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

[Vattila]

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).

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!

 

[biostud]

XMP and EXPO seem to do well being enabled at higher speeds with minimal to no user meddling. V different from years ago on intel.

The HWUB video with Buildzoid timings, gained significant improvements over EXPO settings. I'm just wondering if the extra cache will negate these differences, or if it will build on top of those, or most likely somewhere in between.

 

[Timmah!]

AMD Ryzen 9 7950X3D 3D V-Cache CPU Gaming Benchmarks Leak, Up To 35% Faster Than i9-13900K

Even more benchmarks of the AMD Ryzen 9 7950X3D 3D V-Cache CPU benchmarks have been leaked that show a 35% improvement over the 13900K.

wccftech.com

regarding cb23 score - not bad, pretty much on par with vanilla chip
i wonder if this is stock performance or after some fiddling

 

[Det0x]

7950x3d cb23 - not bad, pretty much on par with vanilla chip
i wonder if this is stock performance or after some fiddling

https://cdn.wccftech.com/wp-content/uploads/2023/02/AMD-Ryzen-9-7950X3D-3D-V-Cache-CPU-Gaming-Benchmarks-Leak-_1.jpg

This is actually pretty good.. 38k points at "120w TDP"

Even if the real powerlimit are 162w PPT its still much better performance/power then the competition

And the leaked gamebenches at unknown settings ain't too shabby either

7950X3D is on average 18% faster than 7950X and 12% faster than Core i9-13900K in these tests.

 

[Timmah!]

maybe its not 120w tdp though? you can increase the powerlimit on non-x cpus, right? maybe you can do here as well?

anyway, i may regret buying 7950x in december seeing this

 

[Asterox]

It looks like a pretty good showing for the 7950X3D. The slight defecit in the 2nd half of the synthetics is very minor.
The only whataboutisms I can envision are:

• Price difference
• Core i9-13900KS not tested
• Core i9-13900K was not allocated DDR5 8,000
• Mobo cost

I'm glad I waited for the 7950X3D.

You dont need a 300$ mobo for Ryzen 9 7950X.

X3D series use even less power, or Gigabyte obviously did a good job with "cheep B650M DS3H".Asrock B650M PG Riptide, or model without Wifi(same specifications as the Wifi version) is the cheapest AM5 mobo in my country.

Protis - Ponuda

www.protis.hr

Asus lol, i don't remember when i saw a cheap and good(regardless of an socket)Asus motherboard.

 

[biostud]

You dont need a 300$ mobo for Ryzen 9 7950X.

X3D series use even less power, or Gigabyte obviously did a good job with "cheep B650M DS3H".Asrock B650M PG Riptide, or model without Wifi(same specifications as the Wifi version) is the cheapest AM5 mobo in my country.

Protis - Ponuda

www.protis.hr

Asus lol, I don't remember when I saw a cheap and good( regardless of an socket)Asus motherboard.

View attachment 77135

View attachment 77136

The Asus prime boards are 6 layer PCB, while most other uses 8 layer, and some ITX boards even more.

 

[Joe NYC]

• Core i9-13900K was not allocated DDR5 8,000

You can't be serious.

 

[biostud]

I'll be damned. The reviews are out February the 27th, my 20 year anniversary as an AT member. Is this a sign?

Huh, apparently I've also been married three years on Monday.

 

[maddie]

Huh, apparently I've also been married three years on Monday.

Apparently?

 

[biostud]

Apparently?

My wife reminded me

 

[DAPUNISHER]

I suspect the new 3D is going to be a monster in MS flight sim. Not that any big reviewer will test it. It isn't canned or easy to replicate, and flying spaghetti monster forbid, they put that kind of time in to make a buck. As I have opined before, add MSFS and Assetto Corsa to the 50+ game test suites and even the 5800X 3D will suddenly look much more competitive in averages against the new CPUs from both vendors.

The account issues excuse being used for as to why Tom's and HUB stopped testing... doesn't fly.

It's $10 for game pass. Sign up a new account and get testing losers.

 

[Mopetar]

Eh, just use Factorio to get an idea of how those games will perform. That's another game that really scales well with the v-cache and it's pretty easy to design a replicable benchmark with it.

 

[DAPUNISHER]

Eh, just use Factorio to get an idea of how those games will perform. That's another game that really scales well with the v-cache and it's pretty easy to design a replicable benchmark with it.

You are missing my point. We would not use Factorio instead, we'd add it to the big test suite along with the others I mentioned. It feels intentional to not focus more on cache friendly titles. I expect that to change with the new 3D models, if it doesn't, it will be very telling, at least by my judgement.

 

[biostud]

I suspect the new 3D is going to be a monster in MS flight sim. Not that any big reviewer will test it. It isn't canned or easy to replicate, and flying spaghetti monster forbid, they put that kind of time in to make a buck. As I have opined before, add MSFS and Assetto Corsa to the 50+ game test suites and even the 5800X 3D will suddenly look much more competitive in averages against the new CPUs from both vendors.

The account issues excuse being used for as to why Tom's and HUB stopped testing... doesn't fly.

It's $10 for game pass. Sign up a new account and get testing losers.

My guess is still around 20% faster than 5800X3D from 10% clock increase and 13% IPC.

 

[DrMrLordX]

You are missing my point. We would not use Factorio instead, we'd add it to the big test suite along with the others I mentioned. It feels intentional to not focus more on cache friendly titles. I expect that to change with the new 3D models, if it doesn't, it will be very telling, at least by my judgement.

Kinda makes you wonder why AMD isn't testing with those titles.

 

[Mopetar]

If it's a 50+ game test suite, by all means add games like that, but if you just have a tight 10-game suite, adding even a single title that's a heavy outlier can swing the average a lot harder. By this point anyone who really cares about MSFS performance is already running a 5800X3D or waiting to buy Zen 4D.

The Zen 4D chips are going to let AMD retake the gaming crown, but let's not tarnish it by trying to load the test suite with some niche titles that blow out the average when even without those titles the chip is still clearly a winner.

Ultimately the argument works the other way and someone will complain about the tests focusing on a small number of cache friendly titles instead of mainstream titles and it just devolves into pointless arguments about the only true way to measure CPU gaming being RT titles, blah, blah, blah, blah.

It's pretty clear that Zen 4D is going to be the top gaming CPU going forward. Does is matter if it's only by 6% instead of 7% because of adding an extra title where it does better to drag up the average?

 

[DAPUNISHER]

Kinda makes you wonder why AMD isn't testing with those titles.

That would be red meat for the haters. They'd go HAM screeching about cherry picking. However, in a 50+ game suite, having a subset devoted to cache friendly titles makes sense.

 

[igor_kavinski]

My only issue right now is what the f is this snappy feedback people say about zen 4 on windows 10 and 11 over Intel. People say it but there's no real info about it. Maybe I'm getting too old to notice stuff like this.

I think it's coz Zen 4 chips boost quite aggressively, always banging their heads against the thermal limit.

 

[Timmah!]

My wife reminded me

So shes buying you 7950x3D for the anniversary?

 

[In2Photos]

So shes buying you 7950x3D for the anniversary?

I was thinking this means he's not getting a new CPU and instead will be buying her a gift!

 

[biostud]

So shes buying you 7950x3D for the anniversary?

Yeah, but no. She doesn't have to be an enabler. As long as she let me my addiction in peace, I'm also paying for it myself.

 

[DAPUNISHER]

The Zen 4D chips are going to let AMD retake the gaming crown, but let's not tarnish it by trying to load the test suite with some niche titles that blow out the average when even without those titles the chip is still clearly a winner.

Yes, I already said to do it for big test suites. Let's not move the goalpost by injecting small sample sizes as a scenario. Let's keep debating my contention. In which case, I could not disagree more about the tarnishing remark. That ain't even close to how I see it.

Almost every game is niche. MSFS has a very hardcore user base. So do racing sims like AC. Why test Shadow of the Tomb Raider, Metro Exodus, or a bunch of the other titles still included? They are not played by many people anymore. Yet many test them. The answer is because they reveal different aspects of how different game engines perform with different CPU architectures, and their platforms. That should include big cache friendly titles. And not just a single example.

If we start eliminating outliers where do we stop? A few titles heavily favor AMD 3D right now. Does that mean we can get rid of the same number of games that heavily favor Intel's platform and CPUs? It's the slippery slope fallacy. Either you include all of the types of games that can reveal different aspects of the CPU and platform performance, or it's a bad look. Furthermore, If we are going to throw out all the games where the 3D has the biggest lead, then again, do the same for Intel. Hell while we are at it, throw out the same number of big leads for Zen 4 too. Even the AM4 3D looks a lot better if we do that.

For myself, there is no logical reason to exclude a decent sample size of games that reveal the benefits of dat big cache. It's a new CPU feature that should be fully examined. Not put through a test suite that fails to show its full potential. Imagine if RTX was treated that way. No one tested Cyberpunk'd or Metro or a couple of other games where RTX makes its best showings. That would look super sus, as if downplaying its dominance when properly utilized. Yet that seems to be what is happening with the 3D in test suites. All of its biggest wins are absent from the charts?

 

[DAPUNISHER]

Yeah, but no. She doesn't have to be an enabler. As long as she let me my addiction in peace, I'm also paying for it myself.

This really must be only your third anniversary (congrats! ) Because how it works is, there's our money and her money.

 

[igor_kavinski]

As long as she let me my addiction in peace, I'm also paying for it myself.

Do you think she will get jealous of your PC because of how much you spend time with it, instead of spending with your wife? Or do you crawl out of bed in the dead of night when she's out cold?

 

[DAPUNISHER]

Do you think she will get jealous of your PC because of how much you spend time with it, instead of spending with your wife?

You realize many of us used a computer called the Amiga right?