Skip navigation

The complexity of the technology and the pace of innovation in the datacenter can be dizzying for anyone working in the space. What really excites me about AMD EPYC™ processors is that the tangible benefits of our products are part of that story. It is our unique feature set that creates an opportunity to drive exceptional performance and low TCO for our customers. At its core, there are three pillars to the EPYC proposition, each comprised of both engineering and economic considerations. First, a refresh is needed for a true datacenter transformation to occur. Second, speed is everything when it comes to data analytics and, thirdly, you don’t have to sacrifice performance for costs in the cloud. I took a shot at distilling this down in more detail below.

 

Refresh Needed for Datacenter Transformation

No question that the move to off-premise mega-datacenters to support entire IT operations for large enterprises is one of the most significant transformations in business (more on that below.) However, the company owned datacenter is still alive and well. There are processing needs and applications that an enterprise may want to keep close to home and under their own management. That doesn’t mean the on-premise infrastructure should stay locked into the past. The AMD EPYC single-socket platform is the game changer that should make a CIO saddled with an aging, underutilized and expensive two-socket system sit up and take notice. Disconnect those old SANS, move to a hyperconverged infrastructure and add secure encryption to your VMs. For example, a Dell PowerEdge 7415, is a VSAN ready node that can reduce your TCO 20% and cut your licensing costs in half1. Let AMD EPYC processors make you the hero with that next infrastructure upgrade.

 

Big Data Needs to be Fast

We have all been at the keynote or analyst seminar where the “growth in generated data” chart is the first slide (not surprisingly, it goes up and to the right). Our technology creates it and our technology must manage it, too. Having data isn’t an advantage anymore. Rather, analyzing it quickly and better than someone else is how you get ahead. Accelerating innovation and unlocking the next discovery cannot be memory bound by your processors’ limitations. AMD EPYC processors free high-performance computing from those constraints. And, paired with our AMD Radeon GPU products, we can apply the right architecture to the problem at hand, be it in inference or deep learning for machine intelligence. Notre Dame and The National Institute of Nuclear Physics in Italy are doing more with AMD EPYC processors, and so can you.

 

Redefining the Economics and Security of Cloud Services

The only reason cloud-based services exist is to deliver at scale a less costly alternative to owning and maintaining your own datacenter. IT customers buy capacity at a certain cost point – either on premise or off premise – it’s that simple. AMD EPYC processors are disrupting the incumbent in this market by being able to deliver more service at the same cost point, or equivalent service more affordably1. Tencent, Microsoft Azure, Baidu, Dropbox and more have picked AMD EPYC processors to support their offerings for the unique set of features and value AMD delivers. And in a world where data security seems to make the headlines every week, AMD EPYC can help deliver secure encryption to virtualized machines across more threads and more cores. You don’t have to choose between losing performance by shutting off hyperthreading or risking data loss between VMs.

 

By providing the right balance of compute, memory, I/O and security for high density environments AMD EPYC is a winning formula. It is changing the dynamics of the datacenter today and it deserves a closer look. The momentum we are seeing across our customers proves these points and we are just getting started. With a strong roadmap in place, I encourage you to begin your journey toward the future with AMD today.

 

Daniel Bounds, senior director, Datacenter Products for AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.  GD-5

 

120% Lower TCO and 50% Lower Licensing Costs: Demartek test report: Dell EMC PowerEdge R7415 AMD EPYC VMware vSAN Mixed Workloads Performance – April 2018 www.demartek.com/Demartek_Dell_EMC_PowerEdge_R7415_vSAN_Mixed_Workloads_Evaluation_2018-04.html

As the world of console, PC and handheld gaming evolves with higher resolution displays, more intense rendering and more vibrant colors, the casino gaming market is following suit. The new normal for a typical casino or slot machine game is multiple, high resolution (up to 4K) screens displaying intricate, 3D graphics that show players their standings amongst others, highlight video content, display engaging ads, and more.

 

This is what the market is demanding. A truly visually engaging experience that helps casinos around the world compete with the likes of console, online, and handheld games.

 

In February 2018, we announced the Ryzen™ Embedded V1000 processor family, which brings together breakthrough performance of the pioneering AMD “Zen” CPU and “Vega” GPU architectures in a seamlessly integrated SOC solution. This provides the ability to deliver high end 3-D graphics on up to four, 4K, 60Mhz refresh displays. This is exactly what the casino gaming industry needs to enable a new higher levels of processing power for next-generation embedded designs, delivering superior graphics and multimedia processing, and compute performance.

 

Companies like Quixant, Advantech, iBase Gaming, Sapphire and Axiomtek have all signed on as Ryzen embedded V1000 customers, and will be showing off their systems at this year’s Global Gaming Expo in Las Vegas at the AMD Booth, number 3814.

 

AMD’s support of the casino gaming industry spans more than a decade. With Ryzen Embedded V1000 and portfolio of discrete graphics processors, a bright future for casinos by enabling engaging, theme-based entertainment presented on multiple large 4K displays, with vibrant 3D graphics. It’s what will keep patrons engaged and trying for the jackpot!

When AMD CEO Lisa Su told BARRON’S what it takes to be successful in the IT industry, she said: “What you need to be successful is, you need to execute, you need to have attractive markets, you need to have that product roadmap, and you need to keep up with the cycle.”

 

This is even more true when it comes to commercial client business, a very attractive market that you can win only by offering the right product but even more importantly by demonstrating the capability to respond to business users’ needs and optimizing customer’s ROI.

 

When we first launched our Ryzen PRO CPUs for the commercial market in the summer of 2017, we revitalized the commercial market. In May this year, we expanded our offering with our new Ryzen PRO processors powered by built-in Radeon™ Vega graphics.

 

In just 8 months we launched 20 new Ryzen processors– including seven of Ryzen PRO processors built for the modern commercial user. The Ryzen PRO 2700U, 2500U and 2300U for mobile, and the 2400G, 2400GE, 2200G and 2200GE for desktop, and we are not stopping there. Earlier this month we announced availability of three new desktop Ryzen PRO CPU models and the return of Athlon™ products to the commercial space. It’s our largest commercial portfolio ever, but even more notable is the broad offering of AMD-based commercial systems from industry top players like Dell, HP and Lenovo.

 

Unique needs, massive opportunity

 

The market for PC processors is estimated as being a $30 billion,1 one third of which is commercial.

 

So, our goal with Ryzen PRO was to unlock that $10 billion opportunity of the $30 billion market. And we are succeeding because we focused intensely on three areas of utmost importance to business users: Security, Reliability, and Performance. By delivering high-performing, premium PCs with excellent ROI and low TCO, focusing on the quality of the end-user’s experience for productivity and business-critical applications, we’re seeing unprecedented adoption in the commercial market.

 

Too many of today’s leading products end up being tomorrow’s paperweights. Not so with AMD Ryzen PRO processors, which include technology specifically designed for future demands, so our customers don’t have to worry about early obsolescence.

 

Industry recognition from the analyst community

 

It’s been particularly rewarding to witness the positive response, acknowledgment and recognition from respected technology industry analysts’ firms on our momentum in the commercial client space.

 

Canalys, a leading global technology market analyst firm with a distinct channel focus, said in one of its notes “Ryzen and EPYC have shined in the consumer and server spaces by hitting three critical targets: better than expected performance, greater core counts and lower pricing relative to Intel Core… there is a real possibility that AMD will surpass Intel in performance in 2019 with its third-generation Ryzen processors.”

 

As well as:

 

“Ryzen PRO processors are particularly competitive for mobile professionals who require GPU performance for industrial and graphic design workloads.”

 

And: “Security is paramount for many businesses, and across its lineup AMD can argue greater hardware security than Intel.”

 

Another market note from IDC, analyzing the Ryzen Pro APU launch, commented:

 

“By embedding GuardMI technology with the standout feature of Secure Boot Process which ensures BIOS level security from power-on to power-off, AMD addressed one of the crucial needs of current enterprise solutions - security.

 

And also, that:

 

“SenseMI technology, offering processor-level machine intelligence, and DASH (Desktop and Mobile Architecture for System Hardware) manageability are some of the additional features baked into the processor to boost performance and enhance controllability aspects most suitable for various business usages.”

 

Gartner has listed AMD Ryzen PRO based solutions in its July 2018 “Recommended Configurations for Notebooks and Desktop PCs, 2018” report in the Mainstream user, Price-Driven user, and Technology-driven user profiles categories. They are listing 8 AMD PR0 processors out of a total of 15 processors they recommend for both notebook and desktop solutions for different users’ scenarios.

 

We’re just getting started

 

At AMD, we’re working hard to develop business solutions for the challenges professional users face every day. We don’t create technology for technology’s sake – we’re focused on meaningful innovation that delivers real value, with real world productivity in mind. For enterprise customers who need flexible client PCs, we’re committed to providing a flexible, no-compromise experience, through AMD Ryzen PRO APUs with Radeon Vega Graphics.

 

As encouraging as our success is, with these new enterprise platforms from the likes of Dell, HP and Lenovo representing an important milestone for AMD - we’re really just getting started. In 2018 and beyond, we’ll strive to lead this space, and address the needs of the premium commercial market - from top-to-bottom.

 

 

John Morris, Sr. Director and General Manger Commercial Sales and Workstation Business at AMD

 

  1. AMD actuals and internal estimates.

As companies ramp up IoT and Edge Compute endeavors, the AMD Embedded product portfolio is well positioned to help customers solve the challenges presented by the increasing complexity of today’s edge environment. The same qualities that the AMD EPYC™ 3000 and AMD Ryzen™ V1000 embedded processors apply to other vertical markets can translate into benefits for IoT solutions for edge gateways, servers and interconnected products.

 

We’ve had great conversations with customers and they are sharing their insights as they build out their IoT and Edge Compute system.

  1. Security: Making sure all devices on the network, no matter how far away from the data center, have security.
  2. Performance: Getting high performance at great cost to enable use cases such as data analytics and machine intelligence at the edge.
  3. Ease of use: Interoperability and flexibility to work across a variety of platforms and ecosystems

 

Luckily for our customers and potential customers, our Embedded processors provide a combination of elegant solutions to address these challenges and more.

 

Security

In the new IoT world, there is an explosion of connected products working at the edge of the network, which creates an increased security vulnerability. Embedded processors from AMD implement features that validate root of trust at the chip level while also fortifying the integrity of other platform facets. An on-chip security processor, in tandem with hardware-validated boot capabilities, helps protect data and helps ensure systems boot up based on trusted software. Security measures are bolstered even further with Secure Memory Encryption to help protect systems against unauthorized physical memory access and Secure Encrypted Virtualization for encrypting virtual machines in memory. These security capabilities are leveraged in IoT systems to deliver “stronger” edge to cloud security.

 

Performance

The AMD EPYC Embedded 3000 Series processors provide the performance and power efficiency to enable a variety of Edge computing platforms; bringing computation analytics and intelligence closer to the customer and even on premises with a compelling feature-set for such solutions. As an added benefit, with a common architecture between the AMD EPYC Embedded 3000 series and the EPYC 7000 SOC for data centers, customers can share common security and RAS features from the edge to the core allowing for seamless migration of functionality and compute tasks to where they are most efficient in the network.

 

The AMD Ryzen Embedded V1000 processors provide an ideal balance of performance and power. High performance CPU cores coupled with integrated graphics enable bring more processing and decision making at the edge enabling a new level of service with lower latency and secure connectivity, ultimately helping to enable lower costs and enhanced data security.

 

Flexibility

AMD is a supporting member of EdgeX Foundry, a group of ecosystem partners with the common goal of improving IoT interoperability. Collaborating with more than 70 participating members towards a quality open environment and framework for building and accelerating IoT deployments. We are using EdgeX as one of our anchors in our IoT strategy and have developed more than a dozen close partnerships with members of EdgeX, including companies like Device Authority, DellEMC, ClearBlade and more, all developing IP in an open, easy and interoperable framework that accelerates IoT adoption.

 

Whatever the future brings for IoT and Edge Computing, AMD embedded products will be ready to support with performance, flexibility and security.

After years of attending the Strata Data Conference, this is my first year at the show in my new role as Vice President and CTO of the Datacenter group for AMD. It’s also the first year for AMD’s new server processor, EPYC™, which only increases my excitement about the conference this week. The AMD EPYC processor is designed specifically for the modern datacenter with high core counts, access to large amounts of memory, ample memory bandwidth and massive I/O. All brought together with the right ratios to create an incredibly flexible workhorse able to meet the needs of a wide variety of workloads.

 

The big data revolution began with the ability to harness many computers in order to process large amounts of data (far larger than ever before). This was an innovative use of software that turned under-utilized smaller servers into a single data processing engine that unleashed the latent power of the data that is the beating heart of every business.

 

The next innovative leap provided the ability to process this huge volume of data in real-time. Advances in networking, storage and software technology enabled real-time streaming processing of huge volumes of data. We are now entering the next stage of innovation: real-time analysis. Analysis is what turns data into insight, and the combined efforts of the global community are making analysis of big data in real-time a reality. The AMD EPYC processors are perfectly matched to support the hardware underpinning all of the computation needed to support this effort.

 

We are proud to be part of a large and growing ecosystem of partners, many of them here at Strata New York: Hortonworks, MapR, DataStax and Couchbase to name just a few; all of whom are actively participating in this ongoing innovation. AMD’s most recent contribution is the EPYC SoC which employs a truly innovative design -  the “no compromise, single socket” system is now a viable choice to replace two-socket systems. This in turn drives down cost, improves energy usage and makes better use of space in the datacenter.

 

Business innovates with data. With AMD EPYC processors, that innovation extends all the  way down the stack into the processor itself. Stop by our booth (#954) at the conference to see some of the more than 50 server platforms that the AMD EPYC processor has been designed into, as well as information on our growing list of partnerships with independent software vendors.

What type of computer user would you consider yourself?

  • Are you an entry-level user that just needs their computer for basic word processing or web browsing?
  • Are you a mainstream user that will do all the above plus some light content creation, spreadsheet analysis or heavy multi-tasking?
  • Or are you a power-user that needs premium performance for software development, VR or 3D modeling?

 

Regardless of whichever type of user you identify with, you need a computing system that matches your performance requirements. With the launch of the AMD Athlon™ PRO and 2nd Gen Ryzen™ PRO processors, AMD offers a complete top to bottom stack of commercial-grade desktop processors designed for each of these types of users.

Slide1.JPG

 

 

Performance for Commercial Desktop User Workloads

The 2nd Gen Ryzen™ PRO desktop processors have been amped up from the 1st Gen Ryzen PRO CPUs, moving to the 12nm process and improved “zen+” architecture. The 2nd Gen Ryzen PRO processors also feature the latest Precision Boost 2 and XFR2 technology3 to allow these CPUs to reach even higher clock speeds than their predecessors. This ultimately means 2nd Gen Ryzen PRO CPUs are generationally faster and continue to provide leading multi-threaded performance versus the competition.1

Slide2.JPG

see footnote #1

Slide3.JPG

see footnote #1

 

The Athlon™ PRO 200GE desktop processor is designed to target entry-level users. This CPU combines the modern “Zen” core architecture with premium Radeon™ Vega graphics to provide the reliable and responsive performance entry-level users need for tasks from word processing, web browsing to video conferencing.2

Slide4.JPG

see footnote #2

Slide5.JPG

see footnote #2

 

Reliability, Manageability & Security for all user workloads

In enterprise environments, Security and Reliability is critical regardless of whether you’re an entry-level or power user. That’s why all AMD Ryzen™ PRO and Athlon™ PRO processors support the same reliability and manageability features (such as 18 month image stability and DASH manageability) and security features (such as Transparent secure memory encryption and Secure boot process) demanded by IT professionals.

Slide6.jpg

 

Desktop System from the leading OEMs

So where can you get a desktop system with these new processors? The 2nd Gen Ryzen PRO and Athlon PRO 200GE model will be available with the major global OEMs including Dell, HP and Lenovo systems, dependent on respective OEM launch schedules4, so you can choose the right solution you need regardless if you’re an entry-level, mainstream or power-user.

Slide7.JPG

 

 

David Tjong, Product Marketing Manager for AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. GD-5

 

 

“Zen” and “Vega” are codenames only and not AMD product names.

 

1. Testing by AMD Performance labs as of 8/24/2018 on the following system. PC manufacturers may vary configurations yielding different results. Results may vary based on driver versions used.

AMD 2nd Gen Ryzen PRO System Config:  AMD Ryzen 7 PRO 2700X, 2700, Ryzen 5 PRO 2600 ‘Turpan’ reference motherboard, 16GB of dual-channel DDR4-3200, GeForce GTX 1080 Graphics Card, Graphics driver 390.77, and a Samsung 850 PRO 512GB SSD using the Windows 10 RS3 operating system. AMD 1st Gen Ryzen PRO System Config: AMD Ryzen 7 PRO 1700X, 1700, Ryzen 5 PRO 1600 X370 Xpower Gaming Titanium motherboard, 16GB of dual-channel DDR4-3200, GeForce GTX 1080 Graphics Card, Graphics driver 390.77, and a Samsung 850 PRO 512GB SSD using the Windows 10 RS3 operating system.

Multiprocessing performance represented by Cinebench R15 nT multiprocessing performance. System performance represented by PCMark10 extended. Each processor achieved the following scores:

AMD Ryzen 7 PRO 2700X, 1720, 7607; AMD Ryzen 7 PRO 2700, 1577, 7472; AMD Ryzen 5 PRO 2600, 1311, 7758; AMD Ryzen 7 PRO 1700X, 1557, 7290; AMD Ryzen 7 PRO 1700, 1355, 7123; AMD Ryzen 5 1600, 1153, 7143.

The Ryzen 7 PRO 2700X achieved a multiprocessing score of 1720 (1720/1557= up to 10% faster than the Ryzen 7 PRO 1700X).  The Ryzen 7 PRO 2700 achieved a multiprocessing score of 1577 (1577/1355=up to 16% faster than the Ryzen 7 PRO 1700).  The Ryzen 5 PRO 2600 achieved a multiprocessing score of 1311 (1311/1153= up to 14% faster than the Ryzen 5 PRO 1600).

The Ryzen 7 PRO 2700X achieved a system score of 7607 (7607/7290= up to 4% faster than the Ryzen 7 PRO 1700X).  The Ryzen 7 PRO 2700 achieved a system score of 7472 (7472/7123=up to 5% faster than the Ryzen 7 PRO 1700).  The Ryzen 5 PRO 2600 achieved a system score of 7756 (7756/7143= up to 9% faster than the Ryzen 5 PRO 1600).

RZP-31

Testing by AMD Performance labs as of 8/24/2018 on the following system. PC manufacturers may vary configurations yielding different results. Results may vary based on driver versions used. AMD System Config:  AMD Ryzen 7 PRO 2700X, Ryzen 5 PRO 2600 ‘Turpan’ reference motherboard, 16GB of dual-channel DDR4-3200, GeForce GTX 1080 Graphics Card, Graphics driver 390.77, and a Samsung 850 PRO 512GB SSD using the Windows 10 RS3 operating system. Intel System Config:  Intel Core i7-8700, i5-8600 Gigabyte Z370 AORUS Gaming5 motherboard, 16GB of dual-channel DDR4-3200, GeForce GTX 1080 Graphics Card, Graphics driver 390.77, and a Samsung 850 PRO 512GB SSD using the Windows 10 RS3 operating system.

Benchmarks used: Cinebench R15 nT (multiprocessing performance), PCMark10 Extended (system performance)

Each processor achieved the following scores:

Ryzen 7 PRO 2700X: 1720, 7607; Ryzen 5 PRO 2600: 1311, 7758; Core i7-8700: 1393, 8581; i5-8600: 1024, 7733.

(1720/1393=up to 24% faster multiprocessing performance on Ryzen 7 PRO 2700X vs the Core i7-8700), (7607/8581=up to 11% slower system performance on Ryzen 7 PRO 2700X vs the Core i7-8700)

(1311/1024=up to 28% faster multiprocessing performance on Ryzen 7 PRO 2600 vs the Core i5-8600), (7758/7733=0% or similar system performance on Ryzen 5 PRO 2600 vs. the Core i5-8600)

RZP-32

2. Testing by AMD Performance labs as of 8/24/2018 on the following system. PC manufacturers may vary configurations yielding different results. Results may vary based on driver versions used. AMD System Config:  AMD Athlon PRO 200GE MSI B450 Tomahawk motherboard, 16GB of dual-channel DDR4-2666, Radeon Vega 3 Graphics, Graphics driver AMD Software version 18.7.1, and a Samsung 850 PRO 512GB SSD using the Windows 10 Pro operating system. Intel System Config:  Intel Pentium G4560 MSI B250 Gaming M3 motherboard, 16GB of dual-channel DDR4-2400, Intel HD Graphics 610, Graphics driver 24.20.100.6194, and a Samsung 850 PRO 512GB SSD using the Windows 10 Pro operating system.

Benchmarks used: Cinebench R15 nT (multiprocessing performance), PCMark10 Extended (system performance), 3DMark11 Performance (graphics performance)

Each processor achieved the following scores:

Athlon PRO 200GE: 357, 2547, 2039; Pentium G4560: 368, 2143, 1222.

(357/368=up to 3% slower multiprocessing performance on Athlon PRO 200GE than the Pentium G4560), (2547/2143=up to 19% faster system performance on Athlon PRO 200GE than the Pentium G4560)

(2039/1222=up to 67% faster system performance on Athlon PRO 200GE than the Pentium G4560)

RZP-35

General office workloads represented with the AMD Office 2016 Productivity Script by AMD performance labs as of 8/24/2018.  PC manufacturers may vary configurations yielding different results. Results may vary based on driver versions used. Athlon™ PRO 200GE vs.  Pentium G4560 Office Productivity Script Time to Complete: 148 vs. 149 seconds (0% faster or similar).

AMD System Config: AMD Athlon PRO 200GE MSI B450 Tomahawk motherboard, 16GB of dual-channel DDR4-2666, Radeon Vega 3 Graphics, Graphics driver AMD Software version 18.7.1, and a Samsung 850 PRO 512GB SSD using the Windows 10 Pro operating system. Intel System Config:  Intel Pentium G4560 MSI B250 Gaming M3 motherboard, 16GB of dual-channel DDR4-2400, Intel HD Graphics 610, Graphics driver 24.20.100.6194, and a Samsung 850 PRO 512GB SSD using the Windows 10 Pro operating system. PC manufacturers may vary configurations yielding different results. Results may vary based on driver versions used.

RZP-36

3. AMD SenseMI technology is built into all Ryzen processors, but specific features and their enablement may vary by product and platform. Learn more at http://www.amd.com/en/technologies/sense-mi. GD-126

4. THE 2ND GENERATION RYZEN PRO DESKTOP PROCESSORS AND ATHLON PRO 200GE MODEL WILL BE AVAILABLE WITH MAJOR GLOBAL OEMS INCLUDING DELL, HP, AND LENOVO SYSTEMS, DEPENDENT ON RESPECTIVE OEM LAUNCH SCHEDULES. A COMPLETE LIST OF PARTICIPATING RETAILERS AND LAUNCH INFORMATION CAN BE FOUND AT WWW.AMD.COM

 

 

Over the last 30 years, industry standard bodies like the TPC and SPEC have developed many standards for performance benchmarking. The motivation behind these standards is to create technically rigorous, vendor-neutral methods of comparison. These standards have enabled buyers to make more informed decisions about their purchases and have given designers and engineers baselines to better understand their systems, ultimately driving innovation and the development of faster, less expensive, and more energy efficient systems.

 

Looking back, the most influential and widely adopted standards were the SPEC CPU Benchmark Suites at the system level, and at the application level, the TPC-C (industry standard for benchmarking transaction processing systems), and the TPC-D and its successor, TPC-H (industry standards for benchmarking decision support systems). These were the forerunners to hundreds of benchmark results, appearing in publications and research papers, and driving an ever-expanding list of innovations.

 

Time marches on and technology-driven innovation continues its relentless advance. Let’s take a closer look at benchmark standards from the TPC in recent years. The TPC has kept pace with the technology, developing and releasing appropriate benchmark standards such as the TPCx-HS and TPCx-BB (benchmark standard for Hadoop based big data analytics), TPCx-DS 2.0 (benchmark standard for decision support on relational and non-relational database systems), and the TPCx-IoT (benchmark standard for IoT gateway systems). In line with the increasing use of virtualization in both private and public clouds, the TPC developed a complete end-to-end virtualization benchmark, TPCx-V.

 

So, what is TPCx-V designed for? It measures the performance of a server running virtualized databases, and models many properties of virtualized servers including: multiple virtual machines (VMs) running at different load levels, online transaction processing workloads, and decision support system workloads. It uses databases of different sizes and load levels, and simulates large fluctuations in the load levels within virtual machines mirroring real-life load elasticity.

 

I am a big fan of talking about the industry’s best and first-ever. For those who follow the evolution of database technologies and industry standards, I want to highlight some historical data: the first TPC-C1 and TPC-D2 results were published by IBM; the first TPC-H3 was published by Sun; more recently, the first TPCx-HS4 and TPCx-IoT5 were published by Cisco.

 

Today, it is my great pleasure to jointly announce the industry’s first ever TPCx-V result. The result was produced using an AMD EPYC™ processor in a Dell EMC server running VMWare.

 

The benchmark configuration consists of one Dell EMC PowerEdge R7415 with one AMD EPYC 7551P processor (32 core/64 threads), 256 GB DDR4 RAM (2400 Mhz) running VMware ESXi 6.5.0 U2 GA. The TPCx-V throughput performance is 541.5 tpsV and price/performance is 57.31 tpsV/$. The results were audited by a TPC certified auditor. The full disclosure report can be found here.

 

Standards-based architectures continue to be the platforms of choice in both private and public clouds, and now AMD has brought choice back to the marketplace. AMD EPYC™ processors offer not only an industry standard based architecture, but many innovations for performance, density and security. I encourage you to learn more about AMD EPYC™ processors in virtualized environments and consider AMD for your next datacenter upgrade cycle.

 

Click here for more information about AMD’S innovative new EPYC™ processors

Click here for more information about TPC

 

Footnotes:

  1. First TPC-C publication: 54 tpmC, $188,562/tpmC, 12/1995, IBM. Fastest as of today: 30,249,688 tpmC, $1.01/tpmC, 12/2010, Oracle
  2. First TPC-D publication: 84 QthD, $52,170/QphD, 09/1992, IBM
  3. First: TPC-H publication 1,280 QthH, $816/QphD, @100GB, 09/1999, Sun. Fastest as of today: 11,612,395 QphH, $0.37/QphH @100TB, 9/2014, Dell
  4. First TPCx-HS publication: 5.07 HSph,$121,231.76/HSph @1TB, 1/2015, Cisco. Fastest as of today: 23.42 HSph, $36,800/HSph @30TB, 10/2015, Cisco
  5. First TPCx-IoT publication: 142,493.85 IoTps,$0.94/ IoTps, 11/2017, Cisco

 

Raghu Nambiar is Corporate Vice President & CTO, Datacenter Ecosystem & Application Engineering for AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.  GD-5