HPC & AI workloads lead to Rome


Last week I travelled to the Italian capital, Rome, for an event which I believe will prove very significant for the international high performance computing (HPC) industry. After many years away from the HPC arena and the overall server market, AMD is back with a bang and a new range of powerful processors through its AMD EPYC series.

The company started its comeback with the AMD EPYC 7601 range - codenamed “Naples” in 2017 and on Wednesday I witnessed the European launch of their next edition - the AMD EPYC 7002 processors which, as you’ve now probably realised, are codenamed “Rome”.

AMD’s decision to re-enter the HPC market has prompted people to be sceptical of their mission and whether they can pull it off. They knew they had to do something radical on returning to the market, and deliver on any performances promises they made.

And, they’ve done precisely all of that in a fantastic example of industry disruption. Their AMD EPYC series has produced a whole collection of new processing world records and has advanced users expectations on performance and speed. Rome was an exciting place to be last week - it certainly felt like we were witnessing the launch of something revolutionary.

So let’s delve a little deeper and look under the hood. AMD’s EPYC 7002 range of processors are the world's first 7nm CPU featuring up to 64 “Zen 2” cores per SOC and delivering up to 23% more instructions per clock (IPC) per core enabling a typical server with EPYC 7002 Series architecture to deliver up to four times more L3 cache compared to the previous generation. All in all, AMD are re-shaping what we can expect from our processors.

Now, I firmly believe this is a terrific development for not only AMD, but for the entire industry and for the other server and processor vendors who I am pleased to also work closely with. Competition creates energy, forward momentum and technological innovation and I know other processor vendors are rolling-up their sleeves and embracing the ‘EPYC’ challenge (sorry - pun intended...) of meeting AMD head-on. It will be really interesting to see how this increased competition shapes the industry and how processor and server architecture evolves over the next 5 years.

Moving from a warm and sunny Rome to the cooler regimes of Iceland, here at Verne Global we are delighted to now include AMD’s EPYC 7002 processors as part of our HPC Cloud platform - hpcDIRECT. Organisations deploying HPC and AI applications can reserve instances enabling them to enjoy AMD’s super processing performance coupled with Verne Global’s industry-leading infrastructure, TrueHPC methodology and expert HPC support.

As a sample from the hpcDIRECT range, gpc.x01.amd with the 7742 CPU, 225-240 watt TDP, provides 3.48 teraflops of peak double-precision performance running at max boost frequency of 3.4 GHz — almost 7 teraflops in a dual-socket server. At its base frequency of 2.25 GHz, the gpc.x01.amd tops out at a theoretical 2.3 double-precision teraflops.

And, because organisations use clusters in different ways and one-size doesn’t fit all, hpcDIRECT offers both standard and optimised server configurations to help organisations decide the exact type of compute they need. Standard compute nodes are designed for more general-purpose computing whereas some servers have been carefully optimised and lean more towards a specialised market or field, for example, more memory, higher networking capabilities, etc.

If you’re interested in sampling hpcDIRECT with AMD EPYC 7002 Series processors please do not hesitate to get in touch via our website and we’ll be pleased to run you through your options. As they say, when in Rome...

Written by Spencer Lamb

See Spencer Lamb's blog

Spencer is Verne Global's Director of Research and head's up our high performance computing work with European research and scientific organisations. He is also a member of the European Technology Platform for High Performance Computing (ETP4HPC).

Related blogs

Thinking Beyond the Clouds with HPC and AI as a Service

I recently had the pleasure of presenting to a team from Dell Technologies talking about high performance computing (HPC) and artificial intelligence (AI) workloads within enterprise organizations. The scale and complexity of HPC is growing tremendously. Even with a predicted slowdown for 2020, analyst firm Intersect 360 is still anticipating the market to grow to $55B by 2024.

Read more

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

HPC and AI collusion – Rumours from the trade show floor

Recently I’ve garnered much of my blog inspiration from industry events. February has been no exception and I benefited from a fascinating day earlier in the month at the HPC and Big Data conference in London, just a stone’s throw from the Houses of Parliament. Here are some of my observations from my discussions there...

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.