11409

LDetector: A Low Overhead Race Detector For GPU Programs

Pengcheng Li, Chen Ding, Xiaoyu Hu, Tolga Soyata
Department of Computer Science, University of Rochester, Rochester, NY, USA
5th Workshop on Determinism and Correctness in Parallel Programming (WoDet 2014), 2014

@article{li2014ldetector,

   title={LDetector: A Low Overhead Race Detector For GPU Programs},

   author={Li, Pengcheng and Ding, Chen and Hu, Xiaoyu and Soyata, Tolga},

   year={2014}

}

Download Download (PDF)   View View   Source Source   

546

views

Data race detection is an important problem in GPU programming. The paper presents a novel solution. It uses the compiler support to privatize shared data and then at run time parallelizes the race checking. It has two distinct features. First, there is no per access monitoring, so the race detection has a low overhead and does not affect the scalability. Second, race checking utilizes the massively parallel hardware of the GPU. Preliminary results show two orders of magnitude performance improvement over a previous method.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: