The DirectX 12 Performance Preview: AMD, NVIDIA, & Star Swarm
by Ryan Smith on February 6, 2015 2:00 PM EST- Posted in
- GPUs
- AMD
- Microsoft
- NVIDIA
- DirectX 12
Mid Quality Performance
Since our evaluation so far has been focused on performance with Star Swarm’s most resource intensive Extreme setting, we wanted to shake things up by trying a lower quality setting.
In this case Star Swarm’s various quality levels adjust both the CPU and GPU workload, with the Mid quality setting reducing both the number of draw calls generated and the amount of work generated per frame for the GPU. As a result we’re not adjusting just the CPU or the GPU workload, but it can give us an idea of what to expect from DirectX 12 and Star Swarm at lower settings more suitable for weaker systems.
Even with this lower quality setting, the CPU results tell us that only the GTX 980 is truly CPU bottlenecked with 2 cores. Everything else from the 290X on down can reach its GPU limit with a relatively weak CPU.
Overall the numbers are different, but the lineup is the same whether it’s Extreme quality or Mid quality. Every vendor still sees massive gains from enabling DirectX 12, though the overall gains aren’t quite as great as with Extreme quality. Meanwhile GTX 750 Ti in particular continues to see the weakest gains from DirectX 12, at only 14% for a 2 core configuration, thanks to a combination of NVIDIA’s lower CPU consumption and earlier GPU bottleneck.
Facebook
Twitter
RSS
245 Comments
View All Comments
dakishimesan - Friday, February 6, 2015 - link
Because DirectX 10 and WDDM 2.0 are tied at the hip, and by extension tied to Windows 10, DirectX 12 will only be available under Windows 10.dakishimesan - Friday, February 6, 2015 - link
PS: great article.FlushedBubblyJock - Sunday, February 15, 2015 - link
First thoughts: R9 290X dx11=8 frames mantle=46 frames TEST= TOTAL FRAUDAlthough the difference there is what AMD told us mantle would do, only in this gigantic liefest is such hilarity achieved.
Another big industry lie-test blubbered out to the sheep at large.
0ldman79 - Monday, February 16, 2015 - link
It looks more like the people that coded that game are not very experienced and have spent far more time optimizing for future API than DX11.Christopher1 - Monday, February 16, 2015 - link
Not necessarily. DX11 no matter how 'optimized' still does not get you as close 'to the metal' as Mantle does. So yes, there can be these kinds of extreme differences in FPS.The_Countess666 - Thursday, February 19, 2015 - link
they are in fact very experienced. but they choose to do the things that previously DX11 bottleneck prevented them from doing in the past.0ldman79 - Saturday, February 21, 2015 - link
That makes sense, still not quite an apples to apples comparison in that situation, though using previously unavailable features on the new API tends to show the differences.The question still remains, will we see similar improvements on the current crop of DX11 games?
I don't think that will be the case, though I could be wrong.
Seems the gains are from multithreading, which is part of the DX11 or 11.1 spec.
RobATiOyP - Sunday, February 21, 2016 - link
Of course you won't see such a performance increase, because games have to be designed and tuned to what the platform is capable of. The console API's have allowed games, lower level access, Mantle, DX12 & Vulkan are about removing a bottleneck caused by the assumptions in DX11 & OpenGL API's which were designed when GPUs were novel items and much evolution has occured since. Those doubting the benchmark, please say why a graphics application would not want to do more draw calls per second!Fishymachine - Monday, February 16, 2015 - link
DX11 can manage up 10k draw calls, Star Storms makes 100k. Also Assasins Creed Unity makes up to 50k in case you wanted a retail game that would skyrocket in low API(there's a spot where even 2 GTX980 get 17fps)The_Countess666 - Thursday, February 19, 2015 - link
this engine was spefiically written to do all the things that previously DX11 doesn't allow game developers to do. it was designed to run headlong into every bottleneck that DX11 has.it is in fact a great demonstrations of the weaknesses of DX11.
the fact that nvidia gets higher framerates in dx11 then ATI is because they optimized the hell out of this game. that isn't viable (costs too much, far too time consuming) for every game and was purely done by nvidia for marketing, but all it really does is further illustrate the need for a low level API where the burden of optimizations is shifted to the game engine developers where it belongs, not the driver developers.