AMD Charges Back into the Datacenter and HPC Workflows with EPYC Processor

By John Russell

June 20, 2017

AMD is charging back into the enterprise datacenter and select HPC workflows with its new EPYC 7000 processor line, code-named Naples, announced today at a “global” launch event in Austin TX. In many ways it was a full frontal assault on Intel’s dominance in the x86 datacenter landscape. Claiming performance and cost advantagaes and supported by statements from key OEMs, ODMs, and hyperscalers – HPE, Dell, and Microsoft Azure for example – AMD is hoping to convince HPC and datacenter customers it is back for the long haul.

Aware there may be market reluctance after its absence from the datacenter, Scott Aylor, AMD corporate VP and GM of enterprise solutions business, said “It’s not enough to come back with one product, you’ve got to come back with a product cadence that moves as the market moves. So not only are we coming back with EPYC, we’re also [discussing follow-on products] so when customers move with us today on EPYC they know they have a safe home and a migration path with Rome.” AMD has committed to socket compatibility between EPYC 7000 line and Rome, code name of the next scheduled generation AMD processor aimed at the datacenter.

AMD showcased some gaudy performance and price-performance benchmarks comparing EPYC to Broadwell line. In a pre-launch briefing with HPCwire, Aylor said, “These numbers are very big, so they show very measurable separation from what is available with Broadwell. Part of that is quite frankly because we didn’t design EPYC to compete with Broadwell. We designed it to compete with what’s coming. When [Intel’s] Skylake comes later this summer, we think these comparisons will still be very strong against the platinum, gold silver and bronze of Skylake.”

Based on the Zen core, EPYC is a line of system on a chip (SoC) devices designed with enhanced memory bandwidth and fast interconnect in mind. AMD also introduced a one-socket device, optimized for many workloads, which AMD says will invigorate a viable one-socket server market. With EPYC, “we can build a no compromise one-socket offering that will allow us to cover up to 50 percent of the two-socket market that is today held by the [Intel Broadwell] E5-2650 and below,” said Aylor.

AMD clearly has big ambitions. Earlier this spring it introduced Ryzen7 processor line, also based on the Zen core, and targeting high performance gaming. EPYC is aimed squarely at the datacenter. Aylor briefed HPCwire on EPYC before the launch and some of the technical details were still not available. It is an SoC product stack with a range of offerings roughly mimicking the Broadwell product stack. EPYC has up to 32 cores and 8 DDR4 channels per CPU allowing it to address 2TB of memory. The I/O is 128 PCIe lanes.

“The SoC approach we have taken allows all of the IO that has historically lived on an external bridge or IO hub to be fully integrated that into the device,” said Aylor. One result is low latency high performance connections. The PCIe lanes are configurable, “so you can use them to connect to SATA links, directly connect to NVMe links. It also facilitates a strong connection to high performance GPUs.” AMD plans to show an EPYC plus Radeon Instinct GPU machine learning platform at its conference this week.”

AMD presented both SPECint (integer) and SPECfp (floating point) performance comparisons with the Broadwell as well as price point comparisons (how much performance the same number of dollars will be of each processor) some of which are shown below.

“We’re tiering products in 32, 24, and 16-core ranges,” said Aylor. The idea, of course, is satisfy widely varying needs. The top end aimed at scale out and HPC workloads, he said. The bottom tier allows users to closely manage per core licensing costs. “We have tried to cover the vast majority of the market that exists today in the Broadwell family,” says Aylor. Every product will have a dedicated security processor.

“Sometime people will say benchmarks are interesting but how do you do in the real world. Well we will showcase a fluid dynamics HPC workload, Apache/Spark, and software defined storage reference architecture [at the launch]. We will also have an open stack cloud based implementation,” said Aylor. AMD was expecting on the order 600 attendees for the EPYC launch.

Moving back into the datacenter is a huge bet by AMD that’s required a very substantial investment in the Zen core and EPYC. Seeking to buttress the gamble, AMD has seemingly got buy-in from several market makers and many ecosystem partners. Here are four endorsements included in the official release; while the statements are on the over enthusiastic side they nonetheless suggest AMD has done productive groundwork with partners:

  • HPE. “The EPYC processor represents a paradigm shift in computing and will usher in a new era for the IT ecosystem,” said Antonio Neri, EVP and general manager Enterprise Group, HPE. “Starting with the Cloudline CL3150 and expanding into other product lines later this year, the arrival of EPYC in HPE systems will be welcomed by customers who are eager to deploy the performance and innovation EPYC delivers.”
  • Dell EMC. “As an industry leader, we are committed to driving IT Transformation for our customers,” said Ashley Gorakhpurwalla, president, server solutions division at Dell EMC, “Our next generation of PowerEdge servers are the bedrock of the modern datacenter that are designed to maximize business scalability and intelligent automation with integrated security. The combination of PowerEdge and the AMD EPYC performance and security capabilities will create unique compute solutions for our customers to accelerate workloads and protect their business.”
  • Baidu. “As the world’s largest Chinese language search engine and leading AI-Tech company, Baidu prides itself on simplifying a complex world through technology,” said By Dr. Zhang Ya Qin, president of Baidu. “The AMD EPYC processor powered one-socket server can significantly increase our datacenter computing efficiency, reduce TCO and lower energy consumption. We will start deploying with the launch of AMD EPYC and I look forward to our cooperation leading to scaled EPYC adoption this year, and ongoing innovations.”
  • Microsoft. “We’ve worked to make Microsoft Azure a powerful enterprise grade cloud platform, that helps guide the success of our customers, no matter their size or geography,” said Girish Bablani, corporate vice president, Azure Compute, Microsoft Corp. “To power Azure, we require the most cutting-edge infrastructure and the latest advances in silicon which is why we intend to be the first global cloud provider to deliver AMD EPYC, and its combination of high performance and value, to customers.”

The single socket gambit is another interesting aspect to AMD’s initiative. Currently two socket servers rule the roost.

Here’s the AMD pitch: “In our one socket offering we have come up with a clever way to maintain all of the I/O capabilities that you would get in a two socket as well as the full complement of eight memory channels. Today people buy two socket, sometimes because they need to, but more often than not because they have to. There are many examples in which I/O rich [workloads] like storage, like GPU compute, and some vertical workloads where people don’t necessarily need two sockets from a CPU performance perspective,” said Aylor.

AMD’s single socket offering cuts costs substantially, according to Aylor. “We’ve selectively optimized a couple of skews for one socket only. So these are skews that are one socket capable only,” said Aylor. As an example of how the one socket and two socket offerings are distinguished, he cited on package interconnect, “The infinity fabric that would normally connect the two sockets in a two socket system, we repurpose that interconnect into more I/O lanes and that’s how you have in a two socket solution 128 lanes of PCIe and in a one socket solution you still keep the same level of connectivity.”

AMD has singled out a number of vertical as good fits for one socket EPYC servers. Perhaps not surprisingly, storage is one. “Not only base line storage but software defined storage with EPYC’s ability to attach a massive number of SATA drives to a one socket. We also see a strong opportunity in certain areas of high performance computing, especially those that tend to focus on memory bound application. And we have an oil and gas reservoir simulation demo,” said Aylor.

Link to AMD press release: https://www.hpcwire.com/off-the-wire/amd-unveils-record-setting-epyc-datacenter-processor/

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!

Better Scientific Software: Turn Your Passion into Cash

September 13, 2019

Do you know your way around scientific software and programming? You think you can contribute to the community by making scientific software better? If so, then the Better Scientific Software (BSSW) organization wants yo Read more…

By Dan Olds

Google’s ML Compiler Initiative Advances

September 12, 2019

Machine learning models running on everything from cloud platforms to mobile phones are posing new challenges for developers faced with growing tool complexity. Google’s TensorFlow team unveiled an open-source machine Read more…

By George Leopold

HPC Perspectives with Dr. Seid Koric

September 12, 2019

Brendan McGinty, director of Industry for the National Center for Supercomputing Applications (NCSA), University of Illinois at Urbana-Champaign, kicks off the first in a series of pieces profiling leaders in high performance computing (HPC), writing for the... Read more…

By Brendan McGinty

AWS Solution Channel

A Guide to Discovering the Best AWS Instances and Configurations for Your HPC Workload

The flexibility and heterogeneity of HPC cloud services provide a welcome contrast to the constraints of on-premises HPC. Every HPC configuration is potentially accessible to any given workload in a well-resourced cloud HPC deployment, with vast scalability to spin up as much compute as that workload demands in any given moment. Read more…

HPE Extreme Performance Solutions

Intel FPGAs: More Than Just an Accelerator Card

FPGA (Field Programmable Gate Array) acceleration cards are not new, as they’ve been commercially available since 1984. Typically, the emphasis around FPGAs has centered on the fact that they’re programmable accelerators, and that they can truly offer workload specific hardware acceleration solutions without requiring custom silicon. Read more…

IBM Accelerated Insights

Building a Solid IA for Your AI

The journey to high performance precision medicine starts with designing and deploying a solid Information Architecture that addresses the spectrum of challenges from data and applications that need to be managed and orchestrated together to empower workloads from analytics to AI. Read more…

IDAS: ‘Automagic’ HPC With Training Wheels

September 12, 2019

High-performance computing (HPC) for research is notorious for having steep barriers to entry. For this reason, high-tech disciplines were early adopters, have used the most cycles and typically drove hardware and softwa Read more…

By Elizabeth Leake

IDAS: ‘Automagic’ HPC With Training Wheels

September 12, 2019

High-performance computing (HPC) for research is notorious for having steep barriers to entry. For this reason, high-tech disciplines were early adopters, have Read more…

By Elizabeth Leake

Univa Brings Cloud Automation to Slurm Users with Navops Launch 2.0

September 11, 2019

Univa, the company behind Grid Engine, announced today its HPC cloud-automation platform NavOps Launch will support the popular open-source workload scheduler Slurm. With the release of NavOps Launch 2.0, “Slurm users will have access to the same cloud automation capabilities... Read more…

By Tiffany Trader

When Dense Matrix Representations Beat Sparse

September 9, 2019

In our world filled with unintended consequences, it turns out that saving memory space to help deal with GPU limitations, knowing it introduces performance pen Read more…

By James Reinders

Eyes on the Prize: TACC’s Frontera Quickly Ramps up Science Agenda

September 9, 2019

Announced a year ago and officially launched a week ago, the Texas Advanced Computing Center’s Frontera – now the fastest academic supercomputer (~25 petefl Read more…

By John Russell

Quantum Roundup: IBM Goes to School, Delft Tackles Networking, Rigetti Updates

September 5, 2019

IBM today announced a new open source quantum ‘textbook’, a series of quantum education videos, and plans to expand its nascent quantum hackathon program. L Read more…

By John Russell

DARPA Looks to Propel Parallelism

September 4, 2019

As Moore’s law runs out of steam, new programming approaches are being pursued with the goal of greater hardware performance with less coding. The Defense Advanced Projects Research Agency is launching a new programming effort aimed at leveraging the benefits of massive distributed parallelism with less sweat. Read more…

By George Leopold

Fastest Academic Supercomputer Enters Full Production at TACC, Just in Time for Hurricane Season

September 3, 2019

Frontera, the NSF supercomputer installed at the Texas Advanced Computing Center (TACC) in June, passed its formal acceptance last week and is now officially la Read more…

By Tiffany Trader

MIT Prepares for Satori…and a New 2 Petaflops Computer Too

August 27, 2019

Sometime this fall, MIT will fire up Satori – an $11.6 million compute cluster donated by IBM and coinciding with the opening of the MIT Stephen A. Schwarzma Read more…

By John Russell

High Performance (Potato) Chips

May 5, 2006

In this article, we focus on how Procter & Gamble is using high performance computing to create some common, everyday supermarket products. Tom Lange, a 27-year veteran of the company, tells us how P&G models products, processes and production systems for the betterment of consumer package goods. Read more…

By Michael Feldman

Supercomputer-Powered AI Tackles a Key Fusion Energy Challenge

August 7, 2019

Fusion energy is the Holy Grail of the energy world: low-radioactivity, low-waste, zero-carbon, high-output nuclear power that can run on hydrogen or lithium. T Read more…

By Oliver Peckham

AMD Verifies Its Largest 7nm Chip Design in Ten Hours

June 5, 2019

AMD announced last week that its engineers had successfully executed the first physical verification of its largest 7nm chip design – in just ten hours. The AMD Radeon Instinct Vega20 – which boasts 13.2 billion transistors – was tested using a TSMC-certified Calibre nmDRC software platform from Mentor. Read more…

By Oliver Peckham

TSMC and Samsung Moving to 5nm; Whither Moore’s Law?

June 12, 2019

With reports that Taiwan Semiconductor Manufacturing Co. (TMSC) and Samsung are moving quickly to 5nm manufacturing, it’s a good time to again ponder whither goes the venerable Moore’s law. Shrinking feature size has of course been the primary hallmark of achieving Moore’s law... Read more…

By John Russell

DARPA Looks to Propel Parallelism

September 4, 2019

As Moore’s law runs out of steam, new programming approaches are being pursued with the goal of greater hardware performance with less coding. The Defense Advanced Projects Research Agency is launching a new programming effort aimed at leveraging the benefits of massive distributed parallelism with less sweat. Read more…

By George Leopold

Cray Wins NNSA-Livermore ‘El Capitan’ Exascale Contract

August 13, 2019

Cray has won the bid to build the first exascale supercomputer for the National Nuclear Security Administration (NNSA) and Lawrence Livermore National Laborator Read more…

By Tiffany Trader

AMD Launches Epyc Rome, First 7nm CPU

August 8, 2019

From a gala event at the Palace of Fine Arts in San Francisco yesterday (Aug. 7), AMD launched its second-generation Epyc Rome x86 chips, based on its 7nm proce Read more…

By Tiffany Trader

Nvidia Embraces Arm, Declares Intent to Accelerate All CPU Architectures

June 17, 2019

As the Top500 list was being announced at ISC in Frankfurt today with an upgraded petascale Arm supercomputer in the top third of the list, Nvidia announced its Read more…

By Tiffany Trader

Leading Solution Providers

ISC 2019 Virtual Booth Video Tour

CRAY
CRAY
DDN
DDN
DELL EMC
DELL EMC
GOOGLE
GOOGLE
ONE STOP SYSTEMS
ONE STOP SYSTEMS
PANASAS
PANASAS
VERNE GLOBAL
VERNE GLOBAL

Ayar Labs to Demo Photonics Chiplet in FPGA Package at Hot Chips

August 19, 2019

Silicon startup Ayar Labs continues to gain momentum with its DARPA-backed optical chiplet technology that puts advanced electronics and optics on the same chip Read more…

By Tiffany Trader

Top500 Purely Petaflops; US Maintains Performance Lead

June 17, 2019

With the kick-off of the International Supercomputing Conference (ISC) in Frankfurt this morning, the 53rd Top500 list made its debut, and this one's for petafl Read more…

By Tiffany Trader

A Behind-the-Scenes Look at the Hardware That Powered the Black Hole Image

June 24, 2019

Two months ago, the first-ever image of a black hole took the internet by storm. A team of scientists took years to produce and verify the striking image – an Read more…

By Oliver Peckham

Cray – and the Cray Brand – to Be Positioned at Tip of HPE’s HPC Spear

May 22, 2019

More so than with most acquisitions of this kind, HPE’s purchase of Cray for $1.3 billion, announced last week, seems to have elements of that overused, often Read more…

By Doug Black and Tiffany Trader

Chinese Company Sugon Placed on US ‘Entity List’ After Strong Showing at International Supercomputing Conference

June 26, 2019

After more than a decade of advancing its supercomputing prowess, operating the world’s most powerful supercomputer from June 2013 to June 2018, China is keep Read more…

By Tiffany Trader

Qualcomm Invests in RISC-V Startup SiFive

June 7, 2019

Investors are zeroing in on the open standard RISC-V instruction set architecture and the processor intellectual property being developed by a batch of high-flying chip startups. Last fall, Esperanto Technologies announced a $58 million funding round. Read more…

By George Leopold

Intel Confirms Retreat on Omni-Path

August 1, 2019

Intel Corp.’s plans to make a big splash in the network fabric market for linking HPC and other workloads has apparently belly-flopped. The chipmaker confirmed to us the outlines of an earlier report by the website CRN that it has jettisoned plans for a second-generation version of its Omni-Path interconnect... Read more…

By Staff report

Intel Debuts Pohoiki Beach, Its 8M Neuron Neuromorphic Development System

July 17, 2019

Neuromorphic computing has received less fanfare of late than quantum computing whose mystery has captured public attention and which seems to have generated mo 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