Announcement

Collapse
No announcement yet.

An Optimized Open-Source Driver Tries To Compete With AMD Catalyst

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

  • arcas
    replied
    So it's pretty much the same old story: despite all the effort spent tweaking the OSS drivers, they're still running at a tiny fraction of the speed of the closed-source binary blobs. Other than supporting older chipsets that Catalyst has put out to pasture, it's difficult to put a positive spin on this.

    Leave a comment:


  • bulletxt
    replied
    Thanks for this benchmark. The problem is that I already knew the results. The OSS driver performs bad and misses plenty of features. Catalyst driver performs good for 3D but is a piece of crap under all the other aspects.

    Under Linux you can never have 1 thing that works good for all scenarios. You have to choose between 2 or more things depending on your needs and will never be 100% satisfied because one day, soon or later, you will surely need that missing feature that only the other choice has.

    Leave a comment:


  • gururise
    replied
    Great article Michael!

    Its quite sad to see how little these tweaks boosted performance on the r600 (46xx and 48xx) series. Maybe, just like AMD, all the resources are being put into the newer generation cards.

    Leave a comment:


  • AnonymousCoward
    replied
    Two comments about the graphs:

    1. At some point, the order changes, Catalyst moves position to between the two mesa results, which is confusing.

    2. Why not have vertical indicators at 30, 60, 120 ... fps instead of automatically determined by the results? From my point of view 30 is ok, 60 is the maximum for most displays, and more than 120 is uninteresting in practice.

    Also, why not put the Xonotic results directly after Nexuiz if you refer to them anyway?

    Originally posted by enrico.tagliavini View Post
    I wonder if enabling S3TC might improve the performance of the radeon driver. Well this can be an idea for the next article
    It does, in applications that enable texture compression the fps are higher when libtxc-dxtn is installed.

    Leave a comment:


  • Temar
    replied
    Originally posted by ChrisXY View Post
    Yes, but if it has 60+ FPS for the applications you need competing (optimizing remaining "bottlenecks") is kind of pointless. That's competing enaugh for me.
    I wouldn't call it "remaining bottlenecks" as long as the binary blob is still 2-40 times faster.

    Originally posted by ChrisXY View Post
    It would be definitely very good if it was supported for more video codecs, but what CPU does your HTPC have and what quality of videos do you want to play?
    My HTPC has an AMD X2 4050e with an onboard AMD HD 3???. It is capable of playing Full-HD videos with the binary blob. However I'm currently using a NVidia GTX430, as XBMC or the Catalyst driver has/had problems with vba (got display errors with some hd-videos) and suspend-to-ram. I'm pretty much done with AMD, my next system will be an Intel Atom with a Nvidia chipset. Nvidia is just the only problem-free solution on Linux.

    Leave a comment:


  • jrch2k8
    replied
    it seems the biggest bottleneck roght now it is on the lack of shader packetizer and threading but the fixed functions seem pretty competitive right now wtih catalyst

    Leave a comment:


  • DanL
    replied
    Originally posted by TAXI View Post
    Well,VDPAU via 3d shaders seems to work
    The last time I checked, it only supported mpeg 1 and 2.

    Leave a comment:


  • pingufunkybeat
    replied
    Yes, it clearly says it's using ffmpeg's h.264 codec implementation, only the display part is done by the vdpau implementation, and that part works just as well with xvideo.

    Leave a comment:


  • Nille
    replied
    Taxi but the decoding runs on the cpu only mpeg2/1 is currently hardware accelerated.

    Leave a comment:


  • V10lator
    replied
    Originally posted by DanL View Post
    Yeah, I really don't need more 3D performance and I'm so tired of waiting for Gallium3D VDPAU
    Well,VDPAU via 3d shaders seems to work, just VDPAU via UVD isn't released:
    Code:
    [    12.045] (II) RADEON(0): [DRI2]   VDPAU driver: r600
    Code:
    # find /usr/lib64 | grep vdpau | grep r600
    /usr/lib64/vdpau/libvdpau_r600.so.1.0
    /usr/lib64/vdpau/libvdpau_r600.so
    /usr/lib64/vdpau/libvdpau_r600.so.1
    Code:
    ==========================================================================
    ?ffne Videodecoder: [ffmpeg] FFmpeg's libavcodec codec family
    Ausgew?hlter Videocodec: [ffh264] vfm: ffmpeg (FFmpeg H.264)
    ==========================================================================
    ==========================================================================
    ?ffne Audiodecoder: [ffmpeg] FFmpeg/libavcodec audio decoders
    AUDIO: 48000 Hz, 2 ch, s16le, 448.0 kbit/29.17% (ratio: 56000->192000)
    Ausgew?hlter Audiocodec: [ffac3] afm: ffmpeg (FFmpeg AC-3)
    ==========================================================================
    AO: [alsa] 48000Hz 2ch s16le (2 bytes per sample)
    Starte Wiedergabe...
    Film-Aspekt ist 2.35:1 - Vorskalierung zur Korrektur der Seitenverh?ltnisse.
    VO: [vdpau] 1920x816 => 1920x816 Planar YV12

    Leave a comment:

Working...
X