使用nvcc -c mag_cuda.cu编译以下代码时:
//Standard Libraries
#include <iostream>
#include <math.h>
#include <vector>
//Project Specific Header
#include "mag.hpp"
__global__
void indv_B_components(int *self_coords, int pole_coords[][3], double *indv_B[][3], int No_poles, int counter_1)
{
some code......
}
//----------------------------------------------------------
//------- Function to Calculate B Field at Each Pole -------
//----------------------------------------------------------
void calc_indv_B()
{
//declare namepspace for internal variables
using namespace mag::internal;
int *ppole_coords = &pole_coords[0][0];
double *pindv_B;
int self_coords[3];
int num_threads_in_block = 256;
int num_blocks = 32*2;
cudaMallocManaged(&pindv_B, No_poles*3*sizeof(int));
//first loop to go over all poles
for(int counter_1 = 0; counter_1 < No_poles; counter_1++)
{
//store coords of the current pole
self_coords[0] = pole_coords[counter_1][0];
self_coords[1] = pole_coords[counter_1][1];
self_coords[2] = pole_coords[counter_1][2];
indv_B_components<<<num_blocks, num_threads_in_block>>>(self_coords, ppole_coords, pindv_B, No_poles, counter_1);
cudaDeviceSynchronize();
}
cudaFree(pindv_B);
//return from function
return;
}
返回以下错误:
错误:无法配置主机函数调用
指的是那一行
indv_B_components<<<num_blocks, num_threads_in_block>>>(self_coords, ppole_coords, pindv_B, No_poles, counter_1);
由于所有参数都已定义并且内核已将主机设备调用的声明为__global__
,所以我不知道是什么原因造成的。
头文件mag.hpp为:
//make sure MAG_H_ module hasnt been defined multiple times
#ifndef MAG_H_
#define MAG_H_
//standard libraries
#include <iostream>
#include <math.h>
#include <vector>
//Namespace for module
namespace mag
{
//define functions
...
void indv_B_components(int *self_coords, int *pole_coords, double *indv_B, int No_poles, int counter_1);
void calc_indv_B();
...
}
#endif //MAG_H_
有帮助吗?
答案 0 :(得分:4)
发生此错误的一种情况是,如果您在调用内核时仅对内核函数进行了“声明”而没有__global__
指示符,例如:
void kernel();
void f()
{
kernel<<<1, 1>>>();
}
__global__
void kernel()
{
}
内核函数的声明必须包含__global__
说明符:
__global__ void kernel();
否则,声明不声明内核函数,而只是声明普通的宿主函数,这就是为什么编译器随后抱怨只能在GPU上启动内核函数的原因……