AMD Showcases Growing Portfolio of EPYC and Radeon-based Systems at SC17

By John Russell

November 13, 2017

AMD’s charge back into HPC and the datacenter is on full display at SC17. Having launched the EPYC processor line in June along with its MI25 GPU the focus here is presenting a full portfolio of partners and systems. AMD is also claiming a 3X price-performance advantage over top end Intel Skylake as it tries to hammer home a compelling message for switching.

“Getting infrastructure and systems ready has been the big focus,” said Scott Aylor, AMD corporate VP and GM of enterprise solutions business. “HPC was always going to be one of the key focused verticals. From EPYC’s ability to connect many GPUs and IO capacity. We have a pretty compelling floating point story especially for memory-bound workloads. You’ll see a lot of that at the show [with] demonstrations around HPC applications.”

He also noted, “Because Skylake was not really in the market when EPYC launched, we had to do all of our comparison with Broadwell. The good news is we now have Skylake in hand as we’ve procured the entire stack and we are holding up extremely well.”

At EPYC’s launch, AMD trotted out an extensive series of price-performance benchmarks (see HPCwire article, AMD Charges Back into the Datacenter and HPC Workflows with EPYC Processor). Today, there were fewer details on performance versus the Skylake line. AMD reported a 3X performance per dollar advantage for EPYC 7601 vs Intel Platinum 8180M1 as measured by SPECfp[i]. Target workloads for AMD solutions include machine learning, weather modeling, computational fluid dynamics, simulation and crash analysis in aviation and automotive manufacturing, oil and gas exploration, according to the company.

Also announced was ROCm 1.7., the latest version of the development platform. It now includes multi-GPU support for the latest Radeon GPU hardware as well as support for TensorFlow and Caffe in the MIOpen libraries. Taken together, the new CPU, GPU, and platform tools are evidence of AMD commitment to a vision of heterogeneous computing platforms, said Aylor, pointing to the diversity of platforms and partners.

AMD reports the following companies are now offering AMD EPYC products or AMD EPYC-based systems:

  • OEM/ODM – Asus, Gigabyte, HPE, Supermicro, Tyan
  • Distributors – ASI Computer Technologies, Tech Data
  • Systems Integrators – AMAX, Boston, Boxx, Clustervision, E4, EchoStreams, Equus / ServersDirect, ICC, Koi, Megware, NEC, Penguin, Silicon Mechanics

This is already a sizeable group given the newness of AMD’s reentry to data center world. It was interesting that Dell EMC was not on the list. It delivered a forceful statement of support when EPYC was launched. Aylor suggested it’s just a matter of timing with Dell before it discloses its plans. (The statements of support in today’s release are provided towards the end of the article.)

He was less specific about AMD’s high-end HPC and supercomputer plans. This is, after all, SC, and AMD once wielded substantial influence at the top. Titan, at Oak Ridge National Laboratory, was built using AMD Opteron processors and remains the fastest U.S. machine on the Top500. AMD is one of six vendors to win PathForward awards.

Aylor said, “We fully expect to participate in a material way both from a CPU and GPU perspective, especially if you think about some of the techniques and technologies we have on the current roadmap as well as those that may be coming in the timeframe that the exascale deployments are coming out. We’ve talked about our involvement in things like Gen-Z. Our involvement in PCI-X where we are looking to open standards for both accelerators and ROCm interconnect. We definitely expect to be a significant player in that over time.”

The Inventec P47 system, launched in August, is a high-end server. It combines a single EPYC 7000 series CPU with four Radeon Instinct MI25 GPUs, each delivering up to 12.3 TFLOPS of single precision performance in a highly scalable platform. For large to hyperscale deployments, AMAX has developed the [SMART]Rack P47, an all-inclusive high- performance rackscale appliance featuring 20x P47 platforms to provide up to a Petaflops of single precision compute performance and more than 10 terabytes of DDR4 memory per rack.

Inventec and its primary distributor AMAX are targeting Project 47 system availability for Q4 of this year (see HPCwire article, AMD Stuffs a Petaflops of Machine Intelligence into 20-Node Rack).

When the EPYC platform was first announced AMD said it planned a one- and two-socket strategy. To date, two-socket servers have dominated the market.

“It’s interesting when we look at the platforms we are putting into the channel and those that are coming out now with systems integrators and system builders. It’s split almost down the middle actually. We tend to see the single socket really resonating on let’s call it the more GPU-centric computing where the CPU tends to be more supervisory as opposed to a foundational computing role,” said Aylor. The one socket has also drawn attention in big data applications where its ability to connect to a massive number of drives is a distinguishing attribute, he said.

Statements of Support for AMD Ecosystem in the Release

ASUS – “As one of the first companies to introduce AMD EPYC-based servers, ASUS understands the need for platforms that can scale to meet the performance and power requirements of data-intensive HPC and virtualization applications,” said Robert Chin, head of ASUS Server business unit. “Server performance and efficiency is critical to any datacenter, however it is especially important when managing the most demanding tasks inherent in deep learning applications. Our EPYC-based ASUS RS720A-E9 and RS700A-E9 servers on the market today meet this challenge for a dramatically improved experience.”

BOXX – “For two decades, BOXX has developed innovative workstations, rendering systems, and servers for engineering, architecture, VFX, motion media, and other industries,” said Shoaib Mohammad, BOXX vice president of marketing and business development. “Now we’re applying that same expertise to advanced, multi-GPU compute solutions for deep learning. With AMD EPYC server processors, we can significantly boost performance, power and memory to drive advancements in data mining, natural language processing, image recognition, and security.”

 EchoStreams – “EchoStreams supports solution providers and integrators of all sizes by delivering the latest server and storage technologies via OEM/ODM platforms purposely designed for different usage models in different markets that require data-intensive management,” said Gene Lee, president, EchoStreams. “With the addition of the high-performance EPYC processors from AMD to our storage portfolio, today we can offer customers an even more powerful solution capable of taking on the complex challenges in the continuously evolving areas of artificial intelligence and deep learning.”

 GIGABYTE Technology – “GIGABYTE Technology is a key go-to-market partner for delivering EPYC processor- based server platforms, offering customers a mature ecosystem, industry-transforming hardware design and serious compute, memory, I/O and power for complex HPC computations,” said Daniel Hou, vice president, research & development, GIGABYTE Technology. “Supercomputing requires significant compute density at the server level to drive a diverse range of applications, and with our R-series and G-series EPYC processor-based rackmount servers available today, GIGABYTE is ready for the next frontier.”

 HPE – “HPE is a foundational partner to AMD on its journey with EPYC,” said Justin Hotard, vice president and general manager, Volume Global Business Unit, HPE. “As the world leader in supercomputers and high performance computing, we are committed to delivering solutions to customers with highly complicated workloads, and AMD delivers the power, density and scalability to help break barriers.”

Penguin Computing – “Penguin Computing is a longstanding leader in open, Linux-based HPC solutions, and we have delivered hundreds of HPC clusters to customers in a variety of vertical markets spanning life sciences, government, manufacturing, financial services and more,” said Philip Pokorny, CTO, Penguin Computing. “The high-performance EPYC processors from AMD, powering our new Altus line of 1U and 2U server platforms, provide the scalability, memory and high core count that are key to driving advanced HPC and machine learning workloads, and enable us to tackle new challenges in supercomputing.”

 Supermicro – “Our high-density compute solutions optimized for the new EPYC processors offer more cores, more memory channels, and more PCI-E expansion lanes than any previous AMD platforms. These enhanced features enable maximum performance-per-watt, scalability and reliability, all of which are vital in solving today’s biggest challenges in science, engineering, simulation, modeling and data analytics,” said Don Clegg, VP of marketing at Supermicro.

TYAN – “The AMD EPYC processor inside our TYAN servers enables us to double down on performance, delivering the power of a dual-socket platform in a single-socket form factor to maximize value and support an array of high-performance applications,” said Danny Hsu, vice president of MiTAC Computing Technology Corporation’s TYAN Business Unit. “Designing products that can handle complex and often difficult workloads in HPC environments requires scalability, efficiency and an exceptionally high-performance infrastructure, which are all qualities we see in the EPYC portfolio, and why we are partnering with AMD to address the major computing challenges of today and tomorrow.”

[i] Based on SPECfp®_rate2006 scores published on www.spec.org as of October 25, 2017. 2 x EPYC 7601 CPU ($4,200 per processor at AMD 1ku pricing) in Sugon A620-G30, Ubuntu 17.04, x86 Open64 v4.5.2.1 Compiler Suite, 512 GB PC4-2666V-R memory running at 2400 1 x 1TB SATA 7200RPM has a peak score of 1850 (base score 1670); versus 2P Xeon Platinum 8180M ($13,011 per processor per ark.intel.com)-based Cisco UCS C240 M5 system with SUSE Linux Enterprise Server 12 SP2, ICC 17.0.3.191, 384GB PC4-2666V-R memory, 1x240GB SATA SSD score of 1830 (base score 1800). SPEC and SPECfp are registered trademarks of the Standard Performance Evaluation Corporation.

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