Skip navigation

Radeon Pro Graphics

12 Posts authored by: deneffe Employee

AMD has been a proud supporter of the Dassault Systèmes user community. Most recently, AMD participated in the COE Annual Experience and TechniFair receiving great feedback from attendees.

 

This month AMD will again have the opportunity to showcase purposeful solutions for the user community at COExperience 2019 in New Orleans, Louisiana. In booth #118, AMD will demonstrate both private cloud workstation solutions as well as public cloud scenarios. Amazon Web Services (AWS) is the featured cloud provider for AMD at this particular event.

 

 

 

I’ve spoken with a variety of users about the benefits of cloud-based workstation computing and it boils down to the following:

  • Mobility – AMD and cloud-based computing allow users to run applications, such as 3DEXPERIENCE CATIA, on almost any device, anywhere there's a network connection, be it a soccer game, coffee shop, office, conference room, customer site or other necessary venue;
  • Flexibility - Enterprises that have deployed applications such as 3DEXPERIENCE CATIA often staff-up or staff-down depending on the project. Rather than ship workstations all over the world to new CAD engineers to build a particular product, companies can send those engineers a link to an AWS instance knowing the results will be on par with expectations;
  • Security - As you can imagine the datasets that these engineers work with -- whether it's an airplane or automobile, or high priced-piece of equipment like a tractor -- need to stay secure and centralized in one location rather than being pushed to edge devices. The benefit of cloud-based computing keeps the data safe from thieves, hackers or other bad actors.

 

I always tell customers and event attendees that cloud-computing is the optimal space for workstation computing. They have the ease of set-up matched with always having access to an extreme set of hardware, mixing and matching different instances on CPU and GPU – making sure each instance runs correctly, without sinking valuable budget funds into extra equipment.

 

AMD also plans to present during the conference in a session called Delivering 3DExperience from the Cloud. The purpose of the presentation is to showcase 3DEXPERIENCE CATIA performance from the cloud specifically with AWS powered by AMD hardware.

 

AMD will also showcase wireless VR use in a technology demonstration with the new version of 3DEXPERIENCE CATIA that allows for interaction with the datasets in VR. AMD Radeon™ Pro Software for Enterprise 19.Q1 enables workstation-grade wireless VR on Radeon™ VR Ready Creator graphics cards, ready to support the upcoming release of AMD Radeon™ Pro ReLive for VR for standalone headsets with 6DoF Technology*.

 

To show our commitment to the community, AMD is a sponsor of Leaders’ Summit at COExperience. AMD supports transformation leaders and decision-makers of COE member organizations as they discuss how technological, cultural and industry-based disruptions are changing the way products are designed and delivered.

 

 

As reminder for those of who will be in New Orleans the week of February 24-27, AMD will be at COExperience in booth #118.

 

We look forward to seeing you there!

 

Michael DeNeffe is Director of Cloud Graphics 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

 

* Radeon VR Ready Creator Products are select Radeon Pro and AMD FirePro GPUs that meet or exceed the Oculus Rift or HTC Vive recommended specifications for video cards/GPUs. Other hardware (including CPU) and system requirements recommended by Oculus Rift or HTC Vive should also be met in order to operate the applicable HMDs as intended. As VR technology, HMDs and other VR hardware and software evolve and/or become available, these criteria may change without notice. PC/System manufacturers may vary configurations, yielding different VR results/performance. Check with your PC or system manufacturer to confirm VR capabilities.  GD-101

Capture.JPG

[Originally posted on 03/23/17]

 

AMD and Citrix® collaborate to deliver performance, scalability, security, and availability of virtualized graphics from both public and private clouds.

 

Virtualized graphics is the last piece of the puzzle for enterprises considering remote workstations or VDI environments. AMD Multiuser GPU (MxGPU) technology is virtualized graphics done right as shared GPU capability is built right into the silicon, helping make it more secure than software virtualization. This approach delivers a consistent, predictable, and cost effective deployment and user experience.

 

AMD and Citrix have been hard at work enabling MxGPU for Citrix HDX™ and we are happy to announce that with Citrix XenApp® and XenDesktop® 7.13, AMD MxGPU is fully integrated and available. You can download our Radeon Pro Software drivers with HDX support now.

 

The combination of these technologies from Citrix and AMD gives IT departments the cost-effective performance and scalability necessary to deliver graphics-accelerated virtual desktops and apps to virtually any user, from knowledge workers, to mobile professionals, to designers expecting the same access to the GPU no matter their workload.

 

This latest announcement by Citrix continues AMD’s momentum in cloud graphics. Enterprises can deploy AMD MxGPU on a number of server platforms from Dell, HP Enterprise, and Supermicro. Combined with our announcements from Google and Alibaba Cloud, our engagement with Citrix demonstrates how hardware-based graphics virtualization can lead the market in performance, scalability, security and availability of virtualized graphics from both public and private clouds.

 

AMD’s vision is that end users want to run their applications on virtually any device, virtually anywhere with confidence. This vision is coming to life with AMD MxGPU on Citrix. Look for more exciting news about AMD hardware-virtualized graphics in the months to come.

 

For more information about AMD Virtualized Graphics and Citrix, please visit www.amd.com/citrix.

 

For more information about AMD MxGPU technology, please visit www.amd.com/mxgpu.

 

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.

Capture.JPG

[Originally posted on 06/07/17]

 

AMD is excited to announce that Citrix’s new hypervisor, XenServer 7.2, supports Radeon™ Pro MxGPU (multiuser GPU) in a technology preview. This means that enterprises can preview our AMD FirePro™ S7150x2 GPUs in virtual desktop infrastructures (VDI). To show it off, AMD was at Citrix Synergy 2017 in Orlando, Florida. In our booth was the first public demonstration of XenServer 7.2 running on AMD GPUs. Not only did we show the power and performance of our GPU technology, but did it from 1092 miles away. You see, the demonstration was delivered from a datacenter outside of New York City by AMD technology partner IMSCAD.

 

The demo was awesome! The complete capabilities of Autodesk apps, Revit, Inventor and AutoCAD were shown off with our AMD FirePro S7150x2 card in an HPE ProLiant DL380 server from IMSCAD’s New York datacenter. Running on Citrix XenServer 7.2, our MxGPU delivered full workstation class performance while being shared four users per GPU. At the other end of the wire, over 1000 miles of it, was an HPE t620 Thin Client powered by AMD Quad-Core APU. So a complete end-to-end AMD solution in full glory!

 

Our second demo was also extensively remote. Why lug heavy and loud servers to a trade show, when you can show off the AMD’s great technologies from a datacenter. In this demo we ran VMware ESXI 6.5 on a Dell PowerEdge R730 server installed with an AMD FirePro S7150x2. Splitting the GPU by 8 users, we delivered a workstation-class experience for Solidworks 2017. Over 440 miles it ran, to the booth at Synergy to an IGEL thin client also powered by an AMD Quad-core APU. So here’s the net/net: AMD end-to-end, hardware virtualized graphics running XenServer 7.2, workstation performance from the datacenter, delivered elegantly to AMD-powered thin clients. What’s not to love?

 

synergy-booth2.jpg

 

Interested?

Any customer who is eligible to upgrade to XenServer 7.2 can start their testing with any host that supports the AMD FirePro™ S7100-series GPUs. To enable XenServer, click here to check out the download and associated release notes. You will also find details via this link on how to submit bugs.

 

To use Citrix XenServer with AMD MxGPU virtualized graphics technology you will need to download the XenServer GIM Driver and the Radeon™ Pro Software Beta here. You will also find the Citrix Deployment Guide on this page. Be sure to give us your feedback!

 

Check out IMSCAD at http://www.imscadglobal.com/article-poc.php and EpiGrid at http://epigrid.com/

 

citrix.jpg

Follow Radeon Pro on Twitter for the latest on virtualization.

 

*Palatov D2 design shown in the images is property of Palatov Motorsport LLC, used with permission.

 

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.

Capture.JPG

[Originally posted on 02/01/18]

 

The talents of Citrix partners are as wide-ranging as the solutions they provide. Systems integrators, Citrix resellers, application developers and service providers for Citrix products have a tribal gathering each year at Citrix Summit. This year in Anaheim, California, AMD joined the party to demonstrate our support for Citrix solutions and collaborate with Citrix partners to deliver graphics from the cloud.

 

It was clear enterprise customers want virtualized graphics solutions that deliver a high performance, advanced security and consistent user experience at a lower total cost of ownership. This aligns with the value proposition that AMD MxGPU (multiuser GPU) offers to the Citrix install base and the partners that support them.

 

5-Details-About-GIM-Open-Source-Infographic_1080p-1075x700.jpg

At Citrix Summit, we demonstrated 2 key use cases. First an application remoting solution with XenApp 7.15 running on Windows Server, delivering a pristine version of Autodesk Inventor from a server outside of New York City. Application remoting is seeing a comeback, we believe, and AMD MxGPU is there to support these use cases.

 

We also showed XenDesktop 7.15 running on VMware ESXI 6.5. Delivering Windows 10 desktops from the cloud is the new first order of business for many enterprises. Empowering demanding users running design and engineering apps is job one for many enterprise IT teams. AMD is there to support this effort.

 

For more information about AMD MxGPU go to the links below:

 

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.

Capture.JPG

[Originally posted on 02/14/18]

 

Open for Business. The Collaborative Cloud.

 

At AMD, open source is in our DNA. We have a legacy of sharing and contributing to open source projects, applications and supporting industry standards. Our goal is to raise the tide for developers and users, enabling open choice across the board.

 

In this vein, I am excited to announce the availability of our Virtualized Graphics KVM host driver to the open source community. You can pick it up now at: AMD Drivers and Support.

 

AMD has made significant progress with our virtualized graphics business in 2017. Many server design wins, and our announcement with Amazon Web Services, illustrates the use of our GPUs running virtually with distributed workloads among multiple users, delivering a consistent solution with great security features for customers.

 

In a day and age where other companies are requiring proprietary software to run virtual environments and then further charging end user licenses, AMD is going the opposite direction. We embrace open source as a way to promote collaboration and sharing, but most of all, to enable our customers, from cloud providers to server manufacturers, to build products that delight their customers.

 

So join us in our quest to build a collaborative cloud. Download our open source host driver now and build a GPU environment in the cloud to make your customers happy.

 

5-Details-About-GIM-Open-Source-Infographic_1080p-1075x700.jpg

 

To get the driver go here

For other AMD open source programs go here: GPUOpen

For more information on AMD Virtualized GPUs go here

 

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.

Capture.JPG

[Originally posted on 02/28/18]

 

AMD MxGPU graphics virtualization technology enables leading Quality of Service (QoS) with performance that is up to nine times more consistent than the competition1.

 

Reliable, predictable infrastructure is paramount in an enterprise environment. IT managers demand robust QoS to meet the needs of a cloud-connected workforce. AMD Multi-User GPU (MxGPU) technology was designed to meet this demand by delivering a predictable and consistent end-user experience.

 

3.jpg

 

A predictable graphics experience for digital workspaces yields value across an organization. IT managers get fewer calls probing unexpected slowdowns. End users know how their workflow will behave and the Program Management Office can practice better business planning through predictable resource allocation.

 

As more independent software vendors adopt GPU acceleration to provide a richer experience for end-users, GPU-bound QoS will continue to be top-of-mind for enterprise data centers. AMD MxGPU technology offers an elegant solution, enabling world class QoS with AMD FirePro™ S7100-series graphics accelerators.

 

AMD MxGPU technology, the world’s first hardware-based virtualized GPU solution, is built on industry standard SR-IOV (Single-Root I/O Virtualization) technology and allows up to 16 virtualized users per physical GPU to work remotely.

 

To learn more about the QoS benefits AMD MxGPU technology brings to your data center, check out the infographic below.

 

5-Reasons-AMD-MxGPU-Graphics-Virtualization-Technology-Delivers-Leading-QoS-Infographic_4K_FIXED.jpg

 

Visit our page on AMD MxGPU technology and download our QoS whitepaper.

 

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.

 

 

 

 

FOOTNOTES

1 - With 16 virtual machines, AMD FirePro™ S7150 x2 delivers up to 9x lower standard deviation in SPECapc® for SOLIDWORKS® 2015 than NVIDIA® Tesla M60, derived using Graphics Composite Scores from SPECapc® for SOLIDWORKS® 2015. Testing conducted by AMD Performance Labs as of August 1st, 2017 under following host and virtual machine configuration: Host: VMware® ESXi™ 6.5.0 with host driver Radeon™ Pro VMware vSphere® Driver – Revision 1.02/NVIDIA® VMware® ESXi™ 6.5 Host Driver 367.106. Virtual Machines: Intel(R) Xeon(R) E5-2698 v4 @2.20 GHz, 4 Cores, 4 Logical Processors, 8GB Physical Memory, 120 GB Storage, Windows 7 Enterprise 64-bit SP1 Build 7601 with Radeon™ Pro Software 17.30 driver/NVIDIA® GRID 370.12 guest graphics driver. Benchmark: SPECapc® for SOLIDWORKS® 2015 simultaneously on 16 virtual machines. NVIDIA® GRID vGPU configuration: Each VM has 1 vGPU assigned from NVIDIA® GRID M60-0Q profile (16 vGPU on a physical GPU). AMD MxGPU configuration: Each VM has 1 vGPU assigned from 16 VFs configuration (16 vGPU on a physical GPU). AMD Graphics Composite Scores, Enumerated Per Virtual Machine Instance: 0.32, 0.32, 0.32, 0.33, 0.32, 0.32, 0.32, 0.33, 0.32, 0.32, 0.32, 0.32, 0.33, 0.32, 0.32, 0.32. NVIDIA® Graphics Composite Scores Results, Enumerated Per Virtual Machine Instance: 0.41, 0.37, 0.31, 0.32, 0.37, 0.32, 0.32, 0.31, 0.37, 0.33, 0.41, 0.29, 0.33, 0.39, 0.33, 0.37. AMD FirePro™ S7150 x2 standard deviation of the Graphic Composite scores: 0.00390. NVIDIA® Tesla M60 standard deviation of the Graphic Composite scores: 0.03618. Performance Differential: 0.03618/0.00390 = ~9.27x higher standard deviation on NVIDIA® Tesla M60. Additional information about the SPEC benchmarks can be found at www.spec.org/gwpg. PC and server manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers. RPW-177

© 2018 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo, Radeon, and combinations thereof are trademarks of Advanced Micro Devices, Inc. SPEC® and the benchmark SPECapc® are registered trademarks of Standard Performance Evaluation Corporation. Other product names used in this publication are for identification purposes only and may be trademarks of their respective companies.

Capture.JPG

[Originally posted on 05/07/18]

 

A couple of weeks ago I had the pleasure of attending the Dassault COE (Community of Experts) 2018 Annual Experience and TechniFair in San Diego.

 

This event had a particularly exciting vibe for me as it was packed with genuine end-users of the full Dassault portfolio including CATIA, SOLIDWORKS, SIMULIA, ENOVIA and DELMIA. Also attending were a lot of AMD software and hardware partners.

 

It was a wonderful opportunity to look at the overall solutions our products enable within the wider ecosystem while focussing on those Dassault users.

 

It was very insightful to hear about real deployments where our AMD products have been used across PLM deployments to enable a wide range of use cases including:

 

  • Interactive 3D rendering
  • Cloud delivered CAD
  • Mobile and thin-client end points

 

Our stand was busy, we were showing CATIA delivered from the cloud and 3D Interactive rendering on HP and Dell. There’s a bit more information about our collaboration with Dassault in this area in this case study.

 

Capture1.JPG

 

Surprisingly we were the only GPU vendor exhibiting, so we attracted a large audience. It was great though to be amongst the full spectrum of the Dassault PLM ecosystem rather than a generic cloud or security conference. Major companies present at the show included HP, Dell and Cisco servers and workstations, to Dassault end-customers like Boeing, Proctor and Gamble and Textron.

 

My speaking session covered “CATIA from the Cloud”, delivering CATIA from the datacenter with virtualized desktops, and the virtualized graphics considerations for the next generation of 3DExperience and PLM deployment, alongside some details of our S7150 products and MxGPU (shared GPU) technologies.

 

20180416_140027-1088x700.jpg

 

This session was particularly insightful because were joined by Keith Horton from Nordam Aerospace, past president of the COE, who described their virtualized CATIA deployment using Cisco C240M5 servers, AMD FirePro™ S7150x2 server GPUs, Citrix XenServer 7.4 with MxGPU capability, and NICE DCV to manage multiple customer design environments and gain benefits in security, remote working and hardware consolidation.

 

I found it exciting to see how Dassault users are integrating growing technologies into their processes, especially in areas where we at AMD are also investing in GPU applications such as VR/AR (Virtual / Augmented reality) and to support the demands of generative design for uses such as additive manufacture. During the event a new VR and AR Committee within COE was announced, and I think the discussions that will emerge will be worth watching.

 

If you missed it, it’s worth pencilling it in for next year and checking out the great recap on the COE website.

 

Last, for those of you in Southern California the week of May 8-10, we will be at Citrix Synergy.

 

Where we’ve partnered with HP in booth #311, where we plan to be showcasing graphical applications such as Solidworks, Autodesk Revit and AutoCad delivered from the cloud to HP thin-clients optimized for Citrix deployments with AMD Embedded APUs.

 

Hope to see there!

 

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.

Capture.JPG

[Originally posted on 06/01/18]

 

Collaboration is the engine for our industry. When companies work together to solve a problem or build something new, magic happens.

 

This is why I am extremely excited to participate in a collaboration between my company, AMD, Amazon Web Services and Siemens. The result of our work will be on full display at Siemens PLM Connections in Phoenix from June 5 to 7.

 

We’ve built a way to deliver graphics accelerated, Siemens NX from Amazon AppStream 2.0. With this solution, Siemens NX designers and engineers can build and create their models remotely, keeping huge data sets centralized and secure in the Amazon cloud. Workflows are optimized, teams can collaborate and the cost to manage infrastructure are lowered.

 

If you are at the show, make sure to attend my session on Tuesday, June 7 at 3pm. I am co-presenting with Paul Brown, Director of Marketing for Siemens NX. We will demonstrate the power and performance of Siemens NX running from Amazon AppStream 2.0 powered by AMD GPUs.

 

Also, drop by the AMD booth where we will give you a hands-on experience of this solution, plus a technical demo of Siemens NX running on AWS Elastic GPU and delivered with the AWS DCV client.

 

Looking forward to seeing you at the show.

 

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.

Capture.JPG

[Originally posted on 08/29/18]

 

AMD is the only company in the world that offers both world-class server CPU and GPU technologies. In the enterprise and cloud spaces those technologies come in the form of our AMD EPYC™ CPUs and our AMD Radeon™ Pro GPUs. Inside AMD, we call this combo A + A.

 

A_plus_A.JPG

For the datacenter market, A + A is akin to two great musicians with different styles, teaming up as a duet to make something magical. Like David Bowie and Freddie Mercury in the song “Under Pressure”.

 

At VMworld 2018 in Las Vegas in the AMD booth, we demonstrated how A + A makes an astounding duet. For the first time, we showed a technology demonstration of a virtualized environment driven by an HPE ProLiant DL385 Gen10 from AMD’s Santa Clara, CA datacenter. Inside, the server we have two 32 core, 64 thread Epyc CPUs and a recently announced dual GPU solution based on the “Vega” architecture1, the Radeon Pro V340. The result, an awesome system for virtualized workloads. And a GPU that delivers 33% greater user density than our competition3.

 

Also, in the booth was our A + A gorilla. It’s a dual Epyc server with 4 Radeon Pro V340s. 8 GPUs (2 per card), each with 56 compute units4 thumping graphics and supported by 2 Epyc 32 core CPUs.

 

IMG_0869.jpg

 

Stop to think about the possibilities of this system in a VDI environment. Each GPU can support 32 VMs, each with 1 GB of ultra-fast memory. That’s 128 workstation-class users per server. Match that with 2 Epyc processors with a combined 64 CPU cores and 128 threads and you get a balanced, beast of a system.

 

And we doubled down on security. Both pieces of silicon brilliance come equipped with security solutions. The Secure Encrypted Virtualization engine on the Epyc CPU and a built-in security processor in our dual Vega, Radeon Pro V340 GPU.

 

Exciting stuff. An astounding solution for virtualized workloads. All AMD, all was on display at VMworld.

 

 

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.

 

 

 

 

 

FOOTNOTES

1. “Vega” is a codename for AMD architecture, and is not product name. GD-122

2. Estimates based on SPECfp®_rate_base2017 using the GCC-02 v7.2 compiler. AMD- based system scored 201 in tests conducted in AMD labs using an “Ethanol” reference platform configured with 2 x AMD EPYC 7601 SOC’s ($4200 each at AMD 1 ku pricing), 512GB memory (16 x 32GB 2R DDR4 2666MHz), Ubuntu 17.04, BIOS 1002E. Intel- based Supermicro SYS-1029U-TRTP server scored 164 in tests conducted by AMD, configured with 2 x 8160 CPU’s (2 x $4702 each per ark.intel.com), 768GB memory (24 x 32GB 2R DDR4 2666MHz), SLES 12 SP3 4.4.92-6.18-default kernel, BIOS set to Extreme performance setting. NAP-77

3. The AMD Radeon™ Pro V340 graphics card supports up to 32 virtual users with 1GB memory profiles per card. The NVIDIA Tesla P40 supports up to 24 virtual users with 1GB memory profiles per card. AMD user density advantage 32/24 = up to 33% greater.

4. AMD Radeon™ and FirePro™ GPUs based on the Graphics Core Next architecture consist of multiple discrete execution engines known as a Compute Unit (“CU”). Each CU contains 64 shaders (“Stream Processors”) working together. GD-78

Capture_Nov9.JPG

 

[Originally posted on 08/24/18]

 

At AMD, we work hard to solve hard problems. And nothing is more gratifying than to deliver on our mantra “build great products.” The Radeon™ Pro V340 is our latest chapter in bringing to market solutions that solve tough challenges.

 

 

In this case, its datacenter graphics. Those GPUs in private or public clouds that handle the acceleration for visualization workloads for engineers, creators, designers and architects. These are professionals that pride themselves on being builders. We built the V340 for builders.

 

RadeonV340_FrontAngle_RGB_5inch-300x175.png

The V340 is a beast. Its a dual-GPU solution based on the advanced AMD “Vega” architecture1, optimized to deliver extreme performance and high user density for virtualized environments. It is the first VDI hardware solution equipped with 32GB of ultra-fast, second-generation high-bandwidth memory, providing massive amounts of memory and bandwidth for today’s most complex design and media workloads.

 

At VMworld 2018 in Las Vegas we unleashed the beast and gave attendees a demonstration of the industry’s only hardware-based GPU virtualization solution enabled by SR-IOV (Single root – IO Virtualization). We even paired the V340 with a 32 core AMD Epyc CPU for the first time, giving the world a glimpse of what can be build with massive amounts of CPU cores and GPU compute units.

 

The V340 hardware combined with our software stack comprises AMD’s MxGPU technology. MxGPU stands for multi-user GPU and it does just that. It lets multiple users share a high performance GPU giving them highly secure, deterministic workstation-class performance, delivered from the cloud. With 2 GPUs pounding on 32 GB of HBM2 framebuffer, it supports up to 32 users per card, enabling density and scalability that is second to none.

 

 

So, if you are a builder, consider a tool built just for you. The AMD Radeon Pro V340.

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.

 

 

 

FOOTNOTES

1. “Vega” is a codename for AMD architecture, and is not product name. GD-122

2. The AMD Radeon™ Pro V340 graphics card supports up to 32 virtual users with 1GB memory profiles per card. The NVIDIA Tesla P40 supports up to 24 virtual users with 1GB memory profiles per card. AMD user density advantage 32/24 = up to 33% greater.

Radeon-Pro-MxGPU-unified-driver-blog-title-image.jpg

[Originally posted on 04/04/17]

 

Effortlessly run professional applications on both physical and virtual machines with the unified Radeon Pro Software Enterprise Driver and manage AMD MxGPU’s at the host and datacenter level with Radeon Pro Settings for VMware.

 

Today’s professionals don’t want their creativity constrained by where they are or what device they are working on, and want the freedom to work remotely without compromise. In parallel, businesses are looking for solutions that improve productivity by making their IT easier to manage and more secure, all with a lower total cost of ownership.

 

AMD’s MxGPU (Multiuser GPU) virtualized graphics addresses all these needs, delivering workstation-class graphics from the data center to virtually any device, virtually anywhere. In addition, virtualization helps ensure that sensitive IP remains secure in the data center, rather than residing outside the firewall on devices that could potentially be compromised.

 

Radeon-Pro-MxGPU-infographic_1920-1176x700.jpg

AMD’s MxGPU, the world’s first hardware virtualized GPU solution, is built on industry standard SR-IOV (Single-Root I/O Virtualization) technology and allows up to 16 virtualized users per physical GPU to work remotely. Unlike software virtualization offerings, AMD’s scalable VDI (Virtual Desktop Infrastructure) technology better protects valuable data by using a dedicated share of local memory for increased security.

 

Deterministic Performance and Unified Driver

 

In combination with Radeon Pro Software, AMD MxGPU virtualized graphics has deterministic performance – delivering the same performance across multiple virtual desktops with the SPECapc® SOLIDWORKS benchmark, while the performance difference between virtual machines using a competing solution is up to 68%1.

 

 

Bringing the power of a physical GPU to virtual environments, AMD MxGPU virtualized graphics uses the unified Radeon Pro Software Enterprise Driver 17.Q1.1 which lets users effortlessly run professional applications on both physical and virtual machines. That means there are virtually no limits what can or can’t be done in VDI, with full OpenGL®, DirectX®, and OpenCL™ acceleration and full ISV certification for Dassault Systèmes SOLIDWORKS®, PTC Creo®, Siemens® NX™, and more.

 

AMD MxGPU virtualized graphics delivers superior performance over the competition in these applications too, with up to 35% faster performance in SOLIDWORKS2, up to 38% faster performance in PTC Creo3, and up to 156% faster performance in Siemens NX4.

 

Radeon Pro Settings for VMware vCenter

 

With support for VMware® vSphere® 6.0 and higher, system admins will love how easy AMD MxGPU virtualized graphics is to set up. The new Radeon Pro Settings for VMware seamlessly integrated into VMware vCenter allows for management of physical GPUs at the host and datacenter level with a simple and intuitive interface.

 

 

Admins can quickly set up a VDI environment, rapidly deploy virtual GPUs to existing virtual machines, and enable hundreds of professionals with just a few mouse clicks depending on the number of GPUs in the system configuration.

 

Pure Virtualized Graphics

 

AMD MxGPU enables pure virtualized graphics, keeping it simple, secure and easy to set up with predictable performance. When combined with the unified Radeon Pro Software Enterprise Driver and Radeon Pro Settings for VMware, AMD makes it easy for IT to choose one flexible, scalable solution to meet a business’s virtualization needs. The best part is there are absolutely no hardware user licensing fees.

 

The unified Radeon Pro Software Enterprise Driver 17.Q1.1 is available here.

 

Radeon Pro Settings for VMware vSphere Client is available here.

 

To learn more, go to www.amd.com/vdi

 

 

 

 

 

FOOTNOTES

1. With driver 16.50, FirePro™ S7150 x2 MxGPU delivers same performance across VMs on SPECapc SOLIDWORKS benchmark, while the performance difference between VMs on Nvidia GRID for Tesla M60 is up to 68%. Testing conducted by AMD Performance Labs as of January 10th, 2017, under following configuration: Host: VMware ESXi 6.5.0. Virtual Machine: Intel Xeon E5-2650 v3 @2.30 GHz, 4 Logical Processors, 8 GB Physical Memory, 120 GB Storage, Windows 7 Ultimate 64 Bits SP1 Build 7601, 16.50 graphics driver for AMD FirePro™ S7150 x2 and 369.17 for Nvidia Tesla M60. For both AMD FirePro™ S7150 x2 and Tesla M60, only one physical GPU was involved for the benchmark. Tesla M60 was configured to use the 2Q profile. S7150 x2 MxGPU virtual GPU number was set to be four. In both configuration, one of the physical GPU is split into four virtual GPUs and assigned to four independent VMs. Another physical GPU is remained unused. The configurations for Tesla M60 and AMD FirePro™ S7150 x2 are equivalent. Benchmark Application: SPECapc SOLIDWORKS benchmarks under M60-2Q profile/AMD FirePro™ 7150 x2 MxGPU – 4 virtual GPUs configurations. AMD FirePro™ S7150 x2: Highest graphics composite in four VMs: 2.43. Lowest graphics composite in four VMs: 2.43. Performance difference: 2.43/2.43 = ~0%. Tesla M60: Highest graphics composite in four VMs: 2.67. Lowest graphics composite in four VMs: 1.59. Performance difference: 2.67/1.59 = ~67.92% difference. PC and server manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers. FP-211

2. AMD FirePro™ S7150 x2 delivers up to 35% faster performance on SPECviewperf 12.1 SOLIDWORKS benchmark than Nvidia Tesla M60. Testing conducted by AMD Performance Labs as of January 10th, 2017, under following configuration: Host: VMware ESXi 6.5.0. Virtual Machine: Intel Xeon E5-2650 v3 @2.30 GHz, 4 Logical Processors, 8 GB Physical Memory, 120 GB Storage, Windows 7 Ultimate 64 Bits SP1 Build 7601, 16.50 graphics driver for AMD FirePro™ S7150 x2 and 369.17 for Nvidia Tesla M60. Benchmark Application: SPECviewperf 12.1 SOLIDWORKS test under single GPU pass-through. AMD FirePro™ S7150 x2 graphics composite: 68.05. Tesla M60 graphics composite: 50.4. Performance Differential: 68.05/50.4 = ~35.02% higher score on AMD FirePro™ S7150 x2. PC and server manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers. FP-208

3. AMD FirePro™ S7150 x2 delivers up to 38% faster performance on SPECviewperf 12.1 PTC Creo benchmark than Nvidia Tesla M60. Testing conducted by AMD Performance Labs as of January 10th, 2017, under following configuration: Host: VMware ESXi 6.5.0. Virtual Machine: Intel Xeon E5-2650 v3 @2.30 GHz, 4 Logical Processors, 8 GB Physical Memory, 120 GB Storage, Windows 7 Ultimate 64 Bits SP1 Build 7601, 16.50 graphics driver for AMD FirePro™ S7150 x2 and 369.17 for Nvidia Tesla M60. Benchmark Application: SPECviewperf 12.1 Creo test under single GPU pass-through. AMD FirePro™ S7150 x2 graphics composite: 42.64. Tesla M60 graphics composite: 30.8. Performance Differential: 42.64/30.8 = ~38.44% higher score on AMD FirePro™ S7150 x2. PC and server manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers. FP-210

4. AMD FirePro™ S7150 x2 delivers up to 156% faster performance on SPECviewperf 12.1 Siemens NX benchmark than Nvidia Tesla M60. Testing conducted by AMD Performance Labs as of January 10th, 2017, under following configuration: Host: VMware ESXi 6.5.0. Virtual Machine: Intel Xeon E5-2650 v3 @2.30 GHz, 4 Logical Processors, 8 GB Physical Memory, 120 GB Storage, Windows 7 Ultimate 64 Bits SP1 Build 7601, 16.50 graphics driver for AMD FirePro™ S7150 x2 and 369.17 for Nvidia Tesla M60. Benchmark Application: SPECviewperf 12.1 Siemens NX test under single GPU pass-through. AMD FirePro™ S7150 x2 graphics composite: 40.48. Tesla M60 graphics composite: 15.83. Performance Differential: 40.48/15.83 = ~155.72% higher score on AMD FirePro™ S7150 x2. PC and server manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers. FP-209

SPEC® and the benchmark name SPECapc® are registered trademarks of the Standard Performance Evaluation Corporation. For more information about SPECapc, see https://www.spec.org/gwpg/apc.static/sw2015info.html.

banner4-2.jpg

[Originally posted on 09/12/17]

 

It’s no secret that most enterprise applications, from standard Windows productivity apps to robust design and engineering apps, run best when they are GPU-accelerated. The number of applications needing graphics acceleration are accelerating rapidly.

 

So, the challenge is how to deliver these GPU-demanding apps to your most demanding users – CAD engineers, creators, and artists. This can be done locally, with high performance graphics on each workstation. However, this is expensive, and not every designer who could benefit from a graphics workstation may get one. Also, the large datasets – design files and creative drawings, accessed by these users are saved locally or on a file share. This raises security headaches, and challenges IT governance requirements.

 

Now, remote delivery for graphics from the cloud addresses these challenges. Apps are executed in the cloud and delivered remotely. Also, data can be stored centrally, and securely, right next to where apps are executed in the cloud, providing great performance for viewing and creating new designs on any device, anywhere on the network. I call this secure mobility.

 

Enabling secure mobility sounds great but doing it efficiently and cost effectively can be a challenge. This is where Amazon Web Services (AWS) and AMD come in.

 

I’m thrilled that AWS has chosen AMD Radeon Pro MxGPU (multiuser GPU) technology for their new Graphics Design instance type on Amazon AppStream 2.0. Amazon AppStream 2.0 is a fully managed, secure application streaming service that allows you to stream desktop applications from AWS to any device running a web browser, without rewriting them. The new Graphics Design instance type runs on our S7150x2 GPU, the virtualized graphics workhorse of our Radeon Pro graphics product. With Graphics Design instances, users can run graphics-accelerated applications at a fraction of the cost of using graphics workstations and can lower the cost of streaming a graphics app on AppStream 2.0 by up to 50%. These instances are ideal for delivering applications that rely on hardware acceleration of DirectX, OpenGL or OpenCL, such as Adobe Premiere Pro, Autodesk Revit or Siemens NX.

 

Net/Net: users get professional grade graphics, on-demand, for accelerated apps, at a lower cost. And since they are delivered from the cloud, secure mobility is now a reality.

 

Radeon Pro graphics include professional graphics products such as Radeon Pro WX Series, Radeon Pro SSG, Radeon Pro Duo as well as legacy product solutions such as AMD FirePro, ATI FirePro, ATI FireMV, ATI FireGL and ATIFireStream.

 

For more information about AMD’s graphics virtualization solutions go to:

 

MXGPU TECHNOLOGY CLOUD SERVICE PROVIDERS

 

Or find out more about Amazon AppStream 2.0 powered by AMD at these links:

 

APPSTREAM 2.0 PRICING DETAILS FAQS AWS: WHAT'S NEW TWITTER FACEBOOK YOUTUBE LINKEDIN

 

 

Michael DeNeffe, AMD’s Director of Cloud Graphics and has extensive experience in network computing, and client device technologies. Links to third-party sites and references to third-party trademarks are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third-party endorsement of AMD or any of its products is implied. Use of third-party names or marks is for informational purposes only and no endorsement of or by AMD is intended or implied.