The NVIDIA GeForce GTX 1080 & GTX 1070 Founders Editions Review: Kicking Off the FinFET Generation
by Ryan Smith on July 20, 2016 8:45 AM ESTCrysis 3
Still one of our most punishing benchmarks 3 years later, Crysis 3 needs no introduction. Crytek’s DX11 masterpiece, Crysis 3’s Very High settings still punish even the best of video cards, never mind the rest. Along with its high performance requirements, Crysis 3 is a rather balanced game in terms of power consumption and vendor optimizations. As a result it can give us a good look at how our video cards stack up on average, and later on in this article how power consumption plays out.
This being the first cycle we’ve used the Very High settings, it’s humorous to see a $700 video card getting 35fps on a 3 year old game. Very High settings give Crysis 3 a level of visual quality many games still can’t match, but the tradeoff is that it obliterates most video cards. We’re probably still 3-4 years out from a video card that can run at 4K with 4x MSAA at 60fps, never mind accomplishing that without the MSAA.
The GTX 1080 does however at least get the distinction of being the one and only card to crack 30fps at 4K. Though 30fps is not suggested for Crysis, it can legitimately claim to be the only card that can even handle the game at 4K with a playable framerate at this time. Otherwise if we turn down the resolution, the GTX 1080 is now the only card to crack 60fps at 1440p. Very close to that mark though is the GTX 1070, which at 58.1fps is a small overclock away from 60fps.
Looking at the generational comparisons, GTX 1080 and GTX 1070 lead by a bit less than usual, at 62% and 51% respectively. The GTX 1080/1070 gap on the other hand is pretty typical, with the GTX 1080 leading by 27% at 4K, 23% at 1440p, and 21% at 1080p.
Facebook
Twitter
RSS
200 Comments
View All Comments
patrickjp93 - Wednesday, July 20, 2016 - link
That doesn't actually support your point...Scali - Wednesday, July 20, 2016 - link
Did I read a different article?Because the article that I read said that the 'holes' would be pretty similar on Maxwell v2 and Pascal, given that they have very similar architectures. However, Pascal is more efficient at filling the holes with its dynamic repartitioning.
mr.techguru - Wednesday, July 20, 2016 - link
Just Ordered the MSI GeForce GTX 1070 Gaming X , way better than 1060 / 480. NVidia Nail it :)tipoo - Wednesday, July 20, 2016 - link
" NVIDIA tells us that it can be done in under 100us (0.1ms), or about 170,000 clock cycles."Is my understanding right that Polaris, and I think even earlier with late GCN parts, could seamlessly interleave per-clock? So 170,000 times faster than Pascal in clock cycles (less in total time, but still above 100,000 times faster)?
Scali - Wednesday, July 20, 2016 - link
That seems highly unlikely. Switching to another task is going to take some time, because you also need to switch all the registers, buffers, caches need to be re-filled etc.The only way to avoid most of that is to duplicate the whole register file, like HyperThreading does. That's doable on an x86 CPU, but a GPU has way more registers.
Besides, as we can see, nVidia's approach is fast enough in practice. Why throw tons of silicon on making context switching faster than it needs to be? You want to avoid context switches as much as possible anyway.
Sadly AMD doesn't seem to go into any detail, but I'm pretty sure it's going to be in the same ballpark.
My guess is that what AMD calls an 'ACE' is actually very similar to the SMs and their command queues on the Pascal side.
Ryan Smith - Wednesday, July 20, 2016 - link
Task switching is separate from interleaving. Interleaving takes place on all GPUs as a basic form of latency hiding (GPUs are very high latency).The big difference is that interleaving uses different threads from the same task; task switching by its very nature loads up another task entirely.
Scali - Thursday, July 21, 2016 - link
After re-reading AMD's asynchronous shader PDF, it seems that AMD also speaks of 'interleaving' when they switch a graphics CU to a compute task after the graphics task has completed. So 'interleaving' at task level, rather than at instruction level.Which would be pretty much the same as NVidia's Dynamic Load Balancing in Pascal.
eddman - Thursday, July 21, 2016 - link
The more I read about async computing in Polaris and Pascal, the more I realize that the implementations are not much different.As Ryan pointed out, it seems that the reason that Polaris, and GCN as a whole, benefit more from async is the architecture of the GPU itself, being wider and having more ALUs.
Nonetheless, I'm sure we're still going to see comments like "Polaris does async in hardware. Pascal is hopeless with its software async hack".
Matt Doyle - Wednesday, July 20, 2016 - link
Typo in the lead sentence of HPC vs. Consumer: Divergence paragraph: "Pascal in an architecture that...""is" instead of "in"
Matt Doyle - Wednesday, July 20, 2016 - link
Feeding Pascal page, "GDDR5X uses a 16n prefetch, which is twice the size of GDDR5’s 8n prefect."Prefect = prefetch