在arm cpu下多字节拷贝的一个实现，4字节对其。比较快。

对于arm系列cpu，int 类型数据的读与写都需要4字节对其，要不然会崩溃滴。。。所以呢，不要把其它类型的数据强制转换成int类型。。

 

#include<sys/types.h>
#include<assert.h>
#include<stdlib.h>

void * arm_memcpy(void * dest,const void * src,size_t len)
{
  unsigned long int index = 0;
  unsigned long int div_len = (unsigned long)len/4;
  char mod_len = (unsigned long)len%4;
 
  assert((dest != NULL)&&(src != NULL));
 

  if (((unsigned long int)dest % 4 == 0) && ((unsigned long int)src % 4 == 0))
    {
        for (index=0; index < div_len; index++)
            {
                ((unsigned long int *)dest)[index] = ((unsigned long int *)src)[index];
            }
        if (mod_len != 0)
            {
                while ( mod_len-- > 0)
                    {
                       ((unsigned char *)dest)[index] = ((unsigned char *)src)[index];
                       index++;
                    }
            }
    }
  else
    {
        for(index=0; index < (unsigned long int)len; index++)
            {
                ((unsigned char *)dest)[index] = ((unsigned char *)src)[index];
            }
    }

  return dest;

}