Here's another one. 780Ti / i7-3770 gets obliterated by 770 / i5-3570K.
The only explanation I can think of for this kind of stuff is that Nvidia has settings and optimizations in their DX12 drivers that are on for some cards, but not others.
There's always the possibility that Nvidia optimized their hardware for Maxwell years ago on the drawing board for what DirectX 11 had to offer. There's the possibility that maybe Maxwell's hardware is better suited in games for DirectX 11 than DirectX 12.
As things stand right now, AMD showcases the kind of performance that DirectX 12 can deliver over DirectX 11, and Nvidia offers more consistent performance between the two APIs. Nvidia’s strong performance in DX11, however, is overshadowed by negative scaling in DirectX 12 and the complete non-existence of any MSAA bug. Given this, it’s hard not to think that Nvidia’s strenuous objections to Ashes had more to do with its decision to focus on DX11 performance over DX12 or its hardware’s lackluster performance when running in that API.
When there is no game yet maybe Nvidia didn't put much work into it? It is pre-alpha right? They might have just been lazy.
Oxide doesn't know what Nvidia did with their driver either, they offered code for the game but that doesn't mean they did any work in their drivers for it yet. Nvidia usually releases a game ready driver for new games right at release. I don't know how long they hold those optimizations out.
I was thinking along the same lines.This reminds me of Tessellation. Recall how NV pretty much said Tessellation wasn't important. Until Fermi. Then it's all about Tessellation.
I'm expecting the same with Pascal. It's all about DX12 & VR post-Pascal.
Mostly from Nvidia they seem to be all up in arms and quick to discredit an alpha level benchmark.Overreacting doesn't begin to describe the conclusions being drawn from this benchmark.
While that could be, why do that when you advertise full DX12 support? Now I know what people will say, supporting it doesn't mean performance in it and I get that but still doesn't add up to me. Besides, 780 and 770 aren't even Maxwell cards. I could accept that we are seeing the potential of AMD cards come out now and Nvidia cards just can't keep pace when you remove overhead. However, it's too early to call it like that.
I'm leaning heavily toward the need for better drivers for DX12 from Nvidia.
While that could be, why do that when you advertise full DX12 support? Now I know what people will say, supporting it doesn't mean performance in it and I get that but still doesn't add up to me. Besides, 780 and 770 aren't even Maxwell cards. I could accept that we are seeing the potential of AMD cards come out now and Nvidia cards just can't keep pace when you remove overhead. However, it's too early to call it like that.
I'm leaning heavily toward the need for better drivers for DX12 from Nvidia.
I agree with this, still too early to draw conclusions, especially with a bench that nvidia doesnt believe will show true dx12 potential.
Our work with Microsoft on DirectX 12 began more than four years ago with discussions about reducing resource overhead. For the past year, NVIDIA has been working closely with the DirectX team to deliver a working design and implementation of DX12 at GDC. - See more at: http://blogs.nvidia.com/blog/2014/03/20/directx-12/#sthash.Lg1CBec0.dpuf
well the NVIDIA driver shloud be optimised
date: march 20, 2014
It would have left them with little time to rearchitect Maxwell if DirectX 12 was a popup thing for them.
"NVIDIA will support the DX12 API on all the DX11-class GPUs it has shipped; these belong to the Fermi, Kepler and Maxwell architectural families. - See more at: http://blogs.nvidia.com/blog/2014/03/20/directx-12/#sthash.Lg1CBec0.hr50ELd0.dpuf"
So I guess that means it's fine to say that AMD's GCN cards all support DX12? Even though they're only feature level 11.1, Fermi and Kepler are even further back at 11.0.
They've been working on DX12 w/ MSFT since 2010 as they claimed when it was announced.
Announced yes, but when did the they start making it a low level api?
Here's another one. 780Ti / i7-3770 gets obliterated by 770 / i5-3570K.
<image>
The only explanation I can think of for this kind of stuff is that Nvidia has settings and optimizations in their DX12 drivers that are on for some cards, but not others.
Thank goodness for no middleware! This is how games should be developed and helmed by the developer themselves beginning to end."All IHVs have had access to our source code for over year, and we can confirm that both Nvidia and AMD compile our very latest changes on a daily basis and have been running our application in their labs for months."
Then, farther on:
"Often we get asked about fairness, that is, usually if in regards to treating Nvidia and AMD equally? Are we working closer with one vendor then another? The answer is that we have an open access policy. Our goal is to make our game run as fast as possible on everyones machine, regardless of what hardware our players have.
To this end, we have made our source code available to Microsoft, Nvidia, AMD and Intel for over a year. We have received a huge amount of feedback. For example, when Nvidia noticed that a specific shader was taking a particularly long time on their hardware, they offered an optimized shader that made things faster which we integrated into our code.
We only have two requirements for implementing vendor optimizations: We require that it not be a loss for other hardware implementations, and we require that it doesnt move the engine architecture backward (that is, we are not jeopardizing the future for the present)."
I agree @raghu78!
AMD was criticized for designing GCN as being so future focused with poor efficiency for the current, but they really had no choice. They don't have the budget to constantly come up with new uarch. GCN was made to last and its made to excel with a new API beyond DX11.
They gambled on GCN & Mantle's success and later pawning for free to various players (Apple, Kronos), which would have to force MS to also adopt it or fall behind. A good move given their financial situation.
As said, the battle at DX12 will certainly be GCN vs Pascal.
What's really interesting is why Faildozer performs so badly. Again we were all told to expect great multi-core scaling and the tests show its HALF the speed of an i7.
The 770 results in the wccftech article appear to be a CPU test (second line) vs "Full System Test" whatever differences that implies. The average CPU framerate number appears to be the same (ish) between them.
Not sure how the benchmark setup works but I think wccftech just screwed up here and ran the wrong thing.
Reading various review, the benchmark is very flexible, so that one can setup to test CPU bottlenecks, GPU bottlenecks or a mixture. On a CPU bottleneck test, graphics settings are minimized.