• 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.

NVIDIA GP102 Titan coming soon

Page 3 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Status
Not open for further replies.
If Big Vega manages to beat the 1080 for a lower price, then you can bet that the $1200 Titan X price won't last and the 1080Ti will replace the 1080 in the price stack. Let's hope that's the case so that we can all get in on a price war!
 
Is it better to be the only game in town or to have to share the spotlight with a competitor?

If it's ready, put it out there and sell it for what you can get for it. In this case, that's $1200. Why wait?
I agree. Nvidia is moving rapidly to fill their Pascal lineup from top to bottom. Good business.
 
Just hold on. 1080ti and Vega incoming.

Small Vega comes first. Vega 11 is what, H2-2017? NVIDIA is so far ahead in all metrics right now that AMD might have trouble beating a GTX 1080. Now imagine one year from now, refined full GP102 with 3840 SPs at higher clocks, maybe Volta in late 2017.
 
Looks like NV will have a 400mm+ chip, a 300mm+ chip and a 200mm+ chip for the first round of Pascal.

When it's time for a refresh they'll drop everything down one segment and put a 500mm+ chip on top of it all.

Think what you want about NV, but they have a plan and a vision and they're executing on it like beasts.
 
Is it better to be the only game in town or to have to share the spotlight with a competitor?

If it's ready, put it out there and sell it for what you can get for it. In this case, that's $1200. Why wait?
When was the last time Nvidia priced its cards based on competition? Since the GTX 7xx, iirc Nvidia has pretty much priced their products in isolation, and it wasn't for lack of competition, but more due to willingness of their customers to pay. They're in it to make money, and they will take whatever money you're willing to fork out for their products. Remember the $3k Titan Z? I'm not blaming Nvidia here, any business would love a bunch of people paying whatever they ask for product/ service. Heck, everyone knows that since 680, Nvdia's been double dipping into their consumer base. I bet shareholders laugh all along their way to the bank. It's very good for a company to have such a customer base. That said, as a consumer, i find it rather annoying that pricing is going the way of Apple products.
 
The Titan Z was a niche product.
You really complain about the pricing? AMD is a no show. Their latest GPU is technical disaster. Do you really want that nVidia is squeezing AMD out of the market?!

At least with these prices there is room for AMD to breathe.
 
Last edited:
I'm really hoping that the 1080 Ti comes in at $650 like the 980 Ti did, and it shifts the others down the chain. GP102 and Vega are what I'm looking at. nVidia certainly isn't wasting any time. I'm surprised they've decided on added a whole extra die, but the HPC market must be able to sustain the GP100 on its own.
 
524mm^2? 🙂

I have to say TSMC is executing very well. To see 500-600 sq mm GPUs like GP100 / GP102 launch almost beside 300sq mm GPUs is phenomenal. AMD is paying for the choice of GF 14LPP and its WSA commitments. Nvidia could really turn the screws on AMD in 2017 once Nvidia gets enough 16FF+ wafers from TSMC to fulfill Nvidia's full demand.
 
So 24% more shader/pixel power than 1080.. seems an ultra steep price hike for that little of a performance increase. Also not impressed with 39% more power way out of line with its increase in speed.
 
I have to say TSMC is executing very well. To see 500-600 sq mm GPUs like GP100 / GP102 launch almost beside 300sq mm GPUs is phenomenal. AMD is paying for the choice of GF 14LPP and its WSA commitments. Nvidia could really turn the screws on AMD in 2017 once Nvidia gets enough 16FF+ wafers from TSMC to fulfill Nvidia's full demand.

I kept saying on these forums that 16FF+ was in excellent shape, both yield wise and xtor performance wise. Not sure why people didn't listen to me 🙁
 
I have to say TSMC is executing very well. To see 500-600 sq mm GPUs like GP100 / GP102 launch almost beside 300sq mm GPUs is phenomenal. AMD is paying for the choice of GF 14LPP and its WSA commitments. Nvidia could really turn the screws on AMD in 2017 once Nvidia gets enough 16FF+ wafers from TSMC to fulfill Nvidia's full demand.
I think nvidia would rather have higher margins than "turn the screws" on amd.
 
So 24% more shader/pixel power than 1080.. seems an ultra steep price hike for that little of a performance increase. Also not impressed with 39% more power way out of line with its increase in speed.

It could come up more though -- 24% shader increase I think is the backstop figure. 1080 appears to still be bandwidth limited in places. Moving to the 384 bit bus should help stop bottlenecking on that front. I think we'll see more than the 24% increase on average. Maybe 30-35% average. 24% as a minimum
 
Status
Not open for further replies.
Back
Top