Question Zen 6 Speculation Thread

Page 169 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Det0x

Golden Member
Sep 11, 2014
1,451
4,922
136
6GHz is really hard...
Not that hard, ive ran multiple Zen5 cpus above 6 ghz (on watercooling)
Come to think of it, Zen4 seems to be almost at the limit at 250W.(7950x)
What we were able to achieve in Raptor Lake 6ghz was the fact that many things overlapped.
Stock PPT limit for a 7950X is 230w, not 250w
And they scale way past 300w as long as you can keep the temps in-check, something lower vmax will help alot with
AFAIK EPYCs do not casually run at 5.7GHz... The quoted 1.7x figure is surely for a top model which means a strongly thermally/power limited SKU. That means 2nm should allow higher real frequency than 2.25/3.7GHz of Bergamo.

Besides that, the new platform increases the number of memory channels and TDP which suits many server workloads.

Mind you that the Zen 5's "server IPC improvement" led to that laughable Zen 5 +40% IPC hypetrain.
My Epyc 4585PX runs 5.7 ghz stock
But yeah i fully understand your point and what your trying to say, i only wanted to fix the wrong napkin math from above.. (comparison was with 1.34x more cores, not 1.5x)

The only thing we know for certain are that the higher core count and lower clocked EPYC SKU's we will see a +27.5% per core performance increase, if the offical AMD slide are to be believed.

How this relates to desktop remains to be seen, but i will be surprised if we dont see way above 6ghz for highest SKU.
 

Attachments

  • 1751449583651.png
    2.1 MB · Views: 9
  • 1751449597445.png
    2.1 MB · Views: 9

Io Magnesso

Senior member
Jun 12, 2025
317
100
71
Not that hard, ive ran multiple Zen5 cpus above 6 ghz (on watercooling)

Stock PPT limit for a 7950X is 230w, not 250w
And they scale way past 300w as long as you can keep the temps in-check, something lower vmax will help alot with

My Epyc 4585PX runs 5.7 ghz stock
But yeah i fully understand your point and what your trying to say, i only wanted to fix the wrong napkin math from above.. (comparison was with 1.34x more cores, not 1.5x)

The only thing we know for certain are that the higher core count and lower clocked EPYC SKU's we will see a +27.5% per core performance increase, if the offical AMD slide are to be believed.

How this relates to desktop remains to be seen, but i will be surprised if we dont see way above 6ghz for highest SKU.
Well, it's not impossible, but... I feel like I've achieved 6GHz by doing this far.
Perhaps your CPU was a hit CPU that can run with a high clock.
However, How about 6GHz as a nominal value from the manufacturer?
 

Io Magnesso

Senior member
Jun 12, 2025
317
100
71
Rang the cry throughout the Intel dominant, pre-Zen era.
That's right That's because Intel was just lazy
But it's a thing of the past
However, it is real that the range of improvement in performance is small.
It will remain small unless you find a way to do it.
 

maddie

Diamond Member
Jul 18, 2010
5,141
5,500
136
That's right That's because Intel was just lazy
But it's a thing of the past
However, it is real that the range of improvement in performance is small.
It will remain small unless you find a way to do it.
Maybe you do research in advanced CPU architectures, but unless you do, this is merely your opinion.
 

MS_AT

Senior member
Jul 15, 2024
713
1,453
96
Come to think of it, Zen4 seems to be almost at the limit at 250W
Maybe there is a misunderstanding here. I think people talking about 6GHz+ clocks are talking only about single core peak boost clock. Not about the multicore steady clock that is affected by the power limit. Single core on either Raptor Lake or Zen4/5 when boosting high does not come close to the power limit.
 

maddie

Diamond Member
Jul 18, 2010
5,141
5,500
136
Well, this is just my guess
But it's the same for you, each other
Nope, I stated a historical fact. I don't know about future IPC increases, and admit it.

Back in the day, when Intel was king, I repeatedly asked if there was some theoretical limit to IPC, and was given the same answer as you do now.

"It's hard from here to get significant IPC increases." None ever answered the direct question of "theoretical limit to IPC".

What we do know is that Keller claimed there's a lot of room for additional IPC improvements. How? ?????
 

yuri69

Senior member
Jul 16, 2013
660
1,188
136
What we do know is that Keller claimed there's a lot of room for additional IPC improvements. How? ?????
Keller told that a lot during his 2018-2019 "Intel speeches". An yeah, we have got some IPC since then.

2019 - Sunny Cove - 18% IPC, 2021 - Golden Cove - 19% IPC; 2024 - Lion Cove - 14% IPC. 1.18 * 1.19 * 1.14 => 60%

Looking at Apple cores, there is still potential to extract IPC.
 

Josh128

Golden Member
Oct 14, 2022
1,016
1,489
106
Lisa Su herself presented a slide about Epyc Venice detailing a 1.7x improvement.

Given the expected 1.34x (256 vs 192) core count increase that leaves roughly 1.275x improvement from IPC and clock.
Suddenly we're above that +25% performance increase per core you call "hope and dreams" 😅

To reach +27.5 performance with a +10% IPC increase, you need a ~ 1.16% clockspeed increase
5.7ghz * 1.16 = 6.612ghz

Do note this is calculated from conservative epyc figures

EPYC gen over gen perf claims are absolutely irrelevant to potential 1t gains on upcoming desktop. Zen 4 desktop gained ~50% MT core for core vs Zen 3 when comparing 16 core SKUs. This was due to increased MT clocks and very minor 8-12% IPC gains.

IMO because of that, its a fools errand to extrapolate 1t desktop gains from Lisas statement. Im just going to reiterate-- I believe 6.5GHz factory boost is most likely a delusional pipedream. ~6.2GHz is still very much in question.
 
Jul 27, 2020
25,599
17,764
146
What we do know is that Keller claimed there's a lot of room for additional IPC improvements. How? ?????
Optimization tricks. Profile the most common code and look at where the most time is being spent then reduce that time spent doing that particular thing. HT is one such trick. It effectively increases the IPC of the core in multicore workloads by ensuring that the core resources are never completely idle and some instructions of either thread are always in flight. Then there's the branch prediction accuracy.


Next, they could do 3-Ahead branch prediction by spending more transistor budget.

Proposed alternative to branch prediction: https://hps.ece.utexas.edu/pub/PruettPatt_BranchRunahead.pdf

Experimentally, they have predicted 16 branches:
Even crazier speeds may be achieved with spintronics where the calculations may take place inside RAM chips themselves without typical RAM latency impact.

 

Io Magnesso

Senior member
Jun 12, 2025
317
100
71
Nope, I stated a historical fact. I don't know about future IPC increases, and admit it.

Back in the day, when Intel was king, I repeatedly asked if there was some theoretical limit to IPC, and was given the same answer as you do now.

"It's hard from here to get significant IPC increases." None ever answered the direct question of "theoretical limit to IPC".

What we do know is that Keller claimed there's a lot of room for additional IPC improvements. How? ?????
Sorry about that
Personally, I believe that the IPC will rarely rise more than 20% from the previous generation.
That's why I was surprised by Intel Skymont
I know how to further improve IPC's Apart from whether it can actually be put into the product
Also, I'm an Intel believer, so I'm not saying this.
Apple's IPC is amazing, but I think it's still small unless there is a drastic improvement in the future.
 
Reactions: maddie

OneEng2

Senior member
Sep 19, 2022
662
903
106
Lisa Su herself presented a slide about Epyc Venice detailing a 1.7x improvement.

Given the expected 1.34x (256 vs 192) core count increase that leaves roughly 1.275x improvement from IPC and clock.
Suddenly we're above that +25% performance increase per core you call "hope and dreams" 😅
Yea, on EPYC which is completely power limited.
AFAIK EPYCs do not casually run at 5.7GHz... The quoted 1.7x figure is surely for a top model which means a strongly thermally/power limited SKU. That means 2nm should allow higher real frequency than 2.25/3.7GHz of Bergamo.

Besides that, the new platform increases the number of memory channels and TDP which suits many server workloads.

Mind you that the Zen 5's "server IPC improvement" led to that laughable Zen 5 +40% IPC hypetrain.
This exactly. On desktop, the top clock is likely due to thermal density issues at max clock rate.
Eloquently put.

That's why I will disregard any talk about 6+ GHz frequencies, even from adroc.
Agree.... I don't disregard adroc because he is adroc though. I disregard his posts because he fails to provide any evidence .... or even reasoning behind his boldly stated "facts". In fairness, I would feel this way about anyone's posts given the same context.
That's right That's because Intel was just lazy
But it's a thing of the past
However, it is real that the range of improvement in performance is small.
It will remain small unless you find a way to do it.
I believe that the real reason that large IPC improvements are "a thing of the past" is due to the fact that large increases in transistor density are also "a thing of the past".

If you get a larger transistor budget for a design, you can make registers wider, buffers deeper, and add a ton of logic to your branch predictor.

If we take it as an assumption that the clock speeds are limited by thermal density, then this also complicates things. Simply packing more transistors into a smaller area makes the thermal density worse by some percentage. If that percentage is near the improved thermal capabilities of the new process, then clock speeds don't improve.
 

Abwx

Lifer
Apr 2, 2011
11,834
4,785
136

Josh128

Golden Member
Oct 14, 2022
1,016
1,489
106
13% average is not 8-12%.



Im aware of AMDs chart. I know CB R23 is only about +6%. I think a lot of the larger numbers in their chart are due to increased memory speed and bandwidth. R23 doesnt touch memory. I consider Zen 4s actual IPC vs Zen 3 at the same memory frequency to be a bit less than AMDs claims here.
 

Abwx

Lifer
Apr 2, 2011
11,834
4,785
136
Im aware of AMDs chart. I know CB R23 is only about +6%. I think a lot of the larger numbers in their chart are due to increased memory speed and bandwidth. R23 doesnt touch memory. I consider Zen 4s actual IPC vs Zen 3 at the same memory frequency to be a bit less than AMDs claims here.
7Zip is 13%, that s remarkable and a more relevant number for usual apps that are mainly INT, CB R23 is FP, beside R23 1T is 9% in this chart, not 6%...
 
Last edited:
Reactions: Tlh97

Josh128

Golden Member
Oct 14, 2022
1,016
1,489
106
beside R23 1T is 9% in this chart, not 6%...
Yeah, but its not true. Just like Zen 4 to Zen 5 R23 claimed uplift of 17% IPC is not true. Thats my point.

Zen 5 is 10.1% faster than Zen 4 per GHz in R23 ST.
Zen 4 is 6.2% faster than Zen 3 per GHz in R23 ST.



 

Attachments

  • 1751476730989.png
    90.2 KB · Views: 4
Last edited:

Doug S

Diamond Member
Feb 8, 2020
3,254
5,626
136
Lisa Su herself presented a slide about Epyc Venice detailing a 1.7x improvement.

Given the expected 1.34x (256 vs 192) core count increase that leaves roughly 1.275x improvement from IPC and clock.
Suddenly we're above that +25% performance increase per core you call "hope and dreams" 😅

To reach +27.5 performance with a +10% IPC increase, you need a ~ 1.16% clockspeed increase
5.7ghz * 1.16 = 6.612ghz

Do note this is calculated from conservative epyc figures


You cannot calculate in that way. At all.

When you're talking about huge CPUs like that in all core loads, changes that improve global cache sizing/ways, memory bandwidth/latency and intercore fabric bandwidth/latency have a huge effect. Those cores also run at far lower speeds under all cores active loads, so improving the clocks in a 192/256 core load tells you almost nothing about improvement in top bin clock of desktop CPUs in single core loads.

What you're doing here is like trying to extrapolate improvement in 0-60 time of a car based on reports of a 70% gain in towing capacity of a truck that uses the same engine.
 

Abwx

Lifer
Apr 2, 2011
11,834
4,785
136
Reactions: Tlh97

Josh128

Golden Member
Oct 14, 2022
1,016
1,489
106


It is, those 17% were for nT, not 1T like the Z3 vs Z4 slide.
Its not for nT. IPC is not a relevant metric to nT due to varying clocks depending on power efficiency and draw. Even if it was, it only improves by 1% vs ST, going from 10% to 11%, which is explainable by run to run variance. Its just a flat out lie by AMD.
 
Reactions: Krteq

OneEng2

Senior member
Sep 19, 2022
662
903
106
In all fairness, I don't think anyone things that an OEM's presentation represents the best way to determine performance improvements.

We all pretty much believe they have slanted their picks .... which makes perfect sense for them to do.
 

Josh128

Golden Member
Oct 14, 2022
1,016
1,489
106
I agree, but I just stated a fact, and was called out as if I was making it up.
In all fairness, I don't think anyone things that an OEM's presentation represents the best way to determine performance improvements.

We all pretty much believe they have slanted their picks .... which makes perfect sense for them to do
 
Reactions: OneEng2
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/    |