AMD's Reviewers Guide for the Ryzen 9 7950X3D Leaks

[AnotherReader]

Why does it still seem like we are struggling with 1080p on top tier hardware?

Top end hardware isn't struggling with 1080p; with the exception of Ashes of the Singularity, the lowest fps in the guide are just below 200 for the 13900k.

 

[A Computer Guy]

We will see this pattern until the stacked cache is below the CPU chiplet. AMD will do this with MI300, but we'll see what tradeoffs come with that approach.

It would be neat if they could stack DRAM. Imagine 128GB ram staked on the CPU.

 

[Harthad]

I'd love to see some World of Warcraft benchmarks with this CPU.
I know it depends a lot on the location, server, time of day, etc but still

 

[AnotherReader]

It would be neat if they could stack DRAM. Imagine 128GB ram staked on the CPU.

That seems to be in the plans too, but I would be wary of it for desktops due to cooling the CPU.

 

[trsttte]

Let's see the 4k results with RT or higher.

CPU tests are always done at lower resolutions, it's a matter of choosing your bottleneck. It's easy for a modern high end GPU to push countless frames at 1080p, so the limit is the CPU capacity to push stuff to be rendered.

The opposite happens with GPU tests, the GPU will take longer and only be able to render a lower number of frames at higher resolutions while the CPU has enough time to keep the pipeline fed.

 

[Space Lynx]

While the tests should be done with higher speed RAM for Intel, I don't think the price differences are correct. These are the lowest prices for a 32 GB kit of DDR5 on PcPartPicker in the USA:

1. DDR5 6000 CL30: $ 146
2. DDR5 6600 CL34: $ 188
3. DDR5 7200 CL34: $ 247

I see. You mean memory latency; in that case, I expect Intel to have lower latency.

$247 ain't shit these days. hell costs $25 for a bowl of chicken wings, I still say 720-0 cl 34 should be Intel's norm

 

[ThrashZone]

$247 ain't shit these days. hell costs $25 for a bowl of chicken wings, I still say 720-0 cl 34 should be Intel's norm

Hi,
Makes the products go faster

 

[Denver]

$247 ain't shit these days. hell costs $25 for a bowl of chicken wings, I still say 720-0 cl 34 should be Intel's norm

I buy 80-90 kg of chicken for U$ 250, the problem is that something is not worth the price charged and you still pay.

 

[AnotherReader]

$247 ain't shit these days. hell costs $25 for a bowl of chicken wings, I still say 720-0 cl 34 should be Intel's norm

If you're buying expensive processors like the 13900k or the 7950 X3D, then a $100 difference isn't much, but it's still important to note that there's a difference, and given that the MSRP for the 7950 X3D is about $ 130 more than than the street price of the 13900k, the difference in price for RAM erases or minimizes the premium for the V-Cache option.

 

[mb194dc]

CPU tests are always done at lower resolutions, it's a matter of choosing your bottleneck. It's easy for a modern high end GPU to push countless frames at 1080p, so the limit is the CPU capacity to push stuff to be rendered.

The opposite happens with GPU tests, the GPU will take longer and only be able to render a lower number of frames at higher resolutions while the CPU has enough time to keep the pipeline fed.

It's unrepresentative of nearly all real world use cases and largely pointless.

If 3d cache doesn't produce a boost at normal use case resolutions, little point in it.

It doesn't matter what CPU you have if you're GPU limited anyway. That should be highlighted.

 

[R-T-B]

I buy 80-90 kg of chicken for U$ 250, the problem is that something is not worth the price charged and you still pay.

Hate to have to say this, but it's literally worth what people will pay. If he buys it, it's worth it (to him anyways).

 

[Space Lynx]

If you're buying expensive processors like the 13900k or the 7950 X3D, then a $100 difference isn't much, but it's still important to note that there's a difference, and given that the MSRP for the 7950 X3D is about $ 130 more than than the street price of the 13900k, the difference in price for RAM erases or minimizes the premium for the V-Cache option.

well honestly I just can't get my mind off chicken wings and wish they were cheaper. I have no idea what else is going on atm...

 

[AnotherReader]

well honestly I just can't get my mind off chicken wings and wish they were cheaper. I have no idea what else is going on atm...

I hear you. Almost every thing is more expensive than a couple of years ago.

 

[TheLostSwede]

well honestly I just can't get my mind off chicken wings and wish they were cheaper. I have no idea what else is going on atm...

 

[AnotherReader]

View attachment 285352

Come on man. You're making me hungry.

 

[A Computer Guy]

Come on man. You're making me hungry.

Listen up bub, my chicken has harry legs and I like my CPU deep fried in 3D barbecue sauce.

 

[phanbuey]

If you're doing workstation tasks then 7900 non x with a cheap gigabyte board tons of ram, and a boatload of fast SSDs , if you're doing gaming then 7800X3D (which is still a good ws chip btw) -- these 7950x3d chips kind of make no sense pricing wise.

 

[AnotherReader]

If you're doing workstation tasks then 7900 non x with a cheap gigabyte board tons of ram, and a boatload of fast SSDs , if you're doing gaming then 7800X3D (which is still a good ws chip btw) -- these 7950x3d chips kind of make no sense pricing wise.

There will be cases other than gaming where a 7950 X3D will be be faster than its regular counterpart. Any application that has a working set larger than 32 MB will benefit from that large cache. Even in W1zzard's review of the 5800X3D, you can see that there are tasks where it is faster than the 5800X despite the clock speed gap.

 

[Ando]

I want to see testing done with lower spec RAM vs optimal 6000 cl30 stuff. The 5800X3D was less memory sensitive, so I assume this will be the same.
A 7800X3D might look very impressive value wise with a cheap RAM kit next to the 13900K.

 

[dirtyferret]

I'd love to see some World of Warcraft benchmarks with this CPU.
I know it depends a lot on the location, server, time of day, etc but still

You would expect the extra cache to show an improvement similar to the 5800X3D, the only question is there a point of diminishing returns for it?

$25 for a bowl of chicken wings

do chicken wings come in a bowl? I thought it was a plate?

 

[Space Lynx]

You would expect the extra cache to show an improvement similar to the 5800X3D, the only question is there a point of diminishing returns for it?


do chicken wings come in a bowl? I thought it was a plate?

you gotta shake the sauce all over baby

mods this is on topic because 7950x3d wouldn't exist if it wasn't for chicken wings, engineers would have no motivation to make money without chicken wings.

therefore, this post is not off-topic.

 

[A Computer Guy]

you gotta shake the sauce all over baby

View attachment 285361

I wasn't planning to go out of the house today but you people are going to make me drive to Buffalo aren't you.

 

[THU31]

Seems like the 3D cache was much more beneficial with DDR4. DDR5 almost doubles the bandwidth with similar latency, so the gains are much smaller.

 

[A Computer Guy]

One things I would be interested to see, if possible, is the effective utilization of the cache.

 

[phanbuey]

There will be cases other than gaming where a 7950 X3D will be be faster than its regular counterpart. Any application that has a working set larger than 32 MB will benefit from that large cache. Even in W1zzard's review of the 5800X3D, you can see that there are tasks where it is faster than the 5800X despite the clock speed gap.

View attachment 285357

Yeah but with asymmetric cores? half of which are 15% slower?... idk.

Yeah it will help in some WS tasks coded to take advantage of it, but in that setup those are mostly outliers.