c++ - CUDA 链接错误 - Visual Express 2008 - 由于(空)配置文件导致 nvcc 致命

Question

在过去的 2 周里，我一直在广泛寻找可能的解决方案来解决我的错误。我已经成功安装了 Cuda 64 位编译器(工具)和 SDK，以及 64 位版本的 Visual Studio Express 2008 和带有 Framework 3.5 的 Windows 7 SDK。我正在使用 Windows XP 64 位。我已经确认 VSE 能够以 64 位编译，因为我使用以下网站上的步骤可以使用所有 64 位选项:(因为 Visual Express 本身不包含 64 位包)

http://jenshuebel.wordpress.com/2009/02/12/visual-c-2008-express-edition-and-64-bit-targets/

64 位安装的注册表更新可在与上述链接相同的页面上的用户评论中找到。

我已经确认了 64 位编译能力，因为“x64”可从“工具->选项->VC++ 目录”下的下拉菜单中获得，并且以 64 位编译不会导致整个项目被“跳过”。我已经包含了 64 位 cuda 工具、64 SDK 和 Visual Express (\VC\bin\amd64) 所需的所有目录。

这是我在尝试以 64 位编译时收到的错误消息:

1>------ Build started: Project: New, Configuration: Release x64 ------
1>Compiling with CUDA Build Rule...
1>"C:\CUDA\bin64\nvcc.exe"    -arch sm_10 -ccbin "C:\Program Files (x86)\Microsoft    Visual Studio 9.0\VC\bin"    -Xcompiler "/EHsc /W3 /nologo /O2 /Zi   /MT  "  -maxrregcount=32  --compile -o "x64\Release\template.cu.obj" "c:\Documents and Settings\All Users\Application Data\NVIDIA Corporation\NVIDIA GPU Computing SDK\C\src\CUDA_Walkthrough_DeviceKernels\template.cu" 
1>nvcc fatal   : Visual Studio configuration file '(null)' could not be found for installation at 'C:/Program Files (x86)/Microsoft Visual Studio 9.0/VC/bin/../..'
1>Linking...
1>LINK : fatal error LNK1181: cannot open input file '.\x64\Release\template.cu.obj'
1>Build log was saved at "file://c:\Documents and Settings\Administrator\My Documents\Visual Studio 2008\Projects\New\New\x64\Release\BuildLog.htm"
1>New - 1 error(s), 0 warning(s)
========== Build: 0 succeeded, 1 failed, 0 up-to-date, 0 skipped ==========

这是我试图以 64 位编译/运行的简单代码:

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>

#include <cuda.h>

void mypause () 
{ 
  printf ( "Press [Enter] to continue . . ." );
  fflush ( stdout );
  getchar();
} 

__global__ void VecAdd1_Kernel(float* A, float* B, float* C, int N)
{
 int i = blockDim.x*blockIdx.x+threadIdx.x;
 if (i<N)
  C[i] = A[i] + B[i]; //result should be a 16x1 array of 250s
} 

__global__ void VecAdd2_Kernel(float* B, float* C, int N)
{
 int i = blockDim.x*blockIdx.x+threadIdx.x;
 if (i<N)
  C[i] = C[i] + B[i]; //result should be a 16x1 array of 400s
}

int main()
{
 int N = 16;
 float A[16];float B[16];
 size_t size = N*sizeof(float);

 for(int i=0; i<N; i++) 
 {
  A[i] = 100.0;
  B[i] = 150.0;
 }

 // Allocate input vectors h_A and h_B in host memory
 float* h_A = (float*)malloc(size);
        float* h_B = (float*)malloc(size);
        float* h_C = (float*)malloc(size);

 //Initialize Input Vectors
 memset(h_A,0,size);memset(h_B,0,size);
 h_A = A;h_B = B;

 printf("SUM = %f\n",A[1]+B[1]); //simple check for initialization

 //Allocate vectors in device memory
 float* d_A;
 cudaMalloc((void**)&d_A,size);
 float* d_B;
 cudaMalloc((void**)&d_B,size);
 float* d_C;
 cudaMalloc((void**)&d_C,size);

 //Copy vectors from host memory to device memory
 cudaMemcpy(d_A,h_A,size,cudaMemcpyHostToDevice);
 cudaMemcpy(d_B,h_B,size,cudaMemcpyHostToDevice);

 //Invoke kernel
 int threadsPerBlock = 256;
 int blocksPerGrid = (N+threadsPerBlock-1)/threadsPerBlock;
 VecAdd1(blocksPerGrid, threadsPerBlock,d_A,d_B,d_C,N);
 VecAdd2(blocksPerGrid, threadsPerBlock,d_B,d_C,N);

 //Copy results from device memory to host memory
 //h_C contains the result in host memory
 cudaMemcpy(h_C,d_C,size,cudaMemcpyDeviceToHost);

 for(int i=0; i<N; i++) //output result from the kernel "VecAdd"
 {
  printf("%f ", h_C[i] );
  printf("\n");
 }
 printf("\n");

 cudaFree(d_A); 
 cudaFree(d_B); 
 cudaFree(d_C);
 free(h_A);
 free(h_B);
 free(h_C);

 mypause();
 return 0;
}

Answer 1

我解决了这个问题

1. 安装 Windows SDK(不要忘记为 64 位操作系统选择所有 x64 选项)
2. 在 PATH 中包含“c:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\bin\amd64”
3. 在目录“c:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\bin\amd64”中创建文件 vcvars64.bat，内容如下:调用 "C:\Program Files\Microsoft SDKs\Windows\v7.1\Bin\SetEnv.cmd"/x64

注意:我这样做是因为:

1. 我正在使用 VC++ Express 2010
2. 我在任何目录中都没有“vcvars64.bat”？？