在过去的两周里，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。我使用的是 Windows XP 64 位。我已确认 VSE 能够以 64 位进行编译，因为我使用以下网站上的步骤提供了所有可用的 64 位选项：（因为 Visual Express 本身并不包含 64 位软件包）
http://jenshuebel.wordpress.com/2009/02/12/visual-c-2008-express-edition-and-64-bit-targets/ 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”可以从“工具->选项->VC++目录”下的下拉菜单中获得，并且在64位中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。
这是我尝试以 64 位进行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 ==========
这是我尝试在 64 位中编译/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;
}
