• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

NVIDIA's SUPER Tease Rumored to Translate Into an Entire Lineup Shift Upwards for Turing

Im never, ever fine with paying the price of a whole mainstream low end PC on a Gpu($1200)
That too I suppose is a stupid personal stand.

You suppose wrong , as i said buy whatever fits your needs and wallet as far as im aware nobody forces you to spend 1200 bucks on a GPU !

The stupid stand is to not buy from X or Y company for some ideological reason . The only thing companies care about is your wallet and that applies to all companies so why should you care about any company instead of the actual product you paying for that's the point im trying to make , but hey to each his own i guess !

These current Rumors are based on a Chinese poster and a German Toms hardware GPU writer expanding on them.

Nvidia first said Computex, At Computex they said E3 so far nothing with 1 day to go.

To my knowledge TPU article is based on wccftech ''rumors '' and that has been confirmed by Videocardz ( the existance of RTX Super not exact specs ) so yeah that makes those '' rumors '' pretty solid .
 
Last edited:
To my knowledge TPU article is based on wccftech ''rumors '' and that has been confirmed by Videocardz ( the existance of RTX Super not exact specs ) so yeah that makes those '' rumors '' pretty solid .

We wont know until Nvidia says anything.

Videocardz is also based on Wccftech and Vonguru which they are using each other as sources.
 
Videocardz is also based on Wccftech and Vonguru which they are using each other as sources.

Nope , quote form Videocardz : '' Disclaimer: we have independently confirmed the SUPER series. '' .

When Videocardz publishes something it's no longer a rumor :laugh: but i agree we will probably know more when Nvidia is ready to talk .
 
Last edited:
Tl;dr

Price cuts without actually cutting prices.
Nvidia is effectively slashing the price of the 2080ti, 2080 and 2070 by $500, $200, and $150 respectively.

Man I hope this is true, this news has made my day. I'm going to run over nvidia forums with popcorn and watch as the entitled people slowly wizen up to what Nvidia has done and start crying. I imagine it's going to be Titan Pascal dumpster fire all over again, would have been awesome if they did this at the 6mo mark.
Uh ... no. You should re-read the rumored specs listed above.

RTX 2060: 1920 CUDA Cores (TU106)
RTX 2060 SUPER: 2176 CUDA cores (TU106), +13%
RTX 2070: 2304 CUDA cores (TU106), +6%
RTX 2070 SUPER: 2560 CUDA cores (TU104), +11%
RTX 2080: 2944 CUDA cores (TU104), +15%
RTX 2080 SUPER: 3072 CUDA cores (TU102), +4%
RTX 2080 TI: 4352 CUDA cores (TU102), +41%

From the looks of this, the 2060 SUPER will come close to matching 2070 performance (at least when OC'd), but the rest are nowhere near their higher-tier counterparts. If the reported 2080 SUPER specs are correct, there's still a 41% gap between it and the 2080 Ti. If this was a "$500 price cut" there would need to be equivalent performance between the 2080 SUPER and Ti. There definitely won't be, particularly if it still has a 256-bit RAM bus.

Doubt it would sting if the margins were overinflated to begin with. Feels like a correction if anything.
Partly, sure, but remember how gargantuan Turing dice are. The 2070 SUPER will move from a 445mm2 die to a 545mm2 die, and the 2080 SUPER from 545mm2 to 754mm2. Even if the 12nm process is relatively cheap, that's not an insignificant increase, and will force them to sell cut-down chips rather than fully enabled ones - which I can't believe is an actual problem given the maturity of the process. Sure, they probably have stockpiles of dud chips that they haven't been able to use for fully enabled SKUs up until now, but at some point this move is going to start costing them significantly. If they need to sell a TU104 off the line as a 2080 SUPER rather than a 2080 Ti, that's $300-400 less money per sale. Even subtracting a bit from the lower BOM for the card, this is significant. I doubt Nvidia cares, but it's a move that shows that they're feeling some pressure.
 
Hmmmm. The plot thickens :)
 
You suppose wrong , as i said buy whatever fits your needs and wallet as far as im aware nobody forces you to spend 1200 bucks on a GPU !

The stupid stand is to not buy from X or Y company for some ideological reason . The only thing companies care about is your wallet and that applies to all companies so why should you care about any company instead of the actual product you paying for that's the point im trying to make , but hey to each his own i guess !



To my knowledge TPU article is based on wccftech ''rumors '' and that has been confirmed by Videocardz ( the existance of RTX Super not exact specs ) so yeah that makes those '' rumors '' pretty solid .
My opinion of your opinion is just as lowly, self self self eh, I want and be damned the consequences.

I better not see you moan about price then eh.
 
@kings mentioned something about the expense of moving to 7nm, that's what I'm referring to. AMD seems to have been able to move to 7nm and do it quite well without having to raise prices. Why can't nVidia do the same?

Not all 7nm are the same. The only thing that really matters is transistor density.
 
So correct me if I'm wrong, does this mean that a 2080 will become a 2070 with the same price as the 2080 and a new 2080 will come out with an even higher price?

This information is not out yet, only speculations... AFAIK
 
So correct me if I'm wrong, does this mean that a 2080 will become a 2070 with the same price as the 2080 and a new 2080 will come out with an even higher price?
As far as I understand, the 2080 will become the 2070 Super, at the 2070 price point. And so on.
 
Uh ... no. You should re-read the rumored specs listed above.

RTX 2060: 1920 CUDA Cores (TU106)
RTX 2060 SUPER: 2176 CUDA cores (TU106), +13%
RTX 2070: 2304 CUDA cores (TU106), +6%
RTX 2070 SUPER: 2560 CUDA cores (TU104), +11%
RTX 2080: 2944 CUDA cores (TU104), +15%
RTX 2080 SUPER: 3072 CUDA cores (TU102), +4%
RTX 2080 TI: 4352 CUDA cores (TU102), +41%

From the looks of this, the 2060 SUPER will come close to matching 2070 performance (at least when OC'd), but the rest are nowhere near their higher-tier counterparts. If the reported 2080 SUPER specs are correct, there's still a 41% gap between it and the 2080 Ti. If this was a "$500 price cut" there would need to be equivalent performance between the 2080 SUPER and Ti. There definitely won't be, particularly if it still has a 256-bit RAM bus.


Partly, sure, but remember how gargantuan Turing dice are. The 2070 SUPER will move from a 445mm2 die to a 545mm2 die, and the 2080 SUPER from 545mm2 to 754mm2. Even if the 12nm process is relatively cheap, that's not an insignificant increase, and will force them to sell cut-down chips rather than fully enabled ones - which I can't believe is an actual problem given the maturity of the process. Sure, they probably have stockpiles of dud chips that they haven't been able to use for fully enabled SKUs up until now, but at some point this move is going to start costing them significantly. If they need to sell a TU104 off the line as a 2080 SUPER rather than a 2080 Ti, that's $300-400 less money per sale. Even subtracting a bit from the lower BOM for the card, this is significant. I doubt Nvidia cares, but it's a move that shows that they're feeling some pressure.

Well only real reason why RTX 2080 Super would use tu102 chip is to have more than 256bit memory bus thus bigger vram amount. 3072 cc with 256bit is full fat tu104, no reason what so ever to use overly big chip for such configured card.

This has got to be one of the most disgusting rebrands I've seen in a while.

And yet there's not even single sku that is rumored to be specced as just simple rebrand(You don't call RX 580 a RX 470 rebrand either, or do you. Or well there's that asian version, but let's not go there). Just new config skus with clusterf**k naming scheme. More the merrier I guess... But if Nvidia don't lower the prices of current offering, but just EOL them and replace these supderduper cards on current price slots. The 2019 year of gaming graphics cards will be expensive and pretty boring.
 
I would not expect the 2070 Super to be really close to the present 2080 FE. Right now the 2080 FE is about 20% faster than a 2070 FE overall according to benches here and the 2080 has 28% more cores than the 2070 with 7.5% faster clocks on the 2080 as well. They both have a 256 bit Memory Bus.

If the 2070 Super comes in at 2560 cores then that is still 15% less cores than the present 2080. Assuming it will have a higher clock speed that will help but anyone can OC a 2080 also. How much the 2070 Super can OC remains to be seen.

My guess when all is said and done a 2070 Super OC will still be at least around 10% slower than a 2080 FE OC.
 
Last edited:
A chart would be nice... :)
@EarthDog
124894



I sorta of feel cheated out of the extra 256 shader cores, and 2 GB GDDR6 (which now is likely a 256-bit bus.)
 
Last edited:
I would be SUPER pissed if I bought a new Nvidia card and their knee jerk reaction to Navi was to undercut the value of the card I just bought.

Marketing at its finest, any RTX owners SUPER happy about their now devalued card?
Why can't people behave rationally any more? (I'm talking to several in this thread and the usual opinionators on Youtube etc.)
Many claim to want competition, yet they bash Nvidia (or Intel) every time they refresh their lineup.
It used to be regarded as a good thing when a company refreshed their lineup, it's a natural thing as yields improve and production costs go down.
Did AMD screw their customers when they refreshed RX 480 with RX 580 or R9 290X with R9 390X?
 
Why can't people behave rationally any more? (I'm talking to several in this thread and the usual opinionators on Youtube etc.)
Many claim to want competition, yet they bash Nvidia (or Intel) every time they refresh their lineup.
It used to be regarded as a good thing when a company refreshed their lineup, it's a natural thing as yields improve and production costs go down.
Did AMD screw their customers when they refreshed RX 480 with RX 580 or R9 290X with R9 390X?
Nvidia and Intel are only allowed to come up with a radically new design at every launch and offer their stuff at the same or lower prices. AMD is the underdog and they can be excused when not doing the same.

E.g: look at how everybody reacted to Turing pricing and then look at the reactions then Navi comes in the same performance ballpark at the same exact prices. One year later.
 
The bins are full... let The Re-Branding start!

@kings mentioned something about the expense of moving to 7nm, that's what I'm referring to. AMD seems to have been able to move to 7nm and do it quite well without having to raise prices. Why can't nVidia do the same?
No no they can't that ship sailed for Jen-Hsun a while ago, and is why he throws-shade at TSMC. He didn't go with them... he' had made his deal with Samsung... so we'll see what he gets. Price might be good but price is only one matrix. He's made his bed and now he has to "promote" it will be "super" comfy-cozy.
 
Last edited:
What do you mean no issues? They have a die half the size of Nvidia's, but their finished product costs just as much. That was the only implied issue.
Do you have a prove that "they costs just as much"?
Just dont eat anything Nvidia throws at you, like "our cards cost too much, that's why they are expensive" or the reason why they didn't move to 7nm. They are just dishonest and not only not telling the truth but they are obviously and intentionally lying. (Yes there is a huge difference between keeping silent and not saying anything and between lying) Nvidia didn't move to 7nm because there were no NEED for it (yet). That is the only and the only reason for that.
 
Last edited:
Nvidia and Intel are only allowed to come up with a radically new design at every launch and offer their stuff at the same or lower prices. AMD is the underdog and they can be excused when not doing the same.

E.g: look at how everybody reacted to Turing pricing and then look at the reactions then Navi comes in the same performance ballpark at the same exact prices. One year later.

The hate towards Nvidia is reaching ridiculous levels. It feels like some people stop thinking rationally!

It's amazing how we got to the point of criticizing them for supposedly going to release better and faster cards!
 
I want to see dual RT 5700 XT with shared VRAM over infinity fabric.
Basically if they could deliver the concept as Ryzen chips.
Manufacturing smaller GPUs and stacking them together it always gonna be cheaper.
 
I want to see dual RT 5700 XT with shared VRAM over infinity fabric.
Multiply GPUs will only work if there invisible to the game engine either through the driver or the API (DirectX/Vulkan.)
 
I want to see dual RT 5700 XT with shared VRAM over infinity fabric.
Basically if they could deliver the concept as Ryzen chips.
Manufacturing smaller GPUs and stacking them together it always gonna be cheaper.
A MCM GPU would need a common scheduler module organizing multiple modules of compute clusters, while operating similarly to a monolithic GPU (with some constraints of course). Designs like this might be coming in the future, but Navi is not designed for this.

Putting two Navi chips with an interconnect would be no different from connecting Nvidia GPUs with NVLink, and would have to be operated in the same way we do multi-GPU today.
 

Videocardz has finally released some specs and it turns out 2080 Super won't use TU102 chip just full TU104 and so on for the rest wich is a bit disapointing this is really the bare minimum Nvidia could do but it's not like they really need to do more anyways . Hopefully vanilla 20 series will get at least a good pricecut .

Nothing to see here for 1080Ti owners , next year is when the exciting stuff comes out .
 
Last edited:
I would be SUPER pissed if I bought a new Nvidia card and their knee jerk reaction to Navi was to undercut the value of the card I just bought.

Marketing at its finest, any RTX owners SUPER happy about their now devalued card?

Wait... isn't that what AMD was doing since every release post HD7970? Maxwell? "Here, have this rebrand" And isn't Navi the exact same thing?

GPUs are supposed to devalue fast, if they do not, it means progress is stalling. That is what we've been looking at post-Pascal to present... 1080ti performance still sells for about MSRP.

This SUPER feels a bit like a Kepler refresh to me. Not a bad thing IMO, more cards = lower prices.
 
  • Like
Reactions: 64K
This SUPER feels a bit like a Kepler refresh to me. Not a bad thing IMO, more cards = lower prices.

That's my take so far as well.
 
How exactly is the card they just bought devalued? Does it all of a sudden get less fps in games, now that a new card is out?

Of course, you can always wait and get something newer and faster. But that will always be true. Should people not buy Zen 2 processors, because Zen 3 will be coming down the road, not to mention Zen 4 or 5?

Devalued by the same exact card now being a tier lower in pricing.

I bought a X1800XT and low, the X1900XT displaced it and devalued it so it lost a couple hundred bucks in value for resale.

Did it still work? Yes.
Was it worth the cost? No.

It's about consumer value, if I buy a premium product I would expect it to be valued as a premium product.

Just my opinion.
 
Back
Top