Ryzen 9 3900X/3950X vs. Core i9 10900K In 380+ Benchmarks

[StephenL]

10400F review:



Intel sucks, AMD rules, right. In rendering, massive compute taks and compilation that is.

What a horrible CPU lineup full with imaginary HW vulnerabilities and horrible power consumption. Oh, wait, a 14nm Intel CPU consumes less than a comparable 7nm AMD 3600X:

So Birdie that test you're referencing the "same" power, the 3600 / 3600X complete it 15% faster. So not really the same power. And that same article, if you'd referenced the Stress test (below), you'd see it using 15-20% more power.

I'm not saying Intel hasn't done great things with their 14nm, but come on. It's time. AMD still takes the "power consumption" win by a significant enough margin.

[/QUOTE]

Stephen

[angrypie]

Another thread ruined by a rabid Intel fanboy.

Bring back debianxfce, at least he was fun.

[creative]

All I can say is I have a R5 3600 and really enjoy it. It feels good to be back on AMD, it's like a breath of fresh air. I know I may get made fun of for saying this but there is something magical about AMD. Give me RYZEN, give me Radeon baby!

[smitty3268]

The fact is Intel does not cheat/lie about its TDP and AMD does lie about its TDP. I wonder what peculiar justification you'll find for that. I mean in this message there was nothing substantial or factual.

AMD's TDP numbers are wildly misleading for desktop chips. So are Intel's. Technically neither of them are "lying" - they both have enough asterisks next to their TDP numbers explaining what they really mean (basically nothing) to get away with it. But they are essentially entirely useless numbers cooked up by marketing that only have a small relation to the actual hardware.

What's crazy is that you think AMD is worse at this then Intel, when they are actually less off on the numbers. Get upset with both companies, sure. But why focus on the less offensive one, unless you have some sort of axe to grind?

That's a rhetorical question. From your post history it's very clear exactly what's going on.

[gentoofu]

Note that to hit the Core i9 10900K numbers from this benchmark, you need to use the Gigabyte Z490 Aorus Master that Intel supplied here. Which is, pretty much a motherboard on steroids if nothing was done on the BIOS prior running the benchmark.

https://www.youtube.com/watch?v=qQ_AETO7Fn4

You'll most likely get lower numbers if you were to use the other Z490 motherboards.

[Royi]

It will be interesting to see how the XT Ryzens will compare when they launch next month.

How do you know they will be released next month? Why do you call them XT? Do you mean higher clocked Zen 2 or Zen 3?

[dud225]

AMD's highest-end desktop (non-Threadripper)

Sorry for the newbie question but I don't understand the difference between Ryzen and Threadripper and EPYC.

[skeevy420]

Sorry for the newbie question but I don't understand the difference between Ryzen and Threadripper and EPYC.

They're different AMD CPUs. Ryzen is entry to enthusiast level, Threadripper is for high end workstations, and EPYC is for servers. All are based on Zen and upgrades to that.

Here's the rabbit hole.

[dud225]

OK so Michael's wording is a bit confusing:

highest-end desktop (non-Threadripper)

Thanks for your answer.

[GruenSein]

Does AMD adhere to its specs?!

AMD Ryzen 7 3700X is rated 65W, consumes 90W no matter how long a test runs.
AMD Ryzen 7 3800X is rated 90W, consumes ~120W no matter how long a test runs.

AMD fanboys have to just shut the f*ck up sometimes. Intel 10900K does adhere to its TDP rating which is exactly 125W:

Am I the only one seeing PL1 at roughly 190W? Simply marking it 125W doesn’t help...