Where is Pascal? Nvidia’s Drive PX 2 prototype powered by Maxwell, not Pascal

[GoodBytes]

At least we can count on Jen-Hsun to always come out on stage with the next iteration of the Titan.  For some reason, I actually really like that display.  "His smooth, peppered hair, and leather jacket rustling in the artificially created wind as he revealed the next generation of high-tier performance.  The crowd 'ooed" and 'awed' as they witnessed him.  He was witnessed."

I like his presentation, they feel so unprepared, like he just comes in directly from his car to the stage, and starts talking... no reversal done, then goes, ok I am done, leave, drops the mic (sometimes) and goes: "back to resume my car drive".

[dragosudeki]

But not in the same sense. HBM is in its adoption face. Lots of component to make HBM work, have quickly seen a downfall in cost, whereas GDDR is in a more 'steady' downfall. Also HBM also put less complexitivity on PCB, leaving off a smaller footprint.

We are starting to derail my point: Couldn't HBM and GDDR5 (not GDDR5x) supplement their needs? Without making things more complex, by introducing a third memory technology to a subset of GPUs between GDDR5 and HBM?

Three memory technologies to help denote whether the card is low-end(GDDR5), mid (GDDR5x) or high-end(HBM)? Likely to see GDDR5 solely exist on the lower end cards where memory is less likely to be a bottleneck. Though, if there was a mid-range card that had GDDR5 and another with GDDR5x, it will get confusing. 

 

Want to sorta add to the multiple memory technologies. Do you think HBM is suffering a bit from all the technologies? I thought HBM would've been better than what we saw, but maybe it wasn't as good as it could have been due to the fact that they are still supporting GDDR5(and possibly now GDDR5x)?

[Sharkyx1]

Or they were tired of everyone over analyzing everything to fucking death.

"Over analyzing"

Hey look the date code is from January 2015!

If nvidia was just more open and said "this is a test model with 980" there would be no debacle

Maybe a couple would say "huh I guess pascal is gonna be late" but there could be no accusation of lying

[Tomsen]

Three memory technologies to help denote whether the card is low-end(GDDR5), mid (GDDR5x) or high-end(HBM)? Likely to see GDDR5 solely exist on the lower end cards where memory is less likely to be a bottleneck. Though, if there was a mid-range card that had GDDR5 and another with GDDR5x, it will get confusing. 

 

Want to sorta add to the multiple memory technologies. Do you think HBM is suffering a bit from all the technologies? I thought HBM would've been better than what we saw, but maybe it wasn't as good as it could have been due to the fact that they are still supporting GDDR5(and possibly now GDDR5x)?

I'm just wondering if there is actually any 'space' between GDDR5 and HBM for GDDR5x.

Surely, it is slowing down the adoption period ever so slightly, but all players are all pushing towards HBM (or any other integrated memory).

Well, bandwidth is really a useless number in itself. You need some actual GPU to effectively use all that bandwidth in its work.

When we see some big GPUs (next generation and/or the generation after), then GDDR wouldn't be sufficient enough.

[Mo_z_Art]

I don't understand why everyone is so cool with nvidia lying. If AMD had done this everyone would be very upset about it...

[VanayadGaming]

I don't understand why everyone is so cool with nvidia lying. If AMD had done this everyone would be very upset about it...

Because most of the people on this forum are nvidia fanboys. Lying about the state of a product is illegal when you are a publicly traded company and SEC is involved. But hey.