Performance impact of dynamic parallelism on different clustering algorithms

Jeffrey DiMarco, Michela Taufer
Computer and Information Sciences, University of Delaware
DSS11 SPIE Defense, Security, and Sensing Symposium – Modeling and Simulation for Defense Systems and Applications VI, 2013


   title={Performance impact of dynamic parallelism on different clustering algorithms},

   author={DiMarco, Jeffrey and Taufer, Michela},



Download Download (PDF)   View View   Source Source   



In this paper, we aim to quantify the performance gains of dynamic parallelism. The newest version of CUDA, CUDA 5, introduces dynamic parallelism, which allows GPU threads to create new threads, without CPU intervention, and adapt to its data. This effectively eliminates the superfluous back and forth communication between the GPU and CPU through nested kernel computations. The change in performance will be measured using two well-known clustering algorithms that exhibit data dependencies: the K-means clustering and the hierarchical clustering. K-means has a sequential data dependence wherein iterations occur in a linear fashion, while the hierarchical clustering has a tree-like dependence that produces split tasks. Analyzing the performance of these data-dependent algorithms gives us a better understanding of the benefits or potential drawbacks of CUDA 5’s new dynamic parallelism feature.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: