How is this any different with Maxwell prices? I admit the Titan price seems off but the Ti's prices are in line withwhat past pricing has been.
On another note, I noticed no one has really said anything about GP102, if it exists. Correct me if I'm wrong but haven't the past Titan's and Ti's been based on Gx100 dies?
My guess is HBM2 isn't ready in mass, or just may be way overkill for desktop cards. Looks like they split the 'big chip' into two: GP100 w/ a HBM2 mem controller for Tesla and Quadro cards and GP102 w/ a GDDR5X mem controller for Titan and 1080ti cards...that is only if that table from chiphell is true. Looks like Nvidia is using the newer memory technologies to really differentiate each product segment, rather than just total amount of memory. Also kinda explains why nvidia went with the slower speed gddr5x for 1080, because they're reserving the faster speeds for the ti.
tesla/quadro: hbm2
Titan/Ti/x80: GDDR5X
x70 and below: GDDR5
Yes but they haven't always been fully enabled, or uncut dies, that have been used for the Titan or the x80Ti IIRC.
Not true, AMD is releasing at least one of the Vega cards with HBM2. It's just that Nvidia is having trouble with HBM2 atm & is the main reason why GP100, with HBM2, is not coming to the desktop.
As I said previously, it's just Nvidia not being able to handle HBM2 as AMD can, probably with the experience they've had since Fury. Notice how users demeaned the Fury launch for being as late as it was, & overpriced, now we'll see if the same standards apply to the big Pascal launch.