Dude were you high or something while writing this
High with holiday spirit.
You think im going to look in this screen to wait every mintue of the day, isn't it normal to take a break off the usual stuff and especially in such a time of the year.
Would you be able to eat same food every day for 3 months straight ?
If I could, I would go right now in the middle of some wild rainforrest and set up camp with survival gear and take a month vacation to relax away from all this at least once a year.
Oh an that "mantle is coming with all it's glory" ...
it's a spoof on starcraft 2 tv pre-launch trailer
Why is it that this particular thread has attracted quite a few new accounts, all arguing in favor of Mantle's marketing slide greatness?
Just something I've noticed.
Because it's the most busy mantle tech thread on the internet, been, and it is right now, besides battlefield forums but those are spread in many threads and more average-gamer type of discussion also I forgot the origin password for my account :whiste:
There are some smart individuals there as well talking about the same stuff I've pointed out and others, not denying that, i've read a few pages here and there.
And I pose a question: If Mantle is so great, why now at the final hour of when it's BF4 target release have we heard NOTHING about it. 2 man months? Hmm... Perhaps not.
They never confirmed anything. Also, they need to build the mantle thing, then they can start optimizing. Building it is what he meant with 2 months, not optimizing which also can be done as many times in later updates.
DX serves a purpose that Mantle does not. It works on all hardware. Mantle only works with GCN. To make Mantle work on everything would likely take away all the advantages it has.
Mantle serves a purpose that DirectX does not.
Mantle may be what some dev's wanted, but they only wanted it because they want to work on a PC like they do with consoles. The only problem is that they need DX to sell their game on PC's.
That is not a constant. It's a variable.
DX may have ways to improve things, but Mantle is not the way, as it is too hardware specific.
That's your opinion.
Haven't we met on same arguments like 3 different forums by now ?
20% from what? Better core scaling? Lower driver and drawcall overhead? 20% overall improvement sounds rather low.
DX10 improved the API execution overhead by 20% of DX9. Yet it took years before we saw a result.
But 20% now, thats quite a lowering from your previous predictions.
It's just the start, they wanted to give a safe number out. It's definitely not only 20%.
The GPU optimizations require more work so that will come gradually, first 20% and then more, but the CPU optimization will be basically instant, 4 or 8 core support out of the box and maybe updates in future to support 12 or more cores, and the CPU optimization will be huge, but wait, depends how much of that extra CPU time they use up on game complexity, so the numbers might be all hiding.
The best showcase would be to update an old game, with visuals and complexity staying the same, like Crysis.
DX 10 didn't remove the core issues which are awful core scaling and the serial nature of the API.
Mantle basically removes all 3 (including draw calls with the 2 above) of these serious issues by default. That has to tell in better fps across the board - yes even in games like BF4 where CPU usage is actually very good, it can still get even better.
I expect to see large gains simply because the CPU and API aren't bottlenecking by forcing one thread.
Yes, over a 100%
Not even mentioning 8 cores here ...
You do know it's only AMD having a singelthreaded DX11 driver right?
NVIDIA's DX11 is multihtreaded....thus you just owned yourself.
I think driver multi-threading is a band aid and doesn't really do much as it sounds.
You maybe check out these 2 slides:
Never heard or saw driver multi-threading being mentioned ... that alone doesn't mean't it's not a big deal but there's no indication it is.
Oh, i didn't notice you posted hard performance data on matle, could you post it again...from objective sources?
Not the first time I ask you to back up your claims and nothing materialize...it this the "lucky" time?
Or will will you post more undocumented guess work?
That which can be asserted without evidence, can be dismissed without evidence.
You've been contradicting our research and circumstantial evidence gained from analyzing the data we know.
Either you didn't analyze the data, or you don't know the data well.
AMD/Dice claimed vastly better core scaling and not to mention the lower overhead, therefore 20% sounds low for the extra work and limited clientage. 20% gains should be possible also for DX11MT, probably more with a proper implementation. And this is not exclusive to one IHV, AMD could bring a new driver anytime. I would assume 50% higher fps for Mantle in purely CPU bound scenarios on a 6+ core CPU. On APUs with 4 threads it might be more limited because there is less room for better CPU/thread scaling.
You think DICE doesn't know how to implement DX11
properly already
?
Here goes my ... opinion piece. (nothing to do with the rest):
Basically CPU Perf would skyrocket, you lose tons of overhead, plus, you get to use 60% of the CPU you weren't using before.
Be wary of these percents talk, they don't transfer that easily.
Let's say we use 8-real core CPU.
5 cores don't even get used, and not all games use 3 anyways, the 4th one if it ever gets used it's probably just a little.
You get to lose the overhead, on each core.
And you can use all the cores you have.
When you calculate it and then effectively it comes out like 500% or more, more because the 3rd core doesn't have to use the driver thread, the driver thread doesn't exist anymore.
This isn't just about multi-threading, those 3 cores that are used, aren't being used to their full extent in the first place.
And that's totally not a joke, but rough numbers. Why do you think it worked the same when the underclocked by 2GHZ ... that's why.
But I'll just say it's my opinion, not with the other stuff I said.
I don't have to be correct with this opinion, being as accurate as possible is what counts.