在 Windows 上的 Qt Creator 中编译 Cuda 代码

So I finally managed to assemble a .pro file that works on my and probably on all Windows systems. The following is an easy test programme that should probably do the trick. The following is a small project file plus test programme that works at least on my system.

文件系统如下:

TestCUDA 
    TestCUDA.pro
    main.cpp
    vectorAddition.cu

项目文件内容为:

TARGET = TestCUDA

# Define output directories
DESTDIR = release
OBJECTS_DIR = release/obj
CUDA_OBJECTS_DIR = release/cuda

# Source files
SOURCES += src/main.cpp

# This makes the .cu files appear in your project
OTHER_FILES +=  vectorAddition.cu

# CUDA settings <-- may change depending on your system
CUDA_SOURCES += src/cuda/vectorAddition.cu
CUDA_SDK = "C:/ProgramData/NVIDIA Corporation/NVIDIA GPU Computing SDK 4.2/C"   # Path to cuda SDK install
CUDA_DIR = "C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v4.2"            # Path to cuda toolkit install
SYSTEM_NAME = Win32         # Depending on your system either 'Win32', 'x64', or 'Win64'
SYSTEM_TYPE = 32            # '32' or '64', depending on your system
CUDA_ARCH = sm_11           # Type of CUDA architecture, for example 'compute_10', 'compute_11', 'sm_10'
NVCC_OPTIONS = --use_fast_math

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

# library directories
QMAKE_LIBDIR += $$CUDA_DIR/lib/$$SYSTEM_NAME 
                $$CUDA_SDK/common/lib/$$SYSTEM_NAME 
                $$CUDA_SDK/../shared/lib/$$SYSTEM_NAME
# Add the necessary libraries
LIBS += -lcuda -lcudart

# The following library conflicts with something in Cuda
QMAKE_LFLAGS_RELEASE = /NODEFAULTLIB:msvcrt.lib
QMAKE_LFLAGS_DEBUG   = /NODEFAULTLIB:msvcrtd.lib

# The following makes sure all path names (which often include spaces) are put between quotation marks
CUDA_INC = $$join(INCLUDEPATH,'" -I"','-I"','"')

# 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
}

注意 QMAKE_LFLAGS_RELEASE =/NODEFAULTLIB:msvcrt.lib:我花了很长时间才弄清楚，但这个库似乎与 Cuda 中的其他东西发生冲突，这会产生奇怪的链接警告和错误.如果有人对此有解释，并且可能有更好的解决方法，我想听听.

#include <cuda.h>
#include <builtin_types.h>
#include <drvapi_error_string.h>

#include <QtCore/QCoreApplication>
#include <QDebug>

// Forward declare the function in the .cu file
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 [])
{
    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;
}

#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);
}