The API interfaces provided by CUDA help programmers to get high performance CUDA applications in GPU, but they cannot support most I/O operations in device codes. The characteristics of CUDA's mapped memory are used here to create a dynamic polling service model in the host which can satisfy most I/O functions such as read/write file and "printf". The technique to implement these I/O functions has some influence on the performance of the original applications. These functions quickly respond to the users' I/O requirements with the "printf" performance better than CUDA's. An easy and effective real-time method is given for users to debug their programs using the I/O functions. These functions improve productivity of converting legacy C/C++ codes to CUDA and broaden CUDA's functions.

1. IEEE Paper on "CUDA's Mapped Memory To Support I/O functions on GPU" , presented at TSINGHUA SCIENCE AND TECHNOLOGY, by Wei Wu, FengbinQi,WangQuan He and Shanshan Wang, Volume 18,Number 6,December 2013.
2. NVIDIA Corporation, CUDA Toolkit 3. 1 Downloads, https://developer. nvidia. com/cuda-toolkit-31-downloads, 2010.
3. S. Lee, S. Min, and R. Eigenmann, OpenMP to GPGPU: A compiler framework for automatic translation and optimization, presented at the 14th ACM SIGPLANSymposium on Principles and Practice of Parallel Programming, Raleigh, NC, USA, 2009.
4. R. Dolbeau, S. Bihan, and F. Bodin, HMPP?: A hybrid multi-core parallelprogramming environment, presented at the 1st Workshop on General Purpose Processing on Graphics Processing Units, Boston, USA, 2007.
5. Khronos Group, The open standard for parallel programming of heterogeneous systems, http://www. khronos. org/opencl, 2011.
6. J. Breitbart, Cupp-A framework for easy CUDA integration, in Proc. the 2009 IEEEInternational Symposium on Parallel&Distributed Processing, Washington, DC, USA, 2009, pp. 1-8.
7. S. Zhang, Y. Zhu, K. Zhao, and Y. Zhang, GPU High Performance Computing withCUDA, (in Chinese). Beijing, China: China WaterPower Press, 2009.
8. D. B. Kirk and W. W. Hwu, Programming Massively Parallel Processors: A Hands-on Approach. Burlington, MA, USA: Morgan Kaufmann Publishers, 2010.
9. J. Sanders and E. Kandrot, CUDA by Example: An Introduction to General-Purpose GPU Programming. Boston, MA, USA: Addison-Wesley,2010.
10. G. Diamos, A. Kerr, and S. Yalamanchili, Ocelot: A dynamic optimizationframework for bulk-synchronousapplications in heterogeneous systems, presented atthe19th International Conference on Parallel Architectures andCompilation Techniques, Vienna, Austria, 2010.

Cuda's Introduction Architecture Input-output Functions Mapping Of Memory.