Page 4 of 11 FirstFirst ... 23456 ... LastLast
Results 31 to 40 of 109

Thread: Open-Source ATI R600/700 Mesa 3D Performance

  1. #31
    Join Date
    Aug 2009
    Posts
    2,264

    Default

    There is definitely something going on with that HD 2600pro.

    It's a wiled guess in the pitch black dark, but could it be that:
    There is some bug in the microcode/firmware/ATI BIOS thing?
    It's a faulty card (smack me in the face for being so terribly newbisch)?
    There is a workaround for some silicon bug in the 'blob' drivers?
    There was something popping up in the background while testing this card?
    It is a card that is not manufactured according to the official ATI/AMD blueprints (maybe I am just a n00b and this doesn't apply for the GPU at all)?

    One would assume that what Bridgman already pointed out; it's not the HD 2600PRO because the results are so a-logical.

  2. #32
    Join Date
    Oct 2007
    Location
    Toronto-ish
    Posts
    7,463

    Default

    I think the quick answer is "we don't know"

    I suspect it's something funny in the software environment rather than GPU/card/microcode etc... though.

  3. #33
    Join Date
    Apr 2008
    Posts
    325

    Default

    I would be worried if you said anything else without evidence to back it up...

    That said, I tend to assume strange glitches are somewhere in the software environment on my systems, and the graphics stack being first suspect

  4. #34
    Join Date
    Apr 2007
    Location
    Hungary
    Posts
    84

    Default

    Quote Originally Posted by Melcar View Post
    Here is an old radeon vs. fglrx test I did. All those games a rather playable. Would like to know what you did to get Tremulous running though; it's a slide show even under masa 7.8, and tends to crash.
    Nice one. This gives place for a lot of improvement as it looks. (Well, I cant test it myself, my hd 5650 mobility is bound to the catalyst, but honestly i have no major problems with 2d/3d performance of the 10.1 for my card.)

  5. #35
    Join Date
    Feb 2008
    Location
    Linuxland
    Posts
    5,130

    Default

    Why all the conspiracy theory? Occam's razor says the HD2600 is just a crappy card..

  6. #36
    Join Date
    Oct 2007
    Location
    Toronto-ish
    Posts
    7,463

    Default

    The 2600 and 3650 are very similar, other than clocks, fab process, and DX10.1 support in the 3650. UVD might be different as well, but that wouldn't affect these tests.

    With the exception of clock speeds, the two GPUs should give very similar results on these tests.

  7. #37
    Join Date
    Mar 2008
    Posts
    97

    Default

    Think the 2600 was running hot maybe?
    I know superior cooling would make a difference on my 4850 ast it reaches 100degrees celcius and downclocks itself.

    EDIT: ***110 degrees

  8. #38
    Join Date
    Jan 2010
    Posts
    26

    Default

    Quote Originally Posted by Melcar View Post
    Here is an old radeon vs. fglrx test I did. All those games a rather playable. Would like to know what you did to get Tremulous running though; it's a slide show even under masa 7.8, and tends to crash.


    Thats what i was looking for, but what about video playback, especially HD videos?

  9. #39
    Join Date
    Feb 2009
    Posts
    54

    Default

    Quote Originally Posted by colo View Post
    Am I the only one who thinks the graphing of the results is absolutely abhorrent? To get any valuable information out of the mess that is, for example, the GL and XV video performance graphs, they should have been at least two times their size. It'd also be nice to have access to the numeric data in tabular form as an option. More often than not, I'd like to compare numbers instead of trying hard to figure out which shade of $colour represents which cardů
    Yes, indeed. It would be better to integrate these graphs over time to get the time average, and simply display a bar graph of the averages.

  10. #40
    Join Date
    Aug 2009
    Posts
    2,264

    Default

    Quote Originally Posted by perpetualrabbit View Post
    Yes, indeed. It would be better to integrate these graphs over time to get the time average, and simply display a bar graph of the averages.
    Or both, because otherwise you'd lose info.

Posting Permissions

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