关于strlen

strlen的实现是通过4个字节4个字节进行枚举，然后通过位运算来判断这4个字节中是否有一个字节含有0，这样的话，效率就提高了4倍。

这个效率提高是假设a&b&c&d与a&b有差不多效率的前提下。

那用8字节8字节来偏移的话，是不是更快呢？32位机上不会，64位机上会提高一倍。因为a&b在64位下会提高一倍，因为32位的寄存器大小是32位的，对于分别MOV高位与低位两次。

本来实验a&b&c&d与a&b的速度的，经实验验证，这两个效率确实是差不多的，然后去看汇编，看指令条数，在没有使用-O优化下，指令的条数差别跟运算符号的个数的倍数相同，就让我感到疑惑了。

下面附上实验的代码：

#include <iostream>
#include <time.h>
#include <cstdio>
#include <string>
using namespace std;

int _strlen(const char *str) {
    const unsigned int *p = (const unsigned int *) str;
    unsigned int low = 0x01010101;
    unsigned int high = 0x80808080;
    while (true) {
        unsigned int d = *p++;
        if (((d - low) & ~d & high) != 0) { // handle [0...256)
        //if (((d - low) & high) != 0) { // handle [0...128)
            break;
        }
    }
    const char *q = (const char *)(p - 1);
    for (int i = 0; i < (int)sizeof(unsigned int); i++) {
        if (q[i] == 0) {
            return q - str + i;
        }
    }
    return -1;
}

int _strlen2(const char *str) {
    const char *p = str;
    while (*p != 0) {
        p++;
    }
    return p - str;
}

int _strlen3(const char *str) {
    const unsigned long long *p = (const unsigned long long *) str;
    unsigned long long low = 0x0101010101010101;
    unsigned long long high = 0x8080808080808080;
    while (true) {
        unsigned long long d = *p++;
        if (((d - low) & ~d & high) != 0) { // handle [0...256)
        //if (((d - low) & high) != 0) { // handle [0...128)
            break;
        }
    }
    const char *q = (const char *)(p - 1);
    for (int i = 0; i < (int)sizeof(unsigned long long); i++) {
        if (q[i] == 0) {
            return q - str + i;
        }
    }
    return -1;
}

size_t _strlen4(const char *str) 
{
  const char *char_ptr;
  const unsigned long int *longword_ptr;
  unsigned long int longword, himagic, lomagic;

  /* Handle the first few characters by reading one character at a time.
     Do this until CHAR_PTR is aligned on a longword boundary.  */
  for (char_ptr = str; ((unsigned long int) char_ptr
            & (sizeof (longword) - 1)) != 0;
       ++char_ptr)
    if (*char_ptr == '

关于strlen

相关推荐