When in Rome: AMD Announces New Epyc CPU for HPC, Server and Cloud Wins

By John Russell

September 18, 2019

Where else but Rome could AMD hold the official Europe launch party for its second generation of Epyc microprocessors, codenamed Rome. Today, AMD did just that announcing key server wins, important cloud provider wins – including IBM Cloud – introduction of a new 64-core, 280-watt CPU aimed at high-end HPC, and indulging in some chest-thumping around performance metrics. And that’s not all. Yesterday, Dell EMC announced five new servers based on second-gen Epyc.

You get the picture. For AMD recently, it’s been (almost) all sunshine and haymaking. There’s also been a noticeable shift in positioning. When AMD plunged back into the datacenter market in 2017, contrition for past error and emphasis on competitive TCO (cum solid technology) were the main talking points. That’s changing as AMD seeks to add technology leadership to the message mix and cash in on its delivery of 7nm promises and product roadmap while Intel stumbles a bit.

In his media pre-briefing yesterday, Scott Aylor tackled technology achievement first. “One of the major themes in San Francisco” at the official launch of the Rome line roughly six weeks ago, “was [our] 80 World Records and counting,” he said. “We’re excited to say that number is going to be eclipsed. We don’t have the final count but know it will be north of 100.”

Last week at Tabor Communication’s conference, HPC &AI on Wall St., Aylor told HPCwire, “We think about pivoting from a TCO oriented play in the market to a leadership performance position that, by the way, has a fantastic TCO.” Rome, AMD hopes, is the platform to start accomplishing that goal.

Here’s a tech snapshot: The second-gen Epyc SoCs are built as nine-die packages with eight 7nm complex core die (CCD) chiplets — with up to eight cores each — surrounding a 14nm I/O die, connected via AMD’s second-gen Infinity fabric. AMD says the next-generation Infinity architecture gives customers access to the most I/O and memory bandwidth in its class, with 128 lanes of PCIe generation 4 (or more in custom builds). The upgraded fabric nearly doubles throughput, pushing 18GT/s socket-to-socket compared with 10.7 GT/s of throughput in the first generation chips.

It’s still good to remember AMD has a smaller waterfront to guard than larger rival Intel and that AMD’s market share remains in single digits although the company has aspirations for double digits in a year or so. In terms of technology, there wasn’t much new revealed at today’s Europe event that hadn’t been disclosed at the US launch. (For a deeper dive into second-gen Epyc’s technology, see HPCwire coverage, AMD Launches Epyc Rome, First 7nm CPU).

For the HPC community, release of the new sku – 7H12 – is perhaps most interesting news. It is nearly the same as the 7742 part but has 280W TDP (+55W); 2.6 GHz base (+350 MHz); 3.3 GHz boost (-100 MHz). The new sku is designed to leverage water cooled systems and is already used by Atos in the BullSequana XH 2000. Aylor noted it’s a “hugely dense platform with the ability to put eight processors essentially in 1U form factor.” The BullSequana XH2000 supports other microprocessors as well, including Intel and Arm (Marvell ThunderX2), and Nvidia GPUs for accelerators.

Atos BullSequana XH2000 supercomputer

Atos has lined up customers for Epyc-based versions of the BullSequana XH2000 – CSC, Finland (7-plus petaflops system), Uninett, Norway (6 petaflops), and GENCi, France (12 petaflops). Moreover, Atos today announced publishing the top results for two-socket nodes on four SPECrate benchmarks and set a new record for the HPL Linpack Benchmark.

Atos issued the following statement: “We’re extremely proud that our BullSequana has achieved these world-record results. Our unique Enhanced Direct Liquid Cooling system provided the most efficient environment for achieving such performance of the AMD EPYC processor,” said Agnès Boudot, SVP, head of HPC & Quantum at Atos. “Our BullSequana equipped with the latest AMD chip, provides our customers with the highest available performance for HPC and AI workloads, with an optimized TCO, to support them in going beyond the limits of traditional simulation.”

Supermicro will also offer systems based on the 7H12 (Ultra & GPU platforms) which are scheduled to be available in Q4 2019. The 7H12 will be broadly available to the market according to Aylor.

On the cloud front, AMD announced IBM Cloud would offer Epyc-based instances. “We have been in in close partnership with IBM Cloud for a long time,” said Aylor. In terms of matching second-gen Epyc to IBM needs, he said, “Think about things like very large container implementations, very high performance bare metal implementations, as well as virtualized environments.”

OVHcloud, a dominant player in Europe, also announced it would use second-gen Epyc. “[They will offer] the 7402P as part of their dedicated hosting environment, leveraging a full flash implementation with direct connect via NVMe to the 7402P which is a single socket solution. And again, looking at driving this in terms of virtualization, so containers really optimized on greatest level of density and thinking about computing economics,” said Aylor. Availability of these instances is expected by EOY 2019.

AMD’s first-gen Epyc has already enjoyed wide success among cloud providers, particularly in pushing 1-socket solutions. The hope is the second-gen devices will do as well. Google and Azure have announced plans to use second-gen Epyc. In his pre-briefing Aylor set high expectation for further adoptions, “You can also see some of the folks that have been on stage with us and can kind of assume where they’re headed. It’s also worth noting that we have a China event in the middle of October where I think there will be substantial news based upon some of the major players in China.”

The Dell EMC news – released yesterday and also discussed at today’s AMD event – had been expected. It included two single-socket and three dual-socket PowerEdge servers based on second-gen Epyc. HPCwire’s sister pub, EnterpriseAI reported yesterday: “With an eye on HPC going mainstream, Ravi Pendekanti (Dell EMC SVP, server infrastructure) said the high-end, two-socket model achieved 3,462 Gigaflops, representing a more than 200-percent performance upgrade based on the Linpack benchmark. Those performance benchmarks grew out of earlier development at Dell EMC’s recently formed HPC and AI Innovation Lab.” (For more see coverage, Dell’s AMD-Powered Server Line Targets High-End Jobs)

The last prominent win previewed by Aylor was Nokia’s decision to use second-gen Epyc processors. AMD reported Nokia will use Epyc to “accelerate its Cloud Packet Core system which helps service providers deliver converged broadband, IoT, and machine-type communication services for 5G.” According to AMD, during testing Nokia was able to get a 2X increase in packet throughput compared to previous systems.

Given the seemingly rapid market traction for second-gen Epyc, there have been reports of concern around meeting demand. AMD seemed to be addressing that by announcing a multi-generation partnership with its fab TSMC (Taiwan Semiconductor Manufacturing Co.) as well as announcing TSMC’s decision to use second-gen Epyc in its own datacenter.

In his pre-briefing Aylor said, “[The multi-generational partnership that we have around seven nanometer [is] a key catalyst for us having this leadership capability in terms of cache density, in terms of core density, and a very compelling level performance. You will hear from TSMC that they have a full commitment and full capability to ramp the volumes that are needed in the market. They believe in the technology so much that they will actually be deploying it in their datacenter. So, TSMC will also talk about how they are now deploying Epyc second generation Rome in their data center for virtualization environments for EDA deployments.”

Let the good time roll for now.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

U.S. CTO Michael Kratsios Adds DoD Research & Engineering Title

July 13, 2020

Michael Kratsios, the U.S. Chief Technology Officer, has been appointed acting Undersecretary of Defense for research and engineering. He replaces Mike Griffin, who along with his deputy Lis Porter, stepped down last wee Read more…

By John Russell

Supercomputer Research Reveals Star Cluster Born Outside Our Galaxy

July 11, 2020

The Milky Way is our galactic home, containing our solar system and continuing into a giant band of densely packed stars that stretches across clear night skies around the world – but, it turns out, not all of those st Read more…

By Oliver Peckham

Max Planck Society Begins Installation of Liquid-Cooled Supercomputer from Lenovo

July 9, 2020

Lenovo announced today that it is supplying a new high performance computer to the Max Planck Society, one of Germany's premier research organizations. Comprised of Intel Xeon processors and Nvidia A100 GPUs, and featuri Read more…

By Tiffany Trader

Xilinx Announces First Adaptive Computing Challenge

July 9, 2020

A new contest is challenging the computing world. Xilinx has announced the first Xilinx Adaptive Computing Challenge, a competition that will task developers and startups with finding creative workload acceleration solutions. Xilinx is running the Adaptive Computing Challenge in partnership with Hackster.io, a developing community... Read more…

By Staff report

Reviving Moore’s Law? LBNL Researchers See Promise in Heterostructure Oxides

July 9, 2020

The reality of Moore’s law’s decline is no longer doubted for good empirical reasons. That said, never say never. Recent work by Lawrence Berkeley National Laboratory researchers suggests heterostructure oxides may b Read more…

By John Russell

AWS Solution Channel

Best Practices for Running Computational Fluid Dynamics (CFD) Workloads on AWS

The scalable nature and variable demand of CFD workloads makes them well-suited for a cloud computing environment. Many of the AWS instance types, such as the compute family instance types, are designed to include support for this type of workload.  Read more…

Intel® HPC + AI Pavilion

Supercomputing the Pandemic: Scientific Community Tackles COVID-19 from Multiple Perspectives

Since their inception, supercomputers have taken on the biggest, most complex, and most data-intensive computing challenges—from confirming Einstein’s theories about gravitational waves to predicting the impacts of climate change. Read more…

President’s Council Targets AI, Quantum, STEM; Recommends Spending Growth

July 9, 2020

Last week the President Council of Advisors on Science and Technology (PCAST) met (webinar) to review policy recommendations around three sub-committee reports: 1) Industries of the Future (IotF), chaired be Dario Gil (d Read more…

By John Russell

Max Planck Society Begins Installation of Liquid-Cooled Supercomputer from Lenovo

July 9, 2020

Lenovo announced today that it is supplying a new high performance computer to the Max Planck Society, one of Germany's premier research organizations. Comprise Read more…

By Tiffany Trader

President’s Council Targets AI, Quantum, STEM; Recommends Spending Growth

July 9, 2020

Last week the President Council of Advisors on Science and Technology (PCAST) met (webinar) to review policy recommendations around three sub-committee reports: Read more…

By John Russell

Google Cloud Debuts 16-GPU Ampere A100 Instances

July 7, 2020

On the heels of the Nvidia’s Ampere A100 GPU launch in May, Google Cloud is announcing alpha availability of the A100 “Accelerator Optimized” VM A2 instance family on Google Compute Engine. The instances are powered by the HGX A100 16-GPU platform, which combines two HGX A100 8-GPU baseboards using... Read more…

By Tiffany Trader

Q&A: HLRS’s Bastian Koller Tackles HPC and Industry in Germany and Europe

July 6, 2020

In this exclusive interview for HPCwire – sadly not face to face – Steve Conway, senior advisor for Hyperion Research, talks with Dr.-Ing Bastian Koller about the state of HPC and its collaboration with Industry in Europe. Koller is a familiar figure in HPC. He is the managing director at High Performance Computing Center Stuttgart (HLRS) and also serves... Read more…

By Steve Conway, Hyperion

OpenPOWER Reboot – New Director, New Silicon Partners, Leveraging Linux Foundation Connections

July 2, 2020

Earlier this week the OpenPOWER Foundation announced the contribution of IBM’s A21 Power processor core design to the open source community. Roughly this time Read more…

By John Russell

Hyperion Forecast – Headwinds in 2020 Won’t Stifle Cloud HPC Adoption or Arm’s Rise

June 30, 2020

The semiannual taking of HPC’s pulse by Hyperion Research – late fall at SC and early summer at ISC – is a much-watched indicator of things come. This yea Read more…

By John Russell

Racism and HPC: a Special Podcast

June 29, 2020

Promoting greater diversity in HPC is a much-discussed goal and ostensibly a long-sought goal in HPC. Yet it seems clear HPC is far from achieving this goal. Re Read more…

Top500 Trends: Movement on Top, but Record Low Turnover

June 25, 2020

The 55th installment of the Top500 list saw strong activity in the leadership segment with four new systems in the top ten and a crowning achievement from the f Read more…

By Tiffany Trader

Supercomputer Modeling Tests How COVID-19 Spreads in Grocery Stores

April 8, 2020

In the COVID-19 era, many people are treating simple activities like getting gas or groceries with caution as they try to heed social distancing mandates and protect their own health. Still, significant uncertainty surrounds the relative risk of different activities, and conflicting information is prevalent. A team of Finnish researchers set out to address some of these uncertainties by... Read more…

By Oliver Peckham

[email protected] Turns Its Massive Crowdsourced Computer Network Against COVID-19

March 16, 2020

For gamers, fighting against a global crisis is usually pure fantasy – but now, it’s looking more like a reality. As supercomputers around the world spin up Read more…

By Oliver Peckham

[email protected] Rallies a Legion of Computers Against the Coronavirus

March 24, 2020

Last week, we highlighted [email protected], a massive, crowdsourced computer network that has turned its resources against the coronavirus pandemic sweeping the globe – but [email protected] isn’t the only game in town. The internet is buzzing with crowdsourced computing... Read more…

By Oliver Peckham

Supercomputer Simulations Reveal the Fate of the Neanderthals

May 25, 2020

For hundreds of thousands of years, neanderthals roamed the planet, eventually (almost 50,000 years ago) giving way to homo sapiens, which quickly became the do Read more…

By Oliver Peckham

DoE Expands on Role of COVID-19 Supercomputing Consortium

March 25, 2020

After announcing the launch of the COVID-19 High Performance Computing Consortium on Sunday, the Department of Energy yesterday provided more details on its sco Read more…

By John Russell

Neocortex Will Be First-of-Its-Kind 800,000-Core AI Supercomputer

June 9, 2020

Pittsburgh Supercomputing Center (PSC - a joint research organization of Carnegie Mellon University and the University of Pittsburgh) has won a $5 million award Read more…

By Tiffany Trader

Honeywell’s Big Bet on Trapped Ion Quantum Computing

April 7, 2020

Honeywell doesn’t spring to mind when thinking of quantum computing pioneers, but a decade ago the high-tech conglomerate better known for its control systems waded deliberately into the then calmer quantum computing (QC) waters. Fast forward to March when Honeywell announced plans to introduce an ion trap-based quantum computer whose ‘performance’ would... Read more…

By John Russell

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

By Doug Black

Leading Solution Providers


Nvidia’s Ampere A100 GPU: Up to 2.5X the HPC, 20X the AI

May 14, 2020

Nvidia's first Ampere-based graphics card, the A100 GPU, packs a whopping 54 billion transistors on 826mm2 of silicon, making it the world's largest seven-nanom Read more…

By Tiffany Trader

‘Billion Molecules Against COVID-19’ Challenge to Launch with Massive Supercomputing Support

April 22, 2020

Around the world, supercomputing centers have spun up and opened their doors for COVID-19 research in what may be the most unified supercomputing effort in hist Read more…

By Oliver Peckham

Australian Researchers Break All-Time Internet Speed Record

May 26, 2020

If you’ve been stuck at home for the last few months, you’ve probably become more attuned to the quality (or lack thereof) of your internet connection. Even Read more…

By Oliver Peckham

15 Slides on Programming Aurora and Exascale Systems

May 7, 2020

Sometime in 2021, Aurora, the first planned U.S. exascale system, is scheduled to be fired up at Argonne National Laboratory. Cray (now HPE) and Intel are the k Read more…

By John Russell

Summit Supercomputer is Already Making its Mark on Science

September 20, 2018

Summit, now the fastest supercomputer in the world, is quickly making its mark in science – five of the six finalists just announced for the prestigious 2018 Read more…

By John Russell

TACC Supercomputers Run Simulations Illuminating COVID-19, DNA Replication

March 19, 2020

As supercomputers around the world spin up to combat the coronavirus, the Texas Advanced Computing Center (TACC) is announcing results that may help to illumina Read more…

By Staff report

$100B Plan Submitted for Massive Remake and Expansion of NSF

May 27, 2020

Legislation to reshape, expand - and rename - the National Science Foundation has been submitted in both the U.S. House and Senate. The proposal, which seems to Read more…

By John Russell

John Martinis Reportedly Leaves Google Quantum Effort

April 21, 2020

John Martinis, who led Google’s quantum computing effort since establishing its quantum hardware group in 2014, has left Google after being moved into an advi Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This