Improved OpenCL interoperability for accelerating computationally intensive visual applications
Continued support for both the Core and Compatibility profiles first introduced with OpenGL 3.2, enabling developers to use a streamlined API or retain backwards compatibility for existing OpenGL code, depending on their needs
Easier porting between mobile and desktop platforms with full OpenGL ES 2.0 API compatibility
Ability to query and load a binary for shader program objects to save re-compilation time
Capability to bind programs individually to programmable stages for programming flexibility
Higher geometric precision with 64-bit floating-point component vertex shader inputs
Increased rendering flexibility with multiple viewports for a rendering surface
Support for new ARB extension introduced with OpenGL 4.1
In advance of the actual show, we got a sneak preview of the SolidWorks 2011 Ultimate CAD Chair - an ergonomic Eyefinity 3-display system powered by an AMD ATI FirePro V8800. The system was assembled by Jeremy Luchini and the Let’s Go Design team.
AMD has focused on the open standard, cross-platform OpenCL standard for GPU-Compute functionality with support for acceleration on both GPUs and CPUs (including embedded and hand-held devices). OpenCL allows the GPU to help the CPU do the computing or data crunching, to enable faster and more efficient processing.
SiSoftware has posted OpenCL benchmarks for GPU based acceleration and compared it to both CUDA and ATI Stream.
Using the latest OpenCL 1.0 Beta 4, the benchmarks show great results: performance parity with CUDA (in some cases OpenCL is faster) and 50% faster than native CAL/STREAM.
The take away conclusion: There is no reason not to port CUDA code to OpenCL now!
At CES, in addition to showing off Kinect, Microsoft also showed off their next generation multi-touch Surface platform on the Samsung SUR40. This new version was powered by the AMD Athlon II X2 embedded processor and Radeon HD 6700M graphic to deliver high performance with low power requirements. See the video below or check out the press release.
MainConcept’s new encoding SDK dramatically improves H.264/AVC HD video encoding times by efficiently harnessing OpenCL and is optimized for the FirePro graphic line. The OpenCL H.264/AVC Encoder SDK contains a high-level Windows library as well as a DirectShow filter for easy integration into a variety of creative, broadcast, and professional applications.
Monday AMD announced it’s first Fusion APU-based systems. What exactly is an APU? For AMD’s this new line of processors means - in a single die design - multi-core CPU (x86) technology, a powerful DirectX®11-capable discrete-level graphics and parallel processing engine, a dedicated high-definition video acceleration block, and a high-speed bus that speeds data across the differing types of processor cores within the design.
It’s not a demo using DCC or CAD software, but it is a great example of setting up Eyefinity across 5 HD portrait displays. It is pretty easy to translate this and imagine its use in professional 3D and CA work.
Impressive demo that makes it clear how this kind of display real-estate driven by a single video card, can really matter.
A lot of reviews out today on the new AMD Radeon HD 6900 series. The official press release spells out the technical features including a new VLIW4 shader architecture, asynchronous dispatch (important for OpenCL and DirectCompute), dual tessellation units, up to 2GB memory, PowerTune thermal limits, and of course, Eyefinity . For gaming enthusiasts, these cards offer great performance but where they really dominate over the competition is the price/performance ratio.
From PC Perspective:
“The Radeon HD 6970 2GB card offers the largest frame buffer for a single GPU solution (512MB more than the GTX 580) and with the architectural improvements brought about with the VLIW4 design, updated tessellation engines and AA enhancements, it is able to keep pace and beat the GTX 570 from NVIDIA in many places and nearly match the much more expensive GTX 580. That puts the HD 6970 in a very competitive situation in terms of performance per dollar.”
How can FirePro help make a SolidWorks user’s life easier?
- Improve productivity and reduce design cycles with cards that are engineered, tested and certified to ensure reliability, and exceptional 3D performance.
- AMD Eyefinity technology lets you run up to six monitors at full HD resolution, simultaneously on a single graphics card. Expand your view and multitask with ease.
Check out the Eyefinity video below which is featured in the blog post.
While there have been many reviews about the newest line of FirePro cards, this one on CG Channel is focused on the DCC market and looks at a wide range of benchmarks as well as real world and practical use scenarios.
It falls into that rare camp of reviews that are actually an interesting read, and not just robotic readout of benchmarks.
What are some of the take aways:
You will get addicted to having 3 or more displays that work together “you’ve got Max or Maya open one of the 30-inchers, Photoshop on the other, ZBrush or Mudbox running on the Cintiq, and your reference art or a web browser open on the 22-inch display!”
The V8800 and V7800 are awesome for DCC performance (and even good for gaming!)
The v5800 best balances performance, features and price. Great choice unless you have really huge models or superdense meshes.
The V3800 would be a good entry-level AutoCAD or SolidWorks card as CAD projects tend to not use the high-resolution textures and complex pixel shaders that DCC app do.
OpenCL apps are not really here, but when they come, these cards will suddenly take on additional new life.
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.