/* Apply a large Gaussian-approximation kernel as a Hogenauer filter
 * for benchmarking purposes.  Handles one sample per 1.6 ns: 6.7
 * seconds for 1 million iterations of blurring 4096 samples with GCC
 * 4.7.2 -O3 on a Core i7-3840QM.
 */

#include <stdlib.h>
#include <stdio.h>

enum {lag = 256, image_size = 4096};

unsigned long buf[image_size] = {0};

int
main(int argc, char **argv)
{
  size_t n = atoi(argv[1]);
  buf[image_size/2] = 1;

  for (size_t j = 0; j < n; j++) {
    for (size_t i = 0; i < image_size - 3 * lag - 3; i++) {
      buf[i + 3 * lag + 2] += buf[i + 3 * lag + 1];
      buf[i + 3 * lag + 1] += buf[i + 3 * lag];
      buf[i + 3 * lag] += buf[i + 3 * lag - 1];
      buf[i + 2 * lag] -= buf[i + 3 * lag];
      buf[i + lag] -= buf[i + 2 * lag];
      buf[i] = buf[i + lag] - buf[i];
    }
  }

  for (size_t i = 0; i < image_size - 3 * lag - 3; i++) {
    if (i) printf((i%8) ? ", " : ",\n");
    printf("%6ld", buf[i]);
  }
  printf("\n");

  return 0;
}