Nvidia's CUDA is Already 5 Years Old
Nvidia's CUDA, Compute Unified Device Architecture, just turned five years old in a relatively quite ceremony held at SC11 and on Nvidia's blog.
The platform, which enables developers to exploit Nvidia GPUs (as well as x86 CPUs) for general-purpose GPU computing purposes was introduced on November 15, 2006 with the GeForce 8 series. Since then, Nvidia claims to have sold more than 350 million CUDA enabled GPUs. The CUDA toolkit has been downloaded more than 1 million times and more than 500 universities around the globe are teaching CUDA classes.
CUDA was, from the very beginning, designed to drive GPUs into high-performance computing applications in military, academic and industrial environments. While it was somewhat slow to start, Nvidia has been successful as, for example, three of the five fastest supercomputers in the world now integrate Tesla acceleration cards, the primary delivery vehicle for CUDA-based accelerators. CUDA apps, which are basically created via C++ like-code with specific extensions was the first generally available high-level language to easily access the processing horsepower in widely available and relatively affordable GPUs.
CUDA, which is still positioned against open high-level platforms, especially OpenCL, survived a looming battle with Intel's canceled Larrabee graphics card and floating point accelerator, but has been frequently criticized that it is not as easy to deploy as Nvidia claims. For example, while basic access to the GPU via CUDA is considered to be relatively easy, the remaining 5 to 10 percent of performance that is hidden in a GPU can only be accessed via detailed knowledge of the architecture of the GPU, especially its memory architecture.
In June of this year, Nvidia rolled out, with a delay of more than two years, multi-CPU x86 CUDA compilers that runs CUDA code on Intel and AMD processors.
- Nvidia,
- cuda ,
- graphics-card ,
- hardware ,
- acceleration
- Microsoft's Next-Gen Surface Available for Pre-Order
- CERN Wants to Upgrade LHC's Luminosity by 10 Times
- Blizzard Celebrates 7 Years of WoW With Gifts
- Can Microsoft Patent a Wind-Powered Data Center?
- BioWare Dates SWTOR Beta Test Weekend
- 2 GB DDR3 Modules Drop to $10 Contract Price
- Deals Nov 18: Logitech Marathon Mouse M705 $26.99 FS
- New AMD Catalyst 11.11 Supports Stage 3D in Flash
- 'Occupy Flash' Aims to End the Tyranny of Adobe's Plug-In
- Seagate: HDD Production Won't Return to Normal For 1 Year
- Windows 8 Will Be Less Demanding of Update Restarts
- Super Tiny Computer Puts Android on Your TV, Laptop
- Galaxy Nexus Owners Complain of Volume Issues
- Researchers Working on HDDs Slim Enough For Tablets
- Oracle Accuses HP of Paying Intel to Keep Itanium on Life Support
- Apple to Become World's Largest PC Maker in H2 2012?
- Deals Nov 21: 60" LG 1080p 600Hz Plasma HDTV $899
- Microsoft Offering $20K, Office Space to Kinect Developers
Hasn't improved much, has it?
Hasn't improved much, has it?
From Nvidia:
Adobe, Microsoft, and others use CUDA in several of their apps. CUDA also comes in handy in game and graphics development. The benefits also go beyond that. Just because "games" and such don't take advantage of CUDA doesn't mean it hasn't helped...
You missed my point.
I didn't say that it was useless.
I said that it hasn't improved much.(Has'nt got better)
My bad. It was just phrased in a way saying CUDA has not improved much, didn't know you meant CUDA itself hasn't improved...
I wish CUDA could help me quit smoking. Other than that, I think its a great platform.
Just two words: Octane Render.
Cuda also makes it possible for smaller companies or individuals to pump out higher quality animations. Using Cycles and only one of my 570s, I can render a frame in about 1/10th the time. A scene that would have taken 10hrs to render, now only takes an hour.
yeah it all happend with the 8000 series, have one 8800GTS 512 from MSI in 2008 and it still works,
id still rather have an open solution to cuda than cuda... nvidia has wronged me in the past and i will never for give them...
id still rather have an open solution to cuda than cuda... nvidia has wronged me in the past and i will never for give them...
They haven't personally wronged you, Alidan. Quit your crying.
There already are several open solutions. OpenCL for one is coming along nicely. But this requires that the hardware manufacturers meet THEIR specs. With CUDA, the software meets Nvidia's specs.
There are simply things OpenCL cannot do that CUDA can. And OpenCL is excellent of course, but AMD cards and Nvidia cards are simply built differently. It's apples and oranges, when it comes to GPU compute performance. Gaming it would be apples and apples, but raw computations are a different monster...
If you've ever used iRay (mental images) or Vray-RT for GPU rendering, you'd know the difference. Since you haven't, it'll give you a point to research.
My Cuda is 45 years old, Nvidia is lagging behind XD
"the remaining 5 to 10 percent of performance that is hidden in a GPU can only be accessed via detailed knowledge of the architecture of the GPU, especially its memory architecture."
Since when is 10% a big deal?
"in a relatively quite ceremony"
Shouldn't that be quiet instead of quite?
Running CUDA on Seti@home and Folding@home. It has proven to be great for scientific and engineering work
10% vs 200 to 2000% increase in performance over CPU's isn't a bad trade off..
quite a difference in Adobe's mercury engine between CUDA being on and off!
but disabling PhysX when a non-Nvidia GPU is present is a cheap move. Glad we have someone like GenL to fix it
quite a difference in Adobe's mercury engine between CUDA being on and off!
Amen to that! CUDA has been a dream for us video editors using Premiere! Not needing to render much (if at all) has enabled my CUDA cards to pay for themselves over and over.
Happy birthday to you CUDA !!!
From Nvidia: Adobe, Microsoft, and others use CUDA in several of their apps. CUDA also comes in handy in game and graphics development. The benefits also go beyond that. Just because "games" and such don't take advantage of CUDA doesn't mean it hasn't helped...
I'm pretty certain that PhysX uses CUDA, so in reality, games do take advantage of it.
Common software for casual consumer are still lacking of support. They need to push something on this area, not just development softwares or University research software.
CUDA has made some inroads since 5 years ago, but it could be so much better. I'm actually surprised that resource-intensive software like Mainconcept has not taken to support CUDA yet.
CUDA CUDA CUDA