AMD Ryzen 9000 Series "Zen 5" Tested on Windows 11 24H2 Update, Shows Significant Performance Gains

[SL2]

WINTEL has never ceased to be, what's with the surprises?

The surprise?

Show me the last time a new Windows version caused such gaming performance uplift, regardless of CPU brand.

 

[Chomiq]

I hope Win10 will get a similar update... And I wonder how it affects performance in applications.

The problem is no one is testing W10 22H2 against W11 24H2 so we don't even know if there is any performance drop on W10.

 

[SL2]

The problem is no one is testing W10 22H2 against W11 24H2 so we don't even know if there is any performance drop on W10.

Well except for L1. Yeah, one game, but I don't see a drop. Which begs the question, is that lack of bloat making up for the lack of branch prediction optimization?

Why everyone say Zen 5 is bad ?

Well it probably also helps that I'm not expecting miracles, just not regressions. Tech is always fun wish I could grab one as well don't get me wrong. Assuming it's out by the time Arrow lake is as a real release should be interesting gaming wise now at least.

www.techpowerup.com

 

[Ferrum Master]

The surprise?

Show me the last time a new Windows version caused such gaming performance uplift, regardless of CPU brand.

What's the point? Windows only has offered performance degradation updates.

 

[Wirko]

It's similar problem to what Intel had with launch of Alder Lake on Windows 10.
Windows was unable to utilize new architecture properly, it was treating all cores as if they were the same, sometimes putting heavy load on e-cores.
Did Intel have time to work with Microsoft prior to launch of Alder Lake? Definitely. Did Microsoft have time to modify scheduler mechanism? Definitely.
Same applies to AMD's Zen 5 launch.

Apart from that, the initial W11 release (or maybe the update to improve behaviour on Alder Lake?) had something broken on the red side, so Ryzen performance dropped a lot. I remember MS being quite open about that, and the issue was fixed in a month or so.

 

[SL2]

What's the point? Windows only has offered performance degradation updates.

Yeah you have no answer, and you still don't get the surprise. Cute Windows bashing BTW, but you picked the wrong thread.

 

[bug]

So people got what they were clamoring for since years... Comment sections around the world were filled with complaints that CPU/GPU manufacturers race for MHz and forget about efficiency, and how "everyone" would forgo massive performance jumps for good efficiency boosts. Fast forward to 2024 when AMD did just that (accidentally, after announcing massive performance boosts too, and partially failing to deliver) and people are unhappy that the CPU is "just" more efficient.

Oh, I don't have a problem with that. It's just that AMD trying to make it look like this was a Zen5-only improvement seemed like they were trying to suggest Zen5 will be faster than Zen4 now.

 

[Daven]

W1zzard, will you re-test 9700X in games and 9950X in applications with Win11 24H2 update?
I know you have lot of work to do but it'd be really good to see the difference (former review vs. newer one).

IMHO, a rereview could wait until the X870E chipset and Arrow Lake CPUs are released. That will give some time for optimizations and any more problems to be ironed out. We would then see the latest and greatest from AMD and Intel go head to head.

 

[kondamin]

Especially those bribing OEMs to purchase only INTEL CPUs... but... unfortunately that's no conspiracy.

Yeah, I get upset about what the Spanish did in the fifteen hundreds in my region too

 

[Crackong]

windows being windows...

 

[AusWolf]

Why don't we expand on the title?

"24H2 shows significant performance gains..." ...with certain CPUs and a 4090 in certain games at 1080p.

So what about all the other hardware/resolution combinations that 99.9% of people use?

 

[AnarchoPrimitiv]

Yeah, I get upset about what the Spanish did in the fifteen hundreds in my region too

Intel was bribing OEMs in the 2000s and at a time when AMD was BEATING Intel in gaming and other performance metrics and their star was rising. Had Intel not engaged in their illegal, anti-competitive and anti-consumer behavior, AMD could have grown tremendously in that period and altered the course of history forever. Don't act like this was some inconsequential action, it could have cost AMD billions.

What's most disturbing of all is that this LITERALLY hurt YOU as a consumer most and you seemingly don't care.....I try not to assume, but it almost seems like you might be an Intel fan that actually approves of this behavior despite the fact that it literally did not benefit you whatsoever and even hurt you as a consumer by reducing competition and therefore raising prices.

This isn't ancient history either as Intel still has their "joint development fund" where they basically throw cash at OEMs to keep AMD CPUs out of the best laptop models (despite the fact that AMDs mobile options have been far more efficient than Intel's in recent years)....again, this only hurts you as a consumer.

I know it must really annoy Intel fans, but the undeniable fact is that in a duopoly, the best situation for consumers is a 50%/50% split in marketshare. This just so happens to mean that at present, AMD capturing marketshare from Intel is OBJECTIVELY beneficial to ALL consumers, Intel fans included, with the inverse being bad for consumers.

 

[Chry]

Yeah so many questions. As others said: What about Intel? AM4? Anyone would like to do some testing? Might take some time... Maybe we'll get more info later.

And the 9000 series are now fully reviewed by all reviewer sites with the non-24H2 benchmarks. Ouch.

Anyway so it's just 24H2 update, or is it a specific update FOR 24H2? Is 26100.1457 already benefiting from those fixes?

In a way this only makes it less appealing to upgrade from 7000 since it just got a 10% boost... Though it is really nice when previous gen gets such uplifts as well. Though I imagine here it was incidental: Not like they had a dedicated team working to improve previous gen performance.

 

[SL2]

Don't act like this was some inconsequential action, it could have cost AMD billions.

What's most disturbing of all is that this LITERALLY hurt YOU as a consumer most and you seemingly don't care.....I

I bet it was a way to say that it's in the past, not that he doesn't care.

Dell used to be all Intel, yet now they're the ONLY one ever to release a 7900M laptop. Things change.

Yeah so many questions. As others said: What about Intel?

It's right there in the video, they're talking about an upcoming test.

Anyway so it's just 24H2 update, or is it a specific update FOR 24H2? Is 26100.1457 already benefiting from those fixes?

It's in the first link.

 

[phints]

Wow Zen 4 and Zen 5 both have a sizable performance increase. Wonder if older Zen 3 does. 24H2 can't come out soon even let's get going Microsoft.

Do we know what changed? New/optimized scheduler? Release date?

 

[Chry]

It's in the first link.

Thanks! In case anyone else missed it, there's a Youtube link in the original post here that includes some Intel testing as well from around 20:00:

TLDW: 0 improvement in games tested except 1 game saw 25% gains for Intel as well.

 

[Dredi]

shame he didn’t do a reference test with an intel machine to see how that does under the patched up windows

He did, just not with all the games.
One outlier, but otherwise looks like no difference between the w11 versions when using intel.

 

[mb194dc]

Why don't we expand on the title?

"24H2 shows significant performance gains..." ...with certain CPUs and a 4090 in certain games at 1080p.

So what about all the other hardware/resolution combinations that 99.9% of people use?

If they showed that then people might realize any CPU will do for pretty much any modern gaming use case. Bar the people spending thousands for huge fps at 1080p and below.

 

[persondb]

WINTEL has never ceased to be, what's with the surprises?

Intel also got a huge boost too(for at least one game, possibly more but that wasn't tested.)

 

[SL2]

Thanks!

I edited my reply to highlight that I wasn't talking about this review, but an upcoming one.

 

[Rjc31]

I'm sorry if this has been answered already but is there any difference in performance at 4K? At work right now and can't research myself!

 

[kondamin]

Intel was bribing OEMs in the 2000s and at a time when AMD was BEATING Intel in gaming and other performance metrics and their star was rising. Had Intel not engaged in their illegal, anti-competitive and anti-consumer behavior, AMD could have grown tremendously in that period and altered the course of history forever. Don't act like this was some inconsequential action, it could have cost AMD billions.

What's most disturbing of all is that this LITERALLY hurt YOU as a consumer most and you seemingly don't care.....I try not to assume, but it almost seems like you might be an Intel fan that actually approves of this behavior despite the fact that it literally did not benefit you whatsoever and even hurt you as a consumer by reducing competition and therefore raising prices.

This isn't ancient history either as Intel still has their "joint development fund" where they basically throw cash at OEMs to keep AMD CPUs out of the best laptop models (despite the fact that AMDs mobile options have been far more efficient than Intel's in recent years)....again, this only hurts you as a consumer.

I know it must really annoy Intel fans, but the undeniable fact is that in a duopoly, the best situation for consumers is a 50%/50% split in marketshare. This just so happens to mean that at present, AMD capturing marketshare from Intel is OBJECTIVELY beneficial to ALL consumers, Intel fans included, with the inverse being bad for consumers.

The reason why I no longer care about what happened 20 years ago is because they were punished for it and the people responsible for it are no longer in the picture and AMD got a cool billion out of it and intel got a 400 million fine on top of it.

It wasn't the reason why AMD went in the toilet for a decade either, they over stretched them selves by building tons of fabs cause that's what real men do (like intel was enticed in doing) and for some reason they thought it a good idea to waste billions (when those were still considered big numbers) on ATI.
The global financial crisis happened and everyone wanted the money they put in AMD back.
Intel Core was a success after the Pentium 4 debacle and bulldozer was a miserable failure.

Yes what intel did was wrong, but they didn't burn the house down that was amd's own doing.

 

[phints]

If they showed that then people might realize any CPU will do for pretty much any modern gaming use case. Bar the people spending thousands for huge fps at 1080p and below.

Or have you considered the fact it's a small team testing an upcoming Windows update to vette this AMD blog post so they selected a small set of obvious worst case (fast cpu+gpu for high fps) initial tests to get results out in a reasonable time frame? Obviously by the time Arrow Lake hits they will have time to test far more scenarios but in the meantime 24H2 is a definite improvement.

 

[Chrispy_]

This might actually be enough reason to move from W10 to W11 for some people. Clearly these fixes aren't going to be back-ported to Windows 10, and last time I looked, W10 was faster than W11 for gaming, but not by the 11% that this update brings to Zen4 and Zen5 users.

 

[rodrigorras]

Right. So Zen5 still isn't significantly faster than Zen4, only more power efficient.

Wrong, in Linux/Workstation/Rendering/Server Workloads is much faster.
Also, 7700x should be compared with 9700x at 105W.

with that in mind, AMD needs to reduce a bit the prices of 9700x .