How to separate CUDA code into multiple files

Question

I am trying separate a CUDA program into two separate .cu files in effort to edge closer to writing a real app in C++. I have a simple little program that:

Allocate

Answer 1

The simple solution is to turn off building of your MyKernel.cu file.

Properties -> General -> Excluded from build

The better solution imo is to split your kernel into a cu and a cuh file, and include that, for example:

//kernel.cu
#include "kernel.cuh"
#include 

__global__ void increment_by_one_kernel(int* vals) {
  vals[threadIdx.x] += 1;
}

void increment_by_one(int* a) {
  int* a_d;

  cudaMalloc(&a_d, 1);
  cudaMemcpy(a_d, a, 1, cudaMemcpyHostToDevice);
  increment_by_one_kernel<<<1, 1>>>(a_d);
  cudaMemcpy(a, a_d, 1, cudaMemcpyDeviceToHost);

  cudaFree(a_d);
}

 

//kernel.cuh
#pragma once

void increment_by_one(int* a);

 

//main.cpp
#include "kernel.cuh"

int main() {
  int a[] = {1};

  increment_by_one(a);

  return 0;
}