AMD Kaveri: Catalyst vs. RadeonSI Gallium3D On Linux

[Soul_keeper]

I just ran these tests on my slackware system with comparable custom package versions.

http://openbenchmarking.org/result/1408128-KH-1408110KH76

The only real problem i'm getting is with l4d2 not rendering/loading the hair for the survivors.

http://cloud-4.steampowered.com/ugc/562141472070481313/E6CD441D6A9F1CA218B752470C063E03D442F350/

Can anyone else with mesa 10.3.0-devel check if they are having this issue ?

[dungeon]

:-(
Instead of 1, 2, 3 or 4 bars 2, 4, 6 or 8 bars. Bloated charts?

I mean you wanna this Kaveri results, but also Kabini and Richland/Trinity, etc and any other... to be added on top of this one .

[bridgman]

No, but some people want to compare the difference between open source and closed source on a dedicated Northern Islands card with Sea Islands in this APU.

Do you mean instead of Sea Islands, or are you imagining something like Crossfire across two totally different hardware generations (which AFAIK neither driver supports).

[drSeehas]

... So not sure, does some people want to combine this APU with the 6870 dedicated card

No, but some people want to compare the difference between open source and closed source on a dedicated Northern Islands card with Sea Islands in this APU.

Oh, i think i understand now you wanna bloated charts with no hardware missed .

:-(
Instead of 1, 2, 3 or 4 bars 2, 4, 6 or 8 bars. Bloated charts?

[dungeon]

This article just compare fglrx driver vs opensource driver using same APU . It is about changing a driver on the same machine

So not sure, does some people want to combine this APU with the 6870 dedicated card

Edit: And inclusion of Kabini and Richland/Trinity would have been nice too.

Oh, i think i understand now you wanna bloated charts with no hardware missed .

[drSeehas]

Radeon HD 6870

Then he must test it again, because of different mesa used and there will be difference when 6870 tested with CPU on this APU against i7-4790k, etc.

Yes!
That is why I asked for to include it for fair comparison.

Edit: And inclusion of Kabini and Richland/Trinity would have been nice too.

[GraysonPeddie]

Nice. I was curious about APU performance differences when running blob vs not. Lots of people are still running Trinity and Richland though so it would be interesting ti also have those numbers and cover the whole APU line worth covering.

How is perceived 2D performance with Catalyst? I cannot run it on my A10-5800K on KDE because composited 2D (smooth scrolling in Firefox and Chrome eg) is so choppy when it feels like butter with Gallium.

I have an AMD A10-5700 APU that I would like to see benchmarked, but the only problem I have is underscan for my 39" HDTV connected through my Marantz AVR-SR5008 receiver via HDMI 1.4 cable. My TV is a Vizio E390-B0 and with Catalyst 14.4, there is no slider to correct underscan. I don't have that problem with Mesa/radeon driver.

[dungeon]

I meant included in the charts together with Kaveri for easy comparison.

Then he must test it again, because of different mesa used and there will be difference when 6870 tested with CPU on this APU against i7-4790k, etc.

[drSeehas]

Radeon HD 6870

From the linked article posted just last week.... http://www.phoronix.com/vr.php?view=20732

I meant included in the charts together with Kaveri for easy comparison.

[Michael]

I would like to see a Radeon HD 6870 tested. It's the best card with open source drivers at the moment. Does it rival itself with Catalyst?

From the linked article posted just last week.... http://www.phoronix.com/vr.php?view=20732