[vtkusers] vtkFixedPointVolumeRayCastMapper initializationperformance improvement

[Lasso, Andras (GE Healthcare)]

As it was suggested, I've filed a bug report for this enhancement. The
bug id is #5443.
 
Andras

________________________________

From: vtkusers-bounces+andras.lasso=med.ge.com at vtk.org
[mailto:vtkusers-bounces+andras.lasso=med.ge.com at vtk.org] On Behalf Of
Lasso, Andras (GE Healthcare)
Sent: Wednesday, August 01, 2007 2:44 PM
To: vtkusers at vtk.org
Subject: [vtkusers] vtkFixedPointVolumeRayCastMapper
initializationperformance improvement


Hi all,
 
I've implemented multi-threaded gradient computation in
vtkFixedPointVolumeRayCastMapper. It can make the volume rendering
initialization step 30-40% faster on a dual-core system (and probably
even faster on a system with more CPUs), if shading is used.
 
Just a few changes were needed, as the
vtkFixedPointVolumeRayCastMapperComputeGradients method was already
prepared for multi-threaded computation. I attach the updated files
(based on VTK-5.0.3 release).
 
Would it be possible to integrate this performance improvement into the
next VTK release?
 
Thanks in advance.
Andras


________________________________

From: vtkusers-bounces+andras.lasso=med.ge.com at vtk.org
[mailto:vtkusers-bounces+andras.lasso=med.ge.com at vtk.org] On Behalf Of
Lasso, Andras (GE Healthcare)
Sent: Tuesday, July 31, 2007 4:46 PM
To: vtkusers at vtk.org
Subject: [vtkusers] Gradients computation speed-up
invtkFixedPointVolumeRayCastMapper by multi-threading


Hi all,
 
I use vtkFixedPointVolumeRayCastMapper for volume rendering. The image
quality is perfect, but I have to wait about 30 sec for the first
rendered image, mainly due gradient computation.
 
Currently (VTK-5.0.3) the gradient computation is implemented in a
single thread. I would expect that on multi-core/CPU systems the
gradient computation could be made 2-4 times faster with a
multi-threaded implementation. Looking at the code I've found that the
algorithm in vtkFixedPointVolumeRayCastMapperComputeGradients is already
prepared for a multi-threaded implementation.
 
Does anyone know why the multi-threaded gradient computation just
prepared, and finally not implemented for
vtkFixedPointVolumeRayCastMapper?
 
Andras
 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.vtk.org/pipermail/vtkusers/attachments/20070802/eb5e14b0/attachment.htm>