News AMD deep-dives Zen 5 — Ryzen 9000 and AI 300 benchmarks, Zen 5, RDNA 3.5 GPU, and XDNA 2 microarchitectures

[TheHerald]

Ah, I misread the name of the CPU; apologies.

And no, I don't see any Intel CPU at the top beating a desktop AMD part:
https://gamersnexus.net/u/styles/la...ages/vlcsnap-2023-12-27-13h49m14s208.jpg.webp

The 13600K is at the middle and it is the highest in the chart. I'm sure T variants should be higher in the list, or at least should be.

And the subsequent power efficiency charts reflect that one closely. (edited)

Regards.

Keep scrolling, they have numbers from a power limited 14700k. It's besting everything.

But again, that chart doesn't show amd being more efficient. It shows amds power limited chips being more efficient than intels power unlimited chips. But intel intel also has power limited chips which should be topping the chart, quite easily as evidenced by the power limited 14700

 

[-Fran-]

Keep scrolling, they have numbers from a power limited 14700k. It's besting everything.

But again, that chart doesn't show amd being more efficient. It shows amds power limited chips being more efficient than intels power unlimited chips. But intel intel also has power limited chips which should be topping the chart, quite easily as evidenced by the power limited 14700

"Blender is up now. You all already know this chart, so we’ll keep it short. We ran the 14700K at 86W limiter, which had it at about 91W, and the 14700K finally outperforms the 7800X3D. All we had to do was run it in a configuration most users won’t use. It produced a 12.1-minute render, a massive worsening from the baseline 14700K’s 8-minute render. This definitely slowed the CPU down, but it became more efficient."

They kind of simulated a T SKU and I was right the T SKUs would be higher in the list

This is the chart you're talking about: https://gamersnexus.net/u/styles/la...k Blender 3.6-4x_foolhardy_Remacri_2.png.webp

So they had to artificially limit the CPU in order to operate in a non-default config.

In short: the Intel lineup (being generous, as it's only 1 SKU tested) wins in 1 test out of all against AMD using a limited (in power) SKU trying to represent a T variant (I think?).

Well, I don't know what to tell you. As I said, colourful interpretations of the charts and data don't change reality. Proof of that is in the continuous advancement in the Data Center for AMD where efficiency is king.

Regards.

 

[TheHerald]

"Blender is up now. You all already know this chart, so we’ll keep it short. We ran the 14700K at 86W limiter, which had it at about 91W, and the 14700K finally outperforms the 7800X3D. All we had to do was run it in a configuration most users won’t use. It produced a 12.1-minute render, a massive worsening from the baseline 14700K’s 8-minute render. This definitely slowed the CPU down, but it became more efficient."

They kind of simulated a T SKU and I was right the T SKUs would be higher in the list

This is the chart you're talking about: https://gamersnexus.net/u/styles/large_responsive_no_watermark_/public/inline-images/GN CPU Benchmark Blender 3.6-4x_foolhardy_Remacri_2.png.webp

So they had to artificially limit the CPU in order to operate in a non-default config.

In short: the Intel lineup (being generous, as it's only 1 SKU tested) wins in 1 test out of all against AMD using a limited (in power) SKU trying to represent a T variant (I think?).

Well, I don't know what to tell you. As I said, colourful interpretations of the charts and data don't change reality. Proof of that is in the continuous advancement in the Data Center for AMD where efficiency is king.

Regards.

First of all its not a T simulation. The t settles at 35w.

Second of all, it didn't just win in 1 test. It won in the only MT test they did. So what "out of all" are you talking about? It won in 1 out of 1 mt tests.

AMD winning in the data centers is proof of the exact opposite. They are winning there cause they don't offer half the cores of their competitor like they do in the desktop.

I'm not saying intel has an architectural advantage, I have no idea about that. All I'm saying is that because they offer a lot more cores at every price point, running those cores at the same power as amds chips results in better efficiency. There is no way around that, a 13700k with its 16 cores will walk all over the 7700x in both efficiency and performance provided you run both at the same power.

I7 and r7, same naming scheme, released at the same time and the same msrp, cost roughly the same even today, I put a 125w limit on both, which one do you think is faster in MT performance, and therefore more efficient? Cause I think the answer is obvious but you ate trying to tap dance around it.