Exploring DirectX 12: 3DMark API Overhead Feature Test
by Ryan Smith & Ian Cutress on March 27, 2015 8:00 AM EST- Posted in
- GPUs
- Radeon
- Futuremark
- GeForce
- 3DMark
- DirectX 12
Closing Thoughts
Wrapping things up, Futuremark’s latest benchmark certainly gives us a new view on DirectX 12, and of course another data point in looking at the performance of the forthcoming API.
Since being announced last year – and really, since Mantle was announced in 2013 – the initial focus on low-level APIs has been on draw call throughput, and for good reason. The current high-level API paradigm has significant CPU overhead and at the same time fails to scale well with multiple CPU cores, leading to a sort of worst-case scenario for trying to push draw calls. At the same time console developers have low enjoyed lower-level access and the accompanying improvement in draw calls, a benefit that is an issue for the PC in the age of so many multiplatform titles.
DirectX 12 then will be a radical overhaul to how GPU programming works, but at its most basic level it’s a fix for the draw call problem. And as we’ve seen in Star Swarm and now the 3DMark API Overhead Feature Test, the results are nothing short of dramatic. With the low-level API offering a 10x-20x increase in draw call throughput, any sort of draw call problems the PC was facing with high-level APIs is thoroughly put to rest by the new API. With the ability to push upwards of 20 million draw calls per second, PC developers should finally be able to break away from doing tricks to minimize draw calls in the name of performance and focus on other aspects of game design.
GDC 2014 - DirectX 12 Unveiled: 3DMark 2011 CPU Time: Direct3D 11 vs. Direct3D 12
Of course at the same time we need to be clear that 3DMark’s API Overhead Feature Test is a synthetic test – and is so by design – so the performance we’re looking at today is just one small slice of the overall performance picture. Real world game performance gains will undoubtedly be much smaller, especially if games aren’t using a large number of draw calls in the first place. But the important part is that it sets the stage for future games to use a much larger number of draw calls and/or spend less time trying to minimize the number of calls. And of course we can’t ignore the multi-threading benefits from DirectX 12, as while multi-threaded games are relatively old now, the inability to scale up throughput with additional cores has always been an issue that DirectX 12 will help to solve.
Ultimately we’re looking at just one test, and a synthetic test at that, but as gamers if we want better understand why game developers such as Johan Andersson have been pushing so hard for low-level APIs, the results of this benchmark are exactly why. From discrete to integrated, top to bottom, every performance level of PC stands to gain from DirectX 12, and for virtually all of them the draw call gains are going to be immense. DirectX 12 won’t change the world, but it will change the face of game programming for the better, and it will be very interesting to see just what developers can do with the API starting later this year.
Facebook
Twitter
RSS
113 Comments
View All Comments
Barilla - Friday, March 27, 2015 - link
Yeah, 285 might outperform the 980 but keep in mind this is a very specific test only focusing one one aspect of rendering a frame. I mean, a man can accelerate faster than an F1 car over very short distance of few meters, but that doesn't really mean much in the real world.Keeping my fingers crossed though since I've always been AMD fan and I hope they can egain some market share.
AndrewJacksonZA - Friday, March 27, 2015 - link
What @Barilla said.akamateau - Thursday, April 30, 2015 - link
ALL Radeon will outperfrom nVidia if the Radeon dGPU is fed by AMD siliocn. Intel degrades AMD Radeon silicon.lowlymarine - Friday, March 27, 2015 - link
The Wii U is based on PowerPC 7xx/G3 and RV770, not ARM or GCN. Unless you're referring the the recently-announced "NX" which for all we know may not even be a traditional home console.eanazag - Friday, March 27, 2015 - link
I did some math on what available information there is for the 390 versus the Titan and it seems to go toe-to-toe. If it has a lead, it won't be huge. I compared some leaked slides with the numbers Anandtech had for the Titan review. I suspect it will use a lot more electricity though and create more heat.We can likely expect it to have much more compute built-in.
Refuge - Friday, March 27, 2015 - link
It doesn't really say anything about the performance of the 285x or the 980, or any of the others for that matter.Just because they can make a couple more million draw calls a second doesn't mean you will ever see anything.
Just means the video card is really good at screaming for more work, not doing it. Hell these draw calls are all way beyond anything realistic anyhow, you will NEVER have one of these GPU's ever make half as many draw calls as being shown in this test in any real world usage scenario.
Vayra - Saturday, March 28, 2015 - link
If anything I would say that the Nvidia cards are more refined and more balanced, based on these draw call results. Nvidia has optimized more to get the most out of Dx11 while AMD shows a lead on actual hardware capacity through the greater gains both relative and absolute on draw call numbers. It is the very same trend you also see in the amount of hardware both companies use in their top tiered cards to achieve similar performance - AMD uses more, Nvidia uses less and wins on efficiency gains.Crunchy005 - Monday, March 30, 2015 - link
Well AMD does win at double precision even over the Titan X. Nvidia pulled a lot of the double precision hardware to save on power, one of the ways maxwell is more efficient. This isn't a bad thing in the gaming community but ruins the Titan X for a lot of compute scenarios. So Nvidia really did lose out a lot in one area to beat AMD at efficiency.http://anandtech.com/show/9059/the-nvidia-geforce-...
akamateau - Thursday, April 30, 2015 - link
If Anandtech benched Radeon silicon being fed by AMD FX or A10 then NO INTEL/nVidia siliocn would even come close to AMD GCN enabled Asynchronous Shader hardware. Intel and nVidia are now second rate siliocn in a DX12 world.Why do yo think so many folks trashed MANTLE. FUD!!!!
xenol - Friday, March 27, 2015 - link
Even if there were no consoles, games wouldn't be targeted for high end PCs. They will be targeted for lower end PCs to increase the amount of market share they can reach. Maybe once in a blue moon, some developer who doesn't care about that will make the next Crysis.