NVIDIA GeForce GTX 980 Ti Silicon Marked "GM200-310"

[RejZoR]

Afaik, R9-390 is still planned for June 2015...

 

[HumanSmoke]

Well I expect at least a "reveal" I mean why host a "PC Gaming Show" If your not gonna bring some new toys to play with. They certainly can't be promoting the 290X...

It might be a let down in any case, just as GM200 was " just" a scaled up GM204, it looks increasingly likely that Fiji is " just" a scaled up Tonga - Hence my comment above about GM200 and Fiji feeling like stopgap measures (or proof of concept at best), and the real cause for excitement being Pascal and Arctic Islands.

 

[bogami]

All together more and more scent marketing to move. (Both want to keep using primarily the price for outgoing 28nm production which is becoming cheaper than anything else, what we see in AMD which lowered the price and the delay in 20 nm technology) are thus again thrown sand in the eye PLL. For thick profit.
It shows that the nvidia wait what AMD can currently offer in 20nm and then released her version of 20nm or are major problems?, were there again ' profit marketing tactic? We'll see.
Somehow not escape the feeling that nVidia is becoming thick pig who it must be maintain from the poor population vith low tricks . Horror where there are times when we get the strongest 4 GPU option for € 1,200 and now is 1 card is so expensive. Horror same manipulation : Market ,information ,people, ITD. They fell so low.

 

[64K]

All together more and more scent marketing to move. (Both want to keep using primarily the price for outgoing 28nm production which is becoming cheaper than anything else, what we see in AMD which lowered the price and the delay in 20 nm technology) are thus again thrown sand in the eye PLL. For thick profit.
It shows that the nvidia wait what AMD can currently offer in 20nm and then released her version of 20nm or are major problems?, were there again ' profit marketing tactic? We'll see.
Somehow not escape the feeling that nVidia is becoming thick pig who it must be maintain from the poor population vith low tricks . Horror where there are times when we get the strongest 4 GPU option for € 1,200 and now is 1 card is so expensive. Horror same manipulation : Market ,information ,people, ITD. They fell so low.

Nvidia is doing what all successful enterprises do. They charge what the market will bear. They do whatever they can to ensure profit for their investors/owners just like all successful businesses do.

 

[radrok]

Nvidia is doing what all successful enterprises do. They charge what the market will bear. They do whatever they can to ensure profit for their investors/owners just like all successful businesses do.

Which is a smart business path

I am pretty sure their next GPU will be a 6GB non cut down variant and we'll probably see a dual GPU earlier than expected, hopefull for a sane price this time around.

 

[arbiter]

It shows that the nvidia wait what AMD can currently offer in 20nm and then released her version of 20nm or are major problems?

20nm was a flop, amd fiji will be using 28nm.

 

[radrok]

20nm was a flop, amd fiji will be using 28nm.

I read somewhere that 20nm was never meant for big chips, only for small socs etc?

 

[HumanSmoke]

I read somewhere that 20nm was never meant for big chips, only for small socs etc?

That would be correct. Ever since TSMC canned its CLN20G process in 2012, there hasn't been a viable 20nm process for large die/large power budget IC's. Even TSMC's own slides confirm CLN20SOC being low power optimized

...and as for Globalfoundries, they made no secret of the fact that 20nm LPM stands for Low Power Manufacturing, and moreover, GloFo's process page which I linked to here, has now disappeared entirely, nor that the company pretty much jettisoned it in favour of pouring funds into licence manufacture of Samsung's 14nm-XM process.
...and yet, some people just seem content to bury their heads in the sand and write their own narrative completely at odds with known fact and the foundries own literature.

 

[looniam]

I like how everyone says that he 980 Ti will be "Cut down without the memory problem." Everyone here does realize that the architecture of Maxwell makes that inherently impossible right?

The memory and cores are directly linked. Disable any of the cores and a proportional amount of the memory will need to be disabled as well - which besides being wasteful, isn't that bad as long as they don't lie about it.

no they're not . . the 970 had L2 cache disabled for binning.

 

[HumanSmoke]

no they're not . . the 970 had L2 cache disabled for binning.

I think it was just a lazy attempt at trolling the thread TBH. Even a casual glance at the GM204 SKU's would show that the (for instance) GTX 980M with 1536 cores (or 128 fewer than the GTX 970) still maintains a 256-bit/ 2MB L2 cache/64 ROP specification of the full GPU (and 4 or 8GB of vRAM). Maybe Captain_Tom should do some further reading before putting forward his deeply flawed observation, which would then show that memory allocation is dependant upon the number of memory controllers, 1 (or 2 if in clamshell mode) memory IC's per 32-bit memory channel (two 32-bit memory channels per 64-bit memory controller) . Memory size then being defined by IC density.

@looniam
I don't know if the GTX 970's issue was what Captain_Tom was driving at, although you're right that the 970's logic segmentation caused the issue you're talking about- reducing ROPs and their attendant L2 without proportionally reducing the memory controllers as Nvidia did with the 970M and 965M.

 

[bogami]

Nvidia is doing what all successful enterprises do. They charge what the market will bear. They do whatever they can to ensure profit for their investors/owners just like all successful businesses do.

Are you very rich or oa blind .it is not a success but manipulation.

 

[matar]

Now is the time Nvidia should fix the GTX 970 with a GTX 970Ti now that card at the same price $329 I would Buy.

 

[arbiter]

Are you very rich or oa blind .it is not a success but manipulation.

Well Which of the 2 companies AMD/Nvidia is strong and which is pretty close to going under?

 

[64K]

Are you very rich or oa blind .it is not a success but manipulation.

Neither but I can look at financial statements for the truth. Nvidia's net profit margins are average for the industry with the exception of AMD which is drowning in red ink.

 

[rtwjunkie]

I like how everyone says that he 980 Ti will be "Cut down without the memory problem." Everyone here does realize that the architecture of Maxwell makes that inherently impossible right?

The memory and cores are directly linked. Disable any of the cores and a proportional amount of the memory will need to be disabled as well - which besides being wasteful, isn't that bad as long as they don't lie about it.

You do realize this isn't a Maxwell problem? It was a GM204 problem when they disabled cores/memory controllers. THAT chip only. It is not an inherent problem in the other GM chip monikers, or at least no evidence has been submitted to support that assertion. Unless you have inside engineering knowledge of Nvidia's HQ.......?.

@bogami While I do appreciate your point, businesses are not in business to cater to people's ability to pay. That viewpoint is directly from an economic system that has proven it can only fail, wherever implemented (Socialism, for those that need help) -"From each according to his ability, To each according to his need (ability to pay)." This was popularized by Karl Marx, but originated with Louis Blanc, the French socialist in 1851.

I guarrantee if you had a business, you would charge what people are willing to pay. Why? You have bills to pay, and maybe a family to support, and would like to move up someday. They are a business, not a non-profit agency. All successful businesses charge what people are willing to py. Those that charge too little (sales and special events notwithstanding) to cover all their necessary research, development, production, personnel and marketing expenses do not profit, and eventually go under.

 

[Dalai Brahma]

For me, a 960Ti 3/4GB 192bit (< $250) would be enough... and I would be so glad.
Release it, Nvidia!! and cut prices!

 

[64K]

We may have a reveal of the GTX 980 Ti coming in 2-3 weeks and possibly it will go on sale in stores right after that if the rumor about the 2015 Computex Trade Show is correct.

http://www.kitguru.net/components/g...ce-geforce-gtx-980-ti-at-computex-next-month/

I figured the R9 390x would drop first but maybe not.

 

[arbiter]

We may have a reveal of the GTX 980 Ti coming in 2-3 weeks and possibly it will go on sale in stores right after that if the rumor about the 2015 Computex Trade Show is correct.

http://www.kitguru.net/components/g...ce-geforce-gtx-980-ti-at-computex-next-month/

I figured the R9 390x would drop first but maybe not.

Nvidia will do some damage if they put that at 6-700$ if the recent rumors that 390x 4gb yes 4gb will start at 850$.

 

[64K]

More rumors that the GTX 980 Ti will preempt AMD's Fijis.

http://videocardz.com/55566/nvidia-geforce-gtx-980-ti-performance-benchmarks

According to this site review sample 980 Ti have already been sent out and it looks like the rumor that it's going to be a cut down GM200 is being reinforced and it will probably be a little slower than a Titan X. My guess is that this can be made up for by increased overclocking potential due to superior non reference coolers which will be available.