Search:

Type: Posts; User: vadimg; Keyword(s):

Page 1 of 2 1 2

Search: Search took 0.14 seconds.

  1. Replies
    33
    Views
    11,650

    Honestly, this option probably makes sense for...

    Honestly, this option probably makes sense for the apps that hit register allocation issues with stock backend. LLVM can solve some issues of that kind. On the other hand, I really hoped that LLVM...
  2. Replies
    14
    Views
    2,511

    Let me also quote Stallman's words from your...

    Let me also quote Stallman's words from your link: "ATI has released free drivers."



    Radeon drivers don't "use" microcode, they just upload it to hardware in order to initialize it and make it...
  3. I suspect the situation is rather the opposite to...

    I suspect the situation is rather the opposite to what many people think. Why some application/driver can be less affected by the ondemand issue? Probably because its cpu usage is closer to 100%, so...
  4. Thanks! I appreciate that. Actually all of my...

    Thanks! I appreciate that. Actually all of my work on r600g was done not for money, nobody paid me for that (except two donations from generous people afterwards), but to make some people (amd gpu...
  5. I don't think it's a big problem for mesa devs to...

    I don't think it's a big problem for mesa devs to recognize the problem. Fixing it is another thing though. I'd like to see some hero come and rewrite most of the mesa stuff with modern gpus in mind,...
  6. Correct me if I wrong, but I believe saying...

    Correct me if I wrong, but I believe saying "Historically Catalyst had problems with games played with wine" is not correct, I'd say "historically wine had problems with non-NVidia drivers". I didn't...
  7. Really, performance of the open source driver can...

    Really, performance of the open source driver can be even higher just because catalyst is not ideal either. I can mostly talk about compiler (it's what I dealt with), and I saw many cases where...
  8. Yes, r600g/sb has an if-conversion pass that...

    Yes, r600g/sb has an if-conversion pass that produces the same result for the IF-MOV-ELSE-MOV-ENDIF pattern, though it's a bit more generic and handles almost any suitable conditional code, e.g. with...
  9. Replies
    503
    Views
    54,472

    Poll: I think the question is not really about the...

    I think the question is not really about the distro, because many complaints here about benchmarks on Ubuntu (including those from myself) are not about the distro itself, but rather about it's...
  10. Looks like Option "SwapbuffersWait" "off" in...

    Looks like Option "SwapbuffersWait" "off" in xorg.conf might help, without it I have ~7000 too.
  11. I think performance can be better with some...

    I think performance can be better with some simple tuning like turning off the compositor and using performance governor for cpu, at least I typically have better results with weaker CPU&GPU than...
  12. The result of Triangle benchmark is above 100...

    The result of Triangle benchmark is above 100 thousands on my 5750 with r600g and I don't think that 4870 renders single triangle 7 times slower. It seems something is wrong with Michael's results,...
  13. Yes, but it doesn't make sense to measure...

    Yes, but it doesn't make sense to measure difference between two runs with unrepeatable benchmark, because you simply can't compare the results. It's like a car race where each racer chooses...
  14. Don't be so shy, I'm pretty sure that for such a...

    Don't be so shy, I'm pretty sure that for such a great developer like you it would be easy to change the driver as well. In the worst case, if there are no more drivers to try, I have no doubts that...
  15. I'm not making up anything because this problem...

    I'm not making up anything because this problem already exists. I never claimed that I know exact reason(s) though, and of course some of my initial ideas may be wrong (I don't even have 25 years of...
  16. I thought it's obvious, but I can explain:...

    I thought it's obvious, but I can explain: single-threaded application is the obvious example of application that doesn't fully utilize multicore cpu, so when the thread is moved between cores due to...
  17. Any single-threaded game won't magically start...

    Any single-threaded game won't magically start using all cpu cores, thus it will never result in 100% cpu utilization, and when the load is distributed among multiple cpus it won't always trigger...
  18. I wonder if I should have added sarcasm tags to...

    I wonder if I should have added sarcasm tags to my previous comments to make my point more clear to you.

    No, I don't need few extra FPS and I don't need your laughable advices, I need a quality...
  19. Well, probably I should have used something like...

    Well, probably I should have used something like 'CPU utilization' instead of 'CPU load' to avoid misunderstanding. English is not my native and some terms do not map very well when translated...
  20. I used the term 'average load' as a percentage of...

    I used the term 'average load' as a percentage of time when cpu is not idle, that is, when CPU is running in C0 power state, as opposed to power-saving states (C1,...) with stopped CPU clocks. That's...
Results 1 to 20 of 39
Page 1 of 2 1 2