GPU histogram computation

Oliver Fluck, Shmuel Aharon, Daniel Cremers, Mikael Rousson
Siemens Corp. Research
In SIGGRAPH ’06: ACM SIGGRAPH 2006 Research posters (2006)


   title={GPU histogram computation},

   author={Fluck, O. and Aharon, S. and Cremers, D. and Rousson, M.},

   booktitle={ACM SIGGRAPH 2006 Research posters},






Download Download (PDF)   View View   Source Source   



Due to the immense computational power of today’s graphics processors (GPU), general purpose computation on GPUs has become a vivid research area. The performance of algorithms running on GPUs highly depends on how well they can be arranged to fit and exploit the processors single instruction multiple data (SIMD) architecture. Many tasks that are considered simple on a CPU such as grouping and counting of values of a domain for statistical purposes appear rather challenging to be implemented on a GPU. In this poster, we present a method to compute histograms in shader programs. On the example of image segmentation, we show that our method enables iterative and histogram guided algorithms to run efficiently on graphics hardware without costly CPU intervention. Using an image segmentation example, we demonstrate how the algorithm can be optimized for smaller regions of interest inside larger domains.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: