AMD: Speculation, Rumors, and Discussion (Archive)

[3dilettante]

Legitreviews published a physical inspection of their reference card:
http://www.legitreviews.com/first-look-at-the-amd-radeon-rx-480-8gb-video-card_183213

Interesting to see unused pins where the crossfire connector used to be before GCN2.

From what I can tell, the non-Nano Fury boards have something similar.

 

[kalelovil]

From what I can tell, the non-Nano Fury boards have something similar.

Okay, nevermind then, I should have checked that.

 

[Silent_Buddha]

Legitreviews published a physical inspection of their reference card:
http://www.legitreviews.com/first-look-at-the-amd-radeon-rx-480-8gb-video-card_183213

Interesting to see unused pins where the crossfire connector used to be before GCN2.

Still amazing how small that Nano board is for the performance it provides. Hopefully see something similar with a HBM enabled Vega board.

Regards,
SB

 

[eastmen]

was this posted ?

http://www.pcper.com/news/Graphics-Cards/Whoops-AMD-Radeon-RX-480-Specifications-Newegg

 

[Rootax]

Not sure of the veracity of the post but here it goes anyway:

I've played around with this little beast and I have to say this is the biggest improvement in years. Polaris is extremely powerful in micropoligons. I didn't even imagine that this kind of performance is possible on a quad raster design. In an extreme test case with 8xMSAA and 64 polys/pixel, the Polaris 10 is the fastest GPU in the market by far.
The second interesting thing is the pipeline stall handling. I wrote a program to test it, and remarkable how it works. I hate dealing with pipeline stalls, because it is hard, but on Polaris the stalls are just reduced by far. Even if I run a badly optimized program, the hardware just "try to solve the problem", and it works great. This behavior reminds me the Larrabee... and now we have it, not from Intel, but a hardware is here to solve a lot of problems

http://semiaccurate.com/forums/showpost.php?p=266518&postcount=2022

If it's true, I can' wait for a bigger version of this (Vega I guess ?).

 

[Kaotik]

https://twitter.com/GFXChipTweeter/status/745768255529295872?ref_src=twsrc^tfw

https://twitter.com/GFXChipTweeter/status/745887920809218049/photo/1?ref_src=twsrc^tfw

Vega 10 is up

 

[Grall]

AMD GPU design is located in Shanghai these days? My my. How things change.

 

[xEx]

This means that the VEGA10 GPUs are ready and they are just finishing the lasts steps?

 

[3dcgi]

AMD GPU design is located in Shanghai these days? My my. How things change.

Significant work is done there but there's still a lot done at multiple north America sites.

 

[Ailuros]

It made sense when I posted it... brain short circuit... I meant to quote love in rio's post with the quote from semi accurate.

In any case reading of OoO rasterizing was a very pleasant surprise

 

[DieH@rd]

 

[Grall]

Significant work is done there but there's still a lot done at multiple north America sites.

Ah, alright. Could there be any efficiency downsides to spreading out work across multiple teams in multiple locations, as compared to NV, which I presume, are having all their engineers assembled in one place?

Also, it would be interesting to know just what Koduri is referring to; "merely" Vega 10 tapeout, or perhaps first silicon from the fab? Something else, like, engineering samples at the lab booting up and working? I hate vague teases like this!

"Long way to go" he says, so probably not finished silicon I suppose. Unless verification process and finalizing drivers and reference board design takes a huge amount of time... *grr!*

 

[Love_In_Rio]

Witcher 3 at 1080p.Not great, in fact quite poor, Tonga level performance.In another user's video the uploader comments the gpu gets quite hot.

 

[CarstenS]

NV doesn't. I know at least on higher ranking engineer living not at the west coast.

 

[Ailuros]

NV doesn't. I know at least on higher ranking engineer living not at the west coast.

Haven't they also a team in India for verification or something along that line?

 

[xEx]

Witcher 3 at 1080p.Not great, in fact quite poor, Tonga level performance.In another user's video the uploader comments the gpu gets quite hot.

GTA 5 RX 480 + i5-6400 Benchmark

highest settings:

 

[Razor1]

GTA performance is around gtx 970 performance and a bit lower, I know its not good form to compare to other reviews like that but still.... Something is wrong with their settings or their computer or ......

 

[lanek]

Witcher 3 at 1080p.Not great, in fact quite poor, Tonga level performance.In another user's video the uploader comments the gpu gets quite hot.

I see mostly in 60fps ( 55-56 in the low, with 63+in high ) range who put it between the 980 and FuryX if i compare with this review http://www.guru3d.com/articles_page...merock_premium_edition_g_panel_review,24.html

Ofc, need to see the setting used.

 

[CSI PC]

I think we need to really wait for this to be validated, but it is questionable whether the 480 is 32 ROPs or 64 ROPs.

Before this picture was even posted, we manged to confirm TMU and ROP counts with our independent other sources, so we have no reason to believe that this is picture is fabricated.
AMD Radeon RX 480 will feature 2304 Stream Processors, 144 Texture Mapping Units (2304/16) and 32 ROPs.
As for the ROPs, it’s only a half of what Hawaii and Fiji have to offer, but it’s unclear how is this going to affect gaming performance.

http://videocardz.com/61371/amd-radeon-rx-480-rumors-part-5

If 32 ROPs ends up being validated sounds more like the product is an evolution of Tonga 380 - many reasons it could be incorrect, depends upon the 'source' accuracy as I am sure GPU-Z is not accurate yet.
Cheers

 

[dskneo]

so far, not good...