No subject

significant initialization differences when the radeon Kernel module has
not been loaded.  I tried disabling dri and dri2 to see if they were the
culprit, but that makes Xorg non functional (weird square block for a mouse
cursor over a black or corrupted display).  I also tried disabling many
other extensions and modules (Render, glx, Composite), but none of them
seemed to be causing the issue.

Does this lend any information in regards to what could be causing the poor
performance with Kicad?  Any ideas what different code paths could be
responsible?  From a rough view from "top" I can see that the CPU usage is
about 80% and 20% for Pcbnew and Xorg in the Catalyst and non Radeon kernel
module load cases (good performance cases) and 20% and 80% for Pcbnew and
Xorg in the normal radeon driver case (the poor performance case).  So it
would seem that Xorg and friends are taking up more CPU (about 3 times as
much) in the poor performance case.

Best regards,

Element Green

--000e0cd72ad2aa362204b2d16b9d
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

<div class=3D"gmail_quote"><div>Hello,</div><div><br></div><div>I happened =
upon this thread when searching for information on slow performance with Ki=
cad and the open source radeon driver.</div><div><a href=3D"http://lists.x.=
org/archives/xorg-driver-ati/2011-August/021077.html" target=3D"_blank">htt=
p://lists.x.org/archives/xorg-driver-ati/2011-August/021077.html</a></div>



<div><br></div><div>I have a ATI/AMD HD 5800 series video card in my laptop=
. =A0I&#39;ve also been rather impressed with the open source driver, even =
compared to Catalyst (which seems to suffer from many problems, especially =
with gnome 3). =A0So I&#39;m very keen on getting Kicad to be usable with i=
t.</div>



<div><br></div><div>After doing a lot of profiling with sysprof, oprofile a=
nd gprof, I discovered that the open source radeon driver works acceptably =
when the radeon Kernel module is not loaded. =A0I discovered this when I wa=
s trying to switch back to the open source driver from Catalyst and there w=
as an issue with the Kernel module loading.</div>



<div><br></div><div>From what I can tell from /var/log/Xorg.0.log there is =
some rather significant initialization differences when the radeon Kernel m=
odule has not been loaded. =A0I tried disabling dri and dri2 to see if they=
 were the culprit, but that makes Xorg non functional (weird square block f=
or a mouse cursor over a black or corrupted display). =A0I also tried disab=
ling many other extensions and modules (Render, glx, Composite), but none o=
f them seemed to be causing the issue.</div>



<div><br></div><div>Does this lend any information in regards to what could=
 be causing the poor performance with Kicad? =A0Any ideas what different co=
de paths could be responsible? =A0From a rough view from &quot;top&quot; I =
can see that the CPU usage is about 80% and 20% for Pcbnew and Xorg in the =
Catalyst and non Radeon kernel module load cases (good performance cases) a=
nd 20% and 80% for Pcbnew and Xorg in the normal radeon driver case (the po=
or performance case). =A0So it would seem that Xorg and friends are taking =
up more CPU (about 3 times as much) in the poor performance case.</div>

<div><br></div><div>Best regards,</div><span><font color=3D"#888888"><div><=
br></div>
<div>Element Green</div><div><br></div>
</font></span></div><br>

--000e0cd72ad2aa362204b2d16b9d--