gcc 4.0.1 autovectorziation of VTK on OS X 10.4 and linux and windowsXP

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

gcc 4.0.1 autovectorziation of VTK on OS X 10.4 and linux and windowsXP

Dan White-3
Hi,

I was wondering if any experts know about
the possibility of the autovectorziation function
of the gcc 4.0.1 (and later) compiler collection
for speeding up the execution of VTK libraries
using the vector provessing power of altivec enabled PPC G4 and G5 chips
and SSE enabled ix86 chips.

is the VTK code vecorizable to any extent?
(I'm not really taking about the parallel processing functionality
in VTK, rather the possibility to use processor vector extensions
on the normal code for the VTK libraries)

Is any of the code written in such a way that the gcc compiler will  
see that it can vectorize it and then do so?

I'm having a go on an OSX VTK 5 CVS (from a while back, not newest  
CVS) build on an G5....

cheers

Dan



Dr. Daniel James White BSc. (Hons.) PhD
Bioimaging Coordinator
Nanoscience Centre and Department of Biological and Environmental  
Sciences
Division of Molecular Recognition
Ambiotica C242
PO Box 35
University of Jyväskylä
Jyväskylä
FIN 40014
Finland

+358 14 260 4183 (work)
+358 468102840 (mobile)
http://www.bioimagexd.org
http://www.chalkie.org.uk
[hidden email]
[hidden email]


_______________________________________________
This is the private VTK discussion list.
Please keep messages on-topic. Check the FAQ at: http://www.vtk.org/Wiki/VTK_FAQ
Follow this link to subscribe/unsubscribe:
http://www.vtk.org/mailman/listinfo/vtkusers
Reply | Threaded
Open this post in threaded view
|

Re: gcc 4.0.1 autovectorziation of VTK on OS X 10.4 and linux and windowsXP

Sean McBride
On 2006-01-31 11:46, Dan White said:

>I was wondering if any experts know about
>the possibility of the autovectorziation function
>of the gcc 4.0.1 (and later) compiler collection
>
>*SNIP*
>
>I'm having a go on an OSX VTK 5 CVS (from a while back, not newest
>CVS) build on an G5....

I've never tried, but am interested to hear your results!  Will you post
back to the list after you try?

--
____________________________________________________________
Sean McBride, B. Eng                 [hidden email]
Rogue Research                        www.rogue-research.com
Mac Software Developer              Montréal, Québec, Canada


_______________________________________________
This is the private VTK discussion list.
Please keep messages on-topic. Check the FAQ at: http://www.vtk.org/Wiki/VTK_FAQ
Follow this link to subscribe/unsubscribe:
http://www.vtk.org/mailman/listinfo/vtkusers
Reply | Threaded
Open this post in threaded view
|

Re: gcc 4.0.1 autovectorziation of VTK on OS X 10.4 and linux and windowsXP

Dan White-3
Hi Sean,

will do,
building right now
on an apple powemac G5 1.6GHz
with c and c++ flags
-fast -maltivec- mcpu=G5 -ftree-vectorize

also trying on an AMD athlon (i think)  1.something GHz  processor  
under linux with
-msse2 -ftree-vectorize

not sure if i even have sse2 on that processor...

no idea if this is really the right set of flags to use...
maybe should use -O3 not -fast  .. anyway we shall see...

Dan


On Jan 31, 2006, at 5:49 PM, Sean McBride wrote:

> On 2006-01-31 11:46, Dan White said:
>
>> I was wondering if any experts know about
>> the possibility of the autovectorziation function
>> of the gcc 4.0.1 (and later) compiler collection
>>
>> *SNIP*
>>
>> I'm having a go on an OSX VTK 5 CVS (from a while back, not newest
>> CVS) build on an G5....
>
> I've never tried, but am interested to hear your results!  Will you  
> post
> back to the list after you try?
>
> --
> ____________________________________________________________
> Sean McBride, B. Eng                 [hidden email]
> Rogue Research                        www.rogue-research.com
> Mac Software Developer              Montréal, Québec, Canada
>
>

Dr. Daniel James White BSc. (Hons.) PhD
Bioimaging Coordinator
Nanoscience Centre and Department of Biological and Environmental  
Sciences
Division of Molecular Recognition
Ambiotica C242
PO Box 35
University of Jyväskylä
Jyväskylä
FIN 40014
Finland

+358 14 260 4183 (work)
+358 468102840 (mobile)
http://www.bioimagexd.org
http://www.chalkie.org.uk
[hidden email]
[hidden email]


_______________________________________________
This is the private VTK discussion list.
Please keep messages on-topic. Check the FAQ at: http://www.vtk.org/Wiki/VTK_FAQ
Follow this link to subscribe/unsubscribe:
http://www.vtk.org/mailman/listinfo/vtkusers