Speed up SSE4.2 strcasestr by avoiding indirect function call.
[glibc.git] / string / strlen.c
blob5f22ce95097d4090c6c32fc7cf6c2ef9cf6e86a8
1 /* Copyright (C) 1991,1993,1997,2000,2003,2009 Free Software Foundation, Inc.
2 This file is part of the GNU C Library.
3 Written by Torbjorn Granlund (tege@sics.se),
4 with help from Dan Sahlin (dan@sics.se);
5 commentary by Jim Blandy (jimb@ai.mit.edu).
7 The GNU C Library is free software; you can redistribute it and/or
8 modify it under the terms of the GNU Lesser General Public
9 License as published by the Free Software Foundation; either
10 version 2.1 of the License, or (at your option) any later version.
12 The GNU C Library is distributed in the hope that it will be useful,
13 but WITHOUT ANY WARRANTY; without even the implied warranty of
14 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15 Lesser General Public License for more details.
17 You should have received a copy of the GNU Lesser General Public
18 License along with the GNU C Library; if not, write to the Free
19 Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
20 02111-1307 USA. */
22 #include <string.h>
23 #include <stdlib.h>
25 #undef strlen
27 /* Return the length of the null-terminated string STR. Scan for
28 the null terminator quickly by testing four bytes at a time. */
29 size_t
30 strlen (str)
31 const char *str;
33 const char *char_ptr;
34 const unsigned long int *longword_ptr;
35 unsigned long int longword, himagic, lomagic;
37 /* Handle the first few characters by reading one character at a time.
38 Do this until CHAR_PTR is aligned on a longword boundary. */
39 for (char_ptr = str; ((unsigned long int) char_ptr
40 & (sizeof (longword) - 1)) != 0;
41 ++char_ptr)
42 if (*char_ptr == '\0')
43 return char_ptr - str;
45 /* All these elucidatory comments refer to 4-byte longwords,
46 but the theory applies equally well to 8-byte longwords. */
48 longword_ptr = (unsigned long int *) char_ptr;
50 /* Bits 31, 24, 16, and 8 of this number are zero. Call these bits
51 the "holes." Note that there is a hole just to the left of
52 each byte, with an extra at the end:
54 bits: 01111110 11111110 11111110 11111111
55 bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
57 The 1-bits make sure that carries propagate to the next 0-bit.
58 The 0-bits provide holes for carries to fall into. */
59 himagic = 0x80808080L;
60 lomagic = 0x01010101L;
61 if (sizeof (longword) > 4)
63 /* 64-bit version of the magic. */
64 /* Do the shift in two steps to avoid a warning if long has 32 bits. */
65 himagic = ((himagic << 16) << 16) | himagic;
66 lomagic = ((lomagic << 16) << 16) | lomagic;
68 if (sizeof (longword) > 8)
69 abort ();
71 /* Instead of the traditional loop which tests each character,
72 we will test a longword at a time. The tricky part is testing
73 if *any of the four* bytes in the longword in question are zero. */
74 for (;;)
76 longword = *longword_ptr++;
78 if (((longword - lomagic) & ~longword & himagic) != 0)
80 /* Which of the bytes was the zero? If none of them were, it was
81 a misfire; continue the search. */
83 const char *cp = (const char *) (longword_ptr - 1);
85 if (cp[0] == 0)
86 return cp - str;
87 if (cp[1] == 0)
88 return cp - str + 1;
89 if (cp[2] == 0)
90 return cp - str + 2;
91 if (cp[3] == 0)
92 return cp - str + 3;
93 if (sizeof (longword) > 4)
95 if (cp[4] == 0)
96 return cp - str + 4;
97 if (cp[5] == 0)
98 return cp - str + 5;
99 if (cp[6] == 0)
100 return cp - str + 6;
101 if (cp[7] == 0)
102 return cp - str + 7;
107 libc_hidden_builtin_def (strlen)