A Giant Leap Forward for Digital Manufacturing

New AMD EPYC technology speeds CAE workloads up to 56%.
Topics in this article

Digital manufacturing workloads, such as computer-aided engineering (CAE), can require serious compute power. Dell Validated Designs for HPC Digital Manufacturing, powered by AMD EPYC™ processors, are already designed to deliver fast performance and easy scaling with modular building blocks. Now, new technologies from AMD promise to accelerate these compute-hungry workloads.

AMD recently announced the release of AMD EPYC 7003 Series Processors with AMD 3D V‑Cache™ technology. Built on the AMD 3D Chiplet architecture, these new processors are designed to deliver significant benefits for demanding digital manufacturing CAE workloads such as computational fluid dynamics (CFD), finite element analysis (FEA) and more.

New technology with a significant performance impact

By employing stacking based on a copper-to-copper hybrid bonding “bumpless” chip-on-wafer process, AMD is able to deliver interconnect densities over 200X compared to 2D interconnects, and over 15X compared to other stacking technologies using solder bumps. This helps lower latency, boost bandwidth and enhance power and thermal efficiencies. As a result, Dell Validated Designs for HPC Digital Manufacturing based on PowerEdge servers with AMD EPYC 7003 Processors with AMD 3D V‑Cache technology can accelerate CAE workloads, by as much as 56%¹, while helping reduce energy consumption.

The impact of this increased compute power is significant. For example, AMD benchmark testing found that servers using AMD EPYC 7003 Series Processors with AMD 3D V-Cache can solve up to ~59% more CFD problems per day² and complete up to ~56% more FEA explicit solver jobs per day than standard 3rd Gen EPYC processor based servers.

For digital manufacturing, where server density is incredibly important, the combination of Dell PowerEdge R6515 and R6525 servers and AMD EPYC processors is ideal for boosting the performance per rack for some digital manufacturing applications. Dell Validated Designs based on these combinations provide a balanced ecosystem that helps businesses achieve faster and more competitive results.

Real-world digital manufacturing results

Dell Validated Designs for HPC Digital Manufacturing are already making an impact. For example, UK-based Wirth Research is dedicated to the belief that life can be more enjoyable and more sustainable, designing technologies that are very energy efficient. The company worked with Verne Global and Dell Technologies to find solutions that could reduce the energy demands of their HPC workloads by up to 70%, using Dell PowerEdge servers based on AMD EPYC processors.

To further advance sustainability, Wirth Research moved their new HPC environment to a Verne Global data center, which is powered by 100% renewable energy. Verne Global provides robust server and storage infrastructure to support the HPC needs of some of the world’s most innovative industries and, like Wirth Research, holds sustainability at the heart of its value proposition.

A technology partnership that pushes boundaries

Dell Technologies collaborates with AMD to push workload boundaries with tailored IT and business solutions that enable better business outcomes. We’re excited about our expanding partnership with AMD and are pleased to announce support for 3rd Gen AMD EPYC processors with AMD 3D V‑Cache technology across our Dell PowerEdge server rack portfolio.

Learn more about Dell Validated Designs for HPC Digital Manufacturing.

¹ MLNX-015: Altair® Radioss® 2021.2 comparison based on AMD internal testing as of 02/14/2022 measuring the time to run the dropsander, neon, and t10m test case simulations. Configurations: 2x 64C AMD EPYC 7773X with AMD 3D V-Cache™ versus 2x 64C AMD EPYC 7763 on the same AMD “Daytona” reference platform. neon is the max result. Results may vary based on factors including silicon version, hardware and software configuration and driver versions.

² MLNX-002C: ANSYS® CFX® 2022.1 comparison based on AMD internal ¹testing as of 2/14/2022 measuring the time to run the cfx_10, cfx_50, cfx_100, cfx_lmans, and cfx_pump test case simulations. CFX_10 is the max result. Configurations: 2x 64C AMD EPYC™ 7773X with AMD 3D V-Cache™ versus 2x 64C AMD EPYC 7763 on the same AMD “Daytona” reference platform. Results may vary based on factors including silicon version, hardware and software configuration and driver versions.

About the Author: Janet Morss

Janet Morss previously worked at Dell Technologies, specializing in  machine learning (ML) and high performance computing (HPC) product marketing.
Topics in this article