Discussion Zen 5 Speculation (EPYC Turin and Strix Point/Granite Ridge - Ryzen 9000)

Page 263 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

FlameTail

Platinum Member
Dec 15, 2021
2,909
1,639
106
More MLID. Claims that Z5 is still strong, but not as strong as originally intended due to bugs. Reasserts he considers the
More MLID. Claims that Z5 is still strong, but not as strong as originally intended due to bugs. Reasserts he considers the 30%+
More MLID. Claims that Z5 is still strong, but not as strong as originally intended due to bugs. Reasserts he considers the 30%+ people dead
More MLID. Claims that Z5 is still strong, but not as strong as originally intended due to bugs. Reasserts he considers the 30%+ people dead wrong.
30% what? IPC or Performance?
 

moinmoin

Diamond Member
Jun 1, 2017
4,993
7,763
136
Regarding the whole hubbub about a Zen 5 "delay" supposedly announced at AMD's earnings call, I strongly recommend checking out primary sources like following transcription instead of solely relying on clickbait "reporting":


The only mention in there about Zen 5 together with something related to H2 is the following:

"And then, we also see Turin, our Zen 5 product coming in the second half of the year."

So Lisa Su is talking about Turin there, an Epyc server CPU family. How that would affect all the other possible Zen 5 based products and what their launch dates will be you can feel free to discuss now.
 

Timmah!

Golden Member
Jul 24, 2010
1,443
683
136
30% what? IPC or Performance?
I hope performance, and i honestly hope Adroc is truthful and its higher, like 50 percent Even if its 50 percent IPC, but due to lower clocks just 30 percent overall, thats meh (to me subjectively as 7950x owner). I got 7950x as replacement for X299 system and it was about 2x as fast. Obviously i dont expect the jump between 2 consecutive gens as high, and i definitely did not expect even whats rumored now, until Adroc ramped up the hype :-D, but now its possibility, 50 percent faster than 7950x would definitely be enticing to buy to me. And it would project nicely into MT performance as well, making 16C Zen5 probably pretty close to 24C Zen4.
 

Timmah!

Golden Member
Jul 24, 2010
1,443
683
136
30% performance improvement is 'meh'?

You guys are wild.
You need to consider it from the point i paid 700 EUROs for 7950x only a year ago. And 30 performance improvement, no matter how massive achievement it is, in historical context, or simply from technological POV, wont be something making obvious difference in performance, most of the times. I mean, the kind of speed-up you would definitely notice. Hell i cant see, the difference between my current CPU and the old one, like half the time, and the other half, when i do, its because its actually 2x faster. Would it be the same, if it was just 30 percent?

And its not like i am getting those 30 percent for free. I have to pay for them another 700 EUROs, most likely. So its a matter of perspective, if such some of money is a pocket change to you, then i see why you think i am "wild". I see it as being reasonable from POV of someone on a limited budget.
 

Glo.

Diamond Member
Apr 25, 2015
5,753
4,659
136
I hope performance, and i honestly hope Adroc is truthful and its higher, like 50 percent Even if its 50 percent IPC, but due to lower clocks just 30 percent overall, thats meh (to me subjectively as 7950x owner). I got 7950x as replacement for X299 system and it was about 2x as fast. Obviously i dont expect the jump between 2 consecutive gens as high, and i definitely did not expect even whats rumored now, until Adroc ramped up the hype :-D, but now its possibility, 50 percent faster than 7950x would definitely be enticing to buy to me. And it would project nicely into MT performance as well, making 16C Zen5 probably pretty close to 24C Zen4.
Do you even comprehend what you have written?

50% IPC increase would absolutely destroy everything ON LOWER CLOCKS, and smaller TDP thermal envelopes.

4 GHz Zen 5 CPU would be 50% faster than 4 GHz Zen 4 CPU.

IPC is the best way that you can extract performance out of hardware, because it breaks the game on lower ends, where clocks do not matter that much.
 

eek2121

Diamond Member
Aug 2, 2005
3,027
4,213
136
Anything before H2, according to AMD's official material would've been an early release.
Many of us fell for the meme, but all that matters is that it comes out on time and the thing is still going to deliver all the same.

1) As mentioned above, AMD explicitly mentioned Turin
2) It is impossible for an unreleased product without a public release date to be delayed
3) July is H2
4) None of it matters much anyway
5) ???
 
Reactions: lightmanek

Tuna-Fish

Golden Member
Mar 4, 2011
1,415
1,732
136
Mm I wonder where they went. 😝

A lot of them went to weird fly-by-night AI chip startups that are probably going to go under within two years. I definitely thought that was a weird career move at the time (starting a startup to directly compete with nVidia), but I guess they got paid nice enough salaries by investors dogpiling into the new hot thing, and might get good exits if they've come up with something patentable that some of the big players want to acquire.
 

yuri69

Senior member
Jul 16, 2013
419
696
136
Have AMD or Intel ever seen IPC increases greater than +20% on average? Just don't cite the example of Zen1 and Conroe. Zen1 is an average IPC of +52% higher than Excavator, but it barely reached the level of Haswell from 2014. Core2(Conroe) is an IPC higher than Core(1)(Yonah) +15-20%.
Conroe managed to pull that IPC gain along with boosting frequency from 2.3GHz to 3+GHz.
 

AMDK11

Senior member
Jul 15, 2019
325
219
116
Conroe managed to pull that IPC gain along with boosting frequency from 2.3GHz to 3+GHz.
I only had in mind the expansion of the core logic and the resulting IPC gain.It is known that Yonah's biggest problem was the lower maximum clock speed, so Conroe's much higher IPC and achieving a much higher clock speed resulted in a significant increase in Core 2 performance.
 
Reactions: yuri69

adroc_thurston

Diamond Member
Jul 2, 2023
3,134
4,505
96
Have AMD or Intel ever seen IPC increases greater than +20% on average? Just don't cite the example of Zen1 and Conroe. Zen1 is an average IPC of +52% higher than Excavator, but it barely reached the level of Haswell from 2014. Core2(Conroe) is an IPC higher than Core(1)(Yonah) +15-20%.
Intel or AMD isn't the standard in large IPC bumps.
 

Gideon

Golden Member
Nov 27, 2007
1,697
3,891
136
Luckily for AMD, the Total Addressable Market for Zen 5 client is a bit broader than just upgrades of AM5 computers.

Yeah, if it indeed ends up being ~30% faster (raw performance not IPC) in ST it's actually about twice as fast as Zen 2

Zen 2 -> Zen 3 was 19% = 119% perf
Zen 3 -> Zen 4 was 35% uplift (clocks + IPC) = 1.19 * 1.35 * 100% ~= 160 %
Zen 4 -> Zen 5 ~30% = 1.19 * 1.35 * 1.30 * 100% ~= 208%

That's raw 1T performance, not IPC, mind you.

Performance gains over generations do add up.
 

AMDK11

Senior member
Jul 15, 2019
325
219
116
Why did you specify +19% for Zen 3 if it is an average IPC increase and, as we know, Zen 3 clocks higher than Zen 2, so the performance should also be higher.
 
Reactions: Tlh97
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |