• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Nvidia = CUDA ATI =???

Nothing and mainly because they dont have the necessary resources to do this either. But that doesn't mean AMD/ATi cards will be left out in the cold. nVIDIA actually said straight from the horse's mouth that they encourage AMD users to take advantage of CUDA. Basically any GPUs under a certain requirements can utilize CUDA whether it be a nVIDIA GPU or ATi GPU.
 
Now i remember. I haven't heard about CAL or Brook+ since it was announced im afraid. Just how are these progressing?

Right now, i know that CUDA will enable SuperPi to run on GPUs real soon.
 
Originally posted by: tanishalfelven
i'm surprised no one mentioned CTM (close to metal) yet.

http://www.google.com.pk/searc...+ati&btnG=Search&meta=
Click to expand...
CTM is deprecated, it was so low-level that it could only be used on R5xx making it a dead-end solution. Its replacement is CAL, which is slightly higher level and as such can be used on newer architectures going forward.

Originally posted by: Cookie Monster
Now i remember. I haven't heard about CAL or Brook+ since it was announced im afraid. Just how are these progressing?

Right now, i know that CUDA will enable SuperPi to run on GPUs real soon.
Click to expand...
Brook+ is actually fairly well established in academia. It was a Stanford project that AMD adopted and further augmented for their own needs. For all practical purposes, it's just as functional as CUDA, although obviously the language differences mean that CUDA and Brook+ code aren't quite compatible even if they are both supersets of C. CAL doesn't get a lot of public attention because it's not often used by developers directly, rather it's the assembly code that other applications can generate and hence is used by toolset developers like RapidMind. The NVIDIA equivalent is PTX , if anyone is interested.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top