Code:
Octree_t* tarr = (Octree*)malloc(nodes * sizeof(Octree_t));
//nodearray[2]->test = 42;
for (int i = 0; i < cnodes; i++)
{
tarr[i] = *nodearray[i];
}
//printf(" test: %d\n",tarr[2].test); //returns 42
cudaError_t err;
Octree_t* gpu_nodearray;
//allocate storage on gpu
err = cudaMalloc( &gpu_nodearray, cnodes * sizeof(Octree_t) != cudaSuccess );
if ( err != cudaSuccess)
{
printf("1: %s\n", cudaGetErrorString(err));
return;
}
err = cudaMemcpy(gpu_nodearray, tarr, cnodes * sizeof(Octree_t), cudaMemcpyHostToDevice);
if ( err != cudaSuccess)
{
printf("3: %s\n", cudaGetErrorString(err));
return;
}
It compiles fine but when I run it, it returns "3: invalid argument". So clearly something is wrong with the cudaMempy. I already looked at similar posts here and I can't find the mistake I made.
Thanks for any help.
The line
err = cudaMalloc( &gpu_nodearray, cnodes * sizeof(Octree_t) != cudaSuccess );
should be
err = cudaMalloc( &gpu_nodearray, cnodes * sizeof(Octree_t));
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.