Announcement

Collapse
No announcement yet.

SteamOS vs. Windows 8.1 NVIDIA Performance

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

  • phoronix
    started a topic SteamOS vs. Windows 8.1 NVIDIA Performance

    SteamOS vs. Windows 8.1 NVIDIA Performance

    Phoronix: SteamOS vs. Windows 8.1 NVIDIA Performance

    For those NVIDIA gaming customers running Microsoft Windows 8.1 that have been thinking about giving Valve's SteamOS Linux-based gaming platform a try, here are some early benchmarks of the SteamOS 1.0 beta that compare the performance to Microsoft Windows 8.1 Pro x64 on multiple NVIDIA GeForce graphics cards.

    http://www.phoronix.com/vr.php?view=19632

  • gilboa
    replied
    Originally posted by narciso View Post
    oops, forget to mention the game, it's Half Life Loast Coast. D3D on windows, OpenGL on SteamOS.
    Given the fact that different code path is used on Windows and Linux, testing a single game doesn't say much about SteamOS (or Linux).
    Never the less, I would imagine that D3D Windows only games that get converted to Linux will suffer from higher over-head that will most likely be far more noticeable as the FPS increases.
    160fps vs. 240fps is far less relevant than 40fps vs. 60fps.

    - Gilboa

    Leave a comment:


  • narciso
    replied
    oops, forget to mention the game, it's Half Life Loast Coast. D3D on windows, OpenGL on SteamOS.


    [QUOTE=tomtomme;383557]
    Originally posted by narciso View Post

    ??
    which game?
    directX vs openGL or openGL vs openGL?

    Leave a comment:


  • tomtomme
    replied
    [QUOTE=narciso;382716]
    Originally posted by phor20 View Post

    For curiosity I've benchmarked the performance between both OS's using a resolution of 2560x1440 8xMSAA, all settings maxed. Using a intel 4770k + GTX680 + 8GB rig.
    I've reached the following numbers:

    Win8.1 - 235,82fps
    SteamOS - 153,65fps

    I tried to apply the following Nvidia optimizations in launch options but the game refused to start. LD_PRELOAD="libpthread.so.0 libGL.so.1"__GL_THREADED_OPTIMIZATIONS=1

    To simulate similar conditions I runned Steam windows client with -steamos prefix and Big picture mode.
    ??
    which game?
    directX vs openGL or openGL vs openGL?

    Leave a comment:


  • narciso
    replied
    [QUOTE=phor20;382656]
    Originally posted by phoronix View Post
    Phoronix: SteamOS vs. Windows 8.1 NVIDIA Performance

    For those NVIDIA gaming customers running Microsoft Windows 8.1 that have been thinking about giving Valve's SteamOS Linux-based gaming platform a try, here are some early benchmarks of the SteamOS 1.0 beta that compare the performance to Microsoft Windows 8.1 Pro x64 on multiple NVIDIA GeForce graphics cards.


    Windows 8.1 NVIDIA Performance,i think is good.
    For curiosity I've benchmarked the performance between both OS's using a resolution of 2560x1440 8xMSAA, all settings maxed. Using a intel 4770k + GTX680 + 8GB rig.
    I've reached the following numbers:

    Win8.1 - 235,82fps
    SteamOS - 153,65fps

    I tried to apply the following Nvidia optimizations in launch options but the game refused to start. LD_PRELOAD="libpthread.so.0 libGL.so.1"__GL_THREADED_OPTIMIZATIONS=1

    To simulate similar conditions I runned Steam windows client with -steamos prefix and Big picture mode.

    Leave a comment:


  • phor20
    replied
    [QUOTE=phoronix;381160]Phoronix: SteamOS vs. Windows 8.1 NVIDIA Performance

    For those NVIDIA gaming customers running Microsoft Windows 8.1 that have been thinking about giving Valve's SteamOS Linux-based gaming platform a try, here are some early benchmarks of the SteamOS 1.0 beta that compare the performance to Microsoft Windows 8.1 Pro x64 on multiple NVIDIA GeForce graphics cards.


    Windows 8.1 NVIDIA Performance,i think is good.

    Leave a comment:


  • gilboa
    replied
    Originally posted by tangram View Post
    This article is an utter disappointment. Openarena, Xonotic? Really?

    And don't use the lame argument of "can't benchmark commercial games across OS" BS. In Team Fortress it's just a matter of having a demo and running timedemo demo in the game's console.
    ... So why don't *you* do it and post the results?
    Alternatively, you could hire Michael to do the benches for you...

    - Gilboa

    Leave a comment:


  • stiiixy
    replied
    Originally posted by tangram View Post
    This article is an utter disappointment. Openarena, Xonotic? Really?

    And don't use the lame argument of "can't benchmark commercial games across OS" BS. In Team Fortress it's just a matter of having a demo and running timedemo demo in the game's console.
    Can that be initiated 'externally' in an automated fashion? Or does it require manually starting the game and entering it in, manually? I also drive manual cars.

    Leave a comment:


  • tangram
    replied
    This article is an utter disappointment. Openarena, Xonotic? Really?

    And don't use the lame argument of "can't benchmark commercial games across OS" BS. In Team Fortress it's just a matter of having a demo and running timedemo demo in the game's console.

    Leave a comment:


  • ua=42
    replied
    Originally posted by sarmad View Post
    It's not about whose fault is it, it's about end user results. We need benchmarks that use the default graphics stack for a platform/game. If a game targets DirectX primarily and is optimized for it then it should be DirectX that is used for the benchmark, not the unoptimized code that targets OpenGL. End users don't care whether DirectX or OpenGL is used, they only care about end results.
    I guess we will have to agree to disagree. I see these kind of reviews as more of a graphics driver progress report, to see if the underlying system has any performance problems.

    Leave a comment:

Working...
X