Originally Posted by gamervivek
It was your point, that it extends to all resolutions isn't against me.
??? - Seriously, whatever you're trying to say there makes absolutely no sense. I demonstrated my point there and you're just dismissing it with incomprehensible statements. All three resolutions demonstrate exactly what I calculated. No additional variance between the Gameworks off and on benchmarks at any resolution, completely invalidating the point you were trying to make about the gap at 1080p meaning the 980 somehow has more CPU overhead. That gap remains constant at all resolutions for the obvious reason that Maxwell will handle Gameworks tesselation better. There's nothing more to say about that, the only thing that changes whatsoever is the 390X's relative positioning in general across the resolutions, Gameworks or not.
No, your whole point was saying that it was 'higher cpu overhead on AMD'.
Your whole point was that the opposite was true, which I clearly demonstrated as being baseless. Now, the point's become to dismiss the obvious with "what ifs" despite no evidence provided on your own end.
My point was that there was something wrong, which would most likely be a CPU overhead problem given Bethesda and Fallout 4's CPU-limited issues (which new benchmarks verify) and the dissipation of the gap once crossing 4K. If there is at all any reason to believe it is instead a front-end problem, evidence would be nice. Otherwise, the obvious culprit does remain CPU overhead.
The AMD cpu overhead came into prominence with eurogamer's publishing of AMD's draw calls deficit especially with lower end CPUs. Their recommendation to do away with it was an i5, much less the overclocked i7 that are used in these benchmark reviews. In fact, most of the brouhaha was about the fact that AMD cards will perform lower with real users than in the reviews because they don't test with low end CPUs which are common among the gaming population.
The general interpretation of higher-end CPUs usually reducing the issue to a non-factor isn't a definite rule. There are clear exceptions out there like WoW at 1080p. As I've said -> Bethesda = CPU problems = overhead becomes a bigger issue.
TPU's latest 980Ti lightning review shows the 390X basically on par with 980 at 1080p. So just going 'AMD cpu overhead' doesn't really cut it.
As I said in the post you quoted, the general consensus is that the 390X is generally on par with the 980 these days. I'll stress it again, I said the same thing. Hence why deviation from that in the absence of Gameworks in a game from a developer notorious for CPU performance issues and in a game that should not be abnormally stressing any GPU's front-end does seem to be pointing towards AMD CPU overhead. You've not presented any reason to believe it's anything else.
So which side has the higher CPU overhead there?
The side with the better CPU scaling and significantly higher FPS with all those tested CPU configurations because it's otherwise proven itself to have superior CPU overhead management would be my guess. That chart doesn't really look like a CPU-limited test on the Fury X's end given it's consistently lower FPS, in any case.Edited by Serandur - 11/11/15 at 12:23am