刚接触CUDA,一个试手程序出了点问题,麻烦帮助。
刚接触CUDA,一个试手程序出了点问题,麻烦帮助。
#include "book.h"
#define N 10
int main(void){
int a[N],b[N],c[N];
int *dev_a,*dev_b,*dev_c;
//在GPU上分配内存
HANDLE_ERROR(cudaMalloc((void**)&dev_a,N * sizeof(int)));
HANDLE_ERROR(cudaMalloc((void**)&dev_b,N * sizeof(int)));
HANDLE_ERROR(cudaMalloc((void**)&dev_c,N * sizeof(int)));
//在CPU上为数组a,b赋值
for (int i=0;i<N;i++)
{
a[i]=-i;
b[i]=i*i;
}
//将数组a,b复制到GPU
HANDLE_ERROR(cudaMemcpy(dev_a,a,N * sizeof(int),cudaMemcpyHostToDevice));
HANDLE_ERROR(cudaMemcpy(dev_b,b,N * sizeof(int),cudaMemcpyHostToDevice));
add<<<N,1>>>(dev_a,dev_b,dev_c);
//将数组c从GPU复制到CPU
HANDLE_ERROR(cudaMemcpy(c,dev_c,N * sizeof(int),cudaMemcpyDeviceToHost));
//显示结果
for(int i=0;i<N;i++)
{
printf("%d+%d=%d\n",a[i],b[i],c[i]);
}
//释放在GPU上分配的内存
cudaFree(dev_a);
cudaFree(dev_b);
cudaFree(dev_c);
return 0;
}
__global__ void add(int *a,int *b,int *c)
{
int tid=blockIdx.x;//计算该索引处的数据
if(tid<N)
c[tid]=a[tid]+b[tid];
}
*********************************************************
1>------ 已启动生成: 项目: CUDAWinApp7, 配置: Debug Win32 ------
1>Compiling with CUDA Build Rule...
1>"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v4.0\\bin\nvcc.exe" -arch sm_10 -ccbin "C:\Program Files\Microsoft Visual Studio 9.0\VC\bin" -Xcompiler "/EHsc /W3 /nologo /Od /Zi /RTC1 /MTd " -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v4.0\\include" -I"C:\Documents and Settings\All Users\Application Data\NVIDIA Corporation\NVIDIA GPU Computing SDK 4.0\C\common\inc" -maxrregcount=32 --compile -o "Debug\CUDA1.cu.obj" "d:\test\CUDAWinApp7\CUDAWinApp7\CUDA1.cu"
1>CUDA1.cu
1>d:/test/CUDAWinApp7/CUDAWinApp7/CUDA1.cu(26): error: identifier "add" is undefined
1>1 error detected in the compilation of "C:/DOCUME~1/awd/LOCALS~1/Temp/tmpxft_000035f4_00000000-6_CUDA1.cpp1.ii".
1>Project : error PRJ0019: 某个工具从以下位置返回了错误代码: "Compiling with CUDA Build Rule..."
1>生成日志保存在“file://d:\test\CUDAWinApp7\CUDAWinApp7\Debug\BuildLog.htm”
1>CUDAWinApp7 - 2 个错误,0 个警告
========== 生成: 成功 0 个,失败 1 个,最新 0 个,跳过 0 个 ==========