OMG 225 watts. It will be like a toaster oven.

very weird infos here , no GDDR5X and HBM2 with 16gb vram shouldn't be out before Q4 !!!

OMG 225 watts. It will be like a toaster oven.

U mean like the next AMD cardz?Anyway go back to u cave troll,or go back to wccftech.

HBM2 is too way exp so impossible release this year.

GDDR5 and other stats looks really shady to me. Supposedly all cards provide 2x performance when compared to previous generation. I can't believe nVidia would make market decision like that. Remember the GTX 970 - they crippled it on purpose and introduced hardware bug as well 😀. I guess time will tell.

The shader core difference seems unlikely.

If those Titan specs are real then this shall be the first titan I will actually consider purchasing as it looks like it will give a decent upgrade to the Ti. Whereas the current 980Ti is basically identical to the TITAN X in every way apart from smaller memory buffer. I seriously SERIOUSLY doubt these are true. This would totally cripple the sales of current generation cards as with these specs even the X80 variant would totally destory the current 980Ti.

HBM2 is too way exp so impossible release this year.

AMD released Fury despite way too expensive too... Also it is for Titan then the word "expensive" is not a problem, AND there is no Pascal to release yet :bigsmile: Also i doubd about 2 GP100, one with inboard memory and the other in the traditional way, outside...

It must be GDDR5.

Seems fabricated but what do I know?

very weird infos here , no GDDR5X and HBM2 with 16gb vram shouldn't be out before Q4 !!!

Don't think either of those will be in high volume production by then end of the year, but the TITANX launching Q4 having HMB2 is achievable but would be in short supply.

Don't think either of those will be in high volume production by then end of the year, but the TITANX launching Q4 having HMB2 is achievable but would be in short supply.

Which would only 'help' the Titan price tags 😀

Specifications possibly real, would be specifications needed really from 2 node jumps. 28nm to 16nm with 20nm been skipped. Means they can pack 2x times the transistors in same die area. The GDDR5 will be the X version which is double bit rate pumped over standard GDDR5 making it twice as fast on average with regards to memory bandwidth. Anyone remember performance jump from 200 series aka the GTX 280 to GTX 480.

not buying it, i don't see why nvidia will use gddr5 instead of gddr5x. Also if the titan specs are true, then you can expect a 3k$ price.

I'll believe it when i see it. Also benchmarks will tell the tale. I'll probably skip that and next generation just to be sure that 4th DX12 gen cards are finally feature complete.

If these are true it is looking good for my next upgrade Volta as I will be skipping Pascal

In what universe is a 512 bit memory interface, clocked at 8000MHZ (effective i can only assume), capable of transfering 512GB data per second. 512 * 4000 (actual clock speed) * 2 (Double Data Rate) = 409.6GB/s transfer speed. To reach 512GB/s on a 512 bit interface, you would need 5GHZ clock speeds (10GHZ effective) As for shader cores and single precision. Assuming that the Pascal chip is of equal size, it seems plausible, considering the reduction from 28nm to 16nm = 57.1% the size. Comparing the 900 series to the 700 series, more specifically the ''Titan black'' which is the most powerful GK110 chip. Compared to the Titan X, which is the most powerful GM200 chip. Titan X 7.1% larger chip 12.9% more transistors 6.6% more Shader cores (nvidia dubbed them ''cuda cores'' 25% fewer Texture Mapping Units 100% more Render output units The 900 series is in practice, a combination of 1. larger chip. 2. improved design. 3. reduction in some areas. and 4. increase in other areas. The production technique, the work done at TSMC is still based on the same 28nm technology, though the yield and quality may have contributed slightly. Comparing the 900 series Titan X and the ''Pascal Titan'' Shader cores = 200% Texture units = 200% Texture mapping units / Raster operators = 200% Transistor count = 204.9% I call bull****. While the speccs may come from Nvidia, i have extreme doubts that these numbers are anything but loosely written down approximations meant for the designers and technicians. Why? I haven't the slightest idea, but i'm guessing it's tough to predict the exact specifications months, or even weeks in advance of large scale production. Doubtless, the guys making the chips, TSMC, cannot guarantee yield quality, thus Nvidia has to work with approximations.

Fake, if it were true the price of cards would be insane like start from 999$ to 1499$

If this chart is legit, it's very impressive, going from 250 Watts to 175 Watts and still be faster 🙂 I'm really looking forward to upgrade to 680, it's really on it's last legs when it comes to performance.

GP100 supports HBM 2 as well as GDDR5 ??? Highly Unlikely