Page 1 of 2 12 LastLast
Results 1 to 10 of 19

Thread: Windows 8 vs. Linux Graphics, Source Benchmarks Coming

Hybrid View

  1. #1
    Join Date
    Jan 2007
    Posts
    15,693

    Default Windows 8 vs. Linux Graphics, Source Benchmarks Coming

    Phoronix: Windows 8 vs. Linux Graphics, Source Benchmarks Coming

    Before the end of the month will be many new and exciting Linux benchmarks on Phoronix, including the Radeon Dynamic Power Management results in full, many updated Windows 8 vs. Ubuntu Linux tests, and Valve Source Engine Linux GPU benchmarks, among others...

    http://www.phoronix.com/vr.php?view=MTQxODM

  2. #2
    Join Date
    Feb 2008
    Posts
    214

    Default

    Could you stop posting about what are you going to do and just post when it's available? All this is bullshit even for a tabloid-like site.

    Thanks.

  3. #3

    Default

    Quote Originally Posted by timofonic View Post
    Could you stop posting about what are you going to do and just post when it's available? All this is bullshit even for a tabloid-like site.

    Thanks.
    It's generally a lot more effective when people provide test requests / feedback / suggestions prior to writing a given article than giving feedback afterwards when nothing can be changed until the next time such tests are done...

  4. #4
    Join Date
    Feb 2008
    Posts
    214

    Default

    Quote Originally Posted by Michael View Post
    It's generally a lot more effective when people provide test requests / feedback / suggestions prior to writing a given article than giving feedback afterwards when nothing can be changed until the next time such tests are done...
    Well, it makes sense. Sorry for over reacting about it, then...

  5. #5

    Default You should actually use Linux in your tests

    Quote Originally Posted by Michael View Post
    It's generally a lot more effective when people provide test requests / feedback / suggestions prior to writing a given article than giving feedback afterwards when nothing can be changed until the next time such tests are done...
    Normally you do benchmarks with Ubuntu, but can you please instead use a linux distro? Debian, Fedora, Mint, Gentoo, there are plenty of distros out there who wish to remain linux distros instead of becoming their own unique enclave.

    We are fast approaching a time when Ubuntu is about as "linux" as android is.

    Or else title your upcoming piece: "Windows 8 vs. Ubuntu Graphics, Source Benchmarks"

    Thanks.

  6. #6
    Join Date
    Aug 2012
    Location
    Pennsylvania, United States
    Posts
    1,941

    Default

    Quote Originally Posted by halfmanhalfamazing View Post
    Normally you do benchmarks with Ubuntu, but can you please instead use a linux distro? Debian, Fedora, Mint, Gentoo, there are plenty of distros out there who wish to remain linux distros instead of becoming their own unique enclave.

    We are fast approaching a time when Ubuntu is about as "linux" as android is.

    Or else title your upcoming piece: "Windows 8 vs. Ubuntu Graphics, Source Benchmarks"

    Thanks.
    I normally don't agree with people like him Michael...but right now I kind of am inclined to. I know you use Ubuntu because its the most common distro, but with all the crap with Xmir and stuff... Maybe you should be switching to Linux Mint (if you still want to remain 'ubuntu-ish') or even Fedora (if you want to start seeing whats the latest PACKAGED code in a packaged distro. I add that last part to exclude Arch because theres any number of things that could skew those numbers. <3 Arch though )

  7. #7

    Default

    Quote Originally Posted by Ericg View Post
    I normally don't agree with people like him Michael...but right now I kind of am inclined to. I know you use Ubuntu because its the most common distro, but with all the crap with Xmir and stuff... Maybe you should be switching to Linux Mint (if you still want to remain 'ubuntu-ish') or even Fedora (if you want to start seeing whats the latest PACKAGED code in a packaged distro. I add that last part to exclude Arch because theres any number of things that could skew those numbers. <3 Arch though )
    I love Fedora a lot and always have, but as can be seen from the articles, I generally only use it for benchmarks around the time it's actually released when the packages are still fresh namely because:

    - Fedora Rawhide packages ship with a lot of debug cruft that can affect the performance so using those experimental packages unfortunately doesn't work out well.

    - Ubuntu is convenient for kernel tests with their Ubuntu Mainline Kernel PPA where they also package the daily Git kernels. As far as I know there isn't any similar archive for Fedora. I can easily build my own Git kernel, but when (re)installing systems often, this is very convenient, plus if people have a question about my kernel configuration or want to also test the latest kernel, I can simply tell them to go to the PPA.

    I think those are my two main gripes these days but yeah aside from that have been using Xubuntu a lot lately.

  8. #8
    Join Date
    Oct 2008
    Posts
    3,251

    Default

    Quote Originally Posted by Michael View Post
    It's generally a lot more effective when people provide test requests / feedback / suggestions prior to writing a given article than giving feedback afterwards when nothing can be changed until the next time such tests are done...
    If you want feedback...

    Please, when comparing the radeon OSS driver to Win8 or fglrx proprietary drivers, add an option of enabling the shader optimizations. (sb) Showing results with it both OFF and ON would be nice.

  9. #9
    Join Date
    Jul 2013
    Posts
    204

    Default

    If not Ubuntu, I definitely say Linux Mint.

  10. #10
    Join Date
    Feb 2013
    Posts
    485

    Default

    Quote Originally Posted by Michael View Post
    It's generally a lot more effective when people provide test requests / feedback / suggestions prior to writing a given article than giving feedback afterwards when nothing can be changed until the next time such tests are done...
    Something for the Haswell graphics test: a couple of people pointed this out in the comments last week, in the frame latency people are more concerned with maximum than average because that is what causes jitter:

    Quote Originally Posted by sireangelus View Post
    To Michael: i think you're missing the purpose of latency benchmarking. It's not only to have a average reading, but what matters most is how many, how frequent and the severity of the frame spikes, because that's the major cause of "perceived lagging"(beyond networking), usually a slightly slower frame average but with a much more stable frame latency is preferable over an inflated fps average with lots of spikes(like we see on this review, windows have It worse.)
    This is also why I prefer to play LoL on Linux even if the avg on windows is way higher.. I have frame latency problems even with VSync on and an apparent rock-solid 60fps
    In the OpenArena latency graph Linux actually fared much better than Windows but that wasn't really obvious. It might be better to report a simple metric that condenses the data to a single value that represents "how many, how frequent and the severity of the frame spikes". I'm not sure what is best, what are other sites doing? The simplest way might be to just report the variance of the latency of each frame (0 is better)? Or add all the latencies of each frame multiplied by some weight that penalises higher values eg "sum(latency**2)". I'm sure others have some ideas.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •