AMD Vega 10, Vega 11, Vega 12 and Vega 20 Rumors and Discussion

AMD has since updated their announcement, confirming that there isn't any on-package memory after all. The chip has a 256-bit GDDR5 memory controller, with the Chinese console shipping with 8GB of the stuff.

As for the die, I agree it sounds like it's a monolithic die due to the presence of GDDR5. However I'm not hedging my bets until AMD confirms it or we get pictures. New dies aren't cheap, even on the now tried and true 16nm process.

 

So this is TSMC, not GloFo? Off-package GDDR5 makes sense, as I don't see what having it on package would achieve, apart from making said package huge.

 

The photo isn't clear enough to make out who may have fabbed it. But it does make it clear that it's a monolithic die. So someone put down some pretty pennies for this...

All semi-custom to date has been TSMC. I certainly wouldn't expect this to be any different, especially with the geopolitical issues at hand.

 

Keep in mind that would theoretically be a TSMC fabbed Polaris so the clock profile might be different and 1.3GHz more reasonable. I'd agree it's more likely Vega as RPM in that market would be significant where image quality is less of an issue. This looks to be a Chinese ESports platform or a distributed mining network in the making.

 

This die looks huge.

 

Maybe big, but I wouln't call it huge. The die size seems to be very comparable to Scorpio Engine or XBox One SoC.

 

• https://videocardz.com/driver/amd-radeon-adrenalin-edition-18-8-1-beta

Primitive shaders?

 

VK_KHR_create_renderpass2 extension was added to Nvidia beta drivers mid July. Not sure about EXT_vertex_attribute_divisor but it's likely related to VK_EXT_vertex_attribute_divisor whose primary Vulkan contributors are from Intel and Nvidia.

 

New patent for culling. Is this included in vega?

https://patents.justia.com/patent/10032308

https://companyprofiles.justia.com/company/amd

 

The first one is from 2016. I guess it's part of how Primitive Shaders would have worked.

 

It's a technique that would go into a primitive shader, but could just as easily be a compute shader. For primitive shaders to work well, AMD likely needs out of order rasterization somehow enabled through the API to avoid all the tracking and synchronization overhead. In theory that's still coming.

 

2Gbps HBM2 is now in a shipping graphics card.



https://www.anandtech.com/show/13210/amd-announces-radeon-pro-wx-8200

So SK Hynix's 2nd gen 2Gbps and 2.4Gbps HBM2 is far enough along to ship (or at least the 2Gbps stuff is).

 

It just shows that the VEGA FRONTIER EDITION was great value for money.

 

New set of Vega20 patches:

https://lists.freedesktop.org/archives/amd-gfx/2018-August/025239.html
https://cgit.freedesktop.org/~agd5f/linux/log/?h=vega20_psp_smu

Interesting things found so far:

SMU11 brings XGMI link support:

Code:

#define NUM_XGMI_LEVELS 2

#define MAX_XGMI_LEVEL (NUM_XGMI_LEVELS - 1)

uint8_t XgmiLinkSpeed [NUM_XGMI_LEVELS];
uint8_t XgmiLinkWidth [NUM_XGMI_LEVELS];
uint16_t XgmiFclkFreq [NUM_XGMI_LEVELS];
uint16_t XgmiUclkFreq [NUM_XGMI_LEVELS];
uint16_t XgmiSocclkFreq [NUM_XGMI_LEVELS];
uint16_t XgmiSocVoltage [NUM_XGMI_LEVELS];

Another check-mark for the leak from over a year ago.

 

Have you seen this AMD slide?
https://images.anandtech.com/doci/13243/1534793013533124984595.jpg

(from https://www.anandtech.com/show/13243/hot-chips-2018-amd-on-raven-ridge-optimizations )

There are two Raven Ridge on the slide.
Could this mean, there is a 7nm Raven Ridge in 2018?
Rumor from here: https://www.computerbase.de/2018-08/amd-raven-ridge-refresh-apu-7-nm/

 

7nm is Zen2, and plain Zen2 is 2019

 

That rumor is a nonsens. AMD confirmed, that the "2018 Raven Ridge" is Ryzen 7 2800H. They would hardly call a 7nm product "2800H".

 

Ok, it seems these 2800H are then selected/binned chips?!

 

I believe Raven Ridge H APUs are ~35W mobile SKUs. Maybe they will be based on newer silicon revision, which will improve energy efficiency. It is also possible that they'll be moved to 12nm lines, but I expected, than 12nm process will be used for the next generation Picasso APU (Raven Ridge shrink).

 

R.I.P NGG:

https://www.mail-archive.com/amd-gfx@lists.freedesktop.org/msg24458.html