10647

Cudagrind: A Valgrind Extension for CUDA

Thomas M. Baumann, Jose Gracia
High Performance Computing Center Stuttgart, Nobelstr. 19, 70565 Stuttgart
arXiv:1310.0901 [cs.SE], (3 Oct 2013)

@article{2013arXiv1310.0901B,

   author={Baumann}, T.~M. and {Gracia}, J.},

   title={"{Cudagrind: A Valgrind Extension for CUDA}"},

   journal={ArXiv e-prints},

   archivePrefix={"arXiv"},

   eprint={1310.0901},

   primaryClass={"cs.SE"},

   keywords={Computer Science – Software Engineering, Computer Science – Operating Systems, Computer Science – Programming Languages},

   year={2013},

   month={oct},

   adsurl={http://adsabs.harvard.edu/abs/2013arXiv1310.0901B},

   adsnote={Provided by the SAO/NASA Astrophysics Data System}

}

Download Download (PDF)   View View   Source Source   Source codes Source codes

Package:

3065

views

Valgrind, and specifically the included tool Memcheck, offers an easy and reliable way for checking the correctness of memory operations in programs. This works in an unintrusive way where Valgrind translates the program into intermediate code and executes it on an emulated CPU. The heavy weight tool Memcheck uses this to keep a full shadow copy of the memory used by a program and tracking accesses to it. This allows the detection of memory leaks and checking the validity of accesses. Though suited for a wide variety of programs, this approach still fails when accelerator based programming models are involved. The code running on these devices is separate from the code running on the host. Access to memory on the device and starting of kernels is being handled by an API provided by the driver being used. Hence Valgrind is unable to understand and instrument operations being run on the device. To circumvent this limitation a new set of wrapper functions have been introduced. These wrap a subset of the CUDA Driver API function that is responsible for (de-)allocation memory regions on the device and the respective memory copy operations. This allows to check whether memory is fully allocated during a transfer and, through the functionality provided by Valgrind, whether the memory transfered to the device from the host is defined and addressable. Through this technique it is possible to detect a number of common programming mistakes, which are very difficult to debug by other means. The combination of these wrappers together with the Valgrind tool Memcheck is being called Cudagrind.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: