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

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • avis
    replied
    Originally posted by xAlt7x View Post
    By that logic we should tweak Linux as well (turning off services like Gnome Tracker, Baloo). And although this sounds good in theory, but in practice​ it will to lead to inconsistent results when someone tries to repeat Michael's benchmarks.
    This makes perfect sense however these services are built on top of the inotify/fnotify subsystem, so they normally should be completely idle.

    Leave a comment:


  • Sonadow
    replied
    Originally posted by mSparks View Post

    Sounds like you dont macOS yet.
    You should. As of 2023 a Linux destop with a high end nvidia gpu and amd cpu with an M2 chip running macOS for a second machine is as good as stable + does everything you could possibly want with insanely high performance can get.

    You also seem to miss the point of this benchmark.
    Linux wins here even if performance was identical - what people want to know is can they buy this laptop chip and expect at least as good as performance as windows it ships with.

    They are probably running a Mac Studio for desktop, which is also a decent setup.

    The fact Linux hands down gets double the performance in some cases is just a bonus/to be expected, this is a 16T CPU, windows generally tops out at 4T for any software that otherwise relies on fork() or atomic Virt Memory. So up to 4x the perf can easily be anticipated (but no benchmarks to show it, cos windows can't fork())

    There is no decent set up that includes windows. Its a steaming pile of clunky under invested shite that is lucky if it can make it through a single days use without exploding.
    Sure, keep yapping all you want when many software, applications and drivers used by billions of people all over the world and in production systems only exist on Windows and no where else, not even Linux.

    The fastest Linux distribution means jack shit when it can't even talk to a specific piece of hardware. Or run a specific workload.

    And that 4T is just complete bullshit.
    Last edited by Sonadow; 20 August 2023, 09:21 AM.

    Leave a comment:


  • mSparks
    replied
    Originally posted by sophisticles View Post

    I'm not trying to provoke a flame war, what I very clearly said was that pure performance is less important than stability.

    Think of a sports car, one car can go 0-60 in 3 sec flat and has a top speed of over 200 mph but breaks down every other month and needs a complete engine overhaul after every track session and the other goes 0-60 in 5 seconds and has a top speed of "only" 160 but the only thing it needs is an oil change and new plugs every 6 months, which is the better car?

    What I think would be interesting is if Michael did an endurance benchmark, like Tom's Hardware did years ago, where they ran 4 very CPU intensive benchmarks simultaneously on a loop for I think it was 48 hours.

    Perhaps Michael could run 4 instances of the PTS benchmark simultaneously a couple of times and see which OS even completes the test much less finishes first.

    I think you may be surprised at the results.

    The point is no one uses an application for 30 seconds at a time, we use our computers for hours at a time and usually we are doing multuple things at the same time, with a number of background tasks running while we work.

    We don't use our computers like a top fuel dragster we use our computers like a Nascar race car, running them nonstop for hours and days and weeks at a time.
    Sounds like you dont macOS yet.
    You should. As of 2023 a Linux destop with a high end nvidia gpu and amd cpu with an M2 chip running macOS for a second machine is as good as stable + does everything you could possibly want with insanely high performance can get.

    You also seem to miss the point of this benchmark.
    Linux wins here even if performance was identical - what people want to know is can they buy this laptop chip and expect at least as good as performance as windows it ships with.

    They are probably running a Mac Studio for desktop, which is also a decent setup.

    The fact Linux hands down gets double the performance in some cases is just a bonus/to be expected, this is a 16T CPU, windows generally tops out at 4T for any software that otherwise relies on fork() or atomic Virt Memory. So up to 4x the perf can easily be anticipated (but no benchmarks to show it, cos windows can't fork())

    There is no decent set up that includes windows. Its a steaming pile of clunky under invested shite that is lucky if it can make it through a single days use without exploding.
    Last edited by mSparks; 19 August 2023, 11:14 PM.

    Leave a comment:


  • paulocoghi
    replied
    Originally posted by avis View Post

    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.
    If the negative impact of those standard Windows's background jobs can "screw up your testing completely", how we could not conclude that these same background jobs will create the same negative impacts and "screw up" the day-today usage "completely".

    Thanks for helping us to understand that, yes, Windows provides negative impacts on its standard form that are so negative, that measures need to be taken to make Windows "benchmarkable".

    Also, thank you to remember us that, yes, the average Linux desktop is so clean that it "install almost zero background jobs" and, thus, provide not only almost zero impact on benchmarks on its standard form, but also almost zero impact on day-to-day usage.

    Thanks for proving, yourself, that Linux is faster than Windows.
    Last edited by paulocoghi; 19 August 2023, 06:42 PM.

    Leave a comment:


  • sophisticles
    replied
    Originally posted by xAlt7x View Post
    @sophisticles , @ Sonadow
    Сan we please stay on topic​ and not provoke flame-wars? This article specifically compares Windows and Linux performance on the same hardware.
    Arguments like "Windows might lose some benchmarks but at least it doesn't suck like Linux for X and Y use-cases" seem fanboy-ish to me.
    I'm not trying to provoke a flame war, what I very clearly said was that pure performance is less important than stability.

    Think of a sports car, one car can go 0-60 in 3 sec flat and has a top speed of over 200 mph but breaks down every other month and needs a complete engine overhaul after every track session and the other goes 0-60 in 5 seconds and has a top speed of "only" 160 but the only thing it needs is an oil change and new plugs every 6 months, which is the better car?

    What I think would be interesting is if Michael did an endurance benchmark, like Tom's Hardware did years ago, where they ran 4 very CPU intensive benchmarks simultaneously on a loop for I think it was 48 hours.

    Perhaps Michael could run 4 instances of the PTS benchmark simultaneously a couple of times and see which OS even completes the test much less finishes first.

    I think you may be surprised at the results.

    The point is no one uses an application for 30 seconds at a time, we use our computers for hours at a time and usually we are doing multuple things at the same time, with a number of background tasks running while we work.

    We don't use our computers like a top fuel dragster we use our computers like a Nascar race car, running them nonstop for hours and days and weeks at a time.

    Leave a comment:


  • sophisticles
    replied
    Originally posted by andre30correia View Post

    Maybe your laptop is not compatible with Linux, i have no such problems with mine
    It's an HP with an Icelake CPU and Intel graphics. If this isn't compatible, what is?

    Leave a comment:


  • mSparks
    replied
    Originally posted by avis View Post
    Michael has never mentioned whether he prepares Windows for benchmarking properly.

    And that's a lot of work that needs to be done otherwise you could be getting quite low results.

    https://www.techpowerup.com/forums/t...chmark.287480/
    Does deleting the System32 folder still need doing on windows 11 or did they finally get rid of it?

    Leave a comment:


  • Mario Junior
    replied
    Originally posted by avis View Post
    Michael has never mentioned whether he prepares Windows for benchmarking properly.

    And that's a lot of work that needs to be done otherwise you could be getting quite low results.

    https://www.techpowerup.com/forums/t...chmark.287480/
    Much BS and schizo shi* for ZERO benefit.

    Leave a comment:


  • xAlt7x
    replied
    Originally posted by avis View Post
    When you test software you want your hardware to be 100% idle or otherwise your results are not worth anything.
    By that logic we should tweak Linux as well (turning off services like Gnome Tracker, Baloo). And although this sounds good in theory, but in practice​ it will to lead to inconsistent results when someone tries to repeat Michael's benchmarks.

    Leave a comment:


  • avis
    replied
    Originally posted by yump View Post
    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.
    Fundamentally your comment cannot be further from the truth.

    When you test software you want your hardware to be 100% idle or otherwise your results are not worth anything.

    Originally posted by yump View Post
    If Windows performs inconsistently in its default configuration, tough luck for Windows.
    This inconsistency takes roughly 2 minutes to be eliminated but people here seem to be totally fine with getting whatever results. Again, Linux beats Windows, hope you're happy.

    Leave a comment:

Working...
X