• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

[VideoCardz] NVIDIA to preview 20nm high-end Maxwell tomorrow

Page 4 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Unified virtual memory seems to have slipped from Maxwell to Pascal (which is now the new name for Volta)

GTC 2014
http://images.anandtech.com/doci/7894/GTC-2014-021.jpg

GTC 2013
http://images.anandtech.com/doci/6842/20130319_101008.JPG

No 20nm product preview was disappointing.

Not sure it been dropped we need more info on 20nm Maxwell parts .
But then again for dGPU UVM would be limiting as system memory is so slow but with N-link BW is increased .
I think unified memory is more important to APU , then dGPU . The PCI-E was system bottleneck BW wise .
Seems today focus was more on CUDA stuff .

Not sure if GTC is used for gaming feature releases .
how many days does GTC last ?
 
Last edited:
2 titans combined (1k$ each)
On top of that, 1000$ premium to pay.

Way to go. They got high from all that money titan made...
 
No talk about Maxwell at all, and indication that a key Maxwell feature has slipped to 2016. Meanwhile, the focus is on yet another Kepler part. Yikes...
 
This will be the most highly anticipated GPU flagship release of all time if true, due to the overwhelmingly positive ink 750ti has received.

I am on the record as guessing GM2xx will hit the shelves before the standard narrative suggests. I guess we will find out! I still find it hard to believe they would have been able to keep such news under wraps.

It isn't a stretch to say that they could be alone @ 20nm for 6+ months.


No talk about Maxwell at all, and indication that a key Maxwell feature has slipped to 2016. Meanwhile, the focus is on yet
another Kepler part. Yikes...

Looks like the prophecy was a little optimistic.
 
Looks like the prophecy was a little optimistic.

Don't get all broken up about it now. 😉

Seriously though, Maxwell will be here before you know it. 20nm Maxwell that it. If you're looking for exact dates, or even ballpark dates, I can't help you.
But like all other things, they eventually creep up and get here all on there own.
 
Unified virtual memory seems to have slipped from Maxwell to Pascal (which is now the new name for Volta)

GTC 2014
http://images.anandtech.com/doci/7894/GTC-2014-021.jpg

GTC 2013
http://images.anandtech.com/doci/6842/20130319_101008.JPG

No 20nm product preview was disappointing.
This, exactly this. Tech in general is getting squeezed pretty hard right now (between technology changes/limits, competition, consumer interest change, etc.), so I understand there being delays and what not. That said, there hasn't been a substantial upgrade to my 7970 in over 2.5 years. That's really telling of the times in my book.

First company that gets a decent 20nm flagship out the door gets my cash.
 
Don't get all broken up about it now. 😉

Seriously though, Maxwell will be here before you know it. 20nm Maxwell that it. If you're looking for exact dates, or even ballpark dates, I can't help you.
But like all other things, they eventually creep up and get here all on there own.

Im broken up about it, my bottom lip is quivering ha,joke.was hoping for more info oh well.
 
This, exactly this. Tech in general is getting squeezed pretty hard right now (between technology changes/limits, competition, consumer interest change, etc.), so I understand there being delays and what not. That said, there hasn't been a substantial upgrade to my 7970 in over 2.5 years. That's really telling of the times in my book.

First company that gets a decent 20nm flagship out the door gets my cash.

Agreed.
 
So will Nvidia milk the anticipation again, releasing a fully fledged version of a card at $1000, a gimped version to gamers at half the price, only to release the full version for gamers later on? It worked wonderfully last time.
 
So will Nvidia milk the anticipation again, releasing a fully fledged version of a card at $1000, a gimped version to gamers at half the price, only to release the full version for gamers later on? It worked wonderfully last time.

Yep i think they will.*shrugs*.
 
So will Nvidia milk the anticipation again, releasing a fully fledged version of a card at $1000, a gimped version to gamers at half the price, only to release the full version for gamers later on? It worked wonderfully last time.

Imagine if they would have released GK110 at the same time they released GK104. It would have been bad news for the competition... :awe:
 
Imagine if they would have released GK110 at the same time they released GK104. It would have been bad news for the competition... :awe:

Yep, and I'd have a pair of those instead instead of putzing around with an assortment of 680s and 7970s. Would never have purchased at $1k though D:
 
I'm unconvinced. If NVidia had a 20nm Maxwell coming this year, they would have talked about it today.

I was under the impression that Maxwell was in the 750ti so all a maxwell 2014 slide says is that the 750ti is still here....
 
How would unified memory work on a discrete graphics card anyway? Wouldn't pci express be a huge bottleneck in bandwidth and latency? I think we'd need a new graphics specific interface, a new agp of some type.
 
Back
Top