Last active
December 30, 2021 22:02
-
-
Save bwedding/b6912e886c811e2ecf319c4ffa4aa7be to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <chrono> | |
#include <algorithm> | |
#include <functional> | |
#include <iostream> | |
#include <random> | |
#include <string> | |
// Return time in seconds as a double. | |
static std::chrono::high_resolution_clock::time_point GetTime(void) | |
{ | |
//double seconds; | |
std::chrono::high_resolution_clock::time_point h_start; | |
h_start = std::chrono::high_resolution_clock::now(); | |
return h_start; | |
} | |
/* Return the length of the null-terminated string STR. Scan for | |
the null terminator quickly by testing four bytes at a time. */ | |
size_t strlenopt(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 == '\0') | |
return char_ptr - str; | |
/* All these elucidatory comments refer to 4-byte longwords, | |
but the theory applies equally well to 8-byte longwords. */ | |
longword_ptr = (unsigned long int *) char_ptr; | |
/* Bits 31, 24, 16, and 8 of this number are zero. Call these bits | |
the "holes." Note that there is a hole just to the left of | |
each byte, with an extra at the end: | |
bits: 01111110 11111110 11111110 11111111 | |
bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD | |
The 1-bits make sure that carries propagate to the next 0-bit. | |
The 0-bits provide holes for carries to fall into. */ | |
himagic = 0x80808080L; | |
lomagic = 0x01010101L; | |
if (sizeof(longword) > 4) | |
{ | |
/* 64-bit version of the magic. */ | |
/* Do the shift in two steps to avoid a warning if long has 32 bits. */ | |
himagic = ((himagic << 16) << 16) | himagic; | |
lomagic = ((lomagic << 16) << 16) | lomagic; | |
} | |
if (sizeof(longword) > 8) | |
abort(); | |
/* Instead of the traditional loop which tests each character, | |
we will test a longword at a time. The tricky part is testing | |
if *any of the four* bytes in the longword in question are zero. */ | |
for (;;) | |
{ | |
longword = *longword_ptr++; | |
if (((longword - lomagic) & ~longword & himagic) != 0) | |
{ | |
/* Which of the bytes was the zero? If none of them were, it was | |
a misfire; continue the search. */ | |
const char *cp = (const char *)(longword_ptr - 1); | |
if (cp[0] == 0) | |
return cp - str; | |
if (cp[1] == 0) | |
return cp - str + 1; | |
if (cp[2] == 0) | |
return cp - str + 2; | |
if (cp[3] == 0) | |
return cp - str + 3; | |
if (sizeof(longword) > 4) | |
{ | |
if (cp[4] == 0) | |
return cp - str + 4; | |
if (cp[5] == 0) | |
return cp - str + 5; | |
if (cp[6] == 0) | |
return cp - str + 6; | |
if (cp[7] == 0) | |
return cp - str + 7; | |
} | |
} | |
} | |
} | |
size_t strlenHw(const char *str) | |
{ | |
const char *p; | |
if (str == NULL) | |
return 0; | |
p = str; | |
while (*p != '\0') | |
p++; | |
return p - str; | |
} | |
std::string randString(int len) | |
{ | |
std::mt19937_64 gen{ std::random_device{}() }; | |
std::uniform_int_distribution<short> dist{ 'a', 'z' }; | |
const unsigned length = len + dist(gen); | |
//std::cout << "Generated string of len " << length << std::endl; | |
std::string str(length, '\0'); | |
for (auto& c : str) | |
c = dist(gen); | |
return str; | |
} | |
int main() | |
{ | |
std::string t; | |
std::chrono::duration<double> tot_cpp_time; | |
auto start_cpp = GetTime(); | |
for (int i = 0; i < 10; i++) | |
{ | |
t = randString(0xfffffff); | |
strlenopt(t.c_str()); | |
} | |
auto stop_cpp = GetTime(); | |
tot_cpp_time = std::chrono::duration_cast<std::chrono::duration<double>>(stop_cpp - start_cpp); | |
std::cout << "GLib Optimized:\t\t\t\t\t\t" << tot_cpp_time.count() << " Seconds\n"; | |
start_cpp = GetTime(); | |
for (int i = 0; i < 10; i++) | |
{ | |
t = randString(0xfffffff); | |
strlenHw(t.c_str()); | |
} | |
stop_cpp = GetTime(); | |
tot_cpp_time = std::chrono::duration_cast<std::chrono::duration<double>>(stop_cpp - start_cpp); | |
std::cout << "Simple Implementation Hand Written:\t\t\t" << tot_cpp_time.count() << " Seconds\n"; | |
start_cpp = GetTime(); | |
for (int i = 0; i < 10; i++) | |
{ | |
t = randString(0xfffffff); | |
strlen(t.c_str()); | |
} | |
stop_cpp = GetTime(); | |
tot_cpp_time = std::chrono::duration_cast<std::chrono::duration<double>>(stop_cpp - start_cpp); | |
std::cout << "Built-In strlen:\t\t\t\t\t" << tot_cpp_time.count() << " Seconds\n"; | |
start_cpp = GetTime(); | |
for (int i = 0; i < 1000; i++) | |
{ | |
t = randString(0xff); | |
strlenopt(t.c_str()); | |
} | |
stop_cpp = GetTime(); | |
tot_cpp_time = std::chrono::duration_cast<std::chrono::duration<double>>(stop_cpp - start_cpp); | |
std::cout << "Short String GLib Optimized:\t\t\t\t" << tot_cpp_time.count() << " Seconds\n"; | |
start_cpp = GetTime(); | |
for (int i = 0; i < 1000; i++) | |
{ | |
t = randString(0xff); | |
strlenHw(t.c_str()); | |
} | |
stop_cpp = GetTime(); | |
tot_cpp_time = std::chrono::duration_cast<std::chrono::duration<double>>(stop_cpp - start_cpp); | |
std::cout << "Short String Simple Implementation Hand Written:\t" << tot_cpp_time.count() << " Seconds\n"; | |
start_cpp = GetTime(); | |
for (int i = 0; i < 1000; i++) | |
{ | |
t = randString(0xff); | |
strlen(t.c_str()); | |
} | |
stop_cpp = GetTime(); | |
tot_cpp_time = std::chrono::duration_cast<std::chrono::duration<double>>(stop_cpp - start_cpp); | |
std::cout << "Short String Built-In strlen:\t\t\t\t" << tot_cpp_time.count() << " Seconds\n"; | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment