• 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.

[PCPER]NVIDIA Talks DX12, DX11 Efficiency Improvements

Page 3 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
krumme said:
Man they are so freaky. They absolutely have no limits. Look at y axis on second graph. Lol. Suddenly different from the first one. And ofcource no info about testing at swarm.

Should rename their site to nvper.com
Click to expand...

Should this data not be offered?



This also caught my eye:

PCPerspective said:
NVIDIA claims that these fixes are not game specific and will improve performance and efficiency for a lot of GeForce users.
Click to expand...
 
Last edited:
Ed1 said:
What it shows is AMD Dx is way sub-par . Nvidia there is in between AMD dx and mantle on low end cpus . Not sure driver version there .
Click to expand...

NV optimizes performance per game, as it has shown in some slides. If AMD does the same, then its obvious that, for a game with 2 APIs, it will optimize for the best one.
Again MANTLE overhead is wayyy smaller than NV´s DX11
 
We have been over this before. Pclab.pl is always good for nv commercial and our native Polish speaking member Erenhardt have explained why. Way back october we knew they would give those bended resuls with mantle.

Tons of bs and pr from nv and yet they jump "dx12" wagon with impressive graphs showing radical improvement with "dx12". Looking from the graphs they provide for pcper and the bended paid junk from pclab one have to wonder how both is possible. Its magic.
 
Last edited:
krumme said:
We have been over this before. Pclab.pl is always good for nv commercial and our native Polish speaking member Erenhardt have explained why. Way back october we knew they would give those bended resuls with mantle.

Tons of bs and pr from nv and yet they jump "dx12" wagon with impressive graphs showing radical improvement with "dx12". Looking from the graphs they provide for pcper and the bended paid junk from pclab one have to wonder how both is possible. Its magic.
Click to expand...

This is much better, right?

http://www.anandtech.com/portal/amd

I wonder where the DirectX 12 news is on Anandtech.
 
http://www.hardwarecanucks.com/news/amd-roy-taylor-directx12/
So, april 2013 there was no info about new dx. AMD didn't knew anything about it.

You want me to believe nvidia is working with MS on the new dx for 4 years now? Okey...

Even if AMD was informed about dx12 a day after that interview, that would put them more than 3 years behind nvidia in dx12 talks! How is that an open standard? If anything that looks like MS and NV shady co-lab.

But if you look at it from the perspective, there was no dx12 development until very recently. Mantle is getting momentum and what ms and nv are doing is damage control.

Running forza demo on i7-3930 and titan is hardly any achievement. This game runs 60fps on APU with mobile CPU-cores! How are we supposed to know if it is even dx12? How could it be if there is no features list for it yet?

But it is good to see some people changed their mind from "There is no dx overhead" to "nv will fix it, mantle sux"
 
AnandThenMan said:
Working Fermi? What does that mean, you don't expect Fermi to work? 😕
Click to expand...

It means that at the time, the demos being shown were running on Fermi hardware. Not the mock up in Jen Hsun's hand. As opposed to NTMBK's allusion that there were in fact no working Fermi products because of said mock up. And because desprado called AMD liars, NTMBK felt compelled to call Nvidia liars to. Tit for tat.
I know, I know.
 
Last edited:
Erenhardt said:
http://www.hardwarecanucks.com/news/amd-roy-taylor-directx12/
So, april 2013 there was no info about new dx. AMD didn't knew anything about it.

You want me to believe nvidia is working with MS on the new dx for 4 years now? Okey...

Even if AMD was informed about dx12 a day after that interview, that would put them more than 3 years behind nvidia in dx12 talks! How is that an open standard? If anything that looks like MS and NV shady co-lab.

But if you look at it from the perspective, there was no dx12 development until very recently. Mantle is getting momentum and what ms and nv are doing is damage control.

Running forza demo on i7-3930 and titan is hardly any achievement. This game runs 60fps on APU with mobile CPU-cores! How are we supposed to know if it is even dx12? How could it be if there is no features list for it yet?

But it is good to see some people changed their mind from "There is no dx overhead" to "nv will fix it, mantle sux"
Click to expand...

In the article you offered:

Microsoft, for its part, denies Mr. Taylor’s earlier claim that DirectX is ending anytime soon.
Click to expand...

Taking on DirectX and Microsoft may of been questionable on Mr Taylor's part!
 
10.jpg


If they are able to beat an 87% gain from using Mantle with just DX11...


I gotta ask, why the the hell do they need to adopt DX12 or even worry themselves over Mantle at all????


:whiste:
 
No that's not the question at all because no one cares. Anyway I think it's absolutely hilarious how all of a sudden D3D is the greatest thing ever invented. Well except DX12 is coming out to fix all that is wrong with it currently.
 
AnandThenMan said:
No that's not the question at all because no one cares. Anyway I think it's absolutely hilarious how all of a sudden D3D is the greatest thing ever invented. Well except DX12 is coming out to fix all that is wrong with it currently.
Click to expand...

Yes, it's totally side-splitting funny.
 
SirPauly said:
Indeed! The question is why did AMD and Mr. Roy Taylor try to offer this illusion?
Click to expand...


They realized that after trying to develop the metal api and the dev tools for Xbone that they suck at it and terribly so.

Time to bring in the ppl who know something about it. Hmm, I wonder who that could be? What's their track record... looks at PS4. Calls AMD, whatever you want. M$ goes all in, since from a marketing position they have already leveraged the DX12 name in the Xbone. Will anyone notice if they brought the silent partner whom they tried to deny existed, but was obvious from the start?
 
SirPauly said:
Indeed! The question is why did AMD and Mr. Roy Taylor try to offer this illusion?
Click to expand...

Why would anyone believe them in the first place?
Talking about future products too early can impact the sales of their current products.

Even now when DX12 is announced, we know very little of what new hardware dependant features there will be.
 
Keysplayr said:
It means that at the time, the demos being shown were running on Fermi hardware. Not the mock up in Jen Hsun's hand. As opposed to NTMBK's allusion that there were in fact no working Fermi products because of said mock up. And because desprado called AMD liars, NTMBK felt compelled to call Nvidia liars to. Tit for tat.
I know, I know.
Click to expand...

JHH lied on stage. Go watch the announcement. He said, and I quote, "And now I have one sitting right here. This, ladies and gentleman, this puppy here, is Fermi." And then held up the Woodscrew Special. That is a flat out, bald faced lie. Yes, samples of Fermi did exist, but that's not what I'm talking about. I'm talking about JHH flat out lying on stage.

Anyway, I'll shut up about it as it doesn't have anything to do with the thread. It was indeed tit for tat, and I should have known better.
 
The one thing that would be exciting would be some sort of acceleration extensions for the igp in either Mantle or DX12.
 
yulgrhet said:
Why so much attacking PC Per, you wanting get thread locked??

To be nice please.
Click to expand...

It's important for us to know the history of a site before reading their article.

If I posted a "Mercedez Benz is the best car ever made" from MercedezBenzIsBest.com and then told every person on here to ignore the site and just read the review/accept it wouldn't that be unreasonable?

I'd rather know that a site has a long history of supporting xyz manufacturer before I read the review that way I can take it with a grain of salt.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top