Featured Articles

Nvidia Shield 2 shows up in AnTuTu

Nvidia Shield 2 shows up in AnTuTu

Nvidia’s original Shield console launched last summer to mixed reviews. It went on sale in the US and so far Nvidia…

More...
AMD CSO John Byrne talks ARM

AMD CSO John Byrne talks ARM

We had a chance to talk about AMD’s upcoming products with John Byrne, Chief Sales Officer, AMD. We covered a number…

More...
AMD Chief Sales Officer thinks GPU leadership is critical

AMD Chief Sales Officer thinks GPU leadership is critical

We had a chance to talk to John Byrne who spent the last two years as Senior Vice President and Chief…

More...
OpenPlus One $299 5.5-inch Full HD phone

OpenPlus One $299 5.5-inch Full HD phone

OnePlus is one of the few small companies that might disrupt the Android phone market, dominated by giant outfits like Samsung.…

More...
KFA2 GTX 780 Ti Hall Of Fame reviewed

KFA2 GTX 780 Ti Hall Of Fame reviewed

KFA2 gained a lot of overclocking experience with the GTX 780 Hall of Fame (HOF), which we had a chance to…

More...
Frontpage Slideshow | Copyright © 2006-2010 orks, a business unit of Nuevvo Webware Ltd.
Thursday, 15 December 2011 10:53

Nvidia open sources CUDA compiler

Written by Nick Farell



GPUs get general purpose parallel computing


Nvidia has announced it will release the source code for its latest CUDA compiler, which allows programs to use Nvidia GPUs for general purpose parallel computing.

The move will mean that more people will be able to play with Nvidia GPUs to create bigger parallel computing projects. The new version is based on LLVM, a popular open source compiler infrastructure that is language-agnostic, so releasing the source will allow developers to extend CUDA support to other programming languages beyond C and C++, and other processors such as AMD GPUs and x86 CPUs.

Nvidia has said that qualified academic researchers and developers can get early access to the CUDA source code by registering with them.

blog comments powered by Disqus

Comments  

 
-8 #1 johndgr 2011-12-15 12:04
It is something positive, but also it is "too little, too late".
Sorry Nvidia, go lock a driver...
 
 
+2 #2 sirroman 2011-12-15 16:02
Time will tell if this is enough to bar the OpenCL surge and FSA.

I think it was clear to everyone that with a proprietary CUDA it would only be downhill from the FSA release.
 
 
0 #3 mech9t5 2011-12-15 16:17
Quoting johndgr:
It is something positive, but also it is "too little, too late".
Sorry Nvidia, go lock a driver...

Your "professional" opinion?
 
 
-1 #4 hoohoo 2011-12-15 17:21
CUDA gets you very close the metal, much closer than OpenCL. Sometimes you need that...
 
 
0 #5 Bl0bb3r 2011-12-16 18:33
^ except it will work only on some cards, soon less than half of discreet market.
 
 
0 #6 youserzero 2011-12-17 02:48
Quoting hoohoo:
CUDA gets you very close the metal, much closer than OpenCL. Sometimes you need that...


I not sure things you imagine really count
 

To be able to post comments please log-in with Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments