2 * Copyright (c) 2009 Xin LI <delphij@FreeBSD.org>
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
8 * 1. Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
17 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27 #include <sys/cdefs.h>
28 __FBSDID("$FreeBSD$");
30 #include <sys/limits.h>
31 #include <sys/types.h>
35 * Portable strlen() for 32-bit and 64-bit systems.
37 * Rationale: it is generally much more efficient to do word length
38 * operations and avoid branches on modern computer systems, as
39 * compared to byte-length operations with a lot of branches.
43 * ((x - 0x01....01) & ~x & 0x80....80)
45 * would evaluate to a non-zero value iff any of the bytes in the
46 * original word is zero. However, we can further reduce ~1/3 of
47 * time if we consider that strlen() usually operate on 7-bit ASCII
48 * by employing the following expression, which allows false positive
49 * when high bit of 1 and use the tail case to catch these case:
51 * ((x - 0x01....01) & 0x80....80)
53 * This is more than 5.2 times as compared to the raw implementation
54 * on Intel T7300 under EM64T mode for strings longer than word length.
57 /* Magic numbers for the algorithm */
59 static const unsigned long mask01 = 0x01010101;
60 static const unsigned long mask80 = 0x80808080;
62 static const unsigned long mask01 = 0x0101010101010101;
63 static const unsigned long mask80 = 0x8080808080808080;
65 #error Unsupported word size
68 #define LONGPTR_MASK (sizeof(long) - 1)
71 * Helper macro to return string length if we caught the zero
77 return (p - str + x); \
81 strlen(const char *str)
84 const unsigned long *lp;
86 /* Skip the first few bytes until we have an aligned p */
87 for (p = str; (uintptr_t)p & LONGPTR_MASK; p++)
91 /* Scan the rest of the string using word sized operation */
92 for (lp = (const unsigned long *)p; ; lp++)
93 if ((*lp - mask01) & mask80) {
94 p = (const char *)(lp);