From patchwork Wed Dec 21 23:05:53 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 18618 Received: (qmail 50637 invoked by alias); 21 Dec 2016 23:06:15 -0000 Mailing-List: contact libc-alpha-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Unsubscribe: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: libc-alpha-owner@sourceware.org Delivered-To: mailing list libc-alpha@sourceware.org Received: (qmail 50562 invoked by uid 89); 21 Dec 2016 23:06:14 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-1.6 required=5.0 tests=BAYES_00, FREEMAIL_ENVFROM_END_DIGIT, FREEMAIL_FROM, RCVD_IN_DNSWL_NONE, SPF_PASS autolearn=no version=3.3.2 spammy=zeroes, H*RU:209.85.192.193, Hx-spam-relays-external:209.85.192.193 X-HELO: mail-pf0-f193.google.com X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:from:to:subject:date:message-id :in-reply-to:references; bh=NVZLlQsYV2Kj7gLmITI+NdbT4n28VYLMPn6QdSxVdiY=; b=e6CSFqDJpOR4UaKjQFZj200r1Kl8L5JVMFlzvWytfZABCjb7U5TIXHbNL4XDjqITUc k8Josg4w0BOfldUlMvymC/wGuGJW6+zm4OfufPNz3HYKCkbMJJEZzAczDp4Y5GDVJvCn wFrABtUQca2It9IjB4LKw5duBXJfD1tsQMajwgmudROXiSuvJI8FBBgQRdyQS+LcYTYO y/aVr+QijnCryaLZ1Yfd2W52JdsiZmuERxpHH1ZvEAPUVUS7AuvPe1g+x0gAUAbHcu/j cju3ljOqpKrKesFDe/u6yRWL3W2byJ+w7DA1xqhh3cOSxtBIE0PBsqdxVF5m7ZFX724B IUaQ== X-Gm-Message-State: AIkVDXLAW3vLJ16NWBLFHzcg9l35OfmI48K9mUC7rApUNYD9Du47nC0cXqsg08WLF2gG5w== X-Received: by 10.84.209.199 with SMTP id y65mr13297646plh.163.1482361570866; Wed, 21 Dec 2016 15:06:10 -0800 (PST) From: Richard Henderson To: libc-alpha@sourceware.org Subject: [PATCH v2 04/16] Improve generic strchr Date: Wed, 21 Dec 2016 15:05:53 -0800 Message-Id: <20161221230605.28638-5-rth@twiddle.net> In-Reply-To: <20161221230605.28638-1-rth@twiddle.net> References: <20161221230605.28638-1-rth@twiddle.net> [BZ #5806] * string/strchr.c: Use string-fzb.h, string-fzi.h, string-extbyte.h. --- string/strchr.c | 164 ++++++++++---------------------------------------------- 1 file changed, 29 insertions(+), 135 deletions(-) diff --git a/string/strchr.c b/string/strchr.c index 25c2fe4..3215126 100644 --- a/string/strchr.c +++ b/string/strchr.c @@ -22,164 +22,58 @@ #include #include +#include +#include +#include +#include #undef strchr +#undef index -#ifndef STRCHR -# define STRCHR strchr +#ifdef STRCHR +# define strchr STRCHR #endif /* Find the first occurrence of C in S. */ char * -STRCHR (const char *s, int c_in) +strchr (const char *s, int c_in) { const unsigned char *char_ptr; - const unsigned long int *longword_ptr; - unsigned long int longword, magic_bits, charmask; + const op_t *word_ptr; + op_t word, repeated_c, found; + uintptr_t i, align; unsigned char c; c = (unsigned char) c_in; + char_ptr = (const unsigned char *) s; /* 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) + Do this until CHAR_PTR is aligned on a word boundary. */ + align = -(uintptr_t)char_ptr % sizeof(word); + for (i = 0; i < align; ++i, ++char_ptr) if (*char_ptr == c) - return (void *) char_ptr; + return (char *) char_ptr; else if (*char_ptr == '\0') return NULL; - /* 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 (sizeof (longword) > 4) - /* Do the shift in two steps to avoid a warning if long has 32 bits. */ - charmask |= (charmask << 16) << 16; - if (sizeof (longword) > 8) - abort (); + /* Set up a word, each of whose bytes is C. */ + repeated_c = ((op_t)-1 / 0xff) * c; - /* 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 (;;) + word_ptr = (const op_t *) char_ptr; + do { - /* 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 as well as 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++; - - /* 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 || - - /* That caught zeroes. Now test for C. */ - ((((longword ^ charmask) + magic_bits) ^ ~(longword ^ charmask)) - & ~magic_bits) != 0) - { - /* Which of the bytes was C or zero? - If none of them were, it was a misfire; continue the search. */ - - const unsigned char *cp = (const unsigned char *) (longword_ptr - 1); - - if (*cp == c) - return (char *) cp; - else if (*cp == '\0') - return NULL; - if (*++cp == c) - return (char *) cp; - else if (*cp == '\0') - return NULL; - if (*++cp == c) - return (char *) cp; - else if (*cp == '\0') - return NULL; - if (*++cp == c) - return (char *) cp; - else if (*cp == '\0') - return NULL; - if (sizeof (longword) > 4) - { - if (*++cp == c) - return (char *) cp; - else if (*cp == '\0') - return NULL; - if (*++cp == c) - return (char *) cp; - else if (*cp == '\0') - return NULL; - if (*++cp == c) - return (char *) cp; - else if (*cp == '\0') - return NULL; - if (*++cp == c) - return (char *) cp; - else if (*cp == '\0') - return NULL; - } - } + word = *word_ptr++; } + while (!has_zero_eq (word, repeated_c)); - return NULL; + found = index_first_zero_eq (word, repeated_c); + if (extractbyte (word, found) == c) + return (char *) (word_ptr - 1) + found; + else + return NULL; } -#ifdef weak_alias -# undef index +#ifndef STRCHR weak_alias (strchr, index) -#endif libc_hidden_builtin_def (strchr) +#endif