在Qt Creator中使用CUDA

byxdaz

已于 2025-05-04 10:23:58 修改

阅读量356

点赞数 8

分类专栏： CUDA 文章标签： CUDA qt

于 2025-05-04 10:23:20 首次发布

本文链接：https://blog.csdn.net/byxdaz/article/details/147674967

版权

CUDA 专栏收录该内容

20 篇文章

订阅专栏

要在Qt Creator项目中使用CUDA进行GPU加速计算，你需要进行一些配置。以下是详细步骤：

1. 安装必要软件

安装最新版本的NVIDIA CUDA Toolkit
确保已安装Qt Creator和兼容的编译器(如MSVC或GCC)

2. 创建Qt项目

打开Qt Creator，创建一个新的Qt Console Application或Qt Widgets Application项目
选择适合的编译工具链(MSVC或MinGW)

3. 配置.pro文件

修改项目的.pro文件，添加CUDA支持：

qmake

QT -= gui

CONFIG += c++11 console cuda
CONFIG -= app_bundle

# 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

# Default rules for deployment.
qnx: target.path = /tmp/$${TARGET}/bin
else: unix:!android: target.path = /opt/$${TARGET}/bin
!isEmpty(target.path): INSTALLS += target


# 添加CUDA支持
CUDA_SOURCES += your_cuda_file.cu
CUDA_DIR = "C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v10.2"  # 修改为你的CUDA安装路径

# 指定 nvcc 路径（Windows 示例）
win32 {
    CUDA_NVCC = $$CUDA_DIR/bin/nvcc.exe
    QMAKE_EXTRA_COMPILERS += cuda
}


# 指定CUDA架构
CUDA_ARCH = sm_50  # 根据你的GPU计算能力设置

# 添加CUDA包含路径
INCLUDEPATH += $$CUDA_DIR/include

# 添加CUDA库路径
win32 {
    CUDA_LIBS = $$CUDA_DIR/lib/x64
} else {
    CUDA_LIBS = $$CUDA_DIR/lib64
}

# 添加必要的CUDA库
LIBS += -L$$CUDA_LIBS -lcudart -lcuda

# 强制使用 nvcc 编译 .cu 文件
cuda.commands = $$CUDA_NVCC -c -arch=$$CUDA_ARCH ${QMAKE_FILE_NAME} -o ${QMAKE_FILE_OUT}
cuda.dependency_type = TYPE_C
cuda.input = CUDA_SOURCES
cuda.output = ${QMAKE_FILE_BASE}.o
QMAKE_EXTRA_COMPILERS += cuda


# 强制统一迭代器调试级别
CONFIG(debug, debug|release) {
    # Debug 配置
    DEFINES += _ITERATOR_DEBUG_LEVEL=2
    CUDA_NVCC_FLAGS += -D_ITERATOR_DEBUG_LEVEL=2
} else {
    # Release 配置
    DEFINES += _ITERATOR_DEBUG_LEVEL=0
    CUDA_NVCC_FLAGS += -D_ITERATOR_DEBUG_LEVEL=0
}


# MSVC编译器设置
win32-msvc {
    # 强制使用动态链接（MD/MDd）
    QMAKE_CXXFLAGS_RELEASE -= -MD
    QMAKE_CXXFLAGS_RELEASE += -MT
    QMAKE_CXXFLAGS_DEBUG -= -MTd
    QMAKE_CXXFLAGS_DEBUG += -MDd

    # 传递给nvcc
    CUDA_NVCC_FLAGS_RELEASE = -Xcompiler "/MD"
    CUDA_NVCC_FLAGS_DEBUG = -Xcompiler "/MDd"
}

4. 创建CUDA源文件

在项目中添加一个.cu文件(例如your_cuda_file.cu):

cpp

#include <cuda_runtime.h>
#include <device_launch_parameters.h>

__global__ void addKernel(int *c, const int *a, const int *b)
{
    int i = threadIdx.x;
    c[i] = a[i] + b[i];
}

extern "C" void launchAddKernel(int *c, const int *a, const int *b, int size)
{
    int *dev_a = 0;
    int *dev_b = 0;
    int *dev_c = 0;
    
    // 分配GPU内存
    cudaMalloc((void**)&dev_c, size * sizeof(int));
    cudaMalloc((void**)&dev_a, size * sizeof(int));
    cudaMalloc((void**)&dev_b, size * sizeof(int));
    
    // 拷贝数据到GPU
    cudaMemcpy(dev_a, a, size * sizeof(int), cudaMemcpyHostToDevice);
    cudaMemcpy(dev_b, b, size * sizeof(int), cudaMemcpyHostToDevice);
    
    // 启动内核
    addKernel<<<1, size>>>(dev_c, dev_a, dev_b);
    
    // 拷贝结果回CPU
    cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToHost);
    
    // 清理
    cudaFree(dev_a);
    cudaFree(dev_b);
    cudaFree(dev_c);
}

5. 在Qt代码中调用CUDA函数

在你的Qt代码中(如main.cpp):

cpp

#include <QCoreApplication>
#include <iostream>

extern "C" void launchAddKernel(int *c, const int *a, const int *b, int size);

int main(int argc, char *argv[])
{
    QCoreApplication a(argc, argv);
    
    const int arraySize = 5;
    const int a[arraySize] = {1, 2, 3, 4, 5};
    const int b[arraySize] = {10, 20, 30, 40, 50};
    int c[arraySize] = {0};
    
    launchAddKernel(c, a, b, arraySize);
    
    std::cout << "Result: ";
    for (int i = 0; i < arraySize; i++) {
        std::cout << c[i] << " ";
    }
    std::cout << std::endl;
    
    return a.exec();
}