[Phoronix] Ubuntu 9.04 vs. Fedora 11 Performance

Kevin Kofler kevin.kofler at chello.at
Sat Jun 13 19:05:13 UTC 2009


Gilboa Davara wrote:
> I subscribed to Phoronix' RSS feed and at least 1/3-1/2 of their news
> stories are on OSS driver (mostly Intel and ATI) driver development -
> far more than any other OSS new site. [1]

Too bad their hardware benchmarks do not match the development news, and too
bad they also feel it necessary to continuously warn about alleged
unsuitability of the Free drivers for production use (when in reality they
just work as long as you pick hardware which is already fully supported,
but their hardware section makes no effort to recommend such hardware).

> However, the sad truth is that -currently- neither xorg-drv-intel nor
> xorg-x11-drv-ati / xorg-x11-drv-radeonhd are capable of generating
> competitive 3D performance (Especially the recent GEM'ed versions of
> xorg-drv-intel) and far less mature than, say, nvidia.ko.

I don't care how they compare with proprietary modules. I want comparisons
between the different Free drivers and recommendations for the best
hardware when benchmarked using Free drivers. They have no such benchmark.

> Asking Phoronix not to report this and/or skew the benchmarks simply
> because the results are politically inconvenient to us is, in my view,
> simply unacceptable.

I disagree, they should not be promoting proprietary software, they should
focus on graphics in Free Software, not with proprietary drivers on an
otherwise Free system.

But even if they did 2 sections about hardware, one with proprietary drivers
and one with Free drivers, comparing what is comparable (i.e., at this
stage, in most cases, proprietary vs. proprietary and Free vs. Free),
that'd already be an improvement. Of course, if the Free drivers manage to
beat the proprietary ones for comparably-priced hardware, that's always
worth reporting! But they shouldn't be required to to even get mentioned at
all in the benchmarks.

>> Indeed, glxgears really sucks as as a benchmark, Phoronix's benchmark
>> suite (as imperfect as it is) is definitely more useful.
> 
> Oh, there's a start :)

Too bad I have to correct myself on that, since you pointed out that their
game benchmark uses proprietary games, and thus their benchmark suite is
NOT a contribution to Free Software.

There are plenty of Free Software 3D games which can be used for
benchmarking (and in fact I care much more about the results with those
games than with proprietary games I'm not going to play anyway).

        Kevin Kofler




More information about the fedora-devel-list mailing list