Low Power Island sounds logical thing do do if it is chiplet CCD + IOD design.
Better question is what's with the "Zen 6 Classic + dense".
MLID said earlier the CCD has 12 fat cores, and if Medusa Point uses classic + dense and is chiplet, then obviously the desktop products using the CCD will...
A theory I have is that if AMD cancelled both their highend and mainstream version of the GPUs (only Navi 44 is left from the original lineup) in early 2023, they possibly didn't have time for highend version any more.
Gotta remember that Navi48 is also a new design, not an originally intended...
The 200 000 number was some sort of reporting mistake, AMD said they didn't give that figure. Not sure if BenchLife got it off record (or from another source), but they deleted the article that said that. I would basically forget the number ever made news, probably is way off.
https://www.computerenhance.com/p/an-interview-with-zen-chief-architect
Mentions not seeing much difference/serious advantage from hypothetically going ARM. According to Clark, the clocks/performance/power qualities of x86 versus ARM (basically the higher clocks, higher power "nature" of x86)...
AMD is stalling gaming progress! AMD GPUs slowing down innovation! Gotta get rid of them!
Absolutely nothing to do with Nintendo consoles based on underpowered Nvidia chips forming the turd baseline for game devs.
Apparently the GB10 SoC is actually two pieces of silicon (see photos on ServeTheHome) and based on Nvidia's press release, the CPU and GPU communicates over "NVLink-C2C" with 5x the bandwidth of PCIe 5.0.
I wonder how the RAM sharing is handled. I guess it is similar as Strix Halo, but it's...
If it follows AMD recipe it should be cost efficient when it comes to the fixed development cost.
Do you think it would be unprofitable due to lack of demand from customers?
Two things - first K8 was pretty much an iteration of K7, and there was another one between them (Athlon XP gets lumped together with original K7 but core is updated).
Second, I think it is a bit of a reductionist viewpoint and it fails to see a difference in how far the "iterations" go. Is it...
Well, those can still throw the spider adapter from 8pins on a double-cable card. Which is what people started recommending for RTX 5090 anyway when the native cables started melting, ironical given how everyone first got new PSUs with native/straight 12+4 cables...
All partner cards have to get Nvidia approval. The thing that happened is likely that
1) visuals design guys want 1 connector/cable to look slick and they got the upper bosses on board with that idea (against the engineers, possibly).
2) inevitable safety issues
3) you (Founders edition cards)...
Doesn't 256bit-bus version pretty much mean it must be LPDDR5X? You can't make that width out of 24bit-interface LPDDR6 chips. (Of course, there is always option of MLID being wrong one or multiple out of those claims, or all.)
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.