我有一些简单的cuda代码，我正在使用nvcc编译到一个静态库，还有一些用户代码，我正在使用g++编译，并链接到以前编译的静态库。 当尝试链接时，即使在nvcccompile命令行中使用-cudart static选项，也会遇到类似cudamalloc的链接器错误。

下面是我的代码:

//kern.hpp
#include <cstddef>

class Kern
{
    private:
        float* d_data;
        size_t size;

    public:
        Kern(size_t s);
        ~Kern();
        void set_data(float *d); 
};

//kern.cu
#include <iostream>
#include <kern.hpp>

__global__ void kern(float* data, size_t size)
{
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if(idx < size) 
    {
        data[idx] = 0;
    }
} 

Kern::Kern(size_t s) : size(s)
{
    cudaMalloc((void**)&d_data, size*sizeof(float));
}

Kern::~Kern()
{
    cudaFree(d_data);
}

void Kern::set_data(float* d)
{
    size_t grid_size = size;
    std::cout << "Starting kernel with grid size " << grid_size << " and block size " << 1 <<
        std::endl;
    kern<<<grid_size, 1>>>(d_data, size);
    cudaError_t err = cudaGetLastError();
    if(err != cudaSuccess)
        std::cout << "ERROR: " << cudaGetErrorString(err) << std::endl;
    cudaDeviceSynchronize();
    cudaMemcpy((void*)d, (void*)d_data, size*sizeof(float), cudaMemcpyDeviceToHost);
    cudaDeviceSynchronize();
}

//main.cpp
#include <iostream>
#include <kern.hpp>

int main(int argc, char** argv)
{
    std::cout << "starting" << std::endl;
    Kern k(256);
    float arr[256];
    k.set_data(arr);
    bool ok = true;
    for(int i = 0; i < 256; ++i) ok &= arr[i] == 0;
    std::cout << (ok ? "done" : "wrong") << std::endl;
}

我正在用nvcc编译kern，如下所示:

nvcc -I ./ -lib --compiler-options '-fPIC' -o libkern.a kern.cu -cudart static

然后使用g++进行main，如下所示:

g++ -o main main.cpp -I ./ -L. -L/opt/cuda/lib64 -lkern

这会产生以下错误:

/usr/bin/ld: ./libkern.a(tmpxft_00001d30_00000000-8_kern.o): in function `Kern::Kern(unsigned long)':
tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x4d): undefined reference to `cudaMalloc'
/usr/bin/ld: ./libkern.a(tmpxft_00001d30_00000000-8_kern.o): in function `Kern::~Kern()':
tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x6b): undefined reference to `cudaFree'
/usr/bin/ld: ./libkern.a(tmpxft_00001d30_00000000-8_kern.o): in function `Kern::set_data(float*)':
tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x152): undefined reference to `__cudaPushCallConfiguration'
/usr/bin/ld: tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x175): undefined reference to `cudaGetLastError'
/usr/bin/ld: tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x1a1): undefined reference to `cudaGetErrorString'
/usr/bin/ld: tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x1c6): undefined reference to `cudaDeviceSynchronize'
/usr/bin/ld: tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x1ee): undefined reference to `cudaMemcpy'
/usr/bin/ld: tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x1f3): undefined reference to `cudaDeviceSynchronize'
/usr/bin/ld: ./libkern.a(tmpxft_00001d30_00000000-8_kern.o): in function `__cudaUnregisterBinaryUtil()':
tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x24e): undefined reference to `__cudaUnregisterFatBinary'
/usr/bin/ld: ./libkern.a(tmpxft_00001d30_00000000-8_kern.o): in function `__nv_init_managed_rt_with_module(void**)':
tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x269): undefined reference to `__cudaInitModule'
/usr/bin/ld: ./libkern.a(tmpxft_00001d30_00000000-8_kern.o): in function `__device_stub__Z4kernPfm(float*, unsigned long)':
tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x305): undefined reference to `__cudaPopCallConfiguration'
/usr/bin/ld: ./libkern.a(tmpxft_00001d30_00000000-8_kern.o): in function `__nv_cudaEntityRegisterCallback(void**)':
tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x430): undefined reference to `__cudaRegisterFunction'
/usr/bin/ld: ./libkern.a(tmpxft_00001d30_00000000-8_kern.o): in function `__sti____cudaRegisterAll()':
tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x44b): undefined reference to `__cudaRegisterFatBinary'
/usr/bin/ld: tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x47c): undefined reference to `__cudaRegisterFatBinaryEnd'
/usr/bin/ld: ./libkern.a(tmpxft_00001d30_00000000-8_kern.o): in function `cudaError cudaLaunchKernel<char>(char const*, dim3, dim3, void**, unsigned long, CUstream_st*)':
tmpxft_00001d30_00000000-5_kern.cudafe1.cpp:(.text+0x4d9): undefined reference to `cudaLaunchKernel'
collect2: error: ld returned 1 exit status

但如果我做了以下事情:

g++ -o main main.cpp -I ./ -L. -L/opt/cuda/lib64 -lkern -lcudart

一切正常。 我的问题是，既然在nvcc编译行中有一个-cudart static，那么libkern.a不应该已经解析了cuda运行时的符号吗？ 为什么g++行中仍然需要-lcudart？

另外，如果我将libkern.a更改为一个共享对象，则在g++行中不链接到cuda运行时是可行的。 即以下作品:

nvcc -I ./ -shared --compiler-options '-fPIC' -o libkern.so kern.cu -cudart static
g++ -o main main.cpp -I ./ -L. -L/opt/cuda/lib64 -lkern

为什么静态库版本失败，但共享对象版本工作？

请注意，我在nvcc行中用-lcudart_statice替换了-cudart statice之后尝试了上述场景，进行该替换后的行为没有发生变化。 这是意料之中的事情，因为这两种选择基本上都是一样的，对吧？

我在Linux上。

nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Wed_Oct_23_19:24:38_PDT_2019
Cuda compilation tools, release 10.2, V10.2.89

g++ --version
g++ (GCC) 10.1.0
Copyright (C) 2020 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

非常感谢任何帮助和/或澄清。