Mesa 9.2 & The R600 SB Back-End Are Good For AMD APUs

[phoronix]

Phoronix: Mesa 9.2 & The R600 SB Back-End Are Good For AMD APUs

From the AMD A10-6800K "Richland" APU I've delivered OpenGL Linux benchmarks of the Radeon HD 8670D graphics and also compared the open-source Gallium3D performance to that of Catalyst. Catalyst still reigns supreme, but in this article are some benchmarks showing the performance between Mesa 9.1 and 9.2 Git and also when deploying the experimental R600 SB shader optimization back-end.

http://www.phoronix.com/vr.php?view=18908

[darkbasic]

Nice, there are no regressions and some performance improvements

[Drago]

I would like to see how catalyst compares here at same conditions ( read PM).

[Andrecorreia]

bad

I would like to see how catalyst compares here at same conditions ( read PM).

catalyst have a inputlag on source games even with 200 fps the games are unplayable

[Alejandro Nova]

This. The only serious problem I found with free drivers is: MSAA is crap and doesn't work (full scene corruption). OTOH, the problems with Catalyst are major, and they include kernel panics, not being able to suspend + resume reliably, missing screen brightness controls (they don't work in Windows 8, work sometimes in Linux + fglrx, and work flawlessly in Linux with the free driver stack) and a horrible input lag.

I'll repeat: Fedora 19 is purring nicely in my E-450 netbook, and everyone with E-xxx APUs should switch to the free driver stack by Linux 3.11.

[mark45]

On related news, Wayland 1.2 RC is out.

[Hamish Wilson]

Considering everything that has happened, I think in terms of drivers both AMD and Intel can now (or at least soon) be considered to be in similar states, now that we have dynamic power management and video acceleration for radeon chips. I wonder if this will make anyone rethink their next APU purchase, or least make their choice a lot more difficult next time.

[pingufunkybeat]

Phoronix: Mesa 9.2 & The R600 SB Back-End Are Good For AMD APUs

From the AMD A10-6800K "Richland" APU I've delivered OpenGL Linux benchmarks of the Radeon HD 8670D graphics and also compared the open-source Gallium3D performance to that of Catalyst. Catalyst still reigns supreme, but in this article are some benchmarks showing the performance between Mesa 9.1 and 9.2 Git and also when deploying the experimental R600 SB shader optimization back-end.

http://www.phoronix.com/vr.php?view=18908

Am I assuming correctly that this is still running with the APU running in the lowest power state?

[bridgman]

Am I assuming correctly that this is still running with the APU running in the lowest power state?

Looks like default clocks, which are not necessarily the lowest state but definitely pretty low.

[ObiWan]

Nexuiz with dpm

http://openbenchmarking.org/result/1307100-UT-1307100UT60