From: Adhemerval Zanella Netto <adhemerval.zanella@linaro.org>
To: Noah Goldstein <goldstein.w.n@gmail.com>
Cc: libc-alpha@sourceware.org, Richard Henderson <rth@twiddle.net>
Subject: Re: [PATCH v5 10/17] string: Improve generic memchr
Date: Tue, 10 Jan 2023 11:33:59 -0300 [thread overview]
Message-ID: <d2586a1b-05e4-64ba-7698-0bb314e6ee99@linaro.org> (raw)
In-Reply-To: <CAFUsyfLONZvFkm3-ChT=WAxt88jY3fkiC5pkkf+EFc=HfV2EOg@mail.gmail.com>
On 09/01/23 18:26, Noah Goldstein wrote:
> On Mon, Jan 9, 2023 at 12:51 PM Adhemerval Zanella Netto
> <adhemerval.zanella@linaro.org> wrote:
>>
>>
>>
>> On 05/01/23 20:49, Noah Goldstein wrote:
>>> On Mon, Sep 19, 2022 at 1:05 PM Adhemerval Zanella via Libc-alpha
>>> <libc-alpha@sourceware.org> wrote:
>>>>
>>>> New algorithm have the following key differences:
>>>>
>>>> - Reads first word unaligned and use string-maskoff function to
>>>> remove unwanted data. This strategy follow arch-specific
>>>> optimization used on aarch64 and powerpc.
>>>>
>>>> - Use string-fz{b,i} and string-opthr functions.
>>>>
>>>> Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
>>>> and powerpc64-linux-gnu by removing the arch-specific assembly
>>>> implementation and disabling multi-arch (it covers both LE and BE
>>>> for 64 and 32 bits).
>>>>
>>>> Co-authored-by: Richard Henderson <rth@twiddle.net>
>>>> ---
>>>> string/memchr.c | 168 +++++-------------
>>>> .../powerpc32/power4/multiarch/memchr-ppc32.c | 14 +-
>>>> .../powerpc64/multiarch/memchr-ppc64.c | 9 +-
>>>> 3 files changed, 48 insertions(+), 143 deletions(-)
>>>>
>>>> diff --git a/string/memchr.c b/string/memchr.c
>>>> index 422bcd0cd6..08d518b02d 100644
>>>> --- a/string/memchr.c
>>>> +++ b/string/memchr.c
>>>> @@ -1,10 +1,6 @@
>>>> -/* Copyright (C) 1991-2022 Free Software Foundation, Inc.
>>>> +/* Scan memory for a character. Generic version
>>>> + Copyright (C) 1991-2022 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
>>>> @@ -20,143 +16,65 @@
>>>> License along with the GNU C Library; if not, see
>>>> <https://www.gnu.org/licenses/>. */
>>>>
>>>> -#ifndef _LIBC
>>>> -# include <config.h>
>>>> -#endif
>>>> -
>>>> +#include <intprops.h>
>>>> +#include <string-fza.h>
>>>> +#include <string-fzb.h>
>>>> +#include <string-fzi.h>
>>>> +#include <string-maskoff.h>
>>>> +#include <string-opthr.h>
>>>> #include <string.h>
>>>>
>>>> -#include <stddef.h>
>>>> +#undef memchr
>>>>
>>>> -#include <limits.h>
>>>> -
>>>> -#undef __memchr
>>>> -#ifdef _LIBC
>>>> -# undef memchr
>>>> +#ifdef MEMCHR
>>>> +# define __memchr MEMCHR
>>>> #endif
>>>>
>>>> -#ifndef weak_alias
>>>> -# define __memchr memchr
>>>> -#endif
>>>> -
>>>> -#ifndef MEMCHR
>>>> -# define MEMCHR __memchr
>>>> -#endif
>>>> +static inline const char *
>>>> +sadd (uintptr_t x, uintptr_t y)
>>>> +{
>>>> + uintptr_t ret = INT_ADD_OVERFLOW (x, y) ? (uintptr_t)-1 : x + y;
>>>> + return (const char *)ret;
>>>> +}
>>>>
>>>> /* Search no more than N bytes of S for C. */
>>>> void *
>>>> -MEMCHR (void const *s, int c_in, size_t n)
>>>> +__memchr (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;
>>>> + if (__glibc_unlikely (n == 0))
>>>> + return NULL;
>>>>
>>>> - const unsigned char *char_ptr;
>>>> - const longword *longword_ptr;
>>>> - longword repeated_one;
>>>> - longword repeated_c;
>>>> - unsigned char c;
>>>> + uintptr_t s_int = (uintptr_t) s;
>>>>
>>>> - c = (unsigned char) c_in;
>>>> + /* Set up a word, each of whose bytes is C. */
>>>> + op_t repeated_c = repeat_bytes (c_in);
>>>> + op_t before_mask = create_mask (s_int);
>>>>
>>>> - /* Handle the first 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 > 0 && (size_t) char_ptr % sizeof (longword) != 0;
>>>> - --n, ++char_ptr)
>>>> - if (*char_ptr == c)
>>>> - return (void *) char_ptr;
>>>> + /* Compute the address of the last byte taking in consideration possible
>>>> + overflow. */
>>>> + const char *lbyte = sadd (s_int, n - 1);
>>>>
>>>> - longword_ptr = (const longword *) char_ptr;
>>>> + /* Compute the address of the word containing the last byte. */
>>>> + const op_t *lword = word_containing (lbyte);
>>>>
>>>> - /* All these elucidatory comments refer to 4-byte longwords,
>>>> - but the theory applies equally well to any size longwords. */
>>>> + /* Read the first word, but munge it so that bytes before the array
>>>> + will not match goal. */
>>>> + const op_t *word_ptr = word_containing (s);
>>>> + op_t word = (*word_ptr | before_mask) ^ (repeated_c & before_mask);
>>>>
>>>> - /* 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)
>>>> + while (has_eq (word, repeated_c) == 0)
>>>> {
>>>> - repeated_one |= repeated_one << 31 << 1;
>>>> - repeated_c |= repeated_c << 31 << 1;
>>>> - if (8 < sizeof (longword))
>>>> - {
>>>> - size_t i;
>>>> -
>>>> - for (i = 64; i < sizeof (longword) * 8; i *= 2)
>>>> - {
>>>> - repeated_one |= repeated_one << i;
>>>> - repeated_c |= repeated_c << i;
>>>> - }
>>>> - }
>>>> + if (word_ptr == lword)
>>>> + return NULL;
>>> Inuitively making lword, lword - 1 so that normal returns don't need the extra
>>> null check would be faster.
>>
>> Hum, I did not follow; could you explain it with more details what you mean here?
>
> I was thinking something like:
>
> ```
> op_t word = *word_ptr;
> op_t mask = find_eq_low (word, repeated_c)
> >> (CHAR_BIT * (s_int % sizeof (uintptr_t)));
> if (mask)
> {
> char *ret = (char *) s + index_first_ (mask);
> return (ret <= lbyte) ? ret : NULL;
> }
> if (word_ptr == lword)
> return NULL;
>
> word = *++word_ptr;
> while (word_ptr != lword)
> {
> if (has_eq (word, repeated_c))
> return (char *) word_ptr + index_first_eq (word, repeated_c);
> word = *++word_ptr;
> }
>
> if (has_eq (word, repeated_c))
> {
>
> /* We found a match, but it might be in a byte past the end
> of the array. */
> char *ret = (char *) word_ptr + index_first_eq (word, repeated_c);
> if (ret <= lbyte)
> return ret;
> }
> return NULL;
> ```
>
> The idea is until the last byte you don't need the extra bounds check (tested
> on test-memchr.c on little-endian).
Alright, this works. I will update the path.
next prev parent reply other threads:[~2023-01-10 14:34 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-19 19:59 [PATCH v5 00/17] Improve generic string routines Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 01/17] Parameterize op_t from memcopy.h Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 02/17] Parameterize OP_T_THRES " Adhemerval Zanella
2022-09-20 10:49 ` Carlos O'Donell
2022-09-19 19:59 ` [PATCH v5 03/17] Add string-maskoff.h generic header Adhemerval Zanella
2022-09-20 11:43 ` Carlos O'Donell
2022-09-22 17:31 ` Adhemerval Zanella Netto
2023-01-05 22:49 ` Noah Goldstein
2023-01-05 23:26 ` Alejandro Colomar
2023-01-09 18:19 ` Adhemerval Zanella Netto
2023-01-09 18:02 ` Adhemerval Zanella Netto
2022-09-19 19:59 ` [PATCH v5 04/17] Add string vectorized find and detection functions Adhemerval Zanella
2023-01-05 22:53 ` Noah Goldstein
2023-01-09 18:51 ` Adhemerval Zanella Netto
2023-01-05 23:04 ` Noah Goldstein
2023-01-09 19:34 ` Adhemerval Zanella Netto
2022-09-19 19:59 ` [PATCH v5 05/17] string: Improve generic strlen Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 06/17] string: Improve generic strnlen Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 07/17] string: Improve generic strchr Adhemerval Zanella
2023-01-05 23:09 ` Noah Goldstein
2023-01-05 23:19 ` Noah Goldstein
2023-01-09 19:39 ` Adhemerval Zanella Netto
2022-09-19 19:59 ` [PATCH v5 08/17] string: Improve generic strchrnul Adhemerval Zanella
2023-01-05 23:17 ` Noah Goldstein
2023-01-09 20:35 ` Adhemerval Zanella Netto
2023-01-09 20:49 ` Richard Henderson
2023-01-09 20:59 ` Noah Goldstein
2023-01-09 21:01 ` Noah Goldstein
2023-01-09 23:33 ` Richard Henderson
2023-01-10 14:18 ` Adhemerval Zanella Netto
2023-01-10 16:24 ` Richard Henderson
2023-01-10 17:16 ` Noah Goldstein
2023-01-10 18:19 ` Adhemerval Zanella Netto
2023-01-10 17:17 ` Noah Goldstein
2023-01-10 18:16 ` Adhemerval Zanella Netto
2022-09-19 19:59 ` [PATCH v5 09/17] string: Improve generic strcmp Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 10/17] string: Improve generic memchr Adhemerval Zanella
2023-01-05 23:47 ` Noah Goldstein
2023-01-09 20:50 ` Adhemerval Zanella Netto
2023-01-05 23:49 ` Noah Goldstein
2023-01-09 20:51 ` Adhemerval Zanella Netto
2023-01-09 21:26 ` Noah Goldstein
2023-01-10 14:33 ` Adhemerval Zanella Netto [this message]
2022-09-19 19:59 ` [PATCH v5 11/17] string: Improve generic memrchr Adhemerval Zanella
2023-01-05 23:51 ` Noah Goldstein
2022-09-19 19:59 ` [PATCH v5 12/17] hppa: Add memcopy.h Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 13/17] hppa: Add string-fzb.h and string-fzi.h Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 14/17] alpha: " Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 15/17] arm: Add string-fza.h Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 16/17] powerpc: " Adhemerval Zanella
2022-09-19 19:59 ` [PATCH v5 17/17] sh: Add string-fzb.h Adhemerval Zanella
2022-12-05 17:07 ` [PATCH v5 00/17] Improve generic string routines Xi Ruoyao
2023-01-05 21:56 ` Adhemerval Zanella Netto
2023-01-05 23:52 ` Noah Goldstein
2023-01-06 13:43 ` Adhemerval Zanella Netto
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=d2586a1b-05e4-64ba-7698-0bb314e6ee99@linaro.org \
--to=adhemerval.zanella@linaro.org \
--cc=goldstein.w.n@gmail.com \
--cc=libc-alpha@sourceware.org \
--cc=rth@twiddle.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).