Difference between revisions of "VTK/MultiThreading"

From KitwarePublic
< VTK
Jump to navigationJump to search
(Replaced content with "This page has been moved [http://www.vtk.org/Wiki/ARB/Topics/MultiThreading here].")
 
Line 1: Line 1:
==Purpose==
+
This page has been moved [http://www.vtk.org/Wiki/ARB/Topics/MultiThreading here].
 
 
VTK has adopted a MPI based strategy for parallelization. New strategies are currently designed to use new architectures like multi-core or hybrid systems. The aim of this page is to provide an overview of the current efforts.
 
 
 
==Strategies==
 
 
 
Several strategies can be used to parallelize VTK. We try to summarize those here :
 
* MPI-based parallelism :
 
** VTK can be executed in an MPI job, even on non-distributed computers. Datasets are then distributed between MPI processes.
 
* Execution Model
 
** Parallel pipeline branches : each independent branch can be executed simultaneously.
 
** Concurrent streaming of multiple pieces : several pieces can be streamed together in a pipeline, each one at a different stage of the pipeline.
 
** Apply a single algorithm concurrently to multiple blocs : if the algorithm treat each bloc independently, it could be applied to all blocs simultaneously.
 
* Intra-algorithm parallelism : many algorithms in VTK can be parallelized at a fine grain (per cell, point, row...) level.
 
 
 
==Current Efforts==
 
 
 
* Execution Model :
 
** Claudio T. Silva et al. have been working on the [http://www.sci.utah.edu/~hvo/papers/pds.pdf HyperFlow] enhancement.
 
* Intra-algorithm :
 
** Imaging pipeline
 
** Ray casting algorithms
 
 
 
The proposed [[Task Stealing framework]] focuses primarily on the intra-algorithm parallelization, and could also be used by the execution model.
 

Latest revision as of 09:28, 12 October 2010

This page has been moved here.