Considering he counts the xtors from HBM in the total...
and CAT, yes, Vega was already slated for 2017, not sure if you knew that.
-
Competitor rules
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
Nvidia GTC16 Webcast Live Stream@5pm/9am PDT *Jen looks great in leather.*
- Thread starter tommybhoy
- Start date
Considering he counts the xtors from HBM in the total...
and CAT, yes, Vega was already slated for 2017, not sure if you knew that.
I get the impression they're going to show nothing.
G(really T)P100 artist's impression. It the Tesla makes it in '16 it'll be right at the end (highly doubt it). No possible way a 600mm2 chip is going to make it into consumer (Geforce Titan / 1080Ti) products before the end of Q1 '17 (likely Q2 '17). Transistor count is a bit lower than expected, and given the huge 600mm2 size, they may well have density issues ...
Tegra PX2 Drive ... board in a glass case, this time with no identifying marks on the heatsink so that people can't identify that it's obviously still Maxwell.
If they had real GP104 they'd have lead with it. They're not going to announce it at the end after people have already tuned out after they've reiterated everything they've been talking about for 2 years re: Tesla / machine learning / NVLink etc.
Probably Q4 for first GP104 .... if lucky.
G(really T)P100 artist's impression. It the Tesla makes it in '16 it'll be right at the end (highly doubt it). No possible way a 600mm2 chip is going to make it into consumer (Geforce Titan / 1080Ti) products before the end of Q1 '17 (likely Q2 '17). Transistor count is a bit lower than expected, and given the huge 600mm2 size, they may well have density issues ...
Tegra PX2 Drive ... board in a glass case, this time with no identifying marks on the heatsink so that people can't identify that it's obviously still Maxwell.
If they had real GP104 they'd have lead with it. They're not going to announce it at the end after people have already tuned out after they've reiterated everything they've been talking about for 2 years re: Tesla / machine learning / NVLink etc.
Probably Q4 for first GP104 .... if lucky.
Caporegime
Woohoo man love confirmed.
The chip - 4 stacks of HBM2 takes up what 367.97mm2? of the area of the interposer alone. Which wouldn't leave enough space for the rest of the spec if the whole package was 600mm2.
Associate
looks like Toad out of super mario ...
Associate
980Ti ordered.....
hehehe desperation move
Glad i got mine last week now for £400 a nice £200 cost to upgrade over my old 970! I would throw my GPU at him now if he would just stop dribbling about AI
Have you actually though?
Baring in mind we've not seen any information which is even remotely related to consumer level Pascal!
Yeah, waiting until tomorrow just in case...
Associate
what time is this on till ?
Soldato
Details specs of P100 on Nvidia website:
https://devblogs.nvidia.com/parallelforall/inside-pascal/
300W TDP!!!!!!!!!!!!!!!!!!!!!!!!!!!!
https://devblogs.nvidia.com/parallelforall/inside-pascal/
300W TDP!!!!!!!!!!!!!!!!!!!!!!!!!!!!