For reference, rough numbers for Zen 4:
7950X Single ~125, Multi ~2200
7900X Single ~120, Multi ~1650
~36% improvement if real. Don't know if that's plausible.
Sorry, I thought it was clear enough that I was talking about 2025 and not just 2024, (and also that I was including the Zen 5c core). Do Kraken Point and Sonoma not exist, or are they not coming with Zen 5 or Zen 5c cores?
I think the full stack (from Fire Range and Strix Halo down to Sonoma) being refreshed with Zen 5 cores shows confidence in the Zen 5 core and its ability to appeal to OEMs and consumers.
Was there another time that they made so complete a mobile stack with this many designs in such a short...
Ah, yes. The infamous ">15% single-thread uplift" from Computex 2022, that the footnote said was from a comparison to the 5950X in Cinebench R23, when the actual result was close to double that.
Speaking of single-thread uplift, I was looking at Passmark scores, wondering where Zen 5 will land...
If sales of Zen 4 is still decent, I am afraid AMD might reveal nothing about performance at CES. Well, Lisa might say exactly the same thing about Zen 5 as Zen 4, when at CES that year she said it was in their labs and looked good.
If CES wasn't so consumer focused, I would think they might...
Maybe Mike was excited more by the interesting changes in architecture than purely by the performance improvement versus the previous generation.
Zen 4 got a lot of its performance increase from clock speed, which might not seem as exciting from the technical perspective of a CPU architect...
It's on page 38 in this thread.
Post in thread 'Zen 5 Discussion (EPYC Turin and Strix Point/Granite Ridge - Ryzen 8000)' https://forums.anandtech.com/threads/zen-5-discussion-epyc-turin-and-strix-point-granite-ridge-ryzen-8000.2607350/post-40981580
A possible reason is that it would save designing another chip if they could reuse it as a low-power APU design, if they found a way to use the Zen 4 cores without scheduling issues when used as an IO die, paired with a Zen 5 CCD.
On the latest podcast episode of The Wan Show on the Linus Tech Tips YouTube channel, in their discussion about Dr. Cutress leaving, Linus said they were aware of the problem of serious tech journalism losing multiple valuable people and outlets, and they intend to expand into written articles...
I don't look at the Zen 5 hybrid rumor as big and little cores. The 16 Zen 4c cores are rather big by themselves by today's standard, and will probably give similar multi-threaded performance as a 5950X, unless the 8 Zen 5 cores consume too much of the power budget. Those 8 'big' cores are...
After I compared to previous launch timeframes, I would have been more surprised if they released it Q4 or later, it would have meant a delay because of a problem or more time to sell Genoa before launching Raphael.
Zen 1 Q3 2015 tapeout, March 2017 desktop launch
Zen 2 Q1 2018 tapeout...
Puts new light on this quote from Mike Clark: "and as we continue to go forward, getting more cores, and getting more cores in a sharing L3 environment, we’ll still try to manage that latency so that when there are lower thread counts in the system, you still getting good latency out of that L3...
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.