memrchr.c 5.56 KB
Newer Older
1
/* memrchr -- find the last occurrence of a byte in a memory block
Paul Eggert's avatar
Paul Eggert committed
2

Paul Eggert's avatar
Paul Eggert committed
3
   Copyright (C) 1991, 1993, 1996-1997, 1999-2000, 2003-2016 Free Software
4
   Foundation, Inc.
Paul Eggert's avatar
Paul Eggert committed
5

6 7 8 9 10 11
   Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
   with help from Dan Sahlin (dan@sics.se) and
   commentary by Jim Blandy (jimb@ai.mit.edu);
   adaptation to memchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
   and implemented by Roland McGrath (roland@ai.mit.edu).

12
   This program is free software: you can redistribute it and/or modify
Paul Eggert's avatar
Paul Eggert committed
13
   it under the terms of the GNU General Public License as published by
14 15
   the Free Software Foundation; either version 3 of the License, or
   (at your option) any later version.
16

Paul Eggert's avatar
Paul Eggert committed
17
   This program is distributed in the hope that it will be useful,
18
   but WITHOUT ANY WARRANTY; without even the implied warranty of
Paul Eggert's avatar
Paul Eggert committed
19 20
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.
21

22 23
   You should have received a copy of the GNU General Public License
   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
24

Paul Eggert's avatar
Paul Eggert committed
25
#if defined _LIBC
26 27
# include <memcopy.h>
#else
28
# include <config.h>
29 30 31
# define reg_char char
#endif

32
#include <string.h>
Paul Eggert's avatar
Paul Eggert committed
33
#include <limits.h>
34 35

#undef __memrchr
36 37 38
#ifdef _LIBC
# undef memrchr
#endif
39 40 41 42 43 44

#ifndef weak_alias
# define __memrchr memrchr
#endif

/* Search no more than N bytes of S for C.  */
Paul Eggert's avatar
Paul Eggert committed
45 46
void *
__memrchr (void const *s, int c_in, size_t n)
47
{
Eric Blake's avatar
Eric Blake committed
48 49 50 51 52
  /* On 32-bit hardware, choosing longword to be a 32-bit unsigned
     long instead of a 64-bit uintmax_t tends to give better
     performance.  On 64-bit hardware, unsigned long is generally 64
     bits already.  Change this typedef to experiment with
     performance.  */
Eric Blake's avatar
Eric Blake committed
53
  typedef unsigned long int longword;
Eric Blake's avatar
Eric Blake committed
54

55
  const unsigned char *char_ptr;
Eric Blake's avatar
Eric Blake committed
56 57 58
  const longword *longword_ptr;
  longword repeated_one;
  longword repeated_c;
59 60 61 62
  unsigned reg_char c;

  c = (unsigned char) c_in;

Eric Blake's avatar
Eric Blake committed
63
  /* Handle the last few bytes by reading one byte at a time.
64 65
     Do this until CHAR_PTR is aligned on a longword boundary.  */
  for (char_ptr = (const unsigned char *) s + n;
Eric Blake's avatar
Eric Blake committed
66
       n > 0 && (size_t) char_ptr % sizeof (longword) != 0;
67 68
       --n)
    if (*--char_ptr == c)
Paul Eggert's avatar
Paul Eggert committed
69
      return (void *) char_ptr;
70

Eric Blake's avatar
Eric Blake committed
71 72
  longword_ptr = (const longword *) char_ptr;

73
  /* All these elucidatory comments refer to 4-byte longwords,
Paul Eggert's avatar
Paul Eggert committed
74
     but the theory applies equally well to any size longwords.  */
75

Eric Blake's avatar
Eric Blake committed
76 77 78 79 80 81
  /* Compute auxiliary longword values:
     repeated_one is a value which has a 1 in every byte.
     repeated_c has c in every byte.  */
  repeated_one = 0x01010101;
  repeated_c = c | (c << 8);
  repeated_c |= repeated_c << 16;
Eric Blake's avatar
Eric Blake committed
82
  if (0xffffffffU < (longword) -1)
83
    {
Eric Blake's avatar
Eric Blake committed
84 85 86
      repeated_one |= repeated_one << 31 << 1;
      repeated_c |= repeated_c << 31 << 1;
      if (8 < sizeof (longword))
87 88 89 90 91 92 93 94 95
        {
          size_t i;

          for (i = 64; i < sizeof (longword) * 8; i *= 2)
            {
              repeated_one |= repeated_one << i;
              repeated_c |= repeated_c << i;
            }
        }
Eric Blake's avatar
Eric Blake committed
96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131
    }

  /* Instead of the traditional loop which tests each byte, 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 equal to c.  We first use an xor
     with repeated_c.  This reduces the task to testing whether *any of the
     four* bytes in longword1 is zero.

     We compute tmp =
       ((longword1 - repeated_one) & ~longword1) & (repeated_one << 7).
     That is, we perform the following operations:
       1. Subtract repeated_one.
       2. & ~longword1.
       3. & a mask consisting of 0x80 in every byte.
     Consider what happens in each byte:
       - If a byte of longword1 is zero, step 1 and 2 transform it into 0xff,
         and step 3 transforms it into 0x80.  A carry can also be propagated
         to more significant bytes.
       - If a byte of longword1 is nonzero, let its lowest 1 bit be at
         position k (0 <= k <= 7); so the lowest k bits are 0.  After step 1,
         the byte ends in a single bit of value 0 and k bits of value 1.
         After step 2, the result is just k bits of value 1: 2^k - 1.  After
         step 3, the result is 0.  And no carry is produced.
     So, if longword1 has only non-zero bytes, tmp is zero.
     Whereas if longword1 has a zero byte, call j the position of the least
     significant zero byte.  Then the result has a zero at positions 0, ...,
     j-1 and a 0x80 at position j.  We cannot predict the result at the more
     significant bytes (positions j+1..3), but it does not matter since we
     already have a non-zero bit at position 8*j+7.

     So, the test whether any byte in longword1 is zero is equivalent to
     testing whether tmp is nonzero.  */

  while (n >= sizeof (longword))
    {
      longword longword1 = *--longword_ptr ^ repeated_c;
132

Eric Blake's avatar
Eric Blake committed
133
      if ((((longword1 - repeated_one) & ~longword1)
134 135 136 137 138
           & (repeated_one << 7)) != 0)
        {
          longword_ptr++;
          break;
        }
Eric Blake's avatar
Eric Blake committed
139
      n -= sizeof (longword);
140 141 142 143
    }

  char_ptr = (const unsigned char *) longword_ptr;

Eric Blake's avatar
Eric Blake committed
144 145 146 147 148 149 150
  /* At this point, we know that either n < sizeof (longword), or one of the
     sizeof (longword) bytes starting at char_ptr is == c.  On little-endian
     machines, we could determine the first such byte without any further
     memory accesses, just by looking at the tmp result from the last loop
     iteration.  But this does not work on big-endian machines.  Choose code
     that works in both cases.  */

151 152 153
  while (n-- > 0)
    {
      if (*--char_ptr == c)
154
        return (void *) char_ptr;
155 156
    }

Eric Blake's avatar
Eric Blake committed
157
  return NULL;
158 159 160 161
}
#ifdef weak_alias
weak_alias (__memrchr, memrchr)
#endif