• 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.

New Zen microarchitecture details

Page 204 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Quad Core + PCH + 128bit DDR-4 should be not more than 100mm2
You are free to bring evidence. Though yes, Skylake manages to fit the uncore in ~24mm^2, but with separate PCH.
You have to take-off Polaris 128bit GDDR-5 memory controllers (16-20mm2), you only need the DDR-4 on the CPU. So the die comes down to ~100mm2
You have a point here, even if "only need" is a little strong of a statement.
HBM2 will be used as a common L4 cache as AMD APUs support a single address space. CPU and GPU can share pointers. This is only possible with a design where HBM2 is a high bandwidth cache. AMD Vega's High bandwidth cache controller is a dead giveaway that this is the design of the future.
Man, Polaris taught you nothing.
 
You are free to bring evidence. Though yes, Skylake manages to fit the uncore in ~24mm^2, but with separate PCH.

Well take Skylake 4+2 die at ~120mm2, if you take off the iGPU(40-45mm2) then you have a Quad Core CPU with everything else intact at less than 80mm2.
So Quad Core RR+ PCH + 128bit DDR-4 controllers shouldn't be more than 100mm2

You have a point here, even if "only need" is a little strong of a statement.

I dont expect AMD to put 16x CUs in RR, im sure 10-12 Vega CUs will be fine with 3000-3200MHz DDR-4 to maintain the absolute performance leader in APU graphics performance for 2017 at sub $200 segment.

But even if they would like just to put Polaris 11 (without the GDDR-5) they could make the die no more than 200mm2 big.
 
Skylake, as i have said, has a separate PCH. Zeppelin is basically a SoC, on the other hand.

Even with the PCH it shouldnt be more than 100mm2.

Yeah, though it would be fairly memory choked, either way.

Yes but it should be a lot faster than latest AMD/Intel APUs both in Desktop and Laptops. And a lot cheaper than having any other memory configuration like HBM, eDRAM etc.
 
And now you're saying DK just randomly made up 40% is SPEC int rate because it suits you to disregard that.

Why don't you ask him if you're after facts?
DK sometimes just ignore corrections or questions asked to him. The question has been asked on RWT, let's see if he ever answers.

He claims what he was told by AMD, not that he has any sources for benchmarks.
In that particular case, isn't the issue that DK claims it's SPEC int rate, while it's SPEC int?

EDIT: Missed the posts that already made that last point clear 🙂
 
Canard PC just stated that all cores boost is to be set between 3.65 and 3.8GHz depending on yields.

Eh?

3.6/4.0 --> 3.6 GHz base, up to 4.0GHz all-core boost. Most common frequency will be between 3.65 - 3.8GHz --- but that is only a guide depending on user power settings.
 
Seems like some review samples have arrived:

8GVUwap.png


Edit: Seems like they deleted the image from the article.
 
Last edited:
I dont know, I know that site and loves to spread BS. I call it "the wccf google-translated to spanish".

Lets wait and see.

PS: The 65w tdp of the lowest 8c/16t seems like a red flag for the authenticity of the article IMO.

PS2: That site published the Ashes "bench" of that faked string zen sku.
 
Last edited:
They are all just rumours and probably speculations, particularly the older ones.
Being speculations means they had no base in reality. Unless it is some sort of explicit leak from a reputed source like benchlife or sweclockers or the site shows some sort of slide/screenshot to examine, I would ignore any price information for now.
It is likely AMD will communicate the prices at the last minute.
 
I have no idea, where was this rumor coming from? The most popular one was 8C/16T Ryzen base CPU cost between 350 and 400$.
LOL that was kinda my point - pricing rumors are silly and completely baseless. Even product/paper launch prices don't always represent street pricing or bundle pricing, so I never get too worked up over it.
 
Back
Top