NVIDIA Segregates Turing GPUs; Factory Overclocking Forbidden on the Cheaper Variant

[Vayra86]

Kepler that old bastard... btw gtx660ti was bigger gk104 die not the same as non-ti used.

Shit - you're right!

295mm² - still is significantly smaller though and it had disabled SMXes including a bus width cut to 192 bit.

 

[Captain_Tom]

Well a name's just a name. If you take a look at die size however - and take into account that a 'similar' die would actually become ever so much smaller with every node shrink - those are going up even for TU106. I think the best metric is however not die size but raw performance. And TU wastes way too much die space on workload specific performance, while leaving raw performance near-stagnant, despite a die size increase.

No matter how you dice it, the 2070 is on the lower end of the bracket pal. Period. Also this is a new node, so you can't compare die sizes to the other nodes (And like you said, much of the die size is wasted for non-gaming uses).

That would be like saying the 1080 Ti is almost the same as the GTX 970 since they have similar die sizes - except you can't say that because you are comparing 16nm dies to 28nm dies. They are different processes with different capabilities.

Fact:

-100
-102
-104 Midrange
-106 Low End
-108

 

[theoneandonlymrk]

So in short term the announced pricing is looking more and more sketchy by the day, with tariffs low stock /high presales, and now the knowledge we are not getting a fair shake at an Oc without paying more im flabbergasted, in all our old games an extra 30% performance is not enough for close to twice the money.
No thanks.

 

[Solidstate89]

dumbing it down till user is by nature dependent on the feature is imo the manufacturer assuming control

So you're just making up your own definition now huh.

 

[Divide Overflow]

This will make a mockery out of MSRPs.

 

[DeathtoGnomes]

saw it on arstechnia you can Google nvidia scanner for rtx

actually its your responsibility to provide proof of your argument. Basically I'm saying what you posted is baseless and wont be taken seriously.

 

[Xzibit]

Well Tom Petersen said on Gamers Nexus that Nvidia does not even look if gpu is OC at RMA process.

He also said all RTXs are voltage locked.

 

[jabbadap]

No matter how you dice it, the 2070 is on the lower end of the bracket pal. Period. Also this is a new node, so you can't compare die sizes to the other nodes (And like you said, much of the die size is wasted for non-gaming uses).

That would be like saying the 1080 Ti is almost the same as the GTX 970 since they have similar die sizes - except you can't say that because you are comparing 16nm dies to 28nm dies. They are different processes with different capabilities.

Fact:

-100
-102
-104 Midrange
-106 Low End
-108

Fact by whom? Nvidia's own marketing have been like this:
GX-102/100: Enthusiast
GX-104: High end
GX-106: Mid range
GX-107: Low end
GX-108: Entry/media

He also said all RTXs are voltage locked.

Where exactly? He said it's have been very restricted, but not exactly locked altogether.

 

[Xzibit]

Where exactly? He said it's have been very restricted, but not exactly locked altogether.

3:15+
Steve: Community decision is that its locked, Tell me why i'm wrong
Tom: Your not wrong

 

[enxo218]

So you're just making up your own definition now huh.

I said in my opinion (which meant to highlight an attempt at a closed ecosystem by nvidia) please leave me alone

actually its your responsibility to provide proof of your argument. Basically I'm saying what you posted is baseless and wont be taken seriously.

I pointed towards the existence of the api and its implementation that isn't baseless and as per responsibility I am unable to use all features of this forum site on opera browser on my phone

 

[killferd]

I actually like this if it results in lower cost for the consumers.
You can still manually overclock all GPU's the only thing is now the chips are presorted according to their capacity (something like this is already happening in RAM samsung vs micron chips...). IF this clarity is passed on to consumer i am all for it.
Now you can in real time choose based on your preference, the only caveat being device ID are hidden or rather not shown on the box so how will we know which is which?

 

[Caring1]

dumbing it down till user is by nature dependent on the feature is imo the manufacturer assuming control

Car analogies spring to mind, as they always do.
Modern vehicles have more driver aids than ever before, and younger drivers seem to know less and less about what makes them tick, or how to repair anything, let alone change a flat tire.
With self driving cars being seen as the future (and Nvidia involved heavily in that) drivers wont need to know anything other than how to get in and set the destination.

 

[Captain_Tom]

Fact by whom? Nvidia's own marketing have been like this:
GX-102/100: Enthusiast
GX-104: High end
GX-106: Mid range
GX-107: Low end
GX-108: Entry/media

LOL your rebuttal is Nvidia's own marketing BS.

AMD really does face an uphill challenge when you have sheep throwing their own koolaid at other people. Also you do notice your own twisted marketing defense still places the $600 "2070" as mid range... right? That's fine, go buy Nvidia's newest $600 550 Ti if you want to.... smh

 

[terroralpha]

i don't know how i feel about this. on one hand, if you are looking for serious overclocking this makes it easier to find a card that will likely clock higher. on the other hand, people who's pockets aren't as deep will have no chance of getting a really good card. also, we lose the excitement of getting a new card and trying to figure out just how good your card is. going forward, we'll know pretty much what to expect depending on how much cash we drop.

having said that, i managed to pre order a gigabyte 2080 Ti "windforce OC" card for $1030 after tax. given that it is a factory overclocked card, i guess it means that it's a binned GPU? that would be awesome.

 

[hat]

Hmm... not really a big deal. More expensive, shinier go faster cards have existed as long as I've been in this game. Doesn't seem too far off from paying extra for ASUS STRIX MAXOC+WTFLOL8GD5 as opposed to the more bland model.

In fact, for some of us, it might actually be a good thing? What if you could buy the bullshit model and flash it with the 1337 BIOS? BIOS editing days are pretty dead, at least for nVidia, but at least you can try flashing a premium bios on a bland model.

 

[Hardware Geek]

Doesn't seem like such a terrible thing to me. They are still letting the end-user overclock their own chips. A factory overclocked model is probably going to cost you more anyway some knowing that the chip has been binned for better overclocking potential you should theoretically mean it lasts longer anyway. That being said I still think this generation is way overpriced and I'm not touching it.

 

[jabbadap]

LOL your rebuttal is Nvidia's own marketing BS.

AMD really does face an uphill challenge when you have sheep throwing their own koolaid at other people. Also you do notice your own twisted marketing defense still places the $600 "2070" as mid range... right? That's fine, go buy Nvidia's newest $600 550 Ti if you want to.... smh

So in your word Vega is mid range GPU and polaris10/20 is low end. Well yes rtx 2070 is made from the chip which have usually been mid range, I give you that. But it's not always all that black and white either, in Fermi years gf104/114 was considered midrange. Kepler changed that to high end as performance was there. Similar way RTX2070 performance will be pretty high endish too(Probably around + couple of percentages up from gtx1080/RX Vega⁶⁴) and yeah price for that will be high end class.

 

[DeathtoGnomes]

I pointed towards the existence of the api and its implementation that isn't baseless and as per responsibility I am unable to use all features of this forum site on opera browser on my phone

directly copy and pasting a link is still an option, you're just making excuses for being lazy. its ok I get it.

 

[jmcosta]

clickbait title
no difference to the enduser

 

[qubit]

Oh FFS, NVIDIA wouldn't pull this stunt if they had more competition. AMD desperately needs to become competitive again, like right now.

 

[yogurt_21]

Hmm... not really a big deal. More expensive, shinier go faster cards have existed as long as I've been in this game. Doesn't seem too far off from paying extra for ASUS STRIX MAXOC+WTFLOL8GD5 as opposed to the more bland model.

In fact, for some of us, it might actually be a good thing? What if you could buy the bullshit model and flash it with the 1337 BIOS? BIOS editing days are pretty dead, at least for nVidia, but at least you can try flashing a premium bios on a bland model.

I was thinking this should make it easier to identify cards that are more likely to OC better, you would just need to get others to post up the device id of the card you're interested in to be able to tell the binning. I kind of like it.

The only problem then is the same old price issue. ie we don't like the trend of increasing card prices. Competition is the only thing that will fix that. Of course that means AMD needs to take note of how much NV is able to make off each card. Even if PC's aren't really their focus right now, business models can shift if there's money to be made.

 

[Sasqui]

Eh, after playing with a 1070 Ti and running into the hardware based power limiters, is this a surprise?

 

[yakk]

Great first step to controlling and monitizing additional revenue from overclocking from clients willing to play more.

After this bit of news dies down, next generation I would imagine nvidia will again tighten the noose more to wring more money from their client base while at the same time assuming more control over what their AIBs can& can't do, if they still want them at that point.

 

[londiste]

Eh, after playing with a 1070 Ti and running into the hardware based power limiters, is this a surprise?

All Pascal cards are limited at:
- Voltage: 1.09V
- Power: TDP+20% (somewhat configurable by manufacturer, I have seen 13% to 30%)

 

[hat]

Great first step to controlling and monitizing additional revenue from overclocking from clients willing to play more.

After this bit of news dies down, next generation I would imagine nvidia will again tighten the noose more to wring more money from their client base while at the same time assuming more control over what their AIBs can& can't do, if they still want them at that point.

Not really? Board partners (like ASUS) often sell multiple versions of the same card, asking more money for the better ones.