloud can enable your organization to leverage the multitude of cloud resources available to production.
This content is produced by UberCloud, Microsoft Azure, and AMD. It was not written by the editorial board of the MIT Technology Review.
