News Leak indicates AMD Ryzen 9000X3D series CPU gaming performance will disappoint

[Admin]

An MSI presentation says that AMD's Ryzen 9000X3D does not have substantially higher performance than the typical version.

Leak indicates AMD Ryzen 9000X3D series CPU gaming performance will disappoint : Read more

 

[kaalus]

13% fps increase over the fastest gaming CPU in the world, and you call that underwhelming?

 

[-Fran-]

13% fps increase over the fastest gaming CPU in the world, and you call that underwhelming?

Also: "It should be noted that the new CPUs were run at the same frequency as the previous generation processors".

Like, that's just an IPC brag (or more like a VCache+IPC one), since you could say, looking at Ry9K's current line up, that the new VCache'd CPUs will clock higher.

So that average is a baseline of potential increase, which makes it even better. This is under the caveat that I do believe the new 3D chips will clock higher.

Regards.

 

[PCWarrior]

13% fps increase over the fastest gaming CPU in the world, and you call that underwhelming?

It’s not a 13% average increase. It is 13% increase at best. MSI showed that the increase will range from 2% to 13% depending on the title. The 13% is about Far Cry 6 and it is an outlier.

 

[uplink-svk]

Calling 2 - 13% increase in a light of utter failure of Intel's 200S line regarding gaming and power effeciency is a bit...awkward, don't You think?

Intel's iterational bread and butter till AyMD came with Zen was what? iPC gain of 2 - 4% per generation of their never-ending "hegemony" of 4c/4t/8t CPU's beginning with Intel® Core™2 Quad Q6600 and ending with 7700K and arrival of Zen CPU's, where 1700X and 8700K broke the ice.

Now up to a double digit generational increase isn't enough? Come on Tom's Hardware, are You for real? 😒

 

[usertests]

Post the slide, Anton

https://videocardz.com/newz/msi-leaks-ryzen-9000x3d-2-to-13-higher-gaming-performance-than-7000x3d

PERFORMANCE IS EXPECTED TO BE BETTER ON PR SAMPLES AND RETAIL CHIPS

 

[blargh4]

Disappointing for who? More "disappointment" based on leaks and pre-release benchmarks? God tech journalism is turning into just non-stop tedious clickbait.

 

[Notton]

I think 11% to 13% max is okay if it's the same price, and they no longer sell the old one anyways.

 

[hotaru251]

double digit improvement is good...is this trying to make intel's "parity" sound not as bad?

also if its not OC'd you lost a lot of performance as zen scales good w/ memory and Zen5 can hit higher speeds (thus better perfomance)

 

[Steve Nord_]

AMD 10000 X3DD series: oops fam, microjet direct die cooling and Socket 6, clock it like a luser and kerb it if you want.

Alt: One does not -simply walk- into MSI baseline overclocking benchmarks.

 

[thestryker]

I don't think a whole lot can necessarily be gleaned from 3 games, but two being 2% and one being 13% doesn't seem surprising.

If you look at the 5700X3D vs the 5800X3D the performance difference doesn't even match the clock difference. HUB showed 4% lower performance on average with a range of 1-8% despite the 9% clock difference: https://www.techspot.com/review/2801-amd-ryzen-5700x3d/

With Zen 5 not being a meaningful uplift over Zen 4 for gaming it stands to reason the biggest benefit on a Zen 5 X3D part would be clock speed based. In theory that would mean similar results to the 5700X3D vs 5800X3D comparison.

Also: "It should be noted that the new CPUs were run at the same frequency as the previous generation processors".

The slides don't say that so I'm not sure where that part of the article came from. There was a singular Cinebench test done comparing the 8 and 16 core Zen 5 X3D parts with the 9700X/9950X at fixed frequency.

This is under the caveat that I do believe the new 3D chips will clock higher.

There's a Cinebench comparison of Zen 4 X3D and Zen 5 X3D that shows large increases which backs this up.

PERFORMANCE IS EXPECTED TO BE BETTER ON PR SAMPLES AND RETAIL CHIPS

This is clearly a generic note as it appears on the fixed frequency slide as well when it clearly wouldn't apply. It may end up being accurate, and I hope it is, but by itself doesn't mean anything.

 

[DavidLejdar]

Well, yeah... if I had a 7000X3D, such uplift may sure not sound enticing enough for an upgrade.

But coming from a 7600X, it is a nice added bonus on top. Based on CPU benchmarks here, 7600X with 4090 at 1080p, it is 131 FPS (average, geomean). With 7800X3D, it is 185 FPS. And with 9800X3D at worst perhaps 200 FPS. So, around or more than +50%. At 1440p the uplift is even more apparently(?) - with benchmark saying 128 with 7600X and 191 with 7800X3D... But then at 4K, there is barely any difference between the CPUs(?), according to another site...

Anyhow, not pre-purchasing. Still sounds like a boost to me though. Respectively, still sounds like a nice CPU to avoid or lower a CPU-bottleneck with a next-gen GPU.

 

[Makaveli]

a 3 game sample and wukong is super gpu bottlenecked.

I will wait until THG actually has a review sample and benchmarks posted.

Well, yeah... if I had a 7000X3D, such uplift may sure not sound enticing enough for an upgrade.

But coming from a 7600X, it is a nice added bonus on top. Based on CPU benchmarks here, 7600X with 4090 at 1080p, it is 131 FPS (average, geomean). With 7800X3D, it is 185 FPS. And with 9800X3D at worst perhaps 200 FPS. So, around or more than +50%. At 1440p the uplift is even more apparently(?) - with benchmark saying 128 with 7600X and 191 with 7800X3D... But then at 4K, there is barely any difference between the CPUs(?), according to another site...

Anyhow, not pre-purchasing. Still sounds like a boost to me though. Respectively, still sounds like a nice CPU to avoid or lower a CPU-bottleneck with a next-gen GPU.

So true alot of people that I see complaining about Zen 5 performance are on Zen 4 and don't need to upgrade.

 

[Mama Changa]

How about we start talking about the game engines. Many are highly unoptimised for large core counts or it's just not possible to get the cpu to do anymore as not everything is parallelalisable.

Zen 5 9600 and 9700 have 40%b lower TDP to still get 2-5% improvement, Intel looks to be doing the same thing on power.

I'd love all the cpu architects on the forum to tell us how they would alter the architecture to get 30-40% gains gen-on-gen. Have a look at Zen 5 in EPYC and on Linux, it's getting 20-55% more performance. Zen 5 isn't a failure, but the world doesn't revolve arounfd gamers luckily. Arrow Lake isn't a failure either. It's the start of something that is long overdue. Just getting similar performance to Raptor Lake at much lower power is a good start for a clean sheet tiled architecture. Better improvements will come with succeeding generations. PAnther Lake and Nova Lake is where we start to see bigger improvements in performance.

 

[halfcharlie]

Nobody is bottlenecked by CPU in gaming in the first place. Anyone making CPU purchase decisions as a result of gaming is just clueless. You could buy a 5 year old i5 and have no issues playing AAA games at 4K. Comparing to the immediate previous gen doesn't really matter either because only the rich upgrade every year, the majority do it every 3-5 years, so even a generation like this with a focus on efficiency is a large upgrade. As much as I'd like to wait for the next gen I'm long overdue for an upgrade and my productivity is suffering.

 

[drivinfast247]

Nobody is bottlenecked by CPU in gaming in the first place. Anyone making CPU purchase decisions as a result of gaming is just clueless. You could buy a 5 year old i5 and have no issues playing AAA games at 4K. Comparing to the immediate previous gen doesn't really matter either because only the rich upgrade every year, the majority do it every 3-5 years, so even a generation like this with a focus on efficiency is a large upgrade. As much as I'd like to wait for the next gen I'm long overdue for an upgrade and my productivity is suffering.

Wrong!

 

[thestryker]

Nobody is bottlenecked by CPU in gaming in the first place. Anyone making CPU purchase decisions as a result of gaming is just clueless. You could buy a 5 year old i5 and have no issues playing AAA games at 4K.

"CPUs Don't Matter For 4K Gaming"... Wrong!

Something we hear a lot is that CPU performance doesn't matter for 4K gaming. Without proper context, CPU benchmark data can be misinterpreted. Let us explain to...

www.techspot.com

 

[doughillman]

Nobody is bottlenecked by CPU in gaming in the first place.

What an incredibly bad take.

 

[YSCCC]

Nobody is bottlenecked by CPU in gaming in the first place. Anyone making CPU purchase decisions as a result of gaming is just clueless. You could buy a 5 year old i5 and have no issues playing AAA games at 4K. Comparing to the immediate previous gen doesn't really matter either because only the rich upgrade every year, the majority do it every 3-5 years, so even a generation like this with a focus on efficiency is a large upgrade. As much as I'd like to wait for the next gen I'm long overdue for an upgrade and my productivity is suffering.

actually quite some games are bottlenecked by CPU, especially when gaming at lower resolutions.

I am using a 14900K and a 3070Ti with 64gb of DDR5 6000 CL30 for MSFS with some resources heavy addon, and get ranging from 40-80FPS, when using developing mode the FPS limitation shows: CPU limited (main thread).

Back to the topic, 2-13% FPS gain seems quite ok/normal for generational change in gaming (which is not for the last gen to directly upgrade unless one have too much money to tinker...) and TBH, since the X3D is gaining the massive gaming performance obviously due to the... extra Cache, chips with both 3D V cahce will not see across the board double digit performance gain running at same frequency is expected, now the problem is, if this is just to showcase IPC gain so they run at same clocks, or that the heat dissipation really limits the clock speed

 

[TheHerald]

Calling 2 - 13% increase in a light of utter failure of Intel's 200S line regarding gaming and power effeciency is a bit...awkward, don't You think?

Intel's iterational bread and butter till AyMD came with Zen was what? iPC gain of 2 - 4% per generation of their never-ending "hegemony" of 4c/4t/8t CPU's beginning with Intel® Core™2 Quad Q6600 and ending with 7700K and arrival of Zen CPU's, where 1700X and 8700K broke the ice.

Now up to a double digit generational increase isn't enough? Come on Tom's Hardware, are You for real? 😒

Intel had a double digit performance increase almost if not every gen (kabylake exception) from the core quad era till skylake. Even their haswell refresh had a bigger gain than zen 4 to zen 5.

 

[TheHerald]

I don't think a whole lot can necessarily be gleaned from 3 games, but two being 2% and one being 13% doesn't seem surprising.

If you look at the 5700X3D vs the 5800X3D the performance difference doesn't even match the clock difference. HUB showed 4% lower performance on average with a range of 1-8% despite the 9% clock difference: https://www.techspot.com/review/2801-amd-ryzen-5700x3d/

The slide is clearly GPU bottlenecked with the exception of farcry. The differences will be bigger than just 2%. Wukong for example running at 60 fps, clearly that's a gpu limit.

 

[atomicWAR]

actually quite some games are bottlenecked by CPU, especially when gaming at lower resolutions.

I am using a 14900K and a 3070Ti with 64gb of DDR5 6000 CL30 for MSFS with some resources heavy addon, and get ranging from 40-80FPS, when using developing mode the FPS limitation shows: CPU limited (main thread).

Back to the topic, 2-13% FPS gain seems quite ok/normal for generational change in gaming (which is not for the last gen to directly upgrade unless one have too much money to tinker...) and TBH, since the X3D is gaining the massive gaming performance obviously due to the... extra Cache, chips with both 3D V cahce will not see across the board double digit performance gain running at same frequency is expected, now the problem is, if this is just to showcase IPC gain so they run at same clocks, or that the heat dissipation really limits the clock speed

Lower res is always harder on the CPU that's how it works...more frames more work. You hit 4K and in most, not all, games you push the bottleneck to the GPU. HalfCharlie isn't totally correct but they aren't completely wrong either in regards to higher res gaming on older CPUs. I ran an Ivy bridge 8c Xeon OC'd to 4.3GHz until the 7950X came out and I was gaming at 4k 90-120 fps in most games. People really don't realize how much you can shift the bottleneck to the GPU if you push the settings and resolution high enough. After 90fps in gaming, unless you're truly competitive...90fps+ is a completely playable/enjoyable experience.

 

[bit_user]

It’s not a 13% average increase. It is 13% increase at best. MSI showed that the increase will range from 2% to 13% depending on the title. The 13% is about Far Cry 6 and it is an outlier.

Can you really have an outlier, with only 3 data points?

Also, the title which improved only 2% could be GPU-limited, as it's going from only 61 to 62 fps? Interestingly, we saw the exact same framerates from that title on both the 8-core and 16-core CPUs. I smell something fishy.

 

[bit_user]

With Zen 5 not being a meaningful uplift over Zen 4 for gaming

There's a meaningful benefit, just not one worthy of a single-gen upgrade. Not sure why you keep repeating that.

https://www.tomshardware.com/pc-com...-tested-ryzen-5-7600x3d-gaming-benchmarks-too
​

 

[bit_user]

Intel had a double digit performance increase almost if not every gen (kabylake exception) from the core quad era till skylake.

This is misleading on a couple points. First of all, Haswell didn't speed up everything by double digits. Anand tech said some things improved by as little as "low single digits". Where they got the bigger gains was surely from things that could utilize AVX2.

https://www.anandtech.com/show/7003/the-haswell-review-intel-core-i74770k-i54560k-tested/9
​

Second, you're fond of touting the i7-4790K, but it's basically just a factory-overclocked i7-4770K. And if you're counting that, then Skylake only improved over it by 5%. I'd argue we should count it, because that's what Intel did instead of a proper desktop release of Broadwell. If you count neither Broadwell nor Haswell Refresh, then you're skipping a generation and measuring the performance difference across two generations.

https://www.anandtech.com/show/9483/intel-skylake-review-6700k-6600k-ddr4-ddr3-ipc-6th-generation/23
​

This revisionist history is something of a new turn, for you.