Carzy Zarx’s PC Gaming Emporium - Catch Up on All the Latest PC Gaming Related News

[JEMC]

Time for some Hardware Rumors

This time it's two (actually about 1.5) about AMD and two about Nvidia.

*AMD*

Rumor 1: AMD have begun shipping Polaris GPUs - 2 different Polaris chips and 4 different GPUs found

http://www.overclock.net/t/1587294/zauba-amd-have-begun-shipping-polaris-gpus-2-different-polaris-chips-and-4-different-gpus-found

and

http://videocardz.com/58101/nvidia-gp104-and-first-polaris-gpu-supposedly-spotted-on-zauba

"AMD have begun shipping Polaris GPUs from the foundries. Based on the information from Zauba, it seems to be two different Polaris chips/families, each with 2 different SKUs/GPUs. Total of 4 new Polaris GPUs. The one with the biggest value is the full Polaris while the other one is the same Polaris GPU but with some shaders/cores disabled."

Polaris chip #1:
GPU #1: Board number: C981
This one is the full chip



GPU #2: Board number: C980.
Based on the value and the board number I would guess that this one is the same as above but have some shaders/cores disabled. Like Fury X and Fury.



Polaris chip #2:
GPU #3: Board number: C924
Full chip



GPU #4: Board number: C913
Disabled shaders/cores

And for comparison, this is what Fury X cost at launch and how much the 290X a little after launch (the value is the last number)

>>My personal Opinion: I can believe it.

 

Rumor 2: The enthusiast version of AMD's next-gen Polaris spotted at CES 2016

http://www.tweaktown.com/news/49581/enthusiast-version-amds-next-gen-polaris-spotted-ces-2016/index.html

"During our CES 2016 travels, we spotted a big GPU - the big version of Polaris. Not the 1080p 60FPS version that the company showed off in Sonoma at its RTG Technology Summit, but the enthusiast version of Polaris."

>>My personal Opinion: Nope, I don't believe it.

 

*NVIDIA*

Rumor1: NVIDIA GP104, smaller die, more pins

http://videocardz.com/58101/nvidia-gp104-and-first-polaris-gpu-supposedly-spotted-on-zauba

"Let’s start with GP104, the GM204 successor, based on Pascal architecture. We are probably looking at first high-end GPU from upcoming 1000 series (the name has not been confirmed). Same as with Kepler and Maxwell, we don’t expect the ‘Big Pascal’ to be released anytime soon. Instead much smaller GPU, that should theoretically be faster than both GTX 980 Ti and TITAN X is expected in the coming months."

"According to 3DCenter the GP104 comes in a 37.5×37.5mm BGA package, which is smaller than GM204’s 40x40mm. What’s worth noting is that the listing from Zauba revealed is has more pins (2152), than GM204 (1745). This could be related to much denser architecture based on smaller fabrication node."

>>My personal opinion: Yep, I believe it, at least most of it... because a TEC? And a 650W one! Going with water is one thing, but with a TEC would be quite surprising.

 

Rumor2: Nvidia Pascal over a year ahead of 14/16nm competition

https://semiaccurate.com/2016/01/11/nvidia-pascal-over-a-year-ahead-of-1416nm-competition/

"Nvidia is more than a year ahead of any competition in the mobile space as their Pascal based Drive PX 2 module proved. Held up by no less than CEO Jen-Hsun Huang, SemiAccurate felt it was an automotive tour de force.

...

Getting back to their lead, Nvidia is so far ahead of the industry it is, well, nigh on incredible. Until the CES unveiling, AMD was widely believed to be 2+ quarters ahead of Nvidia on the process front, their 14nm Polaris GPUs had all the mindshare. On Monday January 4th, 2016, Nvidia showed undeniable proof that they were more than a year ahead of AMD in the race to 14/16nm devices. Not only that they were ahead of assumed leaders Apple and Samsung to devices on this node, way way ahead."

>>My personal opinion: Coming from Semiaccurate and Charlie, it's quite obvious that this is a sarcastic article about a worrying rumor going around, that the Drive PX2 device showed at CES with two Pascal GPUs is fake and used current Maxwell chips.

I don't know if it's true or not, but if it is true, it wouldn't be the first time Nvidia does something like this.