[Nouveau] "enable ctxprog xfer only when we need it to save power" introduces big performance regression

[Lucas Stach]

Am Freitag, den 13.01.2012, 22:26 +0100 schrieb Martin Peres:
> Hi Marcin,
> 
> As promised, I started working on your performance problem.
> 
> Le 29/12/2011 02:38, Marcin Slusarz a écrit :
> > I tried to implement xfers runtime switching, but couldn't figure out 
> > how to change ctxprog behaviour without rebuilding and reuploading 
> > whole thing. Reading host-writable memory from ctxprog would be enough. 
> Well, I did that for you (see the patch enclosed). The patch uses the 
> 4th ctxprog flag register's bit 0 to store the wanted behaviour.
> Mwk suggested me to do so and it worked perfectly.
> 
> You have all the instructions in the commit message, please report on 
> the actual results!
> 
> By the mean time, I'll plug it to a PM brain so as it would switch back 
> and forth between the two modes according to the load or the perflvl.

Isn't it possible that the performance regression seen with xfer
disabled by default is caused by slow memory clock speed? Martin, you
saw only a 1% performance drop on your 8600 which is running with full
speed by default. Marcins nv92 is likely running at a much lower clock
speed. It would be nice to know if the perf regression is still as big
when running with full speed. We could stop caring about this when the
perf regression is not observable in the highest perf level.

> 
> Take care,
> 
> Martin
> _______________________________________________
> Nouveau mailing list
> Nouveau at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/nouveau