AMD Ryzen 7 7840U Windows 11 vs. Linux CPU Performance

[mSparks]

Linux fans who visit the general computer forums and the Windows forums always write that Linux is several times faster than Windows, and that Windows is so slow that it is unworkable.

The linux foundation pays them for this?? Is that what the donations are for?

Has open source religion brainwashed them?

for most real world multithreading operations on a multicore multithread CPU, windows is indeed several orders of magnitude slower than linux and macos - heck any posix system.
This is because NTFS and virtual memory operations are not atomic on windows, and windows has no support for fork()

Only exception to this is if you are running programs on WSL2 or their new linux emulator for android applications, and using a modern filesystem not otherwise available for microsofties on winblows. - Their current workarounds to try and compete.

In situations where that actually matters, developers do not target winblows as a platform, so don't expect any comparison benchmarks.

However the average user setting up WSL2 et al is about as "real world" as putting 3 weeks into tweeking windows 11 so it actually half works, or cooling your CPU with liquid nitrogen.

[Linuxxx]

When you do benchmarking you want your system behavior to be predictable and tests to be repeatable.

If you don't prepare Windows for that, it may run certain background jobs unexpectedly (not limited to Windows Updates) and screw up your testing completely.

Linux doesn't need that because an average Linux desktop install almost has zero background jobs aside from system logging.

I wanted to end this message with some egregiously caustic remarks about someone's extremely intelligent comments but decided not to.

To be fair, Michael's PTS does run each test at least three times to ensure there are no major run-time variations, so all results are reproducible.

And the OOTB Ubuntu settings are anything but performant, yet it still was holding up remarkably well...

[avis]

To be fair, Michael's PTS does run each test at least three times to ensure there are no major run-time variations, so all results are reproducible.

And the OOTB Ubuntu settings are anything but performant, yet it still was holding up remarkably well...

In certain older articles Michael sometime has provided the data on test scores variation but not today, so it's hard to say. I just want a peace of mind, that's it. Making sure that no major background jobs are running and Windows is prepared for benchmarking looks easier than for us arguing almost in vain.

When people ask me to perform benchmarking I make absolutely sure my results are reproducible and verifiable.

Anyways Linux is faster in most of them, so there's that It's unlikely anything can change considering that Windows 11 is running so much cruft by default.

[guzz46]

Linux fans who visit the general computer forums and the Windows forums always write that Linux is several times faster than Windows, and that Windows is so slow that it is unworkable.

The linux foundation pays them for this?? Is that what the donations are for?

Has open source religion brainwashed them?

Years ago my mother brought a low end intel pentium netbook, I think it uses an intel N3050, and that thing was dog slow with windows on it, booting, logging into the desktop, opening applications, and this was a fresh windows install too, you just spent a lot of time waiting for things to happen, but it actually runs ok with linux and xfce on it, web browsing is still kind of slow, but you can't do much about that beyond buying a more powerful laptop, and the thing would run faster if I put something even lighter on it too.

[yump]

birdie you have fundamentally misunderstood the reason for W1zzard's Windows tweaks. Techpowerup is benchmarking hardware, not software. Therefore, the Windows install is neutered to be as static as possible so that all of the difference between results can be attributed to the choice of graphics card. But in this article, the software is the varied parameter. If Windows performs inconsistently in its default configuration, tough luck for Windows.

[yump]

It's bizarre to see such massive swings between different test scenes in LuxCoreRender. I would expect it has the same thread count and activity patterns no matter what the scene is. Maybe some of the scenes use more power?

[mSparks]

It's bizarre to see such massive swings between different test scenes in LuxCoreRender. I would expect it has the same thread count and activity patterns no matter what the scene is. Maybe some of the scenes use more power?

It should problably be dropped as a benchmark, e.g.
image.png
The loser on min of 0.2 and max greater than the "winner", looks like its perf outcome is heavily dependant on some random seed, so all it tells you is "it did some calcs in some time".
It would be great if the benchmarkers generally started doing some proper statistical analysis on the results (ffs, R is cross platform and free/open source, there is no excuse not to) I seriously doubt if there is any statistically significant difference in any of those Luxcore benchmarks.

[Yalok]

Michael
Does "Ubuntu 22.04.3 LTS out-of-the-box with its Linux 6.2 HWE kernel" come with inception patches?

[Volta]

Linux fans who visit the general computer forums and the Windows forums always write that Linux is several times faster than Windows, and that Windows is so slow that it is unworkable.

It seems you forget about other tests where Linux eats windows for breakfast. Now ask yourself who is brainwashed fanboy? Furthermore, as a fanboys you ignored the fact windows isn't patched for the latest vulnerability, so it cheats in performance. It also depends on test choices, but such things are obvious for most people..

[Volta]

Michael has never mentioned whether he prepares Windows for benchmarking properly.

He never prepares Linux properly, so what's your point?

Anyways Linux is faster in most of them, so there's that It's unlikely anything can change considering that Windows 11 is running so much cruft by default.

It's nothing in comparison to what Ubuntu has for default. Debugging in kernel, non optimal governors etc.