This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] Improve generic rawmemchr
- From: Adhemerval Zanella <adhemerval dot zanella at linaro dot org>
- To: Wilco Dijkstra <Wilco dot Dijkstra at arm dot com>, "libc-alpha at sourceware dot org" <libc-alpha at sourceware dot org>
- Cc: nd <nd at arm dot com>
- Date: Tue, 13 Dec 2016 11:22:28 -0200
- Subject: Re: [PATCH] Improve generic rawmemchr
- Authentication-results: sourceware.org; auth=none
- References: <AM5PR0802MB26102E302074A0DD238BE90383BE0@AM5PR0802MB2610.eurprd08.prod.outlook.com> <AM5PR0802MB2610C6C76809B5A0E49B5810839B0@AM5PR0802MB2610.eurprd08.prod.outlook.com>
LGMT [1].
[1] https://sourceware.org/ml/libc-alpha/2016-11/msg00989.html
On 13/12/2016 10:49, Wilco Dijkstra wrote:
> ping
>
>
> From: Wilco Dijkstra
> Sent: 16 November 2016 18:53
> To: libc-alpha@sourceware.org
> Cc: nd
> Subject: [PATCH] Improve generic rawmemchr
>
> Improve generic rawmemchr for targets that don't have an
> assembler version by tailcalling memchr with the maximum size.
> If a target has an optimized memchr this is significantly faster
> (~3x on AArch64), if not, then this makes little difference.
> Also optimize the special case of zero to use strlen as this is
> typically faster than memchr.
>
> ChangeLog:
> 2015-11-16 Wilco Dijkstra <wdijkstr@arm.com>
>
> * string/rawmemchr.c (RAWMEMCHR): Use faster memchr/strlen.
> --
>
> diff --git a/string/rawmemchr.c b/string/rawmemchr.c
> index fa3176d6ac7e25490be415af0459807509d1e02b..1a146af980619ac9a37a3c9d8df3917e7ce5db12 100644
> --- a/string/rawmemchr.c
> +++ b/string/rawmemchr.c
> @@ -1,10 +1,5 @@
> /* Copyright (C) 1991-2016 Free Software Foundation, Inc.
> This file is part of the GNU C Library.
> - 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).
>
> The GNU C Library is free software; you can redistribute it and/or
> modify it under the terms of the GNU Lesser General Public
> @@ -20,157 +15,19 @@
> License along with the GNU C Library; if not, see
> <http://www.gnu.org/licenses/>. */
>
> -#ifdef HAVE_CONFIG_H
> -#include <config.h>
> -#endif
> -
> -#undef __ptr_t
> -#define __ptr_t void *
> -
> -#if defined (_LIBC)
> -# include <string.h>
> -# include <memcopy.h>
> -# include <stdlib.h>
> -#endif
> -
> -#if defined (HAVE_LIMITS_H) || defined (_LIBC)
> -# include <limits.h>
> -#endif
> -
> -#define LONG_MAX_32_BITS 2147483647
> -
> -#ifndef LONG_MAX
> -#define LONG_MAX LONG_MAX_32_BITS
> -#endif
> -
> -#include <sys/types.h>
> -
> -#undef memchr
> +#include <string.h>
>
> #ifndef RAWMEMCHR
> # define RAWMEMCHR __rawmemchr
> #endif
>
> /* Find the first occurrence of C in S. */
> -__ptr_t
> -RAWMEMCHR (const __ptr_t s, int c_in)
> +void *
> +RAWMEMCHR (const void *s, int c)
> {
> - const unsigned char *char_ptr;
> - const unsigned long int *longword_ptr;
> - unsigned long int longword, magic_bits, charmask;
> - unsigned char c;
> -
> - c = (unsigned char) c_in;
> -
> - /* 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 = (const unsigned char *) s;
> - ((unsigned long int) char_ptr & (sizeof (longword) - 1)) != 0;
> - ++char_ptr)
> - if (*char_ptr == c)
> - return (__ptr_t) char_ptr;
> -
> - /* 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. */
> - magic_bits = -1;
> - magic_bits = magic_bits / 0xff * 0xfe << 1 >> 1 | 1;
> -
> - /* Set up a longword, each of whose bytes is C. */
> - charmask = c | (c << 8);
> - charmask |= charmask << 16;
> -#if LONG_MAX > LONG_MAX_32_BITS
> - charmask |= charmask << 32;
> -#endif
> -
> - /* 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 (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)
> - {
> - /* 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 - 1);
> -
> - if (cp[0] == c)
> - return (__ptr_t) cp;
> - if (cp[1] == c)
> - return (__ptr_t) &cp[1];
> - if (cp[2] == c)
> - return (__ptr_t) &cp[2];
> - if (cp[3] == c)
> - return (__ptr_t) &cp[3];
> -#if LONG_MAX > 2147483647
> - if (cp[4] == c)
> - return (__ptr_t) &cp[4];
> - if (cp[5] == c)
> - return (__ptr_t) &cp[5];
> - if (cp[6] == c)
> - return (__ptr_t) &cp[6];
> - if (cp[7] == c)
> - return (__ptr_t) &cp[7];
> -#endif
> - }
> - }
> + if (c != '\0')
> + return memchr (s, c, (size_t)-1);
> + return (char *)s + strlen (s);
> }
> libc_hidden_def (__rawmemchr)
> weak_alias (__rawmemchr, rawmemchr)
>
>
>