[nightly] IMPORTANT : vtk huge rendering performance drop ?

Sebastien Barre barre at sic.sp2mi.univ-poitiers.fr
Tue Nov 2 09:48:59 EST 1999


Hi

Last week Christopher Volpe (CRD) send me strange benchmarks results
(http://www.hds.utc.fr/~barre/vtk/sphere-bench.html). Although he was using
the same graphics board as mine (maxVision Titan II aka 3Dlabs GMX2000) and
a Pentium II *faster* than mine (400 Mhz against 266 Mhz overclocked to 300
Mhz), his results were *much lower* ! I was puzzled. We noticed that I was
using VTK 2.4 official, and he was using VTK 2.4 nightly.

Now for some news : I have just built VTK 2.4 official AND nightly
(yesterday release) on my Visual SGI 320 (NT4), and the results are *very*
annoying :

  - Tcl/Tk 8.0.5
  - Win32OpenGL (visual is truecolor/truecolor/32)

VTK 2.4 official

   1) 256x256 : 3224.3 kpolys/s : [stripper]
   2) 256x256 : 1950.7 kpolys/s : [small_sphere]
   3) 256x256 : 1950.7 kpolys/s : []
   4) 256x256 : 1950.7 kpolys/s : [transparency]
   5) 256x256 : 1393.4 kpolys/s : [texture]
   6) 256x256 : 1388.4 kpolys/s : [texture, transparency]
   7) 256x256 :  888.7 kpolys/s : [wireframe]

VTK 2.4 nightly

   1) 256x256 : 2393.5 kpolys/s : [stripper]
   2) 256x256 : 1950.7 kpolys/s : [small_sphere]
   3) 256x256 : 1283.4 kpolys/s : []
   4) 256x256 : 1266.7 kpolys/s : [transparency]
   5) 256x256 : 1258.5 kpolys/s : [texture, transparency]
   6) 256x256 : 1250.5 kpolys/s : [texture]
   7) 256x256 :  665.8 kpolys/s : [wireframe]

Notice the huge performance drop for stripped geometry (3224 kpolys -> 2393
kpolys ), as well as for all other (1950 kpolys -> 1200).

Christopher told me about Mutex stuff being added all over the place in the
source. Is it related ?

Losing such frame/s is a bit problematic. Did anyone notice the same ? I
have not been following the Quality Dashboard every day looking for Timing
Change, but I guess someone had ? 

I could kept using the official release, but I need Python support (thanks
to David Gobbi). 

Thanks
-- 
Sebastien BARRE
IRCOM-SIC, UMR-CNRS 6615 - Université de Poitiers 
Bât. SP2MI, Bvd 3 - Téléport 2, BP 179 F-86960 Futuroscope Cedex 
Tel. : +33 (0)5 49 49 65 95 / 65 83, Fax : +33 (0)5 49 49 65 70 
http://www-sic.univ-poitiers.fr/ 


-----------------------------------------------------------------------------
This is the private VTK discussion list.  Please keep messages on-topic.
Check the FAQ at: <http://www.automatrix.com/cgi-bin/vtkfaq>
To UNSUBSCRIBE, send message body containing "unsubscribe vtkusers" to
<majordomo at gsao.med.ge.com>.  For help, send message body containing
"info vtkusers" to the same address.     Live long and prosper.
-----------------------------------------------------------------------------




More information about the vtkusers mailing list