I saw a vid on that, pretty impressive! I expect it will be a loooong time before that finds it way into mainstream use. It may well eventually render (
) a long of conventional computing techniques totally obsolete.-
Competitor rules
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
Right lets talk everyone - are we all just been psychologically tricked into "needing" new graphics cards?
- Thread starter Combat squirrel
- Start date
I saw a vid on that, pretty impressive! I expect it will be a loooong time before that finds it way into mainstream use. It may well eventually render (
) a long of conventional computing techniques totally obsolete.
Associate
- Joined
- 2 Sep 2013
- Posts
- 2,093
100% "depends".
For gaming? Maybe. Depends on what you're doing. Too many variables there including your display, frames needed/desired, settings, PSU limitations, CPU limtations, memory limitations, and more that may mean a new graphics card is not necessary or needed because you are held back elsewhere.
For Machine Learning / AI stuff? You ever try to do something and you get Out of Memory? If so, you "need" a new graphics card to continue. But also only if it's got more VRAM. Especially if the only packages out there only currently support CUDA. Because when you're Out of Memory, that's it, there's no workaround (that's GPU based) at that point that you can do anything about.
For gaming? Maybe. Depends on what you're doing. Too many variables there including your display, frames needed/desired, settings, PSU limitations, CPU limtations, memory limitations, and more that may mean a new graphics card is not necessary or needed because you are held back elsewhere.
For Machine Learning / AI stuff? You ever try to do something and you get Out of Memory? If so, you "need" a new graphics card to continue. But also only if it's got more VRAM. Especially if the only packages out there only currently support CUDA. Because when you're Out of Memory, that's it, there's no workaround (that's GPU based) at that point that you can do anything about.