Arm-based Marvell ThunderX2 - the new kid on the HPC block

HPC


As we all know, being the new kid on the block means it sometimes take a little while to make friends and break into those well established networks and friendship circles. It can also be pretty daunting, especially if those friendship circles are deep rooted. Who needs the new guy?

Well this is exactly the challenge that faced the Arm-based Marvell ThunderX2 (TX2) technology. An exciting, new processor trying to enter into an established, well-trodden marketplace with what seems like little or no room left for any challengers.

In its favour however is that it is a really interesting, innovative product that has the genuine potential to be better than the rest, and a product that can go a long way to helping eliminate many of the legacy issues bogging down the more established rivals. The ThunderX2 could be the lightening bolt (pun intended…) that really lights up the HPC processer market.

Key to early adoption is to get users sampling this technology and seeing for real how it stacks up against their existing, more traditional hardware. So how do we entice organisations to see the benefits of this new processor and get them to think outside of the box – beyond their traditional purchasing choices and without the hassle that normally comes with doing something ‘away from the norm’?

Normally organisations need to go through lengthy proof-of-concept processes to procure the necessary Arm server hardware, spend time installing and configuring this alongside their existing systems and infrastructure, and then even more time deploying and optimising their applications. This has been the way organisations have tried and tested not only new versions of their existing hardware but even new applications that come into the marketplace.

Let's be honest - it’s this kind of process that makes trying ‘new stuff’ a pain in the neck, and maybe that’s another reason why we normally stick with the more established users in the market. Not many of us embrace change.

So what if you had a way of jumping onto an Arm TX2 cluster, optimised with the latest networking such as Infiniband, shared storage (block or file), pre-loaded compilers and applications with which you’re familiar with and best of all hands-on support from a group of HPC experts who can help you configure, optimise and understand how to get the most out of your current applications when running on Arm TX2 servers?

This is exactly what Verne Global provide through our hpcDIRECT platform built specifically for intensive HPC applications in the cloud. Unlike offerings from hyperscalers and other organisations which grant you access to a single virtualised Arm node, with hpcDIRECT you can gain access to an optimised bare-metal Arm TX2 cluster configured to our unique TrueHPC standards.

The trial nodes specifications are not your typical one core VM’s that others offer. These are powerful, bare-metal nodes - 256 GB RAM, CPU @ 2.2Ghz, 56 Cores, 240TB of local SSD storage, interconnected with both Ethernet and Infiniband as well as access to 10TB of shared, dynamic storage.

hpcDIRECT doesn’t stop there. Whether your requirement is on-demand or reserved, hpcDIRECT has a standard and optimised SKU to help organisations decide the exact type of Arm TX2 servers suitable for their compute after the trial or even to use straight away. Standard SKU’s are designed for general purpose compute whereas optimised SKUs are carefully selected Arm TX2 servers which lean more towards a specialised market or field, for example, more memory, higher networking capabilities, etc.

Even though the trial nodes have access to a shared 10TB of dynamic storage, the option of a dedicated storage solution for an Arm cluster is also available. This means you don’t have to worry about those unstable or noisy neighbours, but instead can rest assured the storage solution is secure with only one tenant, you. So now you’re not only in the friendship circle, but you’re calling the shots!

Try something new today – click here and test drive the Arm-based Marvell ThunderX2 and experience HPC applications at lightening speed.


Written by Adam Nethersole

See Adam Nethersole's blog

Adam is Senior Director of Marketing at Verne Global and has worked within the areas of sustainability tech and renewable energy for the last 20 years. You can follow him at: @AdamNethersole

Related blogs

Qubits North America - Rumours from the Trade Show Floor

It's lunchtime here in the beautiful city of Amsterdam where I am enjoying my time at the excellent World Summit AI, at which Verne Global are exhibiting, and earlier today our CTO Tate Cantrell moderated an engaging panel on today's hottest AI disruptors. As I take a breather from the networking, I thought I would write some thoughts about another excellent event which I went to a couple of weeks ago - Qubits North America.

Read more


CERN - When science can't use the cloud

Demand for high performance computing (HPC) is growing fast - and you might expect it to become kind of generic. But leading research sites like CERN still make extreme demands.

Read more


DevOps. Stacking up to be a Common Theme at ISC18

Yesterday was a good day to be in Frankfurt. All of the majors in the supercomputing universe descended upon the Messe Frankfurt to begin ISC18 with a series of training seminars. For my morning session, I chose Getting Started with Containers on HPC through Singularity put on by the team at Sylabs, Inc. I have been tracking the progress on Singularity in the HPC community since before Sylabs was founded by CEO Greg Kurtzer in an effort to bring the technology of root secure containers into the realm of enterprise supported software. I was excited to hear about the progress that Sylabs has made and to see where the future of containers lies for the broader HPC community. If I was forced to sum the tutorial into a single portmanteau, it would be DevOps. After this session, it is clear to me that the world of DevOps that has been created in the cloud native universe is on a collision course with HPC. And the future of science says that it can’t happen soon enough.

Read more

We use cookies to ensure we give you the best experience on our website, to analyse our website traffic, and to understand where our visitors are coming from. By browsing our website, you consent to our use of cookies and other tracking technologies. Read our Privacy Policy for more information.