Everybody should read this. It's from Dan Baker who made Lore Engine for Civ5.
Mantle is kind of the disruptive technology that gets everyone rethinking things. Whether this means a new version of OpenGL, or a new version of D3D, we can't say. But it is clear that they will have to adapt if they want to stay relevant. Some of us have been screaming for change for years. The arguments we got in the past were: 1) it couldn't be faster 2) it would be too hard to use, and 3) we have enough performance, so more isn't useful. We wanted to show that all three of these things are provably false.
Yep.His entire premise is based on a 5 year old game (Civ 5) with results using 5 year old tech and a modern game run at low settings.
We do after all have openGL as an existing standard that can support much better draw call rates and GPU extensions (everything Johan wants) and unlike Mantle its another standard many vendors already provide drivers for. OpenGL also happens to be an API that AMD hasn't implemented very well, they have poor performance and bugs on it and have done for a decade. A new API is a big deal, I would far rather we see an evolution of the existing ones and if a new API is necessary then it needs to be developed on concerted with other companies, or its doomed to obscurity.
DX is not universal and has done pretty well.Its quite simple. Mantle is not universal, hence never get a chance. Its economics.
DX is not universal and has done pretty well.
Everybody should read this. It's from Dan Baker who made Lore Engine for Civ5.
Now that's very interesting. Thanks for posting zlatan.
The cynic in me really has to wonder though at some of his statements. In the interview, Baker claims that DirectX made an attempt to be threaded, and failed. Yet the Lore engine, something which he himself had a big part in creating, obviously benefits tremendously from DX11 multithreading. In fact, it helped NVidia dominate AMD in that game for years.
So why was he extolling the benefits of driver command lists in the Lore presentation I linked to on the first page, and now he seems dead set against it?
And benchmarks some of our members have posted on the forum of the Star Swarm benchmark shows that it can benefit from DX11 multithreading in a big way.
The Star Swarm benchmark is seemingly contrived to make Mantle look good. It doesn't use instancing, one of the technologies in DX11 that can drastically reduce the amount of draw calls necessary by using the same geometry to draw multiple objects, and so the amount of draw calls is inflated relative to what it would be in an actual game.
And CPU and GPU utilization are poor on non Mantle systems, which really begs the question of how well it's optimized or DX..
The OP wants an objective discussion, yet refuses to acknowledge when some of his arguments are completely debunked. How can someone possibly be objective if they refuse to change their mind based on solid evidence?
He claims Mantle isn't backward compatible with DirectX. Yet refuses to accept that it doesn't need to be. The GPUs it runs on already have DirectX compatability and as such ARE backward compatible.
Show me one single game that an AMD GCN R9 card cannot play compared to a Nvidia GPU?
He then goes on to post graphs showing BF4 run at very low settings and graphs that only show Nvidia in a good light. His entire premise is based on a 5 year old game (Civ 5) with results using 5 year old tech and a modern game run at low settings.
Star Swarm doesn't use instancing because many of the objects that are using up draw calls have their own AI and pathfinding. I don't think you can instance something in that case.
All the turrents, ships, and projectiles all need their own draw calls in the demo. If there was a forest full of identical trees in space then your argument about the lack of instancing use would make sense.
Very well-informed and interesting post, OP. Apart from the subtle anti-AMD slant that some may take issue with, I think the goal of questioning the precedent set by Mantle is an important one. Is it really sustainable? Will it perhaps inspire refinements in DirectX and then be retired?
While it seems that one of the primary benefits of Mantle is to give a boost to AMD's weak lineup of CPUs, I doubt very highly that this was the reason that AMD developed Mantle. There are obviously some inefficiencies in DX11, and AMD saw a way to address them. As good as Nvidia's implementation of DCL is, the Civ5 example is probably more of the exception than the rule.
With more and more modern games requiring significant CPU power, and many becoming bottlenecked at 1080p, I think it's certainly right to question whether DirectX gaming is eventually going to be weighed down by the overhead even on the most powerful CPUs. We all know that CPUs aren't advancing as quickly as they used to, so this really is more than just an academic issue. When my overclocked 3770K and 4770K processors need to run at 75% capacity in BF4 just to keep up with a 1440p resolution, I do wonder what next year's game engines will require.
Star Swarm doesn't use instancing because many of the objects that are using up draw calls have their own AI and pathfinding. I don't think you can instance something in that case.
All the turrents, ships, and projectiles all need their own draw calls in the demo. If there was a forest full of identical trees in space then your argument about the lack of instancing use would make sense.
Or you just love old benchmarks that show AMD in a bad light?
Newer benchmarks of Civ5 show AMD in much better light than those older ones.
From a very pro nvidia source (alienbabeltech):
http://i0.wp.com/alienbabeltech.com/main/wp-content/uploads/2013/08/CHART-2.jpg?resize=640,1461
Civ5 Ultra settings 8xAA:
1920x1080:
AMD 7970 = 77,7 fps
Nvidia 770 = 80.2 fps
I don't know why you bothered posting this last bit. Only a few games are officially known to use DX11 multithreading, and none of them are in that review.I know both nvidia and AMD have faster cards than those, but their about equal in other games, and in CIV5 their not that far apart either.
Techpowerup:
http://tpucdn.com/reviews/ASUS/R9_290X_Direct_Cu_II_OC/images/perfrel_1920.gif
770 = 79% of a 290x
7970 (1ghz) = 77% of a 290x
Same thing you see above in CIV5.
People are blowing things out of proportion by useing really old benchmark results.
You mean like hardware PhysX?AMD only need to sponsor a 3-4 AAA games per year with Mantle and it's job done.
You mean like hardware PhysX?
Who here thinks that scenario has been a resounding success? It's a niche at best.
No,not like hardware PhysX.
More like what SSDs have done to Hard Disc drives.
Mantle gives greater access to the GCN hardware than DX and will,over time just "ridicule it".
Either Microsoft gets a move on and gives us a 21st century version of DX or its going to be running NVDA cards slower in Mantle games.
That's it.
Naturally NVDA isn't going to stand for that so I expect a similar API to appear fairly soon giving low level access to NV architecture.
There's probably won't work on previous generations either.
Exactly like hardware PhysX - lower level API, exposes extra performance, only works with one vendor with specific cards, and only in rare sponsored titles.No,not like hardware PhysX.
Replaced drives that cost 10x less per GB?More like what SSDs have done to Hard Disc drives.
You mean NVAPI, which has been around for at least a year?Naturally NVDA isn't going to stand for that so I expect a similar API to appear fairly soon giving low level access to NV architecture.
There's probably won't work on previous generations either.
Why would a game studio add extra cost and development time to add Mantle on their own, when there is no payback. It doesnt work on nVidia, it doesnt work on Intel and it doesnt work on consoles.
AMD pays heavily for it to be even used. And this is AMDs official list.
http://www.amd.com/us/products/technologies/mantle/Pages/mantle.aspx#2
4 games, where one is 2015+. And one engine listed.