Fable Legends Early Preview: DirectX 12 Benchmark Analysis
by Ryan Smith, Ian Cutress & Daniel Williams on September 24, 2015 9:00 AM ESTCPU Scaling
When it comes to how well a game scales with a processor, DirectX 12 is somewhat of a mixed bag. This is due to two reasons – it allows GPU commands to be issued by each CPU core, therefore removing the single core performance limit that hindered a number of DX11 titles and aiding configurations with fewer core counts or lower clock speeds. On the other side of the coin is that it because it allows all the threads in a system to issue commands, it can pile on the work during heavy scenes, moving the cliff edge for high powered cards further down the line or making the visual effects at the high end very impressive, which is perhaps something benchmarking like this won’t capture.
For our CPU scaling tests, we took the two high end cards tested and placed them in each of our Core i7 (6C/12T), Core i5 (4C/4T) and Core i3 (2C/4T) environments, at three different resolution/setting configurations similar to the previous page, and recorded the results.
Looking solely at the GTX 980 Ti to begin, and we see that for now the Fable Benchmark only scales at the low resolution and graphics quality. Moving up to 1080p or 4K sees similar performance no matter what the processor – perhaps even a slight decrease at 4K but this is well within a 2% variation.
On the Fury X, the tale is similar and yet stranger. The Fable benchmark is canned, so it should be running the same data each time – but in all three circumstances the Core i7 trails behind the Core i5. Perhaps in this instance there are too many threads on the processor contesting for bandwidth, giving some slight cache pressure (one wonders if some eDRAM might help). But again we see no real scaling improvement moving from Core i3 to Core i7 for our 1920x1080 and 3840x2160.
As we’ve seen in previous reviews, the effects of CPU scaling with regards resolution are dependent on both the CPU architecture and the GPU architecture, with each GPU manufacturer performing differently and two different models in the same silicon family also differing in scaling results. To that end, we actually see a boost at 1280x720 with the AMD 7970 and the GTX 680 when moving from the Core i3 to the Core i7.
If we look at the rendering time breakdown between GPUs on high end configurations, we get the following data. Numbers here are listed in milliseconds, so lower is better:
Looking at the 980Ti and Fury X we see that NVIDIA is significantly faster at GBuffer rendering, Dynamic Global Illumination, and Compute Shader Simulation & Culling. Meanwhile AMD pulls narrower leads in every other category including the ambiguous 'other'.
Dropping down a couple of tiers with the GTX 970 and R9 290X, we see some minor variations. The R9 290X has good leads in dynamic lighting, and 'other', with smaller leads in Compute Shader Simulation & Culling and Post Processing. The GTX 970 benefits on dynamic global illumination significantly.
What do these numbers mean? Overall it appears that NVIDIA has a strong hold on deferred rendering and global illumination and AMD has benefits with dynamic lighting and compute.
Facebook
Twitter
RSS
141 Comments
View All Comments
HotBBQ - Friday, September 25, 2015 - link
Please avoid using green and red together for plots. It's nigh impossible to distinguish if you are red-green colorblind (the most common).Crunchy005 - Friday, September 25, 2015 - link
So we have a 680, 970, 980ti. Why is there a 980 missing and no 700 series cards from nvidia? The 700s were the original cards to go against things like the 7970, 290, 290x. Would be nice see whether those cards are still relevant, although the lack of them showing in benchmarks says otherwise. Also the 980 missing is a bit concerning.Daniel Williams - Friday, September 25, 2015 - link
It's mostly time constraints that limit our GPU selection. So many GPU's with not so many hours in the day. In this case Ryan got told about this benchmark just two days before leaving for the Samsung SSD global summit and just had time to bench the cards and hand the numbers to the rest of us for the writeup.It surely would be great if we had time to test everything. :-)
Oxford Guy - Friday, September 25, 2015 - link
Didn't Ashes come out first?Daniel Williams - Friday, September 25, 2015 - link
Yes but our schedule didn't work out. We will likely look at it at a later time, closer to launch.Oxford Guy - Saturday, September 26, 2015 - link
So the benchmark that favors AMD is brushed to the side but this one fits right into the schedule.This is the sort of stuff that makes people wonder about this site's neutrality.
Brett Howse - Saturday, September 26, 2015 - link
I think you are fishing a bit here. We didn't even have a chance to test Ashes because of when it came out (right at Intel's Developer Forum) so how would we even know it favored AMD? Regardless, now that Daniel is hired on hopefully this will alleviate the backlog on things like this. Unfortunately we are a very small team so we can't test everything we would like to, but that doesn't mean we don't want to test it.Oxford Guy - Sunday, September 27, 2015 - link
Ashes came out before this benchmark, right? So, how does it make sense that this one was tested first? I guess you'd know by reading the ArsTechnica article that showed up to a 70% increase in performance for the 290X over DX11 as well as much better minimum frame rates.Ananke - Friday, September 25, 2015 - link
Hmm, this review is kinda pathetic...NVidia has NO async scheduler in the GPU, the scheduler is in the driver, aka it needs CPU cycles. Then, async processors are one per compute cluster instead one per compute unit, i.e. lesser number.So, once you run a Dx12 game with all AI inside, in a heavy scene it will be CPU constrained and the GPU driver will not have enough resource to schedule, and it will drop performance significantly. Unless, you somehow manage to prioritize the GPU driver, aka have dedicated CPU thread/core for it in the game engine...which is exactly what Dx12 was supposed to avoid - higher level of virtualization. That abstract layer of Dx11 is not there anymore.
So, yeah, NVidia is great in geometry calculations, it's always been, this review confirms it again.
The_Countess - Friday, September 25, 2015 - link
often the fury X GAINS FPS as the CPU speed goes down from i7 to i5 and i3.3 FPS gained in the ultra benchmark going from the i7 to the i3, and 7 in the low benchmark between the i7 and the i5.