• 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.

** The Official Nvidia GeForce 'Pascal' Thread - for general gossip and discussions **

bru

bru

Soldato
Joined
21 Oct 2002
Posts
7,359
Location
kent
Not likely as small Pascal will be a very poor side/upgrade on TitanXs.

Big Pascal is where the real action is going to be with performance 1.8x as much as a TitanX.

Well small Maxwell bested large Kepler, although not by much and that was on the same 28nm process. I think that even small Pascal, with a node shrink and HBM2 should be a decent amount faster.

I still reckon NVidia will surprise us all and launch the Pascal Titan first, but probably in limited supply, just to show us that the future is going to be very right indeed. Of course it will be frightfully expensive.
 
Man of Honour
Joined
21 May 2012
Posts
31,922
Location
Dalek flagship
Well small Maxwell bested large Kepler, although not by much and that was on the same 28nm process. I think that even small Pascal, with a node shrink and HBM2 should be a decent amount faster.

I still reckon NVidia will surprise us all and launch the Pascal Titan first, but probably in limited supply, just to show us that the future is going to be very right indeed. Of course it will be frightfully expensive.

I think Small Pascal will be about 15% to 20% faster than GM200 but will not have anymore than 6/8gb of memory.

This will leave the Titan X in the same position as the old Titan was. Although not as fast as a GTX 980 it was still the better bet for 2160p due to the 6gb of VRAM.

After Small Pascal NVidia will release the Pascal Titan I think and then we all know what happens on the pricing front. If you want big Pascal the Titan version will be the only option on offer.
 
Soldato
OP
Joined
2 Jan 2012
Posts
11,996
Location
UK.
NVIDIA Unveils Pascal GPU: 16GB of memory, 1TB/s Bandwidth

At the Japanese edition of NVIDIA GTC (GPU Technology Conference), NVIDIA finally revealed details behind its 2016 graphics architecture, codenamed Pascal. The architecture was launched at the main GTC event, which took place in San Jose on March 17th, 2015 (watch Jen-Hsun Huang’s GTC keynote here). GTC Japan was hosted by Marc Hamilton.

As always, the Pascal GPU will be manufactured in Taiwan Semiconductor Manufacturing Company (TSMC), using the brand new 16nm FinFET process. This process is much more than a simple number, since it marks the shift from planar, 2D transistors to the FinFET i.e. 3D transistors. This shift required that the engineers make lot of changes in the thought process, and should result in significant power savings.

NVIDIA’s Marc Hamilton said: “Using 3D memory, not only the memory capacity will go up, the memory bandwidth will go up significantly. With a much faster GPU, and higher memory bandwidth, the existing interconnects in the server are just plain outdated. So, we had to develop our own interconnect called NVLink, five times faster than existing technology.

ftqCHVc.png


...Pascal will launch with 16GB HBM2 memory... Pascal is expected to hit the market during the first half of 2016...

http://vrworld.com/2015/11/16/nvidia-unveils-pascal-gpu-16gb-of-memory-1tbs-bandwidth/
 
Soldato
OP
Joined
2 Jan 2012
Posts
11,996
Location
UK.
Next-gen killer hurricane hunter to be armed with Nvidia graphics chips

2ohjhax.jpg

The US government's NOAA agency will build a new computer system boosted by 760 Nvidia Pascal GPUs, according to Ian Buck, the chip company's veep of accelerated computing and CUDA inventor. When will this machine go online? Well, to give you a clue, Pascal is not due to arrive until 2016.

http://www.theregister.co.uk/2015/11/16/nvidia_noaa/
 
Soldato
Joined
22 Aug 2008
Posts
8,338
Great, they're already starting the marketing blitz. First Nvidia "solved" the moon landing debate, now they're saving us from hurricanes. :rolleyes:

 
Last edited:
Caporegime
Joined
20 May 2007
Posts
39,931
Location
Surrey
Looking forward to this. I have skipped the 980Ti on the basis that this die shrink will over a real big jump in performance. I hope I am right!
 

D3K

D3K

Soldato
Joined
13 Nov 2014
Posts
3,808
NVIDIA’s Marc Hamilton said: “Using 3D memory, not only the memory capacity will go up, the memory bandwidth will go up significantly. With a much faster GPU, and higher memory bandwidth, the existing interconnects in the server are just plain outdated. So, we had to develop our own interconnect called NVLink, five times faster than existing technology.”
I'm not familiar with 'interconnects' and 'servers' in this context. Does this essentially boil down to them needing 5x the current bandwidth available?
 
Caporegime
Joined
17 Feb 2006
Posts
29,263
Location
Cornwall
So difficult trying to resist not grabbing a 2nd 980 on the cheap instead of holding out for this..

The waiting game is such a PITA, and really is best played by cheapskates like me :p If you have the money for 2 980s, spare yourself the pain of waiting and just get another :p

Meanwhile, my self-inflicted agony must continue... 14/16nm better be bloody awesome :p
 
Soldato
Joined
11 Mar 2013
Posts
5,470
Thinking about selling my Titan X, but don't think pascal 1080 will be that much faster? Might just keep it. Will a Titan X hold me for 2 more years? I can't afford a pascal Titan this time around. Was hoping a 1080 might be fast enough, but don't think it will.
 
Back
Top Bottom