Java가 C보다 2배 이상 빠릅니다....

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
 
typedef signed char byte;
 
typedef struct _Array
{
	byte *data;
	int len;
}
Array;
 
void new_Array(Array *a, int len)
{
	a->data = (byte *)malloc(len * sizeof(byte));
	a->len = len;
}
 
void del_Array(Array *a)
{
	free(a->data);
}
 
typedef struct _BUI
{
	Array num;
	int len;
}
BUI[1];
 
void new_BUI(BUI b, const char *s)
{
	int len = strlen(s);
	b->len = len;
	new_Array(&b->num, len);
	for (int i = 0; i < len; ++i)
	{
		b->num.data[i] = s[len - i - 1] - '0';
	}
}
 
void del_BUI(BUI b)
{
	del_Array(&b->num);
}
 
int BUI_cmp(const BUI a, const BUI b)
{
	if (a->len > b->len)
	{
		return 1;
	}
	if (a->len < b->len)
	{
		return -1;
	}
	for (int i = a->len - 1; i >= 0; --i)
	{
		if (a->num.data[i] > b->num.data[i])
		{
			return 1;
		}
		if (a->num.data[i] < b->num.data[i])
		{
			return -1;
		}
	}
	return 0;
}
 
#define MAX(A, B) (A > B ? A : B)
 
void BUI_add(BUI r, const BUI a, const BUI b)
{
	Array c;
	new_Array(&c, MAX(a->len, b->len) + 1);
	memset(c.data, 0, c.len);
	memcpy(c.data, a->num.data, a->len);
	for (int i = 0; i < b->len; ++i)
	{
		c.data[i] += b->num.data[i];
	}
	for (int i = 0; i < c.len - 1; ++i)
	{
		if (c.data[i] >= 10)
		{
			c.data[i + 1] += c.data[i] / 10;
			c.data[i] %= 10;
		}
	}
	del_Array(&r->num);
	r->num = c;
	r->len = c.len;
	for (int i = r->num.len - 1; r->num.data[i--] == 0; --r->len);
}
 
void BUI_mul(BUI r, const BUI a, const BUI b)
{
	BUI c;
	new_BUI(c, "0");
	{
		BUI one;
		new_BUI(one, "1");
		BUI i;
		new_BUI(i, "0");
		for (; BUI_cmp(i, a) < 0; BUI_add(i, i, one))
		{
			BUI_add(c, c, b);
		}
		del_BUI(one);
		del_BUI(i);
	}
	del_Array(&r->num);
	r->num = c->num;
	r->len = c->len;
}
 
void BUI_print(BUI b)
{
	for (int i = b->len - 1; i >= 0; --i)
	{
		putchar(b->num.data[i] + '0');
	}
}
 
int main(void)
{
	BUI a;
	new_BUI(a, "123456789");
	BUI b;
	new_BUI(b, "987654321");
	BUI_print(a);
	fputs(" x ", stdout);
	BUI_print(b);
	fputs(" = ", stdout);
	time_t start_time = clock();
	BUI_mul(a, a, b);
	time_t end_time = clock();
	BUI_print(a);
	del_BUI(a);
	del_BUI(b);
	printf("\nelapsed time: %.3f\n", (double)(end_time - start_time) / CLOCKS_PER_SEC);
	printf("%u %u\n", a->num.len, a->len);
	return 0;
}

import java.util.*;
 
class BUI
{
	byte[] num;
	int len;
 
	BUI(String s)
	{
		len = s.length();
		num = new byte[len];
		for (int i = 0; i < len; ++i)
		{
			num[i] = (byte)Character.getNumericValue(s.charAt(len - i - 1));
		}
	}
 
	int cmp(BUI b)
	{
		if (len > b.len)
		{
			return 1;
		}
		if (len < b.len)
		{
			return -1;
		}
		for (int i = len - 1; i >= 0; --i)
		{
			if (num[i] > b.num[i])
			{
				return 1;
			}
			if (num[i] < b.num[i])
			{
				return -1;
			}
		}
		return 0;
	}
 
	void add(BUI a, BUI b)
	{
		byte[] c = new byte[Math.max(a.len, b.len) + 1];
		Arrays.fill(c, (byte)0);
		System.arraycopy(a.num, 0, c, 0, a.num.length);
		for (int i = 0; i < b.len; ++i)
		{
			c[i] += b.num[i];
		}
		for (int i = 0; i < c.length - 1; ++i)
		{
			if (c[i] >= 10)
			{
				c[i + 1] += c[i] / 10;
				c[i] %= 10;
			}
		}
		num = c;
		len = c.length;
		for (int i = num.length - 1; num[i--] == 0; --len);
	}
 
	void mul(BUI a, BUI b)
	{
		BUI c = new BUI("0");
		{
			BUI one = new BUI("1");
			BUI i = new BUI("0");
			for (; i.cmp(a) < 0; i.add(i, one))
			{
				c.add(c, b);
			}
		}
		num = c.num;
		len = c.len;
	}
 
	void print()
	{
		for (int i = len - 1; i >= 0; --i)
		{
			System.out.print(num[i]);
		}
	}
}
 
 
public class Test
{
	public static void main(String[] args)
	{
		BUI a = new BUI("123456789");
		BUI b = new BUI("987654321");
		a.print();
		System.out.print(" x ");
		b.print();
		System.out.print(" = ");
		long start_time = System.currentTimeMillis();
		a.mul(a, b);
		long end_time = System.currentTimeMillis();
		a.print();
		System.out.printf("\nelapsed time: %.3f\n", (end_time - start_time) / 1000.0);
	}
}