Cannot use dynamic parallelism

Accelerated Computing CUDA CUDA Setup and Installation
#1

Hi all,
I am using GTX960 with CUDA 7.5 in Visual Studio 2013. After I have changed to compute_52,sm_52(in CUDA C/C++ -> Device -> Code Generation),
I still failed to use dynamic parallel. Anything else should I configure? Thanks in advance!

Following is the compiling information:

1>D:/RLF/RLF/RLF/kernel.cu(250): error : calling a global function(“change_neighbor_state”) from a global function(“color_max_degree_flow”) is only allowed on the compute_35 architecture or above

1>C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V120\BuildCustomizations\CUDA 7.5.targets(604,9): error MSB3721: The command ““C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\bin\nvcc.exe” -gencode=arch=compute_52,code=“sm_52,compute_52” -gencode=arch=compute_20,code=“sm_20,compute_20” --use-local-env --cl-version 2013 -ccbin “C:\Program Files (x86)\Microsoft Visual Studio 12.0\VC\bin” -rdc=true -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\include” -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\include" -G --keep-dir Debug -maxrregcount=0 --machine 32 --compile -cudart static -g -DWIN32 -D_DEBUG -D_CONSOLE -D_MBCS -Xcompiler “/EHsc /W3 /nologo /Od /Zi /RTC1 /MDd " -o Debug\kernel.cu.obj “D:\RLF\RLF\RLF\kernel.cu”” exited with code 2.
========== Rebuild All: 0 succeeded, 1 failed, 0 skipped ==========

Best,

#2

I just solved the problem, don’t choose the inherit from the parent will do.

#3

Visual Studio has the -G and -g flag set by default, and the compute 2. arch set as well.

Debug mode will prevent important optimizations, so for tests compile for release without -G and -g and compile for 5.2 rather than 2.0 for your GPU.

#4

Thanks for your replay~

#5

Can you show me the exact steps to unflag -G and -g in visual studio 2013? I have some problems to find the thread window.

#6

It will be the difference between compiling a debug project and compiling a release project.