Rumor: Nvidia GeForce 1180 / 2080

[NikosD]

We never compare models but prices.

2080 Ti has a 70% initial price more than 1080 Ti.

Is it going to be 70% faster than 1080 Ti in traditional games ?

Certainly no.

2080 has a price closer to 1080 Ti, that's why I did the comparison between them.

Since Ray-Tracing in gaming is simply not existent and with an unknown future, I can't find a reason to buy RTX cards at these prices.

They simply don't worth their price.

[huhn]

if the planned US none founder edition MSRP are real(1000 and 700 respectively) it's not to bad paying a premium for a flag ship is nothing new.

the 2080 ti has about 48 % more cuda cores than a 2080 and cost about 50 % more but that doesn't change the performance per dollar figures.

[NikosD]

Just announced MSI prices here in Greece.

2080 Ti ~ 1600 €

2080 ~ 1100 €

Is nVidia a completely insane company ?

Are the clients of nVidia completely insane ?

Will see...

[huhn]

and the taxes in greek have nothing to do with that?

and can you link the announcement plz.

and the more you look into these cards the more sense the prices makes and the less sense this whole product makes to me.

the 2080 ti is a ~750 mm² die that's 60 % more than a 1080 ti. this alone makes the card every expensive.

[NikosD]

The VAT here is 24%

The cards are very slow on RTX games and rushed to the market in order to hit AMD and differentiate further nVidia from AMD.

They are completely meaningless right now and with these prices nVidia should offer shares of the company, because it's like that.

It's like you are going to participate in their R&D expenses for something with no use and uncertain future.

We, as customers, don't care if companies are arrogant and make mistakes.

We are not going to pay their unreasonable ambitions.

The more I think about Turing of nVidia the more it looks like 10nm of Intel.

A disaster for the arrogant companies.

https://www.plaisio.gr/search.aspx?q...ode=searchlist

[huhn]

that's not an announcement from anyone.
or is this one too: https://geizhals.de/?cat=gra16_512&x...+-+RTX+2080+Ti

are they slow? they make bigger cards with relative performance taking the size into account and adding some goodies you may never use at all no one forces you to use ray tracing and you can do other things with these tensor cores to which is supposed to be giving you more performance but no one knows how this new fast AA looks.

if this is bad what is vega?

RX 580 is 230 nm and VEGA 64 is 510 nm and only 50 % faster.

don't get me wrong i'm not thrilled that the end user get's the same performance per dollar 2 years later this looks like a "refresh" with much bigger cards.

[NikosD]

What you say, just doesn't make sense.

You don't play games by the die size.

You don't buy cards by the die size.

You are not an investor to support companies.
Period.

[huhn]

nvidia has to pay for the die size...

a GPU with a bigger die cost more money in production. you are not going to pay more for production and ask less money for it that doesn't make sense.

[NikosD]

Oh my...

Things are even worse than I thought they were.

Nvidia’s Director of Technical Marketing, Tom Peterson, joined HotHardware on its 2.5 Geeks podcast and when queried about the RTX 2080 outperforming the GTX 1080 Ti, he said that he thinks there would be cases that would happen but couldn’t say for sure.

So, in all previous releases the xx70 outperformed the xx80 Ti card.

For Turing release, the Director of Technical Marketing of Nvidia, is NOT SURE if even 2080 card can outperform 1080 Ti.

What a disastrous performance!

What a disastrous release!

[nevcairiel]

Originally Posted by NikosD

So, in all previous releases the xx70 outperformed the xx80 Ti card.

That statement isn't really accurate. It was only true for Pascal (ie. a 1070 vs 980 Ti). One generation back, a 970 does in fact not beat a 780 Ti. And before that, a 680 Ti didn't exist. A 690 did, but that was a dual-GPU card, so thats quite a different beast. One generation does not make for an "all previous releases".
The conventional wisdom before Pascal used to be that with a generational change, the models move one up in the performance scale - not two. Pascal was the exception.

[huhn]

the big problem here is 12nm is not a real shrink compared to 16mn it's mostly more power efficient and doesn't allow better clocks.

[NikosD]

Originally Posted by nevcairiel

That statement isn't really accurate.
The conventional wisdom before Pascal used to be that with a generational change, the models move one up in the performance scale - not two. Pascal was the exception.

970 was very close to 780 Ti and it depends on the clock (overclocking) to find the winner.

1070 was clearly faster than 980 Ti.

So, the new norm after 2 years and 3 months of the latest release could someone expect to be the latest one - the Pascal's model.

Pascal could be considered not as an exception, but as the new norm since it's already too old and we only have two generation cards to refer to (970 vs 780 Ti and 1070 vs 980 Ti)

But even using your standards:

2070 is not close to performance to 1080 Ti.

It's a lot slower, could be like 50% slower, it's not close like 970 vs 780 Ti

I doubt 2070 will be faster than 1080, the previous model.
It will struggle to defeat it, if ever.

But we actually have a problem here.

Because your beloved friend, Mr. Leather Jacket Man, said than 2070 is faster than Titan Xp!

So, I actually agreed with him expecting 2070 to be faster than 1080 Ti.

And our friend here, huhn, believed him!

He believed the crook.

And now believe me the phrase "2070 is faster than Titan Xp" is a lot more inaccurate than "xx70 models were faster than xx80 Ti models before Turing cards"

But I am with you.

So far it seems that 2070 will be struggling to be faster than 1080 the previous generation one model up.
(we don't even dare to compare it with 1080 Ti)

2080 is not faster than 1080 Ti.

According to Nvidia it struggles to go ahead of the previous model.

Even with your standards, by all means, the Turing RTX 2000 cards is the definition of performance regression after more than two years of the latest release and the definition of overpriced cards.

Extremely overpriced cards.

They simply don't deliver.

[huhn]

so saying "the 2070 is supposed to outperform a titan Xp" is believing?

and you are ignoring that maxwell is 28 nm and pascal is 16 nm.
this is a very important difference and the reason i think Turing should be delayed for 7 nm. as far as i "know" 7 nm is ready for mass production.
and again 12 nm is just a 16 nm with an intel + so they use the "same" node there is not much you can gain from doing that.

the 2070 will have about 75 % of the performance of a 2080 make it a card that will be close to a 1080.

[NikosD]

So, we all agree that nVidia made a huge mistake by releasing this premature architecture so early, so overpriced, so damaged in performance.

And we should warn potential customers to stay away from this generation of cards - Turing cards.

Clients shouldn't pay the mistake of nVidia.

Agreed.

[nevcairiel]

Everyone should always judge hardware based on actual performance numbers, as provided by independent reviewers. We don't have those yet.

If those rumored numbers come close to reality, it may not be an upgrade for people that already own a 10-series card, but if you don't, might as well get a 2070 instead of a 1080 in the future (once prices settle weeks/months after launch). Unless of course you want a 2080 Ti with its rumored 40-50% increased performance over a 1080 Ti, afterall its the only way to get that level of performance, even if it costs you. But people also bought Titans before, which cost the same, and this time there is actually a huge performance difference, contrary to the Titans which were only a small upgrade over the Ti's of their time.

[NikosD]

But the problem is that 2070 is going to be slower than 1080, by a good chance.

Slower and with higher price, for so long time that probably a new architecture will come because there is no 2070 yet and in the next month.

Also for 2080 Ti latest rumors place the card around 25% faster than 1080 Ti with double the price!

It's simply not worth it.

[huhn]

you can rant about the prices 2 weeks after the release.
the planned MSRP for the 2070 is 500 dollars.

on paper the 2080 ti has 50 % more power than a 2080 and the price is about 50 % more.

the number of people buying a slower card for a higher price is not very high then they will simply not sell.

the vega 64 is kind of an alternate product to the 2070 so nvidia can't dictated the price of the 2070.

[Blue_MiSfit]

Not bright enough I'll wait until I can get one with 1000 nits. That one is only good for 400 average IIRC

[huhn]

it can do the vesa HDR 1000 the highest specified HDR spec i'm aware of.
you can get brightness numbers here:
https://www.rtings.com/monitor/revie...r/predator-x27

even with 10% it is far over 1000 nits. totally able to make you nightblind for the next 5 mins.
with an IPS typical "astounding" CR of 800-1350

[huhn]

the rumor about no tensor cores for 2060 or just staying with pascal are getting more clear.

while i can totally understand that a slower GPU will not be able to do ray tracing i have a hard time understanding why they should not be able to do DLSS or other potential use cases for tensor cores.
when i look at the market share of high end GPUs like 1080 or 1080 ti i you can clearly see a share about 4 after years of availability i see a problem in reaching the same number with msrp of the 20xx series in just a couple of years.

or with other word i don't see more than 2-6 % of user having tensor cores in the next 2 years. if the main stream cards don't have tensor cores.

i "predict" these numbers based on steam surveys: https://store.steampowered.com/hwsur...lcome-to-Steam