使用 msvc 15 在 Qt5.13 中编译 CUDA 代码

我必须在Qt中构建一个cuda代码以及其他c ++文件。但这正在失败。我已经尝试过使用Stackoverflow中可用的示例，但这也失败了。我已经附上了示例代码。请提供建议

.pro 文件

QT       += core gui
greaterThan(QT_MAJOR_VERSION, 4): QT += widgets
CONFIG += c++11
# The following define makes your compiler emit warnings if you use
# any Qt feature that has been marked deprecated (the exact warnings
# depend on your compiler). Please consult the documentation of the
# deprecated API in order to know how to port your code away from it.
DEFINES += QT_DEPRECATED_WARNINGS
# You can also make your code fail to compile if it uses deprecated APIs.
# In order to do so, uncomment the following line.
# You can also select to disable deprecated APIs only up to a certain version of Qt.
#DEFINES += QT_DISABLE_DEPRECATED_BEFORE=0x060000    # disables all the APIs deprecated before Qt 6.0.0
SOURCES += 
main.cpp 
mainwindow.cpp
HEADERS += 
mainwindow.h
FORMS += 
mainwindow.ui
# Default rules for deployment.
qnx: target.path = /tmp/$${TARGET}/bin
else: unix:!android: target.path = /opt/$${TARGET}/bin
!isEmpty(target.path): INSTALLS += target

CUDA_PATH = "C:Program FilesNVIDIA GPU Computing ToolkitCUDAv9.0"
INCLUDEPATH += $$CUDA_PATHinclude
OTHER_FILES +=  vectorAddition.cu
CUDA_SOURCES += vectorAddition.cu
SYSTEM_TYPE = 64
CUDA_ARCH = sm_50
NVCC_OPTIONS = --use_fast_math
QMAKE_LIBDIR += "C:Program FilesNVIDIA GPU Computing ToolkitCUDAv9.0libx64"
CUDA_LIBS = cuda cudart
# The following makes sure all path names (which often include spaces) are put between quotation marks
CUDA_INC = $$join(INCLUDEPATH,'" -I"','-I"','"')
NVCC_LIBS = $$join(CUDA_LIBS,' -l','-l', '')
LIBS += $$join(CUDA_LIBS,'.lib ', '', '.lib')
#Configuration of the Cuda compiler
CONFIG(debug, debug|release) {
# Debug mode
cuda_d.input = CUDA_SOURCES
cuda_d.output = $$CUDA_OBJECTS_DIR/${QMAKE_FILE_BASE}_cuda.o
cuda_d.commands = $$CUDA_DIR/bin/nvcc.exe -D_DEBUG $$NVCC_OPTIONS $$CUDA_INC $$LIBS --machine $$SYSTEM_TYPE -arch=$$CUDA_ARCH -c -o ${QMAKE_FILE_OUT} ${QMAKE_FILE_NAME}
cuda_d.dependency_type = TYPE_C
QMAKE_EXTRA_COMPILERS += cuda_d
}
else {
# Release mode
cuda.input = CUDA_SOURCES
cuda.output = $$CUDA_OBJECTS_DIR/${QMAKE_FILE_BASE}_cuda.o
cuda.commands = $$CUDA_DIR/bin/nvcc.exe $$NVCC_OPTIONS $$CUDA_INC $$LIBS --machine $$SYSTEM_TYPE -arch=$$CUDA_ARCH -c -o ${QMAKE_FILE_OUT} ${QMAKE_FILE_NAME}
cuda.dependency_type = TYPE_C
QMAKE_EXTRA_COMPILERS += cuda
}

主窗口.cpp

#include "mainwindow.h"
#include <QApplication>
#include <QDebug>
#include <cuda.h>
#include <builtin_types.h> //#include <drvapi_error_string.h>
void vectorAddition(const float* a, const float* b, float* c, int n);
void printArray(const float* a, const unsigned int n) {
QString s = "(";
unsigned int ii;
for (ii = 0; ii < n - 1; ++ii)
s.append(QString::number(a[ii])).append(", ");
s.append(QString::number(a[ii])).append(")");
qDebug() << s; }
int main(int argc, char *argv[]) {
QApplication app(argc, argv);
MainWindow w;
w.show();
QCoreApplication(argc, argv);
int deviceCount = 0;
int cudaDevice = 0;
char cudaDeviceName [100];
unsigned int N = 50;
float *a, *b, *c;
cuInit(0);
cuDeviceGetCount(&deviceCount);
cuDeviceGet(&cudaDevice, 0);
cuDeviceGetName(cudaDeviceName, 100, cudaDevice);
qDebug() << "Number of devices: " << deviceCount;
qDebug() << "Device name:" << cudaDeviceName;
a = new float [N];    b = new float [N];    c = new float [N];
for (unsigned int ii = 0; ii < N; ++ii) {
a[ii] = qrand();
b[ii] = qrand();
}
// This is the function call in which the kernel is called
vectorAddition(a, b, c, N);
qDebug() << "input a:"; printArray(a, N);
qDebug() << "input b:"; printArray(b, N);
qDebug() << "output c:"; printArray(c, N);
if (a) delete a;
if (b) delete b;
if (c) delete c;
return app.exec(); }

vectorAddition.cu

#include <cuda.h>
#include <builtin_types.h>
extern "C"
__global__ void vectorAdditionCUDA(const float* a, const float* b, float* c, int n)
{
int ii = blockDim.x * blockIdx.x + threadIdx.x;
if (ii < n)
c[ii] = a[ii] + b[ii];
}
void vectorAddition(const float* a, const float* b, float* c, int n) {
float *a_cuda, *b_cuda, *c_cuda;
unsigned int nBytes = sizeof(float) * n;
int threadsPerBlock = 256;
int blocksPerGrid   = (n + threadsPerBlock - 1) / threadsPerBlock;
// allocate and copy memory into the device
cudaMalloc((void **)& a_cuda, nBytes);
cudaMalloc((void **)& b_cuda, nBytes);
cudaMalloc((void **)& c_cuda, nBytes);
cudaMemcpy(a_cuda, a, nBytes, cudaMemcpyHostToDevice);
cudaMemcpy(b_cuda, b, nBytes, cudaMemcpyHostToDevice);
vectorAdditionCUDA<<<blocksPerGrid, threadsPerBlock>>>(a_cuda, b_cuda, c_cuda, n);
// load the answer back into the host
cudaMemcpy(c, c_cuda, nBytes, cudaMemcpyDeviceToHost);
cudaFree(a_cuda);
cudaFree(b_cuda);
cudaFree(c_cuda);
}

错误日志

main.obj ： 错误 LNK2038： 检测到"运行时库"不匹配： 值"MD_DynamicRelease"与 vectorAddition_cuda.o 中的值"MT_StaticRelease"不匹配 mainwindow.obj ： 错误 LNK2038： 检测到"运行时库"不匹配： 值"MD_DynamicRelease"与 vectorAddition_cuda.o 中的值"MT_StaticRelease"不匹配 moc_mainwindow.obj：错误LNK2038：检测到"运行时库"不匹配：值"MD_DynamicRelease"与vectorAddition_cuda中的值"MT_StaticRelease"不匹配。