From: Adhemerval Zanella <adhemerval.zanella@linaro.org>
To: libc-alpha@sourceware.org
Cc: Joseph Myers <joseph@codesourcery.com>,
caiyinyu <caiyinyu@loongson.cn>,
Richard Henderson <rth@twiddle.net>
Subject: [PATCH 05/17] string: Improve generic strlen
Date: Fri, 2 Sep 2022 17:39:28 -0300 [thread overview]
Message-ID: <20220902203940.2385967-6-adhemerval.zanella@linaro.org> (raw)
In-Reply-To: <20220902203940.2385967-1-adhemerval.zanella@linaro.org>
New algorithm have the following key differences:
- Reads first word unaligned and use string-maskoff functions to
remove unwanted data. This strategy follow arch-specific
optimization used on powerpc, sparc, and SH.
- Use of has_zero and index_first_zero parametrized functions.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
and powercp64-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/strlen.c | 90 +++++++++--------------------------------
sysdeps/s390/strlen-c.c | 10 +++--
2 files changed, 26 insertions(+), 74 deletions(-)
diff --git a/string/strlen.c b/string/strlen.c
index 54f3fb8167..ed71c22414 100644
--- a/string/strlen.c
+++ b/string/strlen.c
@@ -17,84 +17,34 @@
#include <string.h>
#include <stdlib.h>
-
-#undef strlen
-
-#ifndef STRLEN
-# define STRLEN strlen
+#include <stdint.h>
+#include <string-fza.h>
+#include <string-fzb.h>
+#include <string-fzi.h>
+#include <string-maskoff.h>
+
+#ifdef STRLEN
+# define __strlen STRLEN
#endif
/* Return the length of the null-terminated string STR. Scan for
the null terminator quickly by testing four bytes at a time. */
size_t
-STRLEN (const char *str)
+__strlen (const char *str)
{
- const char *char_ptr;
- const unsigned long int *longword_ptr;
- unsigned long int longword, himagic, lomagic;
-
- /* 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 = str; ((unsigned long int) char_ptr
- & (sizeof (longword) - 1)) != 0;
- ++char_ptr)
- if (*char_ptr == '\0')
- return char_ptr - str;
-
- /* All these elucidatory comments refer to 4-byte longwords,
- but the theory applies equally well to 8-byte longwords. */
+ /* Align pointer to sizeof op_t. */
+ const uintptr_t s_int = (uintptr_t) str;
+ const op_t *word_ptr = word_containing (str);
- longword_ptr = (unsigned long int *) char_ptr;
+ /* Read and MASK the first word. */
+ op_t word = *word_ptr | create_mask (s_int);
- /* Computing (longword - lomagic) sets the high bit of any corresponding
- byte that is either zero or greater than 0x80. The latter case can be
- filtered out by computing (~longword & himagic). The final result
- will always be non-zero if one of the bytes of longword is zero. */
- himagic = 0x80808080L;
- lomagic = 0x01010101L;
- if (sizeof (longword) > 4)
- {
- /* 64-bit version of the magic. */
- /* Do the shift in two steps to avoid a warning if long has 32 bits. */
- himagic = ((himagic << 16) << 16) | himagic;
- lomagic = ((lomagic << 16) << 16) | lomagic;
- }
- if (sizeof (longword) > 8)
- abort ();
+ while (! has_zero (word))
+ word = *++word_ptr;
- /* 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. */
- for (;;)
- {
- longword = *longword_ptr++;
-
- if (((longword - lomagic) & ~longword & himagic) != 0)
- {
- /* Which of the bytes was the zero? */
-
- const char *cp = (const char *) (longword_ptr - 1);
-
- if (cp[0] == 0)
- return cp - str;
- if (cp[1] == 0)
- return cp - str + 1;
- if (cp[2] == 0)
- return cp - str + 2;
- if (cp[3] == 0)
- return cp - str + 3;
- if (sizeof (longword) > 4)
- {
- if (cp[4] == 0)
- return cp - str + 4;
- if (cp[5] == 0)
- return cp - str + 5;
- if (cp[6] == 0)
- return cp - str + 6;
- if (cp[7] == 0)
- return cp - str + 7;
- }
- }
- }
+ return ((const char *) word_ptr) + index_first_zero (word) - str;
}
+#ifndef STRLEN
+weak_alias (__strlen, strlen)
libc_hidden_builtin_def (strlen)
+#endif
diff --git a/sysdeps/s390/strlen-c.c b/sysdeps/s390/strlen-c.c
index c96767e329..06413c9a57 100644
--- a/sysdeps/s390/strlen-c.c
+++ b/sysdeps/s390/strlen-c.c
@@ -21,12 +21,14 @@
#if HAVE_STRLEN_C
# if HAVE_STRLEN_IFUNC
# define STRLEN STRLEN_C
+# endif
+
+# include <string/strlen.c>
+
+# if HAVE_STRLEN_IFUNC
# if defined SHARED && IS_IN (libc)
-# undef libc_hidden_builtin_def
-# define libc_hidden_builtin_def(name) \
- __hidden_ver1 (__strlen_c, __GI_strlen, __strlen_c);
+__hidden_ver1 (__strlen_c, __GI_strlen, __strlen_c);
# endif
# endif
-# include <string/strlen.c>
#endif
--
2.34.1
next prev parent reply other threads:[~2022-09-02 20:39 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-02 20:39 [PATCH 00/17] Improve generic string routines Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 01/17] Parameterize op_t from memcopy.h Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 02/17] Parameterize OP_T_THRES " Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 03/17] Add string-maskoff.h generic header Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 04/17] Add string vectorized find and detection functions Adhemerval Zanella
2022-09-03 3:20 ` Noah Goldstein
2022-09-19 14:00 ` Adhemerval Zanella Netto
2022-09-02 20:39 ` Adhemerval Zanella [this message]
2022-09-02 20:39 ` [PATCH 06/17] string: Improve generic strnlen Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 07/17] string: Improve generic strchr Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 08/17] string: Improve generic strchrnul Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 09/17] string: Improve generic strcmp Adhemerval Zanella
2022-09-03 3:31 ` Noah Goldstein
2022-09-19 14:04 ` Adhemerval Zanella Netto
2022-09-03 8:54 ` Richard Henderson
2022-09-02 20:39 ` [PATCH 10/17] string: Improve generic memchr Adhemerval Zanella
2022-09-03 3:47 ` Noah Goldstein
2022-09-19 19:17 ` Adhemerval Zanella Netto
2022-09-19 21:59 ` Noah Goldstein
2022-09-22 17:51 ` Adhemerval Zanella Netto
2022-09-02 20:39 ` [PATCH 11/17] string: Improve generic memrchr Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 12/17] hppa: Add memcopy.h Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 13/17] hppa: Add string-fzb.h and string-fzi.h Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 14/17] alpha: " Adhemerval Zanella
2022-09-02 20:39 ` [PATCH 15/17] arm: Add string-fza.h Adhemerval Zanella
2022-09-05 15:40 ` Richard Earnshaw
2022-09-05 15:50 ` Richard Earnshaw
2022-09-02 20:39 ` [PATCH 16/17] powerpc: " Adhemerval Zanella
2022-09-06 14:48 ` Paul E Murphy
2022-09-19 19:55 ` Adhemerval Zanella Netto
2022-09-02 20:39 ` [PATCH 17/17] sh: Add string-fzb.h Adhemerval Zanella
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=20220902203940.2385967-6-adhemerval.zanella@linaro.org \
--to=adhemerval.zanella@linaro.org \
--cc=caiyinyu@loongson.cn \
--cc=joseph@codesourcery.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).