So now they are going to abandon the overwhelming majority of the market to cater to that little slice of the pie that's GCN? All this before we've even seen a performance demonstration.
How did you get from "do less optimizing" to "abandon"?
The devs that are on board could barely make it more obvious that they'd rather DX just disappeared altogether. The only thing they care about with DX is that it's the majority of the market now, but they have zero wish to keep it that way.
Don't be so literal.
Let me make it really clear so there's no misunderstanding. An overwhelming majority of their customers are going to use the DX render path. They aren't going to not cater to them properly. i.e. abandon them.
M$ has invested too much in DX and making sure that Windows is a must have for (virtually) every PC gamer to simply sit there and allow it to all go to crap. They have let DX become completely unsatisfactory for these devs because there was no alternative for them. It's just another case where lack of competition has caused indifference and stagnation. It's about time something shook them up a bit.
You can't say there is no competition. OpenGL has been around for years. It just hasn't been as good as DirectX for years now.
OpenGL used to be competition. That's why M$ put so much resources behind DX. Once they won that battle though, they took their foot off the gas. DX has been a virtual monopoly since.
What I find interesting in this context is that AMD said they didn't blindside M$ with Mantle. M$ was made fully aware and had no issues. AMD feels that their relationship with M$ is too critical to get into a contest with them. That makes me wonder what went on between the two of them to make all of this OK with M$. Surely the obvious competition between them was discussed. Makes me think that there's some sort of cooperation between them that might not be apparent yet.
I'm curious as to what makes you think MS took their foot off the peddle? They increased performance and made some major changes in the last couple major releases. And OpenGL still gets used, just not nearly as much. If MS was so bad, you'd think OpenGL would be used more.
Mantle could be better, but that could very well be that they have the advantage of building from the ground up, without having to worry about any legacy stuff.
It's apparent that DX has become a bottleneck. Whatever they've done it's not enough. The commentary from the devs who are embracing Mantle speaks to that.
In one swift move AMD gives the Devs what they've been asking for from M$ for years. Doesn't seem like it was a monumental effort that M$ couldn't have done if they wanted to. Especially considering that AMD isn't the software giant that M$ is.
But isn't the main reasons for Mantle's break through, is the use of lower level access and GCN features? DX cannot use those features and remain vendor neutral.
And just because a better solution comes around, doesn't mean they stopped trying. Though we can't claim Mantle as better yet. If it only works on specific hardware, then it isn't exactly better.
And when non GCN hardware is able to be used, will it show the same performance advantages?
I assume that's a rhetorical question, so I'll ask you, Why not?
Because the GCN hardware allows for major advantages in communication between the CPU and GPU that are not present without it. I don't know how much a difference it makes, but it stands to reason that the performance gains may not be the API, but the use of GCN features.
It's apparent that DX has become a bottleneck. Whatever they've done it's not enough. The commentary from the devs who are embracing Mantle speaks to that.
In one swift move AMD gives the Devs what they've been asking for from M$ for years. Doesn't seem like it was a monumental effort that M$ couldn't have done if they wanted to. Especially considering that AMD isn't the software giant that M$ is.
Again, we have only statements from developers who are using Mantle. We have no objective data. One would hardly expect a developer using mantle to say "Oh, yea, we are using mantle just to waste time, DX is better". Just like I am sure you could go 5 different new car dealers and they would all say their car is the best.
Mantle may be in fact a great advance, or it may be seriously over hyped. No one will know until we see concrete data in a variety of games, and how it is supported over time.
Ok. I guess we'll wait on reviews from people who haven't used it then. :\
Yes that is what i have been saying quite a long now.An attempt at sarcasm doesnt really work when it is just a patently ridiculous statement.
Ok. I guess we'll wait on reviews from people who haven't used it then. :\
At any rate, waiting for actual data would be the prudent course of action.
Enough of the parroting. Go data, or go home. IMHO.
Or leave this thread if the hard data presented is not your liking?
Every second week or so there is new games supported. There is plenty of new data and it is presented in this thread. There is 2 good videos from apu13 for those who care to take their time and try to understand why all the devs. are signing up.
Anyone care to share their hard data of an new performance engine comming 2014 that wont be mantle? lol - wow DX is really on a killing streak.
The devs. are signing up for Mantle like nobody could have predicted. What kind of data is that? - its imho far more important and OBJECTIVE data than anything else. And a better indicator of total potential than eg. some bf4 results.
Obviously they know something we dont. Be it performance or transparency/control. Effect can be measured in 100 important ways, some of the ways, non here is not capable of understanding, as engine programming for new AAA is not where the most jobs is.
But whatever the reason - they must be good and plenty. Because the mantle games are comming big time.
So yes, i agree, stop the parroting. We all knew from page 1, we had to wait for bf4 to get first actual game performance. But what we know now, is there will be plenty performance games with mantle 2014/15. That is data.
You still dont get it and your evident desire to defend mantle at all costs doesnt even let you agree with someone stating what is actually a favourable point towards implementing mantle.
Ima just use an example, if you still cant get it, the we have a big trouble regarding reading comprehension:
The dev behind X game currently has only a DX version of it. That means that for this dev he has to spend his time optimizing this DX version to work at acceptable levels with AMD/Intel/NV's GPUs.
Now after hearing the benefits of mantle, this dev decides that the next game he will release, game Y, will have a mantle enabled version out of box, alongside with the usual DX version.
His dev time spent on optimizing for all hardware hasnt become longer because of this, even tho he has to put time into a new API enabled version of game Y. Because now all GCN cards have access to mantle, he can scrap the dev time used on optimizing the DX version for GCN and, for the DX version of the game, even NV and Intel would see better optimizations as now the DX version has to play well with only those 2 uarchs. Why would you care if a game runs terribad on a GCN under DX if you would use the mantle version anyways? Dude A running a NV card benefits from this, dude B running a Intel's iGP benefits from this, and obviously, dude C will get the most benefit as he will be running the mantle version with his GCN card.