ATI's Gallium3D Driver Is Still Playing Catch-Up

[phoronix]

Phoronix: ATI's Gallium3D Driver Is Still Playing Catch-Up

Yesterday we delivered benchmarks showing how the open-source ATI Radeon graphics driver stack in Ubuntu 10.04 is comparing to older releases of the proprietary ATI Catalyst Linux driver. Sadly, the latest open-source ATI driver still is no match even for a two or four-year-old proprietary driver from ATI/AMD, but that is with the classic Mesa DRI driver. To yesterday's results we have now added in our results from ATI's Gallium3D (R300g) driver using a Mesa 7.9-devel Git snapshot from yesterday to see how this runs against the older Catalyst drivers.

http://www.phoronix.com/vr.php?view=14757

[mendieta]

Awesome. Basically, Galium3D >= Radeon for R500. What's the status of Gallium 3D for R600/700 in terms of 3D accel? Thanks!

[darkbasic]

What's the status of Gallium 3D for R600/700 in terms of 3D accel?

Uhm... I guess glxgears

[Pfanne]

did any work go into optimizing, or is it only work on features right now?
what im acutally asking is, if we can expect performance jumps if somebody if one of the developers found time to spend on optimizing the drivers?

[Pfanne]

edit:
did any work go into optimizing, or is it only work on features right now?
what im acutally asking is, if we can expect performance jumps if one of the developers found time to spend on optimizing the drivers?


i hate the edit function.

[marek]

edit:
did any work go into optimizing, or is it only work on features right now?
what im acutally asking is, if we can expect performance jumps if one of the developers found time to spend on optimizing the drivers?


i hate the edit function.

The work is being done on all fronts.

[rohcQaH]

Wow! G3D equals or beats classic mesa in all tests and even surpasses fglrx in some... yet the article is titled "playing Catch-Up".

[V!NCENT]

It's either old X.org and less stable drivers on less distro's Vs some realy nice drivers without downsides although a little later on features and speed.

What about OpenCL though? Is that just raw power using of the GPU or will OpenCL be slower with the state tracker too?

[bridgman]

I expect OpenCL performance is going to be driven by two things - shader compiler efficiency packing multiple instructions into a VLIW, and memory manager maturity. Both are hard but not impossible, and I *think* the OpenCL use cases should be less varied than OpenGL and easier to deal with. Other than that, raw power of the GPU should drive things.

Remember that there hasn't been a lot of optimization on the Gallium3D code base yet, just a push to get to classic Mesa levels so that 300g can replace 300.

[bridgman]

BTW the shape of the resolution vs performance curves (generally flat) indicates that performance is basically CPU limited right now, so a round of profiling and optimizing should make a hefty difference. The question is whether the bulk of the CPU time is being used in the HW driver stack or in the upper level Mesa code.

I'm not sure which of those to hope for