Latest Atrio News
Aug 30, 2021
By Max Alt, Distinguished Technologist and Director, Hybrid HPC Hewlett Packard Enterprise August 30, 2021 Sponsored Content by HPE High-performance computing (HPC) productivity is directly linked to manufacturing competitiveness today because products are designed using computer aided engineering (CAE) tools that depend on HPC. When HPC is easy to manage and use – instead of complex and time-consuming – teams can spend more time on valuable design tasks (instead of tuning workloads). The cost of managing HPC is also reduced. And when HPC performance is faster, teams can create more design iterations, and run more-detailed simulations, in less time. So, they can create products that are safer, and reach the market sooner – or in other words, more competitive. This is one reason manufacturers want powerful HPC solutions they can consume as a utility-like service – and why HPE has created HPE GreenLake for HPC solutions, featuring the leading-edge performance of AMD EPYC processors.  But it’s not the only reason. Businesses are re-evaluating their compute needs, because data volumes keep getting bigger and converged workloads keep getting more complex. So, we all want compute delivered as a service, to take away the hassle of IT management, scaling infrastructure, technology refreshes, and financial hurdles. This change is happening in lots of industries, including energy, life sciences, and financial services. HPE GreenLake for HPC solutions provide that as-a-service experience. The HPC infrastructure is fully managed by HPE. Billing is monthly and based on HPC consumption, so there are no up-front payments. And you always have an on-site capacity buffer, so you can scale up when demand spikes or a new project starts. (You can also scale down flexibly.) How does this approach increase competitive advantage? Let’s look at some of the manufacturing challenges it helps to solve. HPC challenges faced by manufacturers Manufacturers can aim to differentiate in a number of ways: competing on product quality, innovation, or cost-efficiency. But today, companies cannot lead in any of these areas without effective use of CAE. CAE includes a broad range of disciplines, such as: Structural analysis – This includes stress analysis on components and assemblies, which is important in improving safety and quality Fluid analysis – Engineers can use computational fluid dynamics (CFD) to simulate thermal and fluid flows, for example to test aerodynamics Multibody dynamics (MBDs) – Analysis of kinematics (the motion of systems of objects) and calculation of loads Noise, vibration, and harshness (NVH) – simulation and optimization of these effects, for example in cars Multiphysics analysis – A combination of analytic techniques for simulating dynamic, real-world performance of products The tools that enable these disciplines demand powerful HPC resources. Some of the most widely-used CAE tools in manufacturing are ANSYS® Fluent (for fluid analysis), Altair RADIOSS ™ (structural dynamics), OpenFOAM (open source CFD software), and Ansys® LS-DYNA® (finite element analysis/FEA). To achieve leading performance and productivity, teams need to be able to: Access modern HPC technologies that provide a performance edge – Faster HPC maximizes the size, detail level, and speed of simulations. Teams can also work with larger datasets. However, traditional budget cycles allow manufacturers to refresh HPC technologies only once every few years. Reduce management burden, so teams can focus on design work – HPC can be complex and costly to configure and manage. Reducing these burdens can help manufacturers work more productively and efficiently. Scale flexibly to support new projects and business growth – With traditional finance models, HPC can only scale up or out. And acquiring new equipment can be costly and slow. Teams need agility to scale quickly and flexibly when needs change, to maximize ROI. The as-a-service solutions HPE’s solutions deliver cutting-edge performance as a service to solve these problems. Modern HPC technologies are more accessible with HPE GreenLake. You can choose from the entire HPE server and storage portfolio, including standard and custom solutions, and servers powered by the latest 3rd-Gen AMD EPYC processors . With HPE GreenLake there are no up-front payments. Costs are aligned to HPC consumption. Your HPC infrastructure is managed for your by HPE, so teams can finally focus on what they do best. IT is still located where you need it – in your data center or almost any other location. We also help you get the most from HPC workloads by helping you to use containers and other modern approaches. You have the flexibility to scale up or down whenever you need to. HPE helps you monitor your capacity usage, and provides an on-site hardware buffer that can be switched on – or off – whenever your needs change. You only pay for resources you use, so having an on-site buffer is a great way to scale with agility. The difference with 3rd-Gen AMD EPYCTM processors But how about competing on pure performance terms? AMD EPYC™ processors deliver industry-leading performance and scalability for CAE workloads. HPE and AMD have a long-standing partnership focused on delivering the next era of computing for HPC. AMD Infinity Architecture is tightly integrated with HPE server architecture, for advanced performance. The power of 3rd-Gen AMD EPYC technologies provides: High-frequency processors enabling significant per-core performance Highest core counts and large memory capacity, fast memory bandwidth and high ratios of cache per core Balanced performance and efficiency, allowing organizations to accelerate and optimize workflows such as CFD , EDA, and others Performance to handle large scientific and engineering datasets that’s ideal for compute-intensive models and analysis techniques AMD EPYC processors power some of the world’s fastest, most scalable data centers and supercomputers. Together, HPE and AMD can deliver high-performance clusters to power manufacturing workloads of any size, while taking advantage of the technologies afforded by the exascale era. And today, HPE and AMD are defining and delivering the next era of computing for HPC with tuned and optimized HPC solutions – when, where, and how you need it. You can also email your questions and comments to email@example.com . Would you like to apply for our HPE Insiders for HPC client-only community ? It is a dedicated invitation-only space to keep you informed, give you your seat at the table, and have some fun along the way with your peers. Max Alt Hewlett Packard Enterprise Max Alt leads cloud-oriented HPCaaS initiatives including the GreenLake Cloud Services for HPC offering. Prior to joining HPE, Max was SVP AI & HPC Technology at Core Scientific that acquired Atrio in 2020 where Max was the CEO & Founder. Atrio created a leading-edge hybrid cloud platform for HPC orchestration, cluster and container management. Max has a unique background with almost 30 years of experience in software performance technologies and high performance computing. He is both an entrepreneur and a large-scale enterprise leader. Max founded several tech start-ups in the Bay area and he spent 18 years at Intel in various engineering and leadership roles including developing next generation super-computing technologies. Max’s strongest expertise are in computer and server architectures, cloud technologies, operating systems, compilers and software engineering. Max received his BS in Math and Computer Science at Tel Aviv University and his Master’s degree in Software Engineering from Carnegie Mellon University.