So recently I have been using dynamic parallelism with my cuda fluid simulation. Qt is my IDE of choice so ideally I needed it to be compiles with that. As there is not a lot of documentation on it I figured it would be a crime not to share with the world. So here is the .pro file! Enjoy!

TARGET=FluidSim
OBJECTS_DIR=obj

# as I want to support 4.8 and 5 this will set a flag for some of the mac stuff
# mainly in the types.h file for the setMacVisual which is native in Qt5
isEqual(QT_MAJOR_VERSION, 5) {
 cache()
 DEFINES +=QT5BUILD
}
UI_HEADERS_DIR=ui
MOC_DIR=moc

CONFIG-=app_bundle
QT+=gui opengl core
SOURCES += #any srcs you hav 


HEADERS += #any headers you have

FORMS += #whatever you want

OTHER_FILES += #whaterver you want


INCLUDEPATH +=./include /opt/local/include $$(HOME)/NGL/include/
LIBS += -L/opt/local/lib -lGLEW
DESTDIR=./

CONFIG += console
CONFIG -= app_bundle

#This is some stuff for NGL the ncca graphics lib remove if you dont want it
#----------------------------------------------------------------
#------------------------ NGL setup -----------------------------
#----------------------------------------------------------------
# use this to suppress some warning from boost
QMAKE_CXXFLAGS_WARN_ON += "-Wno-unused-parameter"
QMAKE_CXXFLAGS+= -msse -msse2 -msse3
macx:QMAKE_CXXFLAGS+= -arch x86_64
macx:INCLUDEPATH+=/usr/local/include/
# define the _DEBUG flag for the graphics lib
DEFINES +=NGL_DEBUG

unix:LIBS += -L/usr/local/lib
# add the ngl lib
unix:LIBS += -L/$(HOME)/NGL/lib -lNGL

# now if we are under unix and not on a Mac (i.e. linux) define GLEW
linux-*{
 linux-*:QMAKE_CXXFLAGS += -march=native
 linux-*:DEFINES+=GL42
 DEFINES += LINUX
}
DEPENDPATH+=include
# if we are on a mac define DARWIN
macx:DEFINES += DARWIN

#----------------------------------------------------------------
#-------------------------Cuda setup-----------------------------
#----------------------------------------------------------------

#set out cuda sources
CUDA_SOURCES += cudaSrc/*.cu

# Path to cuda SDK install
macx:CUDA_DIR = /Developer/NVIDIA/CUDA-6.5
linux:CUDA_DIR = /usr/local/cuda-6.5
# Path to cuda toolkit install
macx:CUDA_SDK = /Developer/NVIDIA/CUDA-6.5/samples
linux:CUDA_SDK = /usr/local/cuda-6.5/samples

#Cuda include paths
INCLUDEPATH += $$CUDA_DIR/include
INCLUDEPATH += $$CUDA_DIR/common/inc/
INCLUDEPATH += $$CUDA_DIR/../shared/inc/


#cuda libs
macx:QMAKE_LIBDIR += $$CUDA_DIR/lib
linux:QMAKE_LIBDIR += $$CUDA_DIR/lib64
QMAKE_LIBDIR += $$CUDA_SDK/common/lib
#note for dynamic parallelism you need libcudadevrt
LIBS += -lcudart -lcudadevrt

# join the includes in a line
CUDA_INC = $$join(INCLUDEPATH,' -I','-I',' ')

# nvcc flags (ptxas option verbose is always useful)
NVCCFLAGS = --compiler-options -fno-strict-aliasing -use_fast_math --ptxas-options=-v


#prepare intermediat cuda compiler
cudaIntr.input = CUDA_SOURCES
cudaIntr.output = ${OBJECTS_DIR}${QMAKE_FILE_BASE}.o

## Tweak arch according to your hw's compute capability
cudaIntr.commands = $$CUDA_DIR/bin/nvcc -m64 -g -G -gencode arch=compute_52,code=sm_52 -dc $$NVCCFLAGS $$CUDA_INC $$LIBS ${QMAKE_FILE_NAME} -o ${QMAKE_FILE_OUT}

#Set our variable out. These obj files need to be used to create the link obj file
#and used in our final gcc compilation
cudaIntr.variable_out = CUDA_OBJ
cudaIntr.variable_out += OBJECTS
cudaIntr.clean = cudaIntrObj/*.o

QMAKE_EXTRA_UNIX_COMPILERS += cudaIntr


# Prepare the linking compiler step
cuda.input = CUDA_OBJ
cuda.output = ${QMAKE_FILE_BASE}_link.o

# Tweak arch according to your hw's compute capability
cuda.commands = $$CUDA_DIR/bin/nvcc -m64 -g -G -gencode arch=compute_52,code=sm_52 -dlink ${QMAKE_FILE_NAME} -o ${QMAKE_FILE_OUT}
cuda.dependency_type = TYPE_C
cuda.depend_command = $$CUDA_DIR/bin/nvcc -g -G -M $$CUDA_INC $$NVCCFLAGS ${QMAKE_FILE_NAME}
# Tell Qt that we want add more stuff to the Makefile
QMAKE_EXTRA_UNIX_COMPILERS += cuda