• 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.

The AMD Mantle Thread

Page 186 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Status
Not open for further replies.
Is that a CPU benchmark thread or Mantle thread?

Also, why are we discussing financial transactions? The same people keep bringing this up and adds nothing to the topic.

I was under the impression the 45% boost is for the Kaveri cpus.
 
You all should view the Nixxes slideshow:
http://www.slideshare.net/DevCentra...-new-amd-technology-by-jurjen-katsman#btnNext

Gets Mantle specific at slide 17.

Couple of highlights:
slide-23-638.jpg



slide-25-638.jpg



slide-29-638.jpg
 
Last edited:
blackened23 said:
They didn't test mantle themselves. So they were told by AMD. Where else would they get the information, AMD told them 45% and then they say they were told it was more in line with 10% in GPU limited situations. Of course you can twist the words in the article however you want, much like some AMD fans indicated that EA/DICE wasn't paid 8 million dollars for Mantle When 2700+ google search results seem to state that they did.

You can hope for 45%. That's cool. But the chances of that happening, except in excessively cherry picked situations which won't happen in real world gaming? I don't know. Kaveri's pre-launch hype doesn't exactly inspire optimism either. Like you said. AMD have lied before. Right? AMD marketing slides are purposed for hype. Not truth.

Anyway, i'm just saying, 45% is probably not real world. If it's 10 % performance gain for free, if that's what happens as per hardware.fr, that is still respectable.
Click to expand...

No where in the article do they say AMD told them anything. You aren't even twisting words, you are adding words that weren't there to start with.
 
blackened23 said:
They didn't test mantle themselves. So they were told by AMD. Where else would they get the information, AMD told them 45% and then they say they were told it was more in line with 10% in GPU limited situations. Of course you can twist the words in the article however you want, much like some AMD fans indicated that EA/DICE wasn't paid 8 million dollars for Mantle When 2700+ google search results seem to state that they did.

You can hope for 45%. That's cool. But the chances of that happening, except in excessively cherry picked situations which won't happen in real world gaming? I don't know. Kaveri's pre-launch hype doesn't exactly inspire optimism either. Like you said. AMD have lied before. Right? AMD marketing slides are purposed for hype. Not truth.

Anyway, i'm just saying, 45% is probably not real world. If it's 10 % performance gain for free, if that's what happens as per hardware.fr, that is still respectable.
Click to expand...

Sorry but you want me to trust you on a "translation" you done while I know nothing abour French.... NO. I am sure you are adding words on your own. You saw 10% there and make up the worst possbile anti mantle "said by amd" translation, There is no way in hell I trust you my friend but don't take it personally.
 
dguy6789 said:
Mantle naysayers have to feel pretty embarrassed after this
Click to expand...

Not really, turning off motion blur seemed to make them run similarly. I usually just turn motion blur off automatically in games because I hate it.

That motion blur would indicate a GPU effect that is getting a massive performance increase in Mantle, and not CPU?

Kind of the opposite of what people are expecting. That engine looks impressive for a movie to play out in real time, but there is so much stuff going on how the hell do you play that?
 
VulgarDisplay said:
Not really, turning off motion blur seemed to make them run similarly. I usually just turn motion blur off automatically in games because I hate it.

That motion blur would indicate a GPU effect that is getting a massive performance increase in Mantle, and not CPU?

Kind of the opposite of what people are expecting. That engine looks impressive for a movie to play out in real time, but there is so much stuff going on how the hell do you play that?
Click to expand...

Well go notice the numbers of objects of aprox 5k. Remember the apu13 demonstration with was it 50k or 70k?

I think it explains it. Remember this is running on a 6 core 12 thread expensive cpu. !

Dx will just not be able to tacle as many independent object on screen. Its not even comparable.

What is surprising then is the extreme difference for gpu they already have coded into the game. But thats what they promised in november.

The differences is striking for an engine that was made for dx and just adapted for mantle.
 
Last edited:
VulgarDisplay said:
Not really, turning off motion blur seemed to make them run similarly. I usually just turn motion blur off automatically in games because I hate it.
Click to expand...

Well now, that just sounds like sour grapes. Who cares about motion blur,
because I hate it anyways. Who cares about 5000 units, because that's
just too much going on.
 
zlatan said:
object != batch
Click to expand...

Yep i know its not the same. Sorry i just translate it to my gamer language 🙂 bigger and/more individual controlled armies/turrets/whatever. But in this demo its "units". Its makes it difficult to interprete.
 
Last edited:
They didn't disable motion blur on Mantle though.

Also, Mantle had some pretty nasty dips too, so it looks to me like they pulled no punches with this benchmark. :|
 
Small but incredibly effective, like the #1 military in the world :ninja:

Seems in this case though there wasn't any trade off in units, but you gained IQ and performance by disabling motion blur... Which is a trade-off most people would be willing to make.
 
Gloomy said:
They didn't disable motion blur on Mantle though.

Also, Mantle had some pretty nasty dips too, so it looks to me like they pulled no punches with this benchmark. :|
Click to expand...

I wouldnt say that for a rts, there will be huge fluctuation in this kind of game. But man, when can EA get bf4 mantle ready so we can try this ourselves?!
 
And the narrator said "back-off some high end graphics options like motion blur..." so it sounds like more than just motion blur was turned off to make DirectX run that fast.
 
Gloomy said:
I wonder what it's doing special that makes motion blur worth a 90% hit in performance. :hmm:
Click to expand...

Is it not aparent why dx is not working in this kind of situation?

You will easily tank performance 90% if you have to many units for dx too.

When did the goalpost shift like this?

Lol.

Ohh its not nessesary. We dont need more units and stupid cinematic effects....


Well yes we do. We need something moving the rts games seriously forward. Whatever the technology used. New engines or mantle.
 
Last edited:
Well it does look good and seems to work fine even on DirectX. The only thing I have issue with is the superblur that makes DirectX choke.

I could import the frames into photoshop and apply blur manually faster than that.
 
Status
Not open for further replies.

TRENDING THREADS

Back
Top