Sign in with
Sign up | Sign in

The Solution Is Closer Than You Think

AMD: 2D Performance Progress in Windows 7 With Catalyst 10.4?
By

Our next step was to run a few more tests with and without the Task Manager, while measuring the following, simple system parameters:

  • GPU clock frequency
  • CPU clock frequency
  • CPU load
  • Power consumption of the system


The possibility of the graphics cards changing power modes due to the Task Manager or some other program being activated came to my mind, so we decided to observe the GPU power consumption and GPU clock frequency in all tests. In Windows 7, the graphics cards from both manufacturers could theoretically increase their clock frequencies by switching to 3D mode when handling 2D GDI instructions. In the case of the Radeon HD 5870, that'd mean a switch from 157 MHz to 850 MHz. However, all values we listed as measurement points above stayed completely the same when testing with and without the Task Manager.

So why is the performance still increasing when the Task Manager is active, despite the clock frequencies being the same? The explanation was easier than we had initially thought. A little self-written 3D program got us on the right track.

We had forgotten to close this 3D application and were suddenly able to measure a constant increase in 2D performance.

In fact, 2D performance increases as soon as a D2D/D3D device, ideally displayed in window mode, is active in parallel to the direct output. Whether the window is visible or hidden isn’t important. As long as such an output is active, the 2D GDI/DDI disciplines we identified on the previous pages will run faster. There is only one difference: Nvidia’s driver handles blitting a bit better. The Task Manager in Windows 7 already uses D2D, which explains the performance increase when it is open.

Relevance and Interim Conclusion

At this point, we are not really talking about a bug, but rather a paradox. Especially since this increase in performance caused by the mere presence of an active D2D/D3D device raises the entirely-justified question as to why performance is not just as high without it. We can draw the conclusion that, in spite of the alleged separation in Windows 7, GDI is still directly connected to D3D. Whether this can ultimately be attributed to the driver developers involved in the Windows Vista experiment is a question, we cannot answer at this point.

Theoretically, it should be possible for driver developers to remove these last problems as well. Whether they are interested and considered worthwhile remains to be seen, though. The partial reintroduction of 2D hardware acceleration in Windows 7 should in any case be highlighted with a huge question mark.

Ask a Category Expert

Create a new thread in the Reviews comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 54 comments.
This thread is closed for comments
Top Comments
  • 15 Hide
    Anonymous , June 2, 2010 10:13 AM
    Keep doing those 2D testing. It's important for many users.
  • 13 Hide
    Poisoner , June 2, 2010 7:16 AM
    the greater goodTA152H, what you've just said is one of the most insanely idiotic things I have ever heard. At no point in your rambling, incoherent response were you even close to anything that could be considered a rational thought. Everyone in this room is now dumber for having listened to it. I award you no points, and may God have mercy on your soul.


    What was insane about his post?
  • 12 Hide
    Onus , June 2, 2010 10:12 AM
    Just because he applied the sarcasm with a mortar rather than a butter knife does not make TA152H's post insane.
Other Comments
  • 0 Hide
    ta152h , June 2, 2010 6:32 AM
    Well, Microsoft creating an even slower operating system than their previous one is a company tradition. Bloated, slow, buggy software is something they take seriously, and it's not up to companies like AMD or Nvidia to take this privilege from Microsoft. People like it - they keep buying it.

    It's a pity OS/2 never made it. Windows needs real competition. Look what the K8 did to Intel.
  • -3 Hide
    Anonymous , June 2, 2010 6:45 AM
    Lines, ellipses, and polygons are rarely, if ever, used in window system toolkits from the last 5-7 years. You will likely never see them used other than in specialized benchmarks. They are an API vestige of days long past.
  • 2 Hide
    Anonymous , June 2, 2010 6:49 AM
    Am I missing something? 10.5 is the most recent
  • 13 Hide
    Poisoner , June 2, 2010 7:16 AM
    the greater goodTA152H, what you've just said is one of the most insanely idiotic things I have ever heard. At no point in your rambling, incoherent response were you even close to anything that could be considered a rational thought. Everyone in this room is now dumber for having listened to it. I award you no points, and may God have mercy on your soul.


    What was insane about his post?
  • 10 Hide
    Anonymous , June 2, 2010 7:29 AM
    Does Catalyst 10.5 bring anything new to the table?
  • 10 Hide
    spidey180 , June 2, 2010 7:35 AM
    Keep up the good work ATI.
  • 5 Hide
    FUtomNOreg , June 2, 2010 8:41 AM
    Now where did I put that PCMag Winbench CD?????
  • 3 Hide
    outlw6669 , June 2, 2010 9:26 AM
    Quote:
    Does Catalyst 10.5 bring anything new to the table?

    You can now over/underclock while running multiple displays without tearing on the second monitor....
    Other than that, looks to be just a few minor bug fixes.
  • 0 Hide
    crazybaldhead , June 2, 2010 9:42 AM
    Yes, this article needs to be updated for 10.5. Also with the newest drivers, my 4870's GPU clock idles at 600 Mhz and not at 450 Mhz like it used to.
    Upping the idle clock frequencies is not a solution to the 2d performance problem, more like a *simple* workaround.
  • 12 Hide
    Onus , June 2, 2010 10:12 AM
    Just because he applied the sarcasm with a mortar rather than a butter knife does not make TA152H's post insane.
  • 15 Hide
    Anonymous , June 2, 2010 10:13 AM
    Keep doing those 2D testing. It's important for many users.
  • 1 Hide
    cushgod , June 2, 2010 12:20 PM
    10.5 Catalyst is out. Is that even better? Maybe a follow up article.
  • 0 Hide
    juliom , June 2, 2010 12:25 PM
    crazybaldheadYes, this article needs to be updated for 10.5. Also with the newest drivers, my 4870's GPU clock idles at 600 Mhz and not at 450 Mhz like it used to. Upping the idle clock frequencies is not a solution to the 2d performance problem, more like a *simple* workaround.


    Since you don't even know that the 4870 idles at 500 MHz (not 450), double check the 600 MHz you think you saw.
  • 1 Hide
    invlem , June 2, 2010 12:35 PM
    the greater goodTA152H, what you've just said is one of the most insanely idiotic things I have ever heard. At no point in your rambling, incoherent response were you even close to anything that could be considered a rational thought. Everyone in this room is now dumber for having listened to it. I award you no points, and may God have mercy on your soul.


    ... Now I'm going to have to watch that movie again (Billy Madison)
  • 1 Hide
    sohei , June 2, 2010 12:51 PM
    competition is good ...bravo ATI
  • 0 Hide
    misry , June 2, 2010 12:57 PM
    Cushgod10.5 Catalyst is out. Is that even better? Maybe a follow up article.


    While it is only an incremental u/g it is still worth taking. From a practical standpoint, I found 10.4 made the installation of a (no cost) 4350 card to supplant my built-in 4200 chip "worth it". Prior to 10.4 I seemed to get better performance from the 4200. Afterward, while performance remains the same, given a high side margin of error, using the 4350 now notably off-loads tasks from the CPU *and* frees system memory.
  • 1 Hide
    crazybaldhead , June 2, 2010 2:17 PM
    Quote:
    Since you don't even know that the 4870 idles at 500 MHz (not 450), double check the 600 MHz you think you saw.


    Hate to give in to trolls, but hey, here you go;

Display more comments