NVidia is off at SolidWorks World this week, demonstrating their newest NVidia Maximum products and Quadro GPU’s. In particular, they’re proud of this demonstration of their new Quadro2000 against the older Quadro1700, showing the amazing performance boost you can get with a simple hardware upgrade.
Other demos include side-by-side comparisons of SolidWorks powered by NVIDIA Quadro professional GPUs to show how upgrading to the latest generation of Quadro provides up to 3X faster interactive performance and eDrawings in stereoscopic 3D with NVIDIA 3D Vision Pro. The video below demonstrates the performance benefits of the Quadro 2000.
The new SolidWorks2012 offers some limited GPU features focused around making the visuals pop a little more than classic CAD packages. Over at SolidSmack they take it for a test-drive with one of the lower-end professional cards, the Quadro 2000, and find it works surprisingly well.
The image below is a screenshot of a data set from NVIDIA shown in SolidWorks with RealView graphics on. RealView graphics utilize the GPU to render the semi-realistic graphics on the SolidWorks screen. The other window is the PhotoView 360 Preview window. PhotoView 360 is 100% CPU-based rendering and doesn’t task the GPU, so for PV360 rendering your benefits come along with more multi-threaded CPU cores. The SolidWorks models are all CPU as well. The GPU does little for processing the model, so more GPU’s won’t gain you any added performance.
Of course, it sounds like SolidWorks isn’t really pushing the GPU that hard, focusing only on some nice rendering features in the realtime viewport. High-end renderings are still classic CPU raytracing, and none of the software seems to use any GPGPU features, so the lower-end cards make for a nice inexpensive way to add some more “oomph” to your workstation.
Of course, NVidia is quick to point out the growing trend of designers using post-rendering tools like KeyShot and BunkSpeed to do their high-end renderings, which will definitely take advantage of higher-end Quadros.
Apple leaked it a few weeks ago, but now it’s official: NVidia has just announced the Quadro4000 for the Mac. With the same acceleration benefits of the Quadro on the PC, it will greatly improve performance of any graphics or CUDA-related application, like the popular Adobe CS5 suite.
“Adobe Premiere Pro CS5 and the Adobe Mercury Playback Engine, accelerated by NVIDIA Quadro GPUs, have redefined the non-linear editing workflow, delivering huge productivity gains,” said Ginna Baldassarre, senior product manager at Adobe. “Adobe looks forward to working with NVIDIA to help more Mac users reap the benefits of real-time performance and the ability to create compelling, multi-layer projects with multiple HD or higher resolution video clips, all while instantly viewing results.”
For those of you drooling over the power of the new Fermi-driven Quadro’s but without the deep pockets required for the Quadro 4000 or Quadro 5000, NVidia has come to your rescue with two new lower-end products: The Quadro 2000 and Quadro 600.
The Quadro 2000 sports 192 cores and 1GB of GDDR5 memory, and consumes a mere 62W of power and a MSRP estimated around $599. It won’t offer the same horsepower as the 4000, but it’s a great upgrade for those on previous-generation lower-end Quadro systems. It still supports the new 3D Vision Pro, their RF-upgrade to the previous 3D Vision systems, and NVidia’s SLI Multi-OS support.
But if the Quadro 2000 is still beyond your reach, then you can go all the way down to the Quadro 600. The Quadro600 sports only 96 cores, but the same 1GB of GDDR5 slightly slower DDR3 memory. Consuming only 40W, it’s estimated to be available for a mere $199, making it the bargain pricing of anyone wanting to take their bargain basement workstation to the next level. It support 3D Vision Pro, but not the SLI Multi-OS, meaning you probably won’t want to use it for development.
Neither of these cards can touch the higher-end offerings for performance, but for people looking for Nvidia’s “Workstation” class performance with a budget pricing, it’s a great place to start. Both cards also support the “NVidia Mosaic Technology”, which means they have hardware and driver support to scale your desktop up across 8 cards with no special software. This could be great with the Quadro 600, offering some great low-price extreme-performance for high-end renderwall setups.
Perhaps the most impressive piece of information from this announcement is that both cards are single-width PCIe Gen2 x16 cards. This opens up the Quadro to a whole new class of small machines which can’t hold dual-width cards such as blades. There are still power and cooling concerns, especially since both cards are still actively cooled, but it’s a step in the right direction.
Update 10/6/2010: Correction, the Quadro200 does not have GDDR5, rather it has DDR3.
Richard Kerris, CTO, ILM, discusses how NVIDIA Quadro GPUs enabled the creation of breakthrough visual effects. Hear how the ILM creative team was able to create life-like simulations of fire for blockbuster movies, including Harry Potter and the Last Air Bender.
Huge day for NVidia. First the amazing Quadro Fermi series (Read our review of the Quadro 5000), and now new 3D Vision Pro and new AXE systems. First, let’s discuss the impressive new 3D Vision Pro.
NVidia brings their 3D Vision Pro to a new class of applications with one simple change: Switching from IR transmitters to RF transmitters. This effectively eliminates line of sight problems, opening the 3D Vision use for crowds of people, multi-screen displays, and VR environments like the CAVE. Also, this allows them to synchronize glasses to specific displays, as they’ve done in their impressive SIGGRAPH Booth. 3D is a big driver today, and they’ve got around a dozen different 3D displays running different demos all around the booth. Each display has about 4 3d glasses synced to it, and they don’t interfere with other displays, nor do the glasses work with other displays. The display can effectively turn the glasses on and off, without messing with other displays. This kind of managed interface is critical for large-scale professional applications.
“By providing large scale visualization capabilities and remote management capabilities, NVIDIA is pioneering 3D technology for the enterprise, opening the door for professional users and large scale visualization system integrators to utilize 3D in ways not thought of before.” Dr. Jon Peddie, president of Jon Peddie Research.
The other big announcement coming out right now is the slew of updates in the AXE suite, the Application Acceleration Engines. These are the various support technologies based around the NVidia brand like OptiX (ray tracer), SceneX (scene graph) and others. Today they’are announcing major revisions to several of them.
NVIDIA SceniX 6
New Bezier Patch geometry class, using Cg tessellation programs for the smoothest of surfaces on NVIDIA Fermi architecture class GPUs;
OptiX 2 support for faster, interactive ray tracing;
Continued improvements in overall performance and fidelity, and;
Future support for iray by mental images.
NVIDIA Cg Toolkit 3
New tessellation programs, allowing displacement and procedural surfaces to dynamically adapt their tessellation in real-time on the latest NVIDIA Fermi architecture class GPUs, and;
OpenGL 4 and DirectX 11 level of programmability for the latest in portable, cross platform effects.
NVIDIA OptiX 2
Optimizations for new NVIDIA Fermi architecture class GPUs, delivering up to 4X performance over previous generation (GT200) GPUs and >10X over G92;
Support for all NVIDIA CUDA™ architecture-capable NVIDIA GPUs (G92 or later) on Windows, Linux and Mac OSX, and;
Direct3D and fast interoperability in Direct3D and OpenGL; for flexible compositing and hybrid rendering opportunities.
Again, Amazing stuff from the NVidia folks. I look forward to spending some time in their booth later today, and sharing the experience with you all later tonight!
Full press releases on both topics after the break.
NVidia recently held a roundtable discussion in Bonn, Germany and invited several members of the research and press communities. The guys at 3dTest were there and asked the question that comes to mind with several graphics designers: Why buy Quadro? You can get a GTx285 or GTX480 for significantly cheaper ($200-$400, rather than $2000+), so what justifies the 5x to 10x increase in cost?
To this, NVIDIA highlights the efforts made by teams to develop specific drivers that allow in some cases performance gains of about x3 (with drivers AutoCAD or 3ds Max dedicated). The work of engineers at NVIDIA is to study how the software communicates with the 3D map and maximize these exchanges. Thus, the Quadro range has certified drivers and a user can receive technical support. This type of service is essential part of a production where the financial stakes are high and the reliability of the equipment used is a key factor.Then there is the manufacturing quality of Quadro cards (directly provided by NVIDIA, then released by PNY in Europe) that guarantee a more reliable maps.
NewMediaWebinars.com has recently released a new episode of The Digital Scene. The different episodes of this show cover what happens at all the major conferences. In this episode, they focus on using Nvidia technology for 3-D web videos.
NVIDIA shows us how their technology speeds up 3D encoding (on the server side) and 3D decoding (on the client side) for stereoscopic web videos.
The NVidia Quadro line has long been a staple of high-end Visual Effects and Designers, but many people still ask “What does a Quadro offer over a GeForce?” Both are based on the same chipsets, but the Quadro is usually 5x-10x more expensive. A new press release from NVidia talks specifically about the benefits to AutoCAD users, and gives some concrete numbers:
Designers running AutoCAD 2011 on Quadro professional GPUs can also realize significant performance increases. AutoCAD benchmarks show Quadro delivering:
Up to 6x higher performance in ‘3D Hidden’ visual style
Up to 3x faster interactive manipulation of models in ‘Conceptual’ visual style
Up to 2x gains in speed with the ‘Realistic’ and new ‘Shades of Gray’ visual styles†
The main feature of the Quadro line is the various specific application optimizations they’ve integrated into the hardware and the drivers that really don’t impact gamers, but offer significant improvements to features used by designers. Things like improved antialiasing, improved transparency support, and slightly more accurate computations in the depth field. Financially, it offers some benefits as well:
“For designers who spend a portion of their day working with AutoCAD, Quadro is a smart, cost-effective investment that increases productivity,” said Jeff Brown, NVIDIA general manager, Professional Solutions Group. “Streamlined workflows can easily save a designer 30 minutes a day, and for a firm with five designers, this translates to a benefit of more than $100,000 over three years.††”
At the SuperComputing conference back in November of 2009, one could find the still-yet-to-be-released Fermi graphics card running in the NVidia booth. At the recent CEBIT conference, SemiAccurate has spotted a system with four Fermi-based Tesla cards, and even has the picture to prove it. To see a picture of it, you will have to click on through the link below. There is just one small catch however:
Should you want to move to greener pastures, SuperMicro has the servers for you. There were 2 and 4 Tesla/Quadro servers featuring that loveable scamp, Fermi. These were genuine 'puppies', meaning they were not functional, just mockups. There are not enough samples to go around to bring working cards, much less six of them, to a trade show. (As a note to Nvidia PR, SuperMicro was honest when asked about the status of the cards on display. It can be done, no one died!)
VizWorld.com We cover visualization and graphics news from around the internet, including Scientific Visualization, Visual Effects, and Graphics Hardware. Read more on our About Page or learn about our Advertising Options Get updates via twitter from @VizWorld.