Efficient multithreading for manycore processor: Multidimensional domain decomposition using Intel® TBB
logo

Please use this identifier to cite or link to this publication: http://hdl.handle.net/10380/3585
The Insight Toolkit (ITK) utilizes a generic design for image processing filters that allows many developers to rapidly implement new algorithms. While ITK filters benefit from a platform-independent and versatile multithreading capability, the current implementation does not easily achieve high performance. First, ITK relies on a static decomposition of the image into subsets of equal size which is highly inefficient when the computational complexity varies between subsets (unbalanced workloads). Second, the current domain decomposition is limited to subdivide the input domain along a single dimension (typically the slice dimension in a 3-D volume), which causes a multithreading under-utilization when the number of threads is larger than the size of this dimension when using massively parallel compute systems. We previously presented a new itk::TBBImageToImageFilter class that replaced the static task decomposition by a dynamic task decomposition for improved workload balancing, in which the job scheduling task was optimized using the Intel® Threading Building Blocks (TBB) library. In this work, we propose a new multidimensional dynamic image decomposition approach that allows decomposition over an arbitrary number of dimensions. This new generic multithreading capability, combined with the TBB dynamic task scheduler, substantially improves multithreading performance when using massively parallel processors.
Data
minus 6 Datasets (42Mb)
Code
There is no code review at this time.

Reviews
There is no review at this time. Be the first to review this publication!

Quick Comments
Comment by Etienne St-Onge yellow
Code for the filter:
https://github.com/InsightSoftwareConsortium/ITKTBBImageToImageFilter

Data and test:
https://github.com/StongeEtienne/tbbmultidim


Resources
backyellow
Download All
Download Paper , View Paper
Download Source code
Source code repository

Statistics more
backyellow
Global rating: starstarstarstarstar
Review rating: starstarstarstarstar [review]
Code rating:
Paper Quality: plus minus
1 comment

Information more
backyellow
Categories: CMake, Code speed optimization, Parallelization, SMP, Tensor image reconstruction
Keywords: ITK ImageToImage filter, ITK
Tracking Number: Intel® Parallel Computing Center (IPCC) grant
Toolkits: ITK, CMake
Export citation:

Share
backyellow
Share

Linked Publications more
backyellow
A new implementation of itk::ImageToImageFilter for efficient parallelization of image processing... A new implementation of itk::ImageToImageFilter for efficient parallelization of image processing...
by Jaberzadeh A., Scherrer B., Warfield S.
Computing Bone Morphometric Feature Maps from 3-Dimensional Images Computing Bone Morphometric Feature Maps from 3-Dimensional Images
by Vimort J., McCormick M., Paniagua B.

Recommended Publications more
backyellow
Affine Transformation for Landmark Based Registration Initializer in ITK Affine Transformation for Landmark Based Registration Initializer in ITK
by Kim E.Y., Johnson H., Williams N.
Computing Textural Feature Maps for N-Dimensional images Computing Textural Feature Maps for N-Dimensional images
by Vimort J., McCormick M., Budin F., Paniagua B.

View license
Loading license...

Send a message to the author
main_flat
Powered by Midas