有什么方法可以调用CUDA运行时函数调用,例如
cudaMemcpy(...);
在.cpp文件中,使用常规C ++编译器编译?
答案 0 :(得分:17)
来电者C(但可能是C ++)
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <cuda.h>
extern void kernel_wrapper(int *a, int *b);
int main(int argc, char *argv[])
{
int a = 2;
int b = 3;
kernel_wrapper(&a, &b);
return 0;
}
被叫者(CUDA)
__global__ void kernel(int *a, int *b)
{
int tx = threadIdx.x;
switch( tx )
{
case 0:
*a = *a + 10;
break;
case 1:
*b = *b + 3;
break;
default:
break;
}
}
void kernel_wrapper(int *a, int *b)
{
int *d_1, *d_2;
dim3 threads( 2, 1 );
dim3 blocks( 1, 1 );
cudaMalloc( (void **)&d_1, sizeof(int) );
cudaMalloc( (void **)&d_2, sizeof(int) );
cudaMemcpy( d_1, a, sizeof(int), cudaMemcpyHostToDevice );
cudaMemcpy( d_2, b, sizeof(int), cudaMemcpyHostToDevice );
kernel<<< blocks, threads >>>( a, b );
cudaMemcpy( a, d_1, sizeof(int), cudaMemcpyDeviceToHost );
cudaMemcpy( b, d_2, sizeof(int), cudaMemcpyDeviceToHost );
cudaFree(d_1);
cudaFree(d_2);
}
答案 1 :(得分:0)
您可以使用
g++ I/usr/local/cuda/include filename.cpp -o obj -L/usr/local/cuda/lib64 -lcudart
用于编译或
nvcc filename.cu