Wrapper function for cudaMalloc and cudaMemcpy - c++

Question

I was sick of looking at all the boilerplate cuda code for copying data to the device so I wrote this wrapper function:
void allocateAndCopyToDevice(void* device_array, const void* host_array, const size_t &count)
{
gpuErrchk(cudaMalloc((void**)&device_array, count));
gpuErrchk(cudaMemcpy(device_array, host_array, count, cudaMemcpyHostToDevice));
}
but for some reason this resulted in an out of bounds memory access whenever using an array initialized in this way. The initialization code that I used looked like this:
cuDoubleComplex *d_cmplx;
allocateAndCopyToDevice(d_cmplx,cmplx,size*sizeof(cuDoubleComplex));
Could anyone explain why this doesn't work?
After seeing immibis's comment I realized that cudaMalloc expects a pointer to a pointer, so instead I'm passing by value the pointer to the pointer:
void allocateAndCopyToDevice(void** device_array, const void* host_array, const size_t &count)
{
gpuErrchk(cudaMalloc(device_array, count));
gpuErrchk(cudaMemcpy(*device_array, host_array, count, cudaMemcpyHostToDevice));
}
and the initialization now looks like this:
cuDoubleComplex *d_cmplx;
allocateAndCopyToDevice((void **)&d_cmplx,cmplx,size*sizeof(cuDoubleComplex));
It works, but I'm still wondering if there is a better way of doing this? How do other people handle memory transfers in cuda code?

Answer 1

I would do something like
template <typename T>
T* allocateAndCopyToDevice(const T* host_array, std::size_t count)
{
// some static_assert for allowed types: pod and built-in.
T* device_array = nullptr;
gpuErrchk(cudaMalloc(&device_array, count * sizeof(T)));
gpuErrchk(cudaMemcpy(device_array, host_array, count * sizeof(T), cudaMemcpyHostToDevice));
return device_array;
}
and use it:
cuDoubleComplex *d_cmplx = allocateAndCopyToDevice(cmplx, size);