My project contains pure C++ code, i.e inheritance, virtual, run time polymorphism, memory dereferences etc. Also i am using OpenGL for image rendering. To increase my execution performance i am planning to use CUDA. In CUDA website mentioned that CUDA is preferable for only C like.
I want to work with CUDA in my c++ project. Please give me a suggestion to how to integrate CUDA with C++.
I’m also looking for such information. Now I’m learning and trying to compile cppIntegration example from SDK (C:\Documents and Settings\All Users\Application Data\NVIDIA Corporation\NVIDIA GPU Computing SDK\C\src\cppIntegration)
I can’t launch this project not from default directory. I constantly get following error:
1>nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
1>Linking...
1>LINK : fatal error LNK1181: cannot open input file '.\debug\cppIntegration.cu.obj'
I have the following paths written in Microsoft Word:
$(CUDA_INC_PATH);./;“$(NVSDKCUDA_ROOT)\common\inc”
$(CUDA_INC_PATH);“$(NVSDKCUDA_ROOT)\common\inc”;“$(NVSDKCUDA_ROOT)\common\lib”;“$(CUDA_LIB_PATH)”
I copied them to properties of Linker and Compiler. After that errors appead.
We looked the .vcproj file, and in place of " was ".
We deleted " and my error disappeared