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!

Energy Exascale Earth System Model Version 2 Promises Twice the Speed

October 18, 2021

The Energy Exascale Earth System Model (E3SM) is an ongoing Department of Energy (DOE) earth system modeling, simulation and prediction project aiming to “assert and maintain an international scientific leadership posi Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Royalty-free stock illustration ID: 1938746143

MosaicML, Led by Naveen Rao, Comes Out of Stealth Aiming to Ease Model Training

October 15, 2021

With more and more enterprises turning to AI for a myriad of tasks, companies quickly find out that training AI models is expensive, difficult and time-consuming. Finding a new approach to deal with those cascading challenges is the aim of a new startup, MosaicML, that just came out of stealth... Read more…

NSF Awards $11M to SDSC, MIT and Univ. of Oregon to Secure the Internet

October 14, 2021

From a security standpoint, the internet is a problem. The infrastructure developed decades ago has cracked, leaked and been patched up innumerable times, leaving vulnerabilities that are difficult to address due to cost Read more…

SC21 Announces Science and Beyond Plenary: the Intersection of Ethics and HPC

October 13, 2021

The Intersection of Ethics and HPC will be the guiding topic of SC21's Science & Beyond plenary, inspired by the event tagline of the same name. The evening event will be moderated by Daniel Reed with panelists Crist Read more…

AWS Solution Channel

Cost optimizing Ansys LS-Dyna on AWS

Organizations migrate their high performance computing (HPC) workloads from on-premises infrastructure to Amazon Web Services (AWS) for advantages such as high availability, elastic capacity, latest processors, storage, and networking technologies; Read more…

Quantum Workforce – NSTC Report Highlights Need for International Talent

October 13, 2021

Attracting and training the needed quantum workforce to fuel the ongoing quantum information sciences (QIS) revolution is a hot topic these days. Last week, the U.S. National Science and Technology Council issued a report – The Role of International Talent in Quantum Information Science... Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Royalty-free stock illustration ID: 1938746143

MosaicML, Led by Naveen Rao, Comes Out of Stealth Aiming to Ease Model Training

October 15, 2021

With more and more enterprises turning to AI for a myriad of tasks, companies quickly find out that training AI models is expensive, difficult and time-consuming. Finding a new approach to deal with those cascading challenges is the aim of a new startup, MosaicML, that just came out of stealth... Read more…

Quantum Workforce – NSTC Report Highlights Need for International Talent

October 13, 2021

Attracting and training the needed quantum workforce to fuel the ongoing quantum information sciences (QIS) revolution is a hot topic these days. Last week, the U.S. National Science and Technology Council issued a report – The Role of International Talent in Quantum Information Science... Read more…

Eni Returns to HPE for ‘HPC4’ Refresh via GreenLake

October 13, 2021

Italian energy company Eni is upgrading its HPC4 system with new gear from HPE that will be installed in Eni’s Green Data Center in Ferrera Erbognone (a provi Read more…

The Blueprint for the National Strategic Computing Reserve

October 12, 2021

Over the last year, the HPC community has been buzzing with the possibility of a National Strategic Computing Reserve (NSCR). An in-utero brainchild of the COVID-19 High-Performance Computing Consortium, an NSCR would serve as a Merchant Marine for urgent computing... Read more…

UCLA Researchers Report Largest Chiplet Design and Early Prototyping

October 12, 2021

What’s the best path forward for large-scale chip/system integration? Good question. Cerebras has set a high bar with its wafer scale engine 2 (WSE-2); it has 2.6 trillion transistors, including 850,000 cores, and was fabricated using TSMC’s 7nm process on a roughly 8” x 8” silicon footprint. Read more…

What’s Next for EuroHPC: an Interview with EuroHPC Exec. Dir. Anders Dam Jensen

October 7, 2021

One year after taking the post as executive director of the EuroHPC JU, Anders Dam Jensen reviews the project's accomplishments and details what's ahead as EuroHPC's operating period has now been extended out to the year 2027. Read more…

University of Bath Unveils Janus, an Azure-Based Cloud HPC Environment

October 6, 2021

The University of Bath is upgrading its HPC infrastructure, which it says “supports a growing and wide range of research activities across the University.” Read more…

Ahead of ‘Dojo,’ Tesla Reveals Its Massive Precursor Supercomputer

June 22, 2021

In spring 2019, Tesla made cryptic reference to a project called Dojo, a “super-powerful training computer” for video data processing. Then, in summer 2020, Tesla CEO Elon Musk tweeted: “Tesla is developing a [neural network] training computer... Read more…

Enter Dojo: Tesla Reveals Design for Modular Supercomputer & D1 Chip

August 20, 2021

Two months ago, Tesla revealed a massive GPU cluster that it said was “roughly the number five supercomputer in the world,” and which was just a precursor to Tesla’s real supercomputing moonshot: the long-rumored, little-detailed Dojo system. Read more…

Esperanto, Silicon in Hand, Champions the Efficiency of Its 1,092-Core RISC-V Chip

August 27, 2021

Esperanto Technologies made waves last December when it announced ET-SoC-1, a new RISC-V-based chip aimed at machine learning that packed nearly 1,100 cores onto a package small enough to fit six times over on a single PCIe card. Now, Esperanto is back, silicon in-hand and taking aim... Read more…

CentOS Replacement Rocky Linux Is Now in GA and Under Independent Control

June 21, 2021

The Rocky Enterprise Software Foundation (RESF) is announcing the general availability of Rocky Linux, release 8.4, designed as a drop-in replacement for the soon-to-be discontinued CentOS. The GA release is launching six-and-a-half months... Read more…

US Closes in on Exascale: Frontier Installation Is Underway

September 29, 2021

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, held by Zoom this week (Sept. 29-30), it was revealed that the Frontier supercomputer is currently being installed at Oak Ridge National Laboratory in Oak Ridge, Tenn. The staff at the Oak Ridge Leadership... Read more…

Intel Completes LLVM Adoption; Will End Updates to Classic C/C++ Compilers in Future

August 10, 2021

Intel reported in a blog this week that its adoption of the open source LLVM architecture for Intel’s C/C++ compiler is complete. The transition is part of In Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Hot Chips: Here Come the DPUs and IPUs from Arm, Nvidia and Intel

August 25, 2021

The emergence of data processing units (DPU) and infrastructure processing units (IPU) as potentially important pieces in cloud and datacenter architectures was Read more…

Leading Solution Providers

Contributors

AMD-Xilinx Deal Gains UK, EU Approvals — China’s Decision Still Pending

July 1, 2021

AMD’s planned acquisition of FPGA maker Xilinx is now in the hands of Chinese regulators after needed antitrust approvals for the $35 billion deal were receiv Read more…

HPE Wins $2B GreenLake HPC-as-a-Service Deal with NSA

September 1, 2021

In the heated, oft-contentious, government IT space, HPE has won a massive $2 billion contract to provide HPC and AI services to the United States’ National Security Agency (NSA). Following on the heels of the now-canceled $10 billion JEDI contract (reissued as JWCC) and a $10 billion... Read more…

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…

Julia Update: Adoption Keeps Climbing; Is It a Python Challenger?

January 13, 2021

The rapid adoption of Julia, the open source, high level programing language with roots at MIT, shows no sign of slowing according to data from Julialang.org. I Read more…

Quantum Roundup: IBM, Rigetti, Phasecraft, Oxford QC, China, and More

July 13, 2021

IBM yesterday announced a proof for a quantum ML algorithm. A week ago, it unveiled a new topology for its quantum processors. Last Friday, the Technical Univer Read more…

The Latest MLPerf Inference Results: Nvidia GPUs Hold Sway but Here Come CPUs and Intel

September 22, 2021

The latest round of MLPerf inference benchmark (v 1.1) results was released today and Nvidia again dominated, sweeping the top spots in the closed (apples-to-ap Read more…

Frontier to Meet 20MW Exascale Power Target Set by DARPA in 2008

July 14, 2021

After more than a decade of planning, the United States’ first exascale computer, Frontier, is set to arrive at Oak Ridge National Laboratory (ORNL) later this year. Crossing this “1,000x” horizon required overcoming four major challenges: power demand, reliability, extreme parallelism and data movement. Read more…

Intel Unveils New Node Names; Sapphire Rapids Is Now an ‘Intel 7’ CPU

July 27, 2021

What's a preeminent chip company to do when its process node technology lags the competition by (roughly) one generation, but outmoded naming conventions make i Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire