Discussion Speculation: Zen 4 (EPYC 4 "Genoa", Ryzen 7000, etc.)

Page 439 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Vattila

Senior member
Oct 22, 2004
809
1,412
136
Except for the details about the improvements in the microarchitecture, we now know pretty well what to expect with Zen 3.

The leaked presentation by AMD Senior Manager Martin Hilgeman shows that EPYC 3 "Milan" will, as promised and expected, reuse the current platform (SP3), and the system architecture and packaging looks to be the same, with the same 9-die chiplet design and the same maximum core and thread-count (no SMT-4, contrary to rumour). The biggest change revealed so far is the enlargement of the compute complex from 4 cores to 8 cores, all sharing a larger L3 cache ("32+ MB", likely to double to 64 MB, I think).

Hilgeman's slides did also show that EPYC 4 "Genoa" is in the definition phase (or was at the time of the presentation in September, at least), and will come with a new platform (SP5), with new memory support (likely DDR5).

Untitled2.png


What else do you think we will see with Zen 4? PCI-Express 5 support? Increased core-count? 4-way SMT? New packaging (interposer, 2.5D, 3D)? Integrated memory on package (HBM)?

Vote in the poll and share your thoughts! :)
 
Last edited:
  • Like
Reactions: richardllewis_01

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
Being modern actually seems to hurt the 5800x3d gaming performance relative to the 5800x (techpowerup).

I think that's because modern games tend to prefer raw computational power and memory bandwidth. Latency is still important though to be sure, but as games become larger and more detailed, bandwidth is starting to become a bigger deal.

A good example of that are the Spider-Man games. The addition of ray tracing means that the initial bvh setup and continued maintenance relies on both CPU compute and memory bandwidth for performance as the data sets are too large to fit in cache.
 

Geddagod

Golden Member
Dec 28, 2021
1,296
1,368
106
and where did I mention gaming ? The world does not revolve around gaming, in fact the opposite. The process we are now running in DC needs affinity set so 8 cores can be on the same chiplet to use the L3 cache, as this really page a difference in speed. And with 2 chiplets, we need extra cache on both.

And NO, the 7950x is not 10% slower than a 13900k, maybe 2%. Show me the 10% (and not on benchmark outlier)
The article is about gaming.
The person you replied to was about gaming.
You talked about gaming perf when you said "Considering how the 7950x absolutely kills the 5950x, and double the cache from the 5800x3d, I would believe anything from this processor", as you said as a reply to the person talking about gaming.

The 10% figure is from the 3DCenter meta review data.
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
26,171
15,324
136
The article is about gaming.
The person you replied to was about gaming.
You talked about gaming perf when you said "Considering how the 7950x absolutely kills the 5950x, and double the cache from the 5800x3d, I would believe anything from this processor", as you said as a reply to the person talking about gaming.

The 10% figure is from the 3DCenter meta review data.
want to link that article ?
 

moinmoin

Diamond Member
Jun 1, 2017
5,064
8,032
136
I don't think the extra V-cache on the second chiplet is going to be well used if at all by the other chiplet.
As the L3$ is a victim cache for the given CCX it obviously won't be used by other CCXs. Worst case the content of both CCXs' L3$es eventually end up being duplicates of each other, though I don't expect that to be likely to happen.
 

Geddagod

Golden Member
Dec 28, 2021
1,296
1,368
106
Don't bother with that type of posters, The 7600X is already beating the 13900K in gaming with good RAM Kits. The 7800X3D will just treat the 13900K like a redheaded stepchild.
Doesn't the 13900k have a better mem-controller than the 7600x? Maybe a tuned 7600x can beat a stock 13900k, but does, on average, a tuned 13900k lose to a tuned 7600x? I HIGHLY doubt it.
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
26,171
15,324
136
Again with the gaming crap. You said its faster, not in what and by who. And that's one website. Anadtech found 1.5% different in gaMING.

You are such a troll.
 
  • Like
Reactions: Mopetar

Geddagod

Golden Member
Dec 28, 2021
1,296
1,368
106
Again with the gaming crap. You said its faster, not in what and by who. And that's one website. Anadtech found 1.5% different in gaMING.

You are such a troll.
How am I a troll? You replied to a person posting an article about GAMING, while just generalizing performance. How is it a stretch to assume you were also talking about gaming?
That is actually NOT one website. A meta review, be definition, is a combination of multiple reviewers.
Anandtech is JUST one reviewer. This meta review combines 20? I think reviewers.
 

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
Again with the gaming crap. You said its faster, not in what and by who. And that's one website. Anadtech found 1.5% different in gaMING.

You are such a troll.

The 3D center analysis is a meta-analysis of multiple reviews, including Anandtech. Anandtech also used a 6900XT during their gaming portion which bottlenecks these ultra fast CPUs, so it's near useless for gauging gaming performance for both Zen 4 and Raptor Lake.

Also, having a contrary opinion isn't trolling. He backed up his comment and just because you don't like his opinion he's a troll? That's ridiculous, and just goes to show how Anandtech forums has become an AMD echo chamber over the years since AMD took back market share with Zen 2 and Zen 3.

Thirdly, the V-cache CPUs are primarily marketed towards improving gaming performance in the consumer CPUs, so I don't know why you're so surprised he's talking about gaming.
 

Geddagod

Golden Member
Dec 28, 2021
1,296
1,368
106
Care to back up this comment?
I mean Intel's mem controller on the 13900k supports higher speeds than the one on the 7600x. Which imo is pretty impressive considering how Intel also has raptor lake supporting DDR4 as well, but that's not important.
Edit: 5600 MHz on 13900k vs 5200 Mhz on 7600x
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
26,171
15,324
136
The 3D center analysis is a meta-analysis of multiple reviews, including Anandtech. Anandtech also used a 6900XT during their gaming portion which bottlenecks these ultra fast CPUs, so it's near useless for gauging gaming performance for both Zen 4 and Raptor Lake.

Also, having a contrary opinion isn't trolling. He backed up his comment and just because you don't like his opinion he's a troll? That's ridiculous, and just goes to show how Anandtech forums has become an AMD echo chamber over the years since AMD took back market share with Zen 2 and Zen 3.

Thirdly, the V-cache CPUs are primarily marketed towards improving gaming performance in the consumer CPUs, so I don't know why you're so surprised he's talking about gaming.
Talking about Raptor lake in a Zen 4 thread is not trolling ? And vcache primarily gaming ? Its started in Milan-x, and THEN went to Zen 3. There are a lot more places that cache helps other than gaming, you guys act the world revolves around gaming.

Edit: and the 5800x3d is known as the best gaming chip out there.
 

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
I mean Intel's mem controller on the 13900k supports higher speeds than the one on the 7600x. Which imo is pretty impressive considering how Intel also has raptor lake supporting DDR4 as well, but that's not important.
Edit: 5600 MHz on 13900k vs 5200 Mhz on 7600x

His comment was totally incorrect and that's why he hasn't backed up his statement with benchmarks. There maybe an outlier perhaps where the 7600x beats the 13900K, but overall, the 7600x is not in the same league as the 13900K.....and that's for both gaming and productivity.
 
  • Like
Reactions: Exist50

Geddagod

Golden Member
Dec 28, 2021
1,296
1,368
106
Talking about Raptor lake in a Zen 4 thread is not trolling ? And vcache primarily gaming ? Its started in Milan-x, and THEN went to Zen 3. There are a lot more places that cache helps other than gaming, you guys act the world revolves around gaming.
I talked about Raptor Lake because that's what the article that you were replying too compared the 7950x3D to raptor lake. The tittle is literarily "7950x3D is 30% faster than the 13900k", to Exist 50 said I doubt it will be that high, to which YOU replied about the 7950x3D " I would believe anything from this processor. "
Also you talked about the 7950x3d FIRST and THEN Milan-X. Milan-X was at the end of your comment.
 

Geddagod

Golden Member
Dec 28, 2021
1,296
1,368
106
So if you take 30 crap reviews and 2 good ones. then the average is not worth reading. Its does not matter how many, its how many of the GOOD review sites say what. And for the most part they all agree that Zen4 and Raptor lake trade blows, but Raptor lake does it using WAY more power.
What makes those other reviewers crap?
Btw, the metareviews from 3Dcenter.org are usually supported by large-data set benchmarks from other popular (maybe you consider them "good") benchmarkers such as hardware unboxed.
For example the 5800x3d is ~15% faster than the 5800x in both hardware unboxed 41 game benchmark, as WELL as the meta review from 3Dcenter.
 

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
Talking about Raptor lake in a Zen 4 thread is not trolling ? And vcache primarily gaming ? Its started in Milan-x, and THEN went to Zen 3. There are a lot more places that cache helps other than gaming, you guys act the world revolves around gaming.

Raptor Lake is the competition, so it's naturally going to be discussed when talking about Zen 4 3D's potential performance. And while you are correct that V-cache had its inspiration in servers/HPC, the consumer chips are marketed heavily towards gaming. Consumer oriented productivity workloads don't seem to benefit from the V cache.

Like it or not, gaming is the most cache sensitive workload for consumers.

Edit: and the 5800x3d is known as the best gaming chip out there.

Bang for buck I would agree, but as for best performance it's not even in the top 5 since Raptor Lake and Zen 4 are out.
 

Exist50

Platinum Member
Aug 18, 2016
2,452
3,102
136
These numbers aren't stock comparisons of 5800X vs. 3D - they are at normalised 4,4Ghz frequency, increasing the relative advantage. The reasoning being that the frequency gap will be much less this time.
The frequency difference between the 5800X and 5800X3D is what, like 5% if that? There's still a large gap unaccounted for. And then consider that closing that frequency gap will probably be the main improvement from Zen4 X3D, so where're the additional gains coming from?
 
  • Like
Reactions: Carfax83

Exist50

Platinum Member
Aug 18, 2016
2,452
3,102
136
Again, you only speak for some people, not the DC community. The upcoming project (tomorrow) would be killer if both ccds' had 96m cache. See the DC forum for details, but stop speaking for everyone.
The link in question was literally about gaming. But what I said applied identically to any workload. Cross-CCX cache snooping makes no sense with the latencies involved, so there's going to be no gains there, and you're presumably loading each core anyway. Why would you expect a dual die config to provide more advantage from V-Cache than a single die?
 

Exist50

Platinum Member
Aug 18, 2016
2,452
3,102
136
He isn't speaking for everyone or anything lmao, idk what's up with this "white knighting" for the DC community.
It's an excuse for him to make absurd performance claims and then defend those as "curing cancer" or some other non-sequitur. He used to say that Zen 3 had twice the performance per core at half the power vs Golden Cove. Obviously, no benchmarks exist to back up those claims, but as we see here, clearly that doesn't stop some people.

This shouldn't even be a discussion. The original link we were responding to was explicitly about gaming performance, so of course that'll be the topic of discussion. And given that AMD explicitly markets its consumer 3D V-Cache chips for gaming, seems perfectly applicable too. Obviously, if a 16c V-Cache chip does come out, it would be useful for other things, so it would be on-topic and pertinent to know performance, but I'm not seeing anyone posting benchmarks for those.
 
  • Like
Reactions: Carfax83
Jul 27, 2020
20,040
13,738
146
Why would you expect a dual die config to provide more advantage from V-Cache than a single die?
Isn't it possible for game developers to detect the presence of a dual die V-cache CPU and then peg various threads across the two CCXs? That would maximize the amount of cache available to the game.
 

nicalandia

Diamond Member
Jan 10, 2019
3,331
5,282
136
This is just delusional.
Really? Why? Because you say so?

The 7600X has been shown to be faster than the 5800X3D(both using 4090 GPU)

Here the most recent and comprehensive review of the 5800X3D vs 13900K, The top of the line Intel is 1.5% faster on average than the 13900K where it matters the most.

So who is delusional now? The guy who say that the Stack 3D V cache will not matter because Intel enjoys a hefty 10% Gaming lead or me who is saying that Zen4(7600X) and Raptor Lake(13900K) are basically a match and that the 7800X3D will more than likely beat it soundly?
 

Exist50

Platinum Member
Aug 18, 2016
2,452
3,102
136
Isn't it possible for game developers to detect the presence of a dual die V-cache CPU and then peg various threads across the two CCXs? That would maximize the amount of cache available to the game.
My understanding of current game's behavior is that they highly prefer to share one CCX for the sake of inter-thread communication and common data sharing. I doubt a separate V-Cache CCX would substantially change things independent of the core count increase.
 
  • Like
Reactions: BorisTheBlade82