AMD Unveils ROCm 1.7 Open Platform

Supports AMD EPYC, Radeon Instinct performance

DENVER, CO, Nov 14, 2017 – At SC17, AMD and its ecosystem partners announce immediate availability of a suite of new, high-performance systems powered by AMD EPYC CPUs and AMD Radeon Instinct GPUs to accelerate innovation in supercomputing. AMD combines this broad portfolio with software, featuring the new ROCm 1.7 open platform with updated development tools and libraries, enabling complete AMD EPYC-based PetaFLOPS systems.

By comprehensively supporting both heterogeneous supercomputing systems and memory-bound, CPU driven, high-performance platforms with EPYC, AMD uniquely addresses the needs of multiple workloads with up to a 3X advantage in performance per dollar for the EPYC 7601 vs the Intel Xeon Platinum 8180M1. 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, and more.

“The industry’s leading system providers are here at SC17 with a full breadth of AMD-based solutions that deliver outstanding compute capability across HPC workloads,” said Forrest Norrod, senior vice president and general manager of enterprise, embedded and semi-custom products, AMD. “The power of the AMD portfolio is further underscored by investments we made in our open platform approach. Only AMD offers high-performance CPU and GPU products, along with a completely open source software development environment with ROCm.”

All AMD PetaFLOPS Supercomputing Platform

A highlight for AMD at SC17 is the Inventec P47 system that combines the performance of 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. The [SMART]Rack P47 also features HPC-optimized [SMART]DC DCiM software to remotely monitor, manage and orchestrate GPU-based deployments where real-time temperature, power and system health are particularly crucial to help ensure uninterrupted operation, as well as AMD’s ROCm software platform for the ultimate ease of implementation for deep learning, inference and training workloads.

“As a high-performance technology provider enabling enterprises to close the gap between scale up performance, compute density and cost, AMAX sees the P47 as a game changer,” said Julia Shih, VP of business development, AMAX. “Starting from a single P47 platform, we can scale upwards to supercomputing-class performance by leveraging AMD EPYC, AMD Radeon Instinct, and the ROCm software platform to support Deep Learning, rendering, and a host of other workloads. The [SMART]Rack P47 is the first turnkey PetaFLOPS-in-a-Rack solution geared towards technical performance and business acceleration, married with ease of use. We are excited to announce that we are now taking pre-orders for both the P47 server and the fully-integrated [SMART]Rack P47, with delivery estimated in Q1 of 2018.”

ROCm Open Software Platform

AMD EPYC and AMD Radeon Instinct performance is fully supported by the new ROCm 1.7 release. Expanding on the most versatile open source software platform for heterogeneous computing systems, ROCm 1.7 delivers math libraries and software development support using modern programming languages to unlock the power of GPU acceleration and other accelerators like FPGAs. The ROCm 1.7 release includes multi-GPU support for the latest Radeon GPU hardware, as well as support for TensorFlow and Caffe in the MIOpen libraries.

The foundation for heterogeneous computing strategies is in place through the new AMD technology solution set formed from EPYC, Radeon Instinct, and ROCm 1.7. The availability of the P47 platform and the release of ROCm 1.7 are milestones that demonstrate how optimization and innovation are thriving at the hardware level. Learn more about how AMD is building high-performance solutions for open supercomputing applications at the SC17 show in Denver, November 13 – 17. AMD will demonstrate applications and answer questions in the AMD booth #825.

“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.”

“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 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 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 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 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, chief technology officer, 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.”

“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. “Supermicro’s broad portfolio of EPYC-based A+ Servers, available today in 1U, 2U, 4U and tower form factors, conquer these challenges, helping our enterprise customers to stay ahead in the extremely competitive HPC market while lowering overall TCO.”

“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.”

Availability

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

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

About AMD

For more than 45 years, AMD has driven innovation in high-performance computing, graphics and visualization technologies ― the building blocks for gaming, immersive platforms, and the datacenter. Hundreds of millions of consumers, leading Fortune 500 businesses and cutting-edge scientific research facilities around the world rely on AMD technology daily to improve how they live, work and play. AMD employees around the world are focused on building great products that push the boundaries of what is possible.

For more information, visit www.amd.com.

1. 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. See www.spec.org for more information. NAP-49

Leave a Reply

Your email address will not be published. Required fields are marked *