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 industry updates delivered to you every week!

Kathy Yelick on Post-Exascale Challenges

April 18, 2024

With the exascale era underway, the HPC community is already turning its attention to zettascale computing, the next of the 1,000-fold performance leaps that have occurred about once a decade. With this in mind, the ISC Read more…

2024 Winter Classic: Texas Two Step

April 18, 2024

Texas Tech University. Their middle name is ‘tech’, so it’s no surprise that they’ve been fielding not one, but two teams in the last three Winter Classic cluster competitions. Their teams, dubbed Matador and Red Read more…

2024 Winter Classic: The Return of Team Fayetteville

April 18, 2024

Hailing from Fayetteville, NC, Fayetteville State University stayed under the radar in their first Winter Classic competition in 2022. Solid students for sure, but not a lot of HPC experience. All good. They didn’t Read more…

Software Specialist Horizon Quantum to Build First-of-a-Kind Hardware Testbed

April 18, 2024

Horizon Quantum Computing, a Singapore-based quantum software start-up, announced today it would build its own testbed of quantum computers, starting with use of Rigetti’s Novera 9-qubit QPU. The approach by a quantum Read more…

2024 Winter Classic: Meet Team Morehouse

April 17, 2024

Morehouse College? The university is well-known for their long list of illustrious graduates, the rigor of their academics, and the quality of the instruction. They were one of the first schools to sign up for the Winter Read more…

MLCommons Launches New AI Safety Benchmark Initiative

April 16, 2024

MLCommons, organizer of the popular MLPerf benchmarking exercises (training and inference), is starting a new effort to benchmark AI Safety, one of the most pressing needs and hurdles to widespread AI adoption. The sudde Read more…

Kathy Yelick on Post-Exascale Challenges

April 18, 2024

With the exascale era underway, the HPC community is already turning its attention to zettascale computing, the next of the 1,000-fold performance leaps that ha Read more…

Software Specialist Horizon Quantum to Build First-of-a-Kind Hardware Testbed

April 18, 2024

Horizon Quantum Computing, a Singapore-based quantum software start-up, announced today it would build its own testbed of quantum computers, starting with use o Read more…

MLCommons Launches New AI Safety Benchmark Initiative

April 16, 2024

MLCommons, organizer of the popular MLPerf benchmarking exercises (training and inference), is starting a new effort to benchmark AI Safety, one of the most pre Read more…

Exciting Updates From Stanford HAI’s Seventh Annual AI Index Report

April 15, 2024

As the AI revolution marches on, it is vital to continually reassess how this technology is reshaping our world. To that end, researchers at Stanford’s Instit Read more…

Intel’s Vision Advantage: Chips Are Available Off-the-Shelf

April 11, 2024

The chip market is facing a crisis: chip development is now concentrated in the hands of the few. A confluence of events this week reminded us how few chips Read more…

The VC View: Quantonation’s Deep Dive into Funding Quantum Start-ups

April 11, 2024

Yesterday Quantonation — which promotes itself as a one-of-a-kind venture capital (VC) company specializing in quantum science and deep physics  — announce Read more…

Nvidia’s GTC Is the New Intel IDF

April 9, 2024

After many years, Nvidia's GPU Technology Conference (GTC) was back in person and has become the conference for those who care about semiconductors and AI. I Read more…

Google Announces Homegrown ARM-based CPUs 

April 9, 2024

Google sprang a surprise at the ongoing Google Next Cloud conference by introducing its own ARM-based CPU called Axion, which will be offered to customers in it Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Leading Solution Providers

Contributors

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Eyes on the Quantum Prize – D-Wave Says its Time is Now

January 30, 2024

Early quantum computing pioneer D-Wave again asserted – that at least for D-Wave – the commercial quantum era has begun. Speaking at its first in-person Ana Read more…

GenAI Having Major Impact on Data Culture, Survey Says

February 21, 2024

While 2023 was the year of GenAI, the adoption rates for GenAI did not match expectations. Most organizations are continuing to invest in GenAI but are yet to Read more…

The GenAI Datacenter Squeeze Is Here

February 1, 2024

The immediate effect of the GenAI GPU Squeeze was to reduce availability, either direct purchase or cloud access, increase cost, and push demand through the roof. A secondary issue has been developing over the last several years. Even though your organization secured several racks... Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire