#include <stdbool.h>
#include <stddef.h>
#include <string.h>
#include <stdio.h>
#include <stdint.h>
#include <time.h>

#define BLCKSZ 8192
#define LOOPS 1000

static inline bool
allzeros_char(const void *ptr, size_t len)
{
	const char *p = (const char *) ptr;

	for (size_t i = 0; i < len; i++)
	{
		if (p[i] != 0)
			return false;
	}
	return true;
}

static inline bool
allzeros_size_t(const void *ptr, size_t len)
{
	const size_t *p = (const size_t *) ptr;

	for (size_t i = 0; i < len / sizeof(size_t); i++)
	{
		if (p[i] != 0)
			return false;
	}
	return true;
}

bool
pg_memory_is_all_zeros(const void *ptr, size_t len)
{
	const char *p = (const char *) ptr;
	const char *end = &p[len];
#ifdef RANIERS_OPTIMIZATION
	const char *aligned_end;
#else
	const char *aligned_end = (const char *) ((uintptr_t) end & (~(sizeof(size_t) - 1)));
#endif

	while (((uintptr_t) p & (sizeof(size_t) - 1)) != 0)
	{
		if (p == end)
			return true;

		if (*p++ != 0)
			return false;
	}

#ifdef RANIERS_OPTIMIZATION
	aligned_end = (const char *) ((uintptr_t) end & (~(sizeof(size_t) - 1)));
#endif
	for (; p < aligned_end; p += sizeof(size_t))
	{
		if (*(size_t *) p != 0)
			return false;
	}

	while (p < end)
	{
		if (*p++ != 0)
			return false;
	}

	return true;
}


#define NANOSEC_PER_SEC 1000000000

// Returns difference in nanoseconds
int64_t
get_clock_diff(struct timespec *t1, struct timespec *t2)
{
	int64_t nanosec = (t1->tv_sec - t2->tv_sec) * NANOSEC_PER_SEC;
	nanosec += (t1->tv_nsec - t2->tv_nsec);

	return nanosec;
}

int main()
{
	size_t pagebytes[BLCKSZ] = {0};
	volatile bool result;
	struct timespec start,end;
	int64_t char_time, size_t_time;

	clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &start);

	for (int i = 0; i < LOOPS; i++)
	{
		result = allzeros_char(pagebytes, BLCKSZ);
	}

	clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &end);
	char_time = get_clock_diff(&end, &start);
	printf("char: done in %ld nanoseconds\n", char_time);

#if TEST_PRE_ALIGNED_VERSION
	clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &start);

	for (int i = 0; i < LOOPS; i++)
	{
		result = allzeros_size_t(pagebytes, BLCKSZ);
	}

	clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &end);
	size_t_time = get_clock_diff(&end, &start);
	printf("size_t: done in %ld nanoseconds (%g times faster than char)\n", size_t_time, (double) char_time / size_t_time);
#endif

	clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &start);

	for (int i = 0; i < LOOPS; i++)
	{
		result = pg_memory_is_all_zeros(pagebytes, BLCKSZ);
	}

	clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &end);
	size_t_time = get_clock_diff(&end, &start);
	printf("size_t: done in %ld nanoseconds (%g times faster than char)\n", size_t_time, (double) char_time / size_t_time);

	return 0;
}