The Von MatricesI think the much simpler explanation is the one that Cadaveca posted at the last leak. The different SKUs are getting mixed up and 3200SP and 8GB is for a dual-GPU card, the successor to GTX 690. The single GPU part, successor to the GTX 680/GTX 770 would therefore have 4GB and 1600SP. To me, this is much more reasonable.

Remember, GTX 750 Ti outperforms the GTX 660 Ti by 20% and yet it has 20% fewer shaders, so assuming the same scaling, a 1600SP GTX 880 would have almost 50% more performance than GTX 770/680, completely in line with a generational improvement.

btarunrI know, right? It made sense for GTX 560 Ti (GF114) to have 384sp, and 256-bit/32 ROP. A chip with four times the cores (1536sp) with 256-bit/32 ROP is so totally unimaginable! NVIDIA would never make such a chip. :rolleyes:

Oh wait...it did. The GK104.:slap:

Ermagerd...3200 SP and 256-bit/32 ROP? Totally unimaginable and borderline blasphemous!

TheGuruStudNo. Just no.

The Von MatricesIf we had no idea what the Maxwell architecture was, then I could see your point. But since we have GM107 and we know it has fewer shaders than GK106 (for more performance), then it be a very unexpected move for GM104 to have double the shaders of GK104.



Care to explain your reasoning?

TheGuruStud750 is not competition for a 660 nor faster than a 660.

ZoneDymoAnd you know this because you asked every person who owns such a config right?
*Removed (language)*
If you are just browsing the internet or any of those other stuff you can and will do on a pc other then gaming which barely require a gpu of any kind, you dont want your pc to use up tons of electricity.

robert3892I don't think you'll see good 4K support until 2015

Prima.VeraMake that 2016 and realistically speaking 2017. ;)

Long have been the times when you could have a 75%-90% performance increase over previews generation (3870-4870-5870 anyone?).
Now we should be lucky if there is a stunning 25% increase. ;)

btarunrwill be based on the brand new "GM204" silicon, which most reports suggest, is based on the existing 28 nm silicon fab process (...) When 20 nm is finally smooth, it wouldn't surprise us if NVIDIA optically shrinks these chips to the new process, like it did to the G92 (from 65 nm to 55 nm). The GM204 chip is rumored to feature 3,200 CUDA cores, 200 TMUs, 32 ROPs, and a 256-bit wide GDDR5 memory interface. It succeeds the company's current workhorse chip, the GK104.

The Von MatricesI have to disagree with you here. 20nm isn't going to be less expensive than 28nm per transistor, so there's no financial incentive for a die shrink and thus it won't be done. It makes more financial sense to sell a large 28nm chip than a smaller 20nm chip.

20nm will only be for the extreme high end this generation and will only be used in cases where it's impossible to manufacture a larger 28nm chip (e.g. you can't make a 28nm, 15 billion transistor, 1100mm^2 GM100). 20nm won't become mainstream until NVidia (or anyone else) can't achieve their performance targets on 28nm, which likely will not happen until the generation after this.

btarunrI know, right? It made sense for GTX 560 Ti (GF114) to have 384sp, and 256-bit/32 ROP. A chip with four times the cores (1536sp) with 256-bit/32 ROP is so totally unimaginable! NVIDIA would never make such a chip. :rolleyes:

Oh wait...it did. The GK104.:slap:

Ermagerd...3200 SP and 256-bit/32 ROP? Totally unimaginable and borderline blasphemous!

ZoneDymoSeems unlikely, the R9 295x2 does a fine job at 4k, if the next AMD card (r9 380x?) single card is as fast as that one we should be well on our way

RejZoRThey usually are, though not always. The HD4800 to HD5800 transition was awesome, because the boost was actually 100%. I wish every gfx iteration would be in such a way. Otherwise we pay twice the price for 30% bumps that are almost an insult to gamers.

GhostRyderThat's just probably how its going to remain for the foreseeable future sadly. On all fronts the walls are starting to slow us down to crawls when it comes to making things bigger, faster, stronger, (etc joke). CPU's barely get faster, GPU's jump by small increments, its just the way things are going to keep going. Likely things will only change once they start working on power consumption and getting it down then eventually throwing that out the window and turning the cards loose. Or maybe there is something coming that will cause a huge jump, who knows in reality...

Prima.VeraRead again what I've wrote. Your logic applies only if the next generation cards are 100% faster than the previews one (295x2 is a dual GPU btw...)

RCoonAlright, I don't expect any miracles then. Same process, but more cores? It's just Kepler with 400 more cores on a slightly more energy efficient architecture. So they might deal with the heat increase by adding more cores by using the slightly more efficient archi, and in turn gain a small performance increase from 2880 cores to 3200. I'm assuming the 870 will have ~3000 cores to hit a price point between the two.

Call me cynical, but I don't see the 780ti lowering in price and the 880 taking its place. The 880 is going to hit a higher price point. Then there's the simple fact that the 860 is probably going to just be a rebranded 780ti and everything else below will likely be a rebrand too. Ugh... new GPU releases are so disappointing these days... nothing to get excited about, especially when you know the price gouging is imminent.