X-Git-Url: https://git.gag.com/?a=blobdiff_plain;f=lib%2Fmemrchr.c;h=da93ca0ba52a2cd88ce0cf225a832ef14bf8c606;hb=cf7169a2ede9bb08b71de68fe0c8bbecf827abe6;hp=50b27c0291b374bee42b48d3348fde86bfc29965;hpb=138fc7e67e3d9845cd7d81aad0e9c7724784f9b9;p=debian%2Ftar diff --git a/lib/memrchr.c b/lib/memrchr.c index 50b27c02..da93ca0b 100644 --- a/lib/memrchr.c +++ b/lib/memrchr.c @@ -1,7 +1,7 @@ /* memrchr -- find the last occurrence of a byte in a memory block Copyright (C) 1991, 1993, 1996, 1997, 1999, 2000, 2003, 2004, 2005, - 2006, 2007 Free Software Foundation, Inc. + 2006, 2007, 2008 Free Software Foundation, Inc. Based on strlen implementation by Torbjorn Granlund (tege@sics.se), with help from Dan Sahlin (dan@sics.se) and @@ -33,7 +33,9 @@ #include #undef __memrchr -#undef memrchr +#ifdef _LIBC +# undef memrchr +#endif #ifndef weak_alias # define __memrchr memrchr @@ -43,146 +45,116 @@ void * __memrchr (void const *s, int c_in, size_t n) { + /* 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. */ + typedef unsigned long int longword; + const unsigned char *char_ptr; - const unsigned long int *longword_ptr; - unsigned long int longword, magic_bits, charmask; + const longword *longword_ptr; + longword repeated_one; + longword repeated_c; unsigned reg_char c; - int i; c = (unsigned char) c_in; - /* Handle the last few characters by reading one character at a time. + /* Handle the last few bytes by reading one byte at a time. Do this until CHAR_PTR is aligned on a longword boundary. */ for (char_ptr = (const unsigned char *) s + n; - n > 0 && (size_t) char_ptr % sizeof longword != 0; + n > 0 && (size_t) char_ptr % sizeof (longword) != 0; --n) if (*--char_ptr == c) return (void *) char_ptr; + longword_ptr = (const longword *) char_ptr; + /* All these elucidatory comments refer to 4-byte longwords, but the theory applies equally well to any size longwords. */ - longword_ptr = (const 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. */ - - /* Set MAGIC_BITS to be this pattern of 1 and 0 bits. - Set CHARMASK to be a longword, each of whose bytes is C. */ - - magic_bits = 0xfefefefe; - charmask = c | (c << 8); - charmask |= charmask << 16; -#if 0xffffffffU < ULONG_MAX - magic_bits |= magic_bits << 32; - charmask |= charmask << 32; - if (8 < sizeof longword) - for (i = 64; i < sizeof longword * 8; i *= 2) - { - magic_bits |= magic_bits << i; - charmask |= charmask << i; - } -#endif - magic_bits = (ULONG_MAX >> 1) & (magic_bits | 1); - - /* 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. */ - while (n >= sizeof longword) + /* 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; + if (0xffffffffU < (longword) -1) { - /* We tentatively exit the loop if adding MAGIC_BITS to - LONGWORD fails to change any of the hole bits of LONGWORD. - - 1) Is this safe? Will it catch all the zero bytes? - Suppose there is a byte with all zeros. Any carry bits - propagating from its left will fall into the hole at its - least significant bit and stop. Since there will be no - carry from its most significant bit, the LSB of the - byte to the left will be unchanged, and the zero will be - detected. - - 2) Is this worthwhile? Will it ignore everything except - zero bytes? Suppose every byte of LONGWORD has a bit set - somewhere. There will be a carry into bit 8. If bit 8 - is set, this will carry into bit 16. If bit 8 is clear, - one of bits 9-15 must be set, so there will be a carry - into bit 16. Similarly, there will be a carry into bit - 24. If one of bits 24-30 is set, there will be a carry - into bit 31, so all of the hole bits will be changed. - - The one misfire occurs when bits 24-30 are clear and bit - 31 is set; in this case, the hole at bit 31 is not - changed. If we had access to the processor carry flag, - we could close this loophole by putting the fourth hole - at bit 32! - - So it ignores everything except 128's, when they're aligned - properly. - - 3) But wait! Aren't we looking for C, not zero? - Good point. So what we do is XOR LONGWORD with a longword, - each of whose bytes is C. This turns each byte that is C - into a zero. */ - - longword = *--longword_ptr ^ charmask; - - /* Add MAGIC_BITS to LONGWORD. */ - if ((((longword + magic_bits) - - /* Set those bits that were unchanged by the addition. */ - ^ ~longword) - - /* Look at only the hole bits. If any of the hole bits - are unchanged, most likely one of the bytes was a - zero. */ - & ~magic_bits) != 0) + repeated_one |= repeated_one << 31 << 1; + repeated_c |= repeated_c << 31 << 1; + if (8 < sizeof (longword)) { - /* Which of the bytes was C? If none of them were, it was - a misfire; continue the search. */ - - const unsigned char *cp = (const unsigned char *) longword_ptr; - - if (8 < sizeof longword) - for (i = sizeof longword - 1; 8 <= i; i--) - if (cp[i] == c) - return (void *) &cp[i]; - if (7 < sizeof longword && cp[7] == c) - return (void *) &cp[7]; - if (6 < sizeof longword && cp[6] == c) - return (void *) &cp[6]; - if (5 < sizeof longword && cp[5] == c) - return (void *) &cp[5]; - if (4 < sizeof longword && cp[4] == c) - return (void *) &cp[4]; - if (cp[3] == c) - return (void *) &cp[3]; - if (cp[2] == c) - return (void *) &cp[2]; - if (cp[1] == c) - return (void *) &cp[1]; - if (cp[0] == c) - return (void *) cp; + size_t i; + + for (i = 64; i < sizeof (longword) * 8; i *= 2) + { + repeated_one |= repeated_one << i; + repeated_c |= repeated_c << i; + } } + } + + /* 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; - n -= sizeof longword; + if ((((longword1 - repeated_one) & ~longword1) + & (repeated_one << 7)) != 0) + { + longword_ptr++; + break; + } + n -= sizeof (longword); } char_ptr = (const unsigned char *) longword_ptr; + /* 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. */ + while (n-- > 0) { if (*--char_ptr == c) return (void *) char_ptr; } - return 0; + return NULL; } #ifdef weak_alias weak_alias (__memrchr, memrchr)