AMD Snags Nvidia Supercomputer Client With FirePro & GPUOpen

When AMD revealed their GPUOpen and Boltzmann Initiative, it seemed like a last-ditch effort to get back some GPU computing and enterprise marketshare. Nvidia had struck first with CUDA and because of its success, many GPU computing platforms have largely been based on CUDA, with OpenCL lagging behind. With the Boltzmann Initiative AMD hoped to steal some Nvidia CUDA customers and they’ve just snagged a big one with their FirePro GPUs.

In partnerships with AMD, CGG, a geoscience company working on gas, oil and resource mining simulations switched over from a full CUDA platform to one entirely based on OpenCL and compatible with AMD. What’s more, they dropped all of their existing Nvidia GPUs and upgraded to FirePro S9150’s based on Hawaii (290X/390X). With the recent changes in graphics architecture, AMD has led in terms of computing with GCN especially shining in this regard.

With one major conversion under their belt, AMD now has a great example to show off to other potential customers. With HIP, up to 90% of CUDA code can be ported without any extra developer input and it looks like the befits of moving to AMD’s platform are worth the 10% of work. Hopefully, AMD will continue to score more enterprise wins, a market which they haven’t done as a well in for a while, and it is incredibly lucrative.

AMD Boltzmann Initiative Brings C++ & CUDA Compiler/Compatibility

While AMD has long-held decent marketshare in the consumer space, the high performance compute segment has long alluded the graphics firm. With the announcement of the so-called Boltzmann Initiative today though, AMD is planning to turn a leaf on their troubles and plow ahead with a better than ever graphics compute toolkit.

Frist off are a new set of HSA extensions dubbed, HSA+. While not part of the main HSA initiatives, the extensions will allow better use of discrete graphics in a HSA environment. Combined with a new headless Linux driver, this should help spur performance with a unified memory space, reduced latency and better system controls.

The next addition is the new Heterogeneous Compute Compiler or HCC. While AMD has long supported the open source OpenCL while Nvidia runs their own CUDA, HCC is a change in direction away from OpenCL. While AMD continues to in invested in and working on OpenCL, HCC will offer more competitive features compared to UCDA, until one day OpenCL support and features catches up. HCC is also C++ based which will allow for easy transition from CUDA.

Lat of all is Heterogeneous-compute Interface for Portability or HIP. Even with HCC being familiar and similar to CUDA, AMD recognizes that getting developers to switch is no easy task. With HIP, AMD is providing a compatibility layer for 90% of CUDA code, it means developers will only need to do fresh work on a small portion of the code in order to run on AMD hardware. One can only hope that there will be some trickle down effect on the consumer software market as well where CUDA has also been dominant.

In a market where CUDA has long dominated, AMD is finally making the moves that will make them competitive. If AMD is able to keep their Boltzmann Initiative up to date and provide support, there is probably a lot of room to grow int he HPC segment given their poor marketshare today. With a more lucrative HPC business in their back pocket, AMD will also be in a better position to invest in their consumer lineup.

NVIDIA Releases GeForce 350.05 Hotfix Driver

NVIDIA, though rolling out regular WHQL-signed drivers, has just released a stop-gap GeForce 350.05 Hotfix driver, addressing problems with the recent 349.88 WHQL-signed driver.

The Hotfix addresses the following problems, as listed on the NVIDIA website:

  • Battlefield Hardline – crash with Direct X error message on some systems

  • Dragon Age: Inquisition – TDR crash

Not advertised is that the Hotfix driver introduces OpenCL 1.2 support, as discovered by Expreview. OpenCL is expected to be a highlight of NVIDIA’s up-coming R350 drivers.

The GeForce 350.05 Hotfix driver can be downloaded from NVIDIA’s website.

Source: TechPowerUp

AMD Catalyst Omega Driver Released Early, Then Pulled

On Friday, AMD’s latest GPU driver, the Catalyst Omega, was prematurely released on – then subsequently pulled from – AMD’s website. The early release was presumably accidental, since links to the driver and to a number of tech site articles announcing the news have been deleted. But, while we await it’s (re)release, we have the Catalyst Omega’s impressive specs to pore over.

Catalyst Omega is said to raise high-end GPU performance by up to 19%, and a staggering 29% on APU cards. The new driver boasts a number of additional features, such as Virtual Super Resolution, which renders games at 4K then scales them down to the monitor’s respective resolution, making anti-aliasing obsolete.

Other video features include Fluid Motion to reduce judder and increase interpolation, Contour Removal to remove compression artifacts cleanly, and 1080p Detail Enhancement to scale up and sharpen images for larger monitors.

The treats don’t end there, though, with support for Gaming Evolved client specific features (notably FPS measure and streaming) , TressFX Hair 3.0, OpenCL 2.0, and Mantle game capture. Using EyeInfinity, Catalyst Omega is capable of powering 24 monitor arrays on 4 GPU systems. FreeSync, Alienware Graphics Amplifier, and 5K support is also incorporated.

There is no news yet on when the Catalyst Omega driver will officially be made available.

Source: Gameranx

FirePro W8100 Professional Graphics Solution Announced by AMD

AMD has just launched the AMD FirePro W8100 professional graphics card, bringing a new generation of AMD Graphics Core Next architecture as well as even grater workstation performance, which is dubbed to be 38x better than any other competing product on the market.

Featuring OpenCL, a best-in-class 8 GB of GDDR5 memory, 4.2 TFLOPS single-precision compute performance, 2.1 TFLOPS double-precision compute performance and of course OpenCL, the AMD FirePro W8100 is said to be designed for Media & Entertainment workflows, as well as engineering analysis and supercomputing applications.

In terms of productivity, the FirePro W8100 is said to be the ideal professional-grade solution for 4K Computer Aided Design (CAD) and other applications dedicated towards video editing, colour correction, compositing, design visualisation and GPU-accelerated compute tasks. Thanks to its super-fast memory and vast capacity, users are said to be able to load large datasets or handle ultra-HD video frames on the GPU’s internal memory for processing purposes, resulting in reduced lag and improved overall responsiveness.

Users are also said to have the option to combine up to four AMD FirePro W8100 cards in a single system in order to have over 16 TFLOPS compute performance, in addition to increased productivity with up to four 4K display support and certified application performance with differentiated graphics features.

The FirePro W8100 is said to deliver support for increasing real-time 4K productivity with single-GPU and multi-GPU configurations from various system integrators, including Armari, CARRI, Colfax, Exxact, Mouse Computers, PSSC Labs, Scan International, Tarox, Versatile Distribution Services, Workstation Specialists and Wortmann.

AMD has stated that it will start shipping in July from SAPPHIRE Technology, AMD FirePro Ultra Workstation providers as well as major workstation providers.

Thank you TechPowerUp for providing us with this information
Image courtesy of TechPowerUp

AMD Unveils The FirePro S10000 12GB Edition GPU Accelerator

AMD announced the new FirePro S10000 12GB Edition graphics card, designed for big data high-performance computing workloads for single precision and double precision performance. The new accelerator is the first in the industry to come with 12GB of onboard memory.

“Our compute application customers asked for a solution that offers increased memory to support larger data sets as they create new products and services. In response, we are announcing the AMD FirePro S10000 12GB Edition graphics card to meet that additional memory demand with support for OpenCL and high-end compute and graphics technologies,” said David Cummings, senior director and general manager of professional graphics at AMD.

AMD FirePro S10000 12GB server graphics card is based on two Tahiti graphics processing units with 12GB of GDDR5 memory with ECC and outputs 5.91 TFLOPS of peak single-precision and 1.48 TFLOPS of double-precision floating-point performance. The board features ECC memory and DirectGMA support allowing developers working with large models and assemblies to take advantage of the massively parallel processing capabilities of AMD GPUs based on the latest AMD Graphics core next architecture.

The AMD FirePro S10000 12GB Edition graphics card is a compelling solution for a variety of scenarios and markets, including finance, oil and gas, computer aided engineering, genetic sequencing, computational fluid dynamics, structural mechanics, numeral analytics, reservoir simulation, seismic processing, molecular dynamics, satellite imaging, explicit crash test simulation and so on.

Thank you XbitLabs for providing us with this information
Image courtesy of XbitLabs

AMD Collaborate With Adobe For OpenCL “Richland APU” Acceleration

AMD has just announced the results of some of its long standing collaboration with Adobe to bring OpenCL acceleration to programs like Adobe Photoshop and Premiere Pro. As a result Adobe has just released Photoshop CC and Premiere Pro CC which both feature OpenCL acceleration. These new program revisions from Adobe allow GPU acceleration so AMD APUs (both FirePro and Consumer APUs) can become more competitive in comparison to the competition from Intel.

As you can see without OpenCL AMD is more or less totally battered by Intel in Adobe Premiere Pro CC and Adobe Photoshop CC, but with OpenCL acceleration on its A10-6800K APU it is able to comfortable beat Intel’s i5 3470 thanks to the combination of the CPU and GPU working together.

This move is part of AMD’s HSA (Heterogeneous System Architecture) initiative and AMD is currently making big pushes to combined the CPU and GPU power in its APU devices to work in sync with each other. This will allow AMD to claw back some performance ground from Intel’s CPUs despite having dramatically weaker CPU components. AMD and Adobe’s collaboration together is quite impressive and boasts 64 qualified graphics devices on the official hardware support list. OpenCL acceleration of Premiere Pro can be enabled manually by users of the software.

Images courtesy of AMD