#!/usr/bin/perl

# by bliako @ PerlMonks.org
# date: 01-Jul-2021
# see https://perlmonks.org/?node_id=11134582
# lame example for utilising GPGPU via Inline::C
# TODO: extend to taking params and returning back results

use strict;
use warnings;

use FindBin;

use Inline C => Config =>
	cc => $FindBin::Bin.'/nvcc-compile.pl',
	ld => $FindBin::Bin.'/nvcc-link.pl',
;

use Inline C => <<'EOC';
// from https://developer.nvidia.com/blog/easy-introduction-cuda-c-and-c/
#include <stdio.h>

__global__
void saxpy(int n, float a, float *x, float *y)
{
  int i = blockIdx.x*blockDim.x + threadIdx.x;
  if (i < n) y[i] = a*x[i] + y[i];
}

int main()
{
  int N = 1<<20;
  float *x, *y, *d_x, *d_y;
  x = (float*)malloc(N*sizeof(float));
  y = (float*)malloc(N*sizeof(float));

  cudaMalloc(&d_x, N*sizeof(float)); 
  cudaMalloc(&d_y, N*sizeof(float));

  for (int i = 0; i < N; i++) {
    x[i] = 1.0f;
    y[i] = 2.0f;
  }

  cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);
  cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);

  // Perform SAXPY on 1M elements
  saxpy<<<(N+255)/256, 256>>>(N, 2.0f, d_x, d_y);

  cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);

  float maxError = 0.0f;
  for (int i = 0; i < N; i++)
    maxError = max(maxError, abs(y[i]-4.0f));
  printf("Max error: %f\n", maxError);

  cudaFree(d_x);
  cudaFree(d_y);
  free(x);
  free(y);
  return 0; // << late edit!
}
EOC
main;