C++ CUDA.cu文件中发生多定义错误的原因_C++_Gcc_Cuda

C++ CUDA.cu文件中发生多定义错误的原因

c++ gcc cuda

C++ CUDA.cu文件中发生多定义错误的原因,c++,gcc,cuda,C++,Gcc,Cuda,我正在学习使用CUDA。我编写了两个.cu文件，一个包含主函数，另一个用作提供所有其他函数的库。但在编译这两个.cu文件时，我遇到了多个定义错误。我展示了一个玩具示例，如下所示： main.cu文件： #ifndef MAIN #define MAIN #include "book.h" #include <iostream> #include "lib.h" using namespace std; int main(int argc, char const *argv[])

我正在学习使用CUDA。我编写了两个

.cu

文件，一个包含主函数，另一个用作提供所有其他函数的库。但在编译这两个

.cu

文件时，我遇到了多个定义错误。我展示了一个玩具示例，如下所示：

main.cu

文件：

#ifndef MAIN
#define MAIN
#include "book.h"
#include <iostream>
#include "lib.h"

using namespace std;

int main(int argc, char const *argv[])
{
    HelloWorld();
    return 0;
}
#endif

#ifndef LIB
#define LIB

#include "book.h"
#include <iostream>
#include "lib.h"

using namespace std;

void HelloWorld(){
    cout <<"HelloWorld" << endl;
    return;
}
#endif

#ifndef LIB_H
#define LIB_H

#include <iostream>

using namespace std;

void HelloWorld();
#endif

#ifndef __BOOK_H__
#define __BOOK_H__
#include <stdio.h>

static void HandleError( cudaError_t err,
                         const char *file,
                         int line ) {
    if (err != cudaSuccess) {
        printf( "%s in %s at line %d\n", cudaGetErrorString( err ),
                file, line );
        exit( EXIT_FAILURE );
    }
}
#define HANDLE_ERROR( err ) (HandleError( err, __FILE__, __LINE__ ))


#define HANDLE_NULL( a ) {if (a == NULL) { \
                            printf( "Host memory failed in %s at line %d\n", \
                                    __FILE__, __LINE__ ); \
                            exit( EXIT_FAILURE );}}

template< typename T >
void swap( T& a, T& b ) {
    T t = a;
    a = b;
    b = t;
}


void* big_random_block( int size ) {
    unsigned char *data = (unsigned char*)malloc( size );
    HANDLE_NULL( data );
    for (int i=0; i<size; i++)
        data[i] = rand();

    return data;
}

int* big_random_block_int( int size ) {
    int *data = (int*)malloc( size * sizeof(int) );
    HANDLE_NULL( data );
    for (int i=0; i<size; i++)
        data[i] = rand();

    return data;
}


// a place for common kernels - starts here

__device__ unsigned char value( float n1, float n2, int hue ) {
    if (hue > 360)      hue -= 360;
    else if (hue < 0)   hue += 360;

    if (hue < 60)
        return (unsigned char)(255 * (n1 + (n2-n1)*hue/60));
    if (hue < 180)
        return (unsigned char)(255 * n2);
    if (hue < 240)
        return (unsigned char)(255 * (n1 + (n2-n1)*(240-hue)/60));
    return (unsigned char)(255 * n1);
}

__global__ void float_to_color( unsigned char *optr,
                              const float *outSrc ) {
    // map from threadIdx/BlockIdx to pixel position
    int x = threadIdx.x + blockIdx.x * blockDim.x;
    int y = threadIdx.y + blockIdx.y * blockDim.y;
    int offset = x + y * blockDim.x * gridDim.x;

    float l = outSrc[offset];
    float s = 1;
    int h = (180 + (int)(360.0f * outSrc[offset])) % 360;
    float m1, m2;

    if (l <= 0.5f)
        m2 = l * (1 + s);
    else
        m2 = l + s - l * s;
    m1 = 2 * l - m2;

    optr[offset*4 + 0] = value( m1, m2, h+120 );
    optr[offset*4 + 1] = value( m1, m2, h );
    optr[offset*4 + 2] = value( m1, m2, h -120 );
    optr[offset*4 + 3] = 255;
}

__global__ void float_to_color( uchar4 *optr,
                              const float *outSrc ) {
    // map from threadIdx/BlockIdx to pixel position
    int x = threadIdx.x + blockIdx.x * blockDim.x;
    int y = threadIdx.y + blockIdx.y * blockDim.y;
    int offset = x + y * blockDim.x * gridDim.x;

    float l = outSrc[offset];
    float s = 1;
    int h = (180 + (int)(360.0f * outSrc[offset])) % 360;
    float m1, m2;

    if (l <= 0.5f)
        m2 = l * (1 + s);
    else
        m2 = l + s - l * s;
    m1 = 2 * l - m2;

    optr[offset].x = value( m1, m2, h+120 );
    optr[offset].y = value( m1, m2, h );
    optr[offset].z = value( m1, m2, h -120 );
    optr[offset].w = 255;
}


#if _WIN32
    //Windows threads.
    #include <windows.h>

    typedef HANDLE CUTThread;
    typedef unsigned (WINAPI *CUT_THREADROUTINE)(void *);

    #define CUT_THREADPROC unsigned WINAPI
    #define  CUT_THREADEND return 0

#else
    //POSIX threads.
    #include <pthread.h>

    typedef pthread_t CUTThread;
    typedef void *(*CUT_THREADROUTINE)(void *);

    #define CUT_THREADPROC void
    #define  CUT_THREADEND
#endif

//Create thread.
CUTThread start_thread( CUT_THREADROUTINE, void *data );

//Wait for thread to finish.
void end_thread( CUTThread thread );

//Destroy thread.
void destroy_thread( CUTThread thread );

//Wait for multiple threads.
void wait_for_threads( const CUTThread *threads, int num );

#if _WIN32
    //Create thread
    CUTThread start_thread(CUT_THREADROUTINE func, void *data){
        return CreateThread(NULL, 0, (LPTHREAD_START_ROUTINE)func, data, 0, NULL);
    }

    //Wait for thread to finish
    void end_thread(CUTThread thread){
        WaitForSingleObject(thread, INFINITE);
        CloseHandle(thread);
    }

    //Destroy thread
    void destroy_thread( CUTThread thread ){
        TerminateThread(thread, 0);
        CloseHandle(thread);
    }

    //Wait for multiple threads
    void wait_for_threads(const CUTThread * threads, int num){
        WaitForMultipleObjects(num, threads, true, INFINITE);

        for(int i = 0; i < num; i++)
            CloseHandle(threads[i]);
    }

#else
    //Create thread
    CUTThread start_thread(CUT_THREADROUTINE func, void * data){
        pthread_t thread;
        pthread_create(&thread, NULL, func, data);
        return thread;
    }

    //Wait for thread to finish
    void end_thread(CUTThread thread){
        pthread_join(thread, NULL);
    }

    //Destroy thread
    void destroy_thread( CUTThread thread ){
        pthread_cancel(thread);
    }

    //Wait for multiple threads
    void wait_for_threads(const CUTThread * threads, int num){
        for(int i = 0; i < num; i++)
            end_thread( threads[i] );
    }

#endif
#endif  // __BOOK_H__

lib.h

文件：

#ifndef MAIN
#define MAIN
#include "book.h"
#include <iostream>
#include "lib.h"

using namespace std;

int main(int argc, char const *argv[])
{
    HelloWorld();
    return 0;
}
#endif

#ifndef LIB
#define LIB

#include "book.h"
#include <iostream>
#include "lib.h"

using namespace std;

void HelloWorld(){
    cout <<"HelloWorld" << endl;
    return;
}
#endif

#ifndef LIB_H
#define LIB_H

#include <iostream>

using namespace std;

void HelloWorld();
#endif

#ifndef __BOOK_H__
#define __BOOK_H__
#include <stdio.h>

static void HandleError( cudaError_t err,
                         const char *file,
                         int line ) {
    if (err != cudaSuccess) {
        printf( "%s in %s at line %d\n", cudaGetErrorString( err ),
                file, line );
        exit( EXIT_FAILURE );
    }
}
#define HANDLE_ERROR( err ) (HandleError( err, __FILE__, __LINE__ ))


#define HANDLE_NULL( a ) {if (a == NULL) { \
                            printf( "Host memory failed in %s at line %d\n", \
                                    __FILE__, __LINE__ ); \
                            exit( EXIT_FAILURE );}}

template< typename T >
void swap( T& a, T& b ) {
    T t = a;
    a = b;
    b = t;
}


void* big_random_block( int size ) {
    unsigned char *data = (unsigned char*)malloc( size );
    HANDLE_NULL( data );
    for (int i=0; i<size; i++)
        data[i] = rand();

    return data;
}

int* big_random_block_int( int size ) {
    int *data = (int*)malloc( size * sizeof(int) );
    HANDLE_NULL( data );
    for (int i=0; i<size; i++)
        data[i] = rand();

    return data;
}


// a place for common kernels - starts here

__device__ unsigned char value( float n1, float n2, int hue ) {
    if (hue > 360)      hue -= 360;
    else if (hue < 0)   hue += 360;

    if (hue < 60)
        return (unsigned char)(255 * (n1 + (n2-n1)*hue/60));
    if (hue < 180)
        return (unsigned char)(255 * n2);
    if (hue < 240)
        return (unsigned char)(255 * (n1 + (n2-n1)*(240-hue)/60));
    return (unsigned char)(255 * n1);
}

__global__ void float_to_color( unsigned char *optr,
                              const float *outSrc ) {
    // map from threadIdx/BlockIdx to pixel position
    int x = threadIdx.x + blockIdx.x * blockDim.x;
    int y = threadIdx.y + blockIdx.y * blockDim.y;
    int offset = x + y * blockDim.x * gridDim.x;

    float l = outSrc[offset];
    float s = 1;
    int h = (180 + (int)(360.0f * outSrc[offset])) % 360;
    float m1, m2;

    if (l <= 0.5f)
        m2 = l * (1 + s);
    else
        m2 = l + s - l * s;
    m1 = 2 * l - m2;

    optr[offset*4 + 0] = value( m1, m2, h+120 );
    optr[offset*4 + 1] = value( m1, m2, h );
    optr[offset*4 + 2] = value( m1, m2, h -120 );
    optr[offset*4 + 3] = 255;
}

__global__ void float_to_color( uchar4 *optr,
                              const float *outSrc ) {
    // map from threadIdx/BlockIdx to pixel position
    int x = threadIdx.x + blockIdx.x * blockDim.x;
    int y = threadIdx.y + blockIdx.y * blockDim.y;
    int offset = x + y * blockDim.x * gridDim.x;

    float l = outSrc[offset];
    float s = 1;
    int h = (180 + (int)(360.0f * outSrc[offset])) % 360;
    float m1, m2;

    if (l <= 0.5f)
        m2 = l * (1 + s);
    else
        m2 = l + s - l * s;
    m1 = 2 * l - m2;

    optr[offset].x = value( m1, m2, h+120 );
    optr[offset].y = value( m1, m2, h );
    optr[offset].z = value( m1, m2, h -120 );
    optr[offset].w = 255;
}


#if _WIN32
    //Windows threads.
    #include <windows.h>

    typedef HANDLE CUTThread;
    typedef unsigned (WINAPI *CUT_THREADROUTINE)(void *);

    #define CUT_THREADPROC unsigned WINAPI
    #define  CUT_THREADEND return 0

#else
    //POSIX threads.
    #include <pthread.h>

    typedef pthread_t CUTThread;
    typedef void *(*CUT_THREADROUTINE)(void *);

    #define CUT_THREADPROC void
    #define  CUT_THREADEND
#endif

//Create thread.
CUTThread start_thread( CUT_THREADROUTINE, void *data );

//Wait for thread to finish.
void end_thread( CUTThread thread );

//Destroy thread.
void destroy_thread( CUTThread thread );

//Wait for multiple threads.
void wait_for_threads( const CUTThread *threads, int num );

#if _WIN32
    //Create thread
    CUTThread start_thread(CUT_THREADROUTINE func, void *data){
        return CreateThread(NULL, 0, (LPTHREAD_START_ROUTINE)func, data, 0, NULL);
    }

    //Wait for thread to finish
    void end_thread(CUTThread thread){
        WaitForSingleObject(thread, INFINITE);
        CloseHandle(thread);
    }

    //Destroy thread
    void destroy_thread( CUTThread thread ){
        TerminateThread(thread, 0);
        CloseHandle(thread);
    }

    //Wait for multiple threads
    void wait_for_threads(const CUTThread * threads, int num){
        WaitForMultipleObjects(num, threads, true, INFINITE);

        for(int i = 0; i < num; i++)
            CloseHandle(threads[i]);
    }

#else
    //Create thread
    CUTThread start_thread(CUT_THREADROUTINE func, void * data){
        pthread_t thread;
        pthread_create(&thread, NULL, func, data);
        return thread;
    }

    //Wait for thread to finish
    void end_thread(CUTThread thread){
        pthread_join(thread, NULL);
    }

    //Destroy thread
    void destroy_thread( CUTThread thread ){
        pthread_cancel(thread);
    }

    //Wait for multiple threads
    void wait_for_threads(const CUTThread * threads, int num){
        for(int i = 0; i < num; i++)
            end_thread( threads[i] );
    }

#endif
#endif  // __BOOK_H__

我使用以下命令编译文件：

nvcc *.cu -O3 -o a.out -lm -ccbin=/usr/bin/g++

然后我得到了错误消息，如

浮点到颜色的多重定义（uchar4*，float const*）”

否则，如果我对

book.h

中的一个include进行注释，编译将成功，程序将正确运行。我发现一个可能的原因是gcc的版本，所以我尝试使用gcc-4.4和gcc-4.8，但在这两种情况下都会发生错误。我也尝试过使用g++，但它不能解决这个问题。我的代码怎么了？

谢谢大家帮助我

您有多个定义，因为函数位于头文件中。这意味着包含该文件的每个翻译单元都将具有该函数的副本

将其移动到实现文件和链接，或将函数标记为

inline

需要改进的其他事项：

永远不要在头文件中放置

using namespace

指令。这是一个严重的环境污染

宁愿选择std：：swap而不是自制的朴素的

swap

模板