Passing dynamic array of structs to GPU kernel - c++

Question

I try to pass my dynamic array of structs to kernel but it doesn't works. I get - "Segmentation fault (core dumped)"
My code - EDITED
#include <stdio.h>
#include <stdlib.h>
struct Test {
unsigned char *array;
};
__global__ void kernel(Test *dev_test) {
}
int main(void) {
int n = 4;
int size = 5;
unsigned char *array[size];
Test *dev_test;
// allocate for host
Test *test = (Test*)malloc(sizeof(Test)*n);
for(int i = 0; i < n; i++)
test[i].array = (unsigned char*)malloc(size);
// fill data
for(int i=0; i<n; i++) {
unsigned char temp[] = { 'a', 'b', 'c', 'd' , 'e' };
memcpy(test[i].array, temp, size);
}
// allocate for gpu
cudaMalloc((void**)&dev_test, n * sizeof(Test));
for(int i=0; i < n; i++) {
cudaMalloc((void**)&(array[i]), size * sizeof(unsigned char));
cudaMemcpy(&(dev_test[i].array), &(array[i]), sizeof(unsigned char *), cudaMemcpyHostToDevice);
}
kernel<<<1, 1>>>(dev_test);
return 0;
}
How correctly I should allocate gpu memory and copy data to this memory?

Answer 1

You need to allocate memory for struct member array.
Test *test = malloc(sizeof(Test)*n);
for(int i = 0; i < n; i++)
test[i]->array = malloc(size);
I would suggest to read this answer to cope up with other issues after this fix.

Answer 2

what is your card ? if your card support compute capability >= 3.0, try the unified memory system , to have same data in host/device memory
you can have a look here :
it should maybe look like this one :
int main(void) {
int n = 4;
int size = 5;
Test *test;
cudaMallocManaged(&test, n * size);
unsigned char values[] = { 'a', 'b', 'c', 'd' , 'e' };
for(int i=0; i<n; i++)
{
unsigned char* temp;
cudaMallocManaged(&temp, size*sizeof(char) );
memcpy(temp, values, sizeof(values) );
}
// avoid copy code, makes a deep copy of objects
kernel<<<1, 1>>>(test);
return 0;
}
And i hope you know it, but Don't forget do call cudaFree & delete/free on allocated memory. (better to use std::vector and use data() to access to raw pointer)