我正在使用clang编译以下代码： clang++ -std=c++11 -emit-llvm -c -S $1 --cuda-gpu-arch=sm_30。这将生成vectoradd-cuda-nvptx64-nvidia-cuda-sm_30.ll和vectoradd.ll文件。运行某些LLVM分析的目标是传递给内核，这可能会对它进行检测。所以我想将分析后的IR链接到可执行文件，但是我不确定如何执行。当我尝试将.ll文件与llvm-link链接时，出现错误Linking globals named '_Z9vectoraddPiS_S_i': symbol multiply defined!。我不太确定如何实现此目标，因此不胜感激。

#define THREADS_PER_BLOCK 512

__global__ void vectoradd(int *A,int *B,int *C,int N) {
  int gi = threadIdx.x + blockIdx.x * blockDim.x;
  if ( gi < N) {
    C[gi] = A[gi] + B[gi];
  }
}

int main(int argc,char **argv) {
  int N = 10000,*d_A,*d_B,*d_C;

  /// allocate host memory
  std::vector<int> A(N);
  std::vector<int> B(N);
  std::vector<int> C(N);

  /// allocate device memory
  cudaMalloc((void **) &d_A,N * sizeof(int));
  cudaMalloc((void **) &d_B,N * sizeof(int));
  cudaMalloc((void **) &d_C,N * sizeof(int));

  /// populate host data
  for ( size_t i = 0; i < N; ++i) {
    A[i] = i; B[i] = i;
  }

  /// copy to device
  cudaMemcpy(d_A,&A[0],N * sizeof(int),cudaMemcpyHostToDevice);
  cudaMemcpy(d_B,&B[0],cudaMemcpyHostToDevice);

  dim3 block(THREADS_PER_BLOCK,1,1);
  dim3 grid((N + THREADS_PER_BLOCK - 1) / THREADS_PER_BLOCK,1);

  vectoradd<<<grid,block>>>(d_A,d_B,d_C,N);
  cudaDeviceSynchronize();

  cudaMemcpy(&C[0],cudaMemcpyDeviceToHost);

  return 0;
}