Ubitus’ GameCloud solution is designed to deliver instant console-level gaming experiences on demand without the need for high-end computers or game consoles. The solution will be demonstrated at Computex 2015 in Taipei (June 2-6). Ubitus will use an AMD FirePro W7100 based server running games on a wide range of devices including TV, set-top-boxes, Mac, PC, tablets and Smartphones.
Game titles will be presented in the exhibition including “Lego: Marvel Super Heroes”, “Middle Earth: Shadow of Mordor” and “Injustice: Among the Gods” from Warner Bros that usually require high-end hardware to play.
At NAFEMS World Congress 2015 (June 21-24), Leonard Hoffnung from Siemens PLM Software, will discuss how GPUs and heterogeneous computing can be used to accelerate NX Nastran modal frequency response analysis for a Noise, Vibration, and Harshness application typical in the automotive industry.
Heterogeneous computing, or the use of GPU accelerators together with conventional single- or multiple-CPU systems, has become increasingly prevalent over the last decade. Heterogeneous systems have gained popularity, as they offer much higher theoretical flop rates compared with conventional workstations. However, successfully utilizing heterogeneous systems to improve the performance of engineering applications can be challenging.
In this paper, we examine a new method to utilize heterogeneous computing with multiple GPUs in a typical auto industry NVH (Noise, Vibration, and Harshness) application, modal frequency response analysis. Demands for improved fidelity have led to large and computationally expensive modal frequency response jobs over large frequency ranges. As problem sizes have increased, the dominant cost in a modal frequency response job has shifted from eigensolution to the frequency response calculation itself. Accordingly, we present a method to improve performance using multiple GPUs to target the frequency response calculation. The method takes advantage of multiple GPUs while minimizing inter-process communication for best efficiency. Two examples demonstrate the effectiveness of the method. The first illustrates the speedup potential with multiple GPUs in the response calculation specifically. The second example shows the performance impact of the improved response calculation, in the context of a complete industrial frequency response analysis.
AMD recently presented their data center roadmap for 2015-2016 and one stand out was the plans for for a “high-performance server APU”. AMD already has a strong presence in the high performance server market with the FirePro S-series, in particular the S9150 for HPC and VDI.
At their financial analyst day presentation, AMD outline a roadmap to develop a high-performance server APU that will offer multi-teraflops performance closer to the performance of the FirePro S-series GPUs, but all on a single CPU/GPU chip.
AMD FirePro and the SolidWorks team have collaborated in SolidWorks 2015 and now SolidWorks 2015 to bring OIT (order independent transparency) to designers and engineer. OIT introduced in SolidWorks 2014 fixes visual artifacts caused by inaccurate “depth sorting” of the geometry that often happens in the older “blended mode” and also provides up to 10X performance.
In SolidWorks 2015, OIT is used as a part and assembly preview from the feature tree (called Ghost Preview). This feature enables preview of one or more hidden bodies or components from the FeatureManager design tree, making it easier to find hidden parts. The information is stored on the GPU so it is very fast, making SolidWorks faster and easier to use. Without a FirePro card to run OIT, it take a lot longer to preview parts and assemblies.
In addition to OIT, the Geometry Boost feature on AMD FirePro WX100 series cards means FSAA (Full-Scene Anti-Aliasing) can now be turned on in SolidWorks permanently without significantly impacting the workflow. RealView is also enabled and significantly accelerated.
Want to learn more about using the new OIT, FSAA and RealView features in SolidWorks 2015, then check out the Develop3D Webinar May 14, 2015.
The International Workshop on OpenCL (IWOCL) is an annual meeting of OpenCL users, researchers, developers and suppliers to share OpenCL best practise, and to promote the evolution and advancement of the OpenCL standard.
At the upcoming Advanced Hands-On OpenCL Tutorial attendees will be able use their own laptops (Windows, Linux or OS/X) to log onto the HP ProLiant DL380 Gen9 server powered by an AMD FirePro S9150 server GPU running OpenCL 2.0.
The tutorial will use a mix of OpenCL’s C and C++ host APIs and focus on more advanced OpenCL concepts. The format will be a 50/50 split between lectures and exercises. Attendees will need to use their own laptops (Windows, Linux or OS/X) and either run locally or and log into the HP ProLiant DL380 Gen9 server powered by an AMD FirePro S9150.
This video from the Hannover Messe 2015 conference demos Sysgen’s remote graphics solution using 8 AMD FirePro R5000 cardd. This means that 8 Design and Engineering professionals can operate remotely from their thin or low power client PC/laptop and still operate with full 3D performance.
The demo shows a server hosting eight AMD FirePro R5000 cards running Solidworks and AutoCAD software accessed by the latest SAPPHIRE small format zero client using Terradici PC over Internet hardware. This configuration allows workstation performance to be accessed from anywhere, enabling workflows to be shared from different locations or with users in different time zone
A few weeks back AMD and HP announced that AMD FirePro S9150 server GPUs were an available configuration option for HP ProLiant DL380 Gen9, the world’s best-selling server. That combination targeted smaller deployments for academics and small business.
For organizations that want to build larger clusters, they can now get the power of AMD FirePro S9150 server GPUs on the HP XL250a Gen9 Server, designed to support larger clusters for high performance compute.
If you don’t recall, the AMD FirePro S9150 is the GPU that powered the most energy efficient supercomputer in the Green500). A single card breaks the 2.0 TFLOPS double precision barrier. With 16GB of GDDR5 memory and maximum power consumption of 235 watts, AMD FirePro S9150 server GPUs provide massive compute performance while helping maximize available power budgets.
In this video from NAB 2015, Mike Griggs demonstrates something amazing: A single Mac Pro can drive a seamless and simultaneous workflow between MODO, MARI and NUKE by using the dual AMD FirePro GPUs on the Mac.
As Mike points out, even as a model is polygon optimizing in MODO, he can still be working in MARI to work in the textures - all at the same time. Essentially he is running a 3-man workflow on just one one machine being controlled by one man!
This is a video worth watching to understand how to integrate MODO, MARI and NUKE and how they take advantage of AMD FirePro W-Series acceleration.
This out-take video from Post Magazine shows a clip from an interview with AMD FirePro’s Melanie Ball about what was exciting and new at NAB 2015.
Melanie talks about the collaboration partnership with Avid for Media Composer, which is now supporting AMD FirePro on Mac and Windows, as well as with The Pixel Farm for its OpenCL-acceleartd PFTrack software. She also describes OpenCL acceleration in Black Magic Davinci Resolve. The full interview can be viewed at http://www.postmagazine.com/Video-Center/NAB/PostTV-2015-AMD.aspx.
In this advanced, hands-on tutorial, we assume the attendee is already familiar with OpenCL, and has probably written at least one OpenCL program. The tutorial will focus on more advanced OpenCL concepts, such as:
Shipping kernel code,
Portable binaries with SPIR
OpenCL kernel compiler options
Optimised host-device communications
Using multiple OpenCL devices
Coalesced memory accesses
Tuning work-group sizes
OpenCL / OpenGL interoperability
The OpenCL ecosystem:
OpenCL 2.0 and future versions
Other OpenCL resources
The tutorial will use a mix of OpenCL’s C and C++ host APIs. The format will be a 50/50 split between lectures and exercises. Attendees will need to use their own laptops (Windows, Linux or OS/X) and log into a remote server running an OpenCL platform. Alternatively, students can load OpenCL onto their own laptops prior to the course (Intel, AMD and NVIDIA provide OpenCL SDKs. Apple laptops with X-code include OpenCL by default. Be sure to configure X-code to use the command line interface).
The International Workshop on OpenCL (IWOCL) is an annual meeting of OpenCL users, researchers, developers and suppliers to share OpenCL best practise, and to promote the evolution and advancement of the Khronos OpenCL standard.
FireUser.com is a community resource for CAD, visualization, 3D, video and engineering professionals to learn about the latest acceleration and display technologies and news with a focus on the AMD FirePro workstation graphics line.