From patchwork Sat Dec 17 06:57:22 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 18530 Received: (qmail 93362 invoked by alias); 17 Dec 2016 06:57:54 -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 92945 invoked by uid 89); 17 Dec 2016 06:57:51 -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=caught, holes X-HELO: mail-pg0-f66.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=C6vaR8b6Uu34MihZhuKQ5d1360hRU0/cohDZ+ixOAPY=; b=FaecV6u6GgH4e0Ffp+xXjE87rDGsdwF9L9kpv7H7r0n1jHqxi0pGTYuwQsVlmhD69M GDAF0T7ga6j8k1a713BAKYAxYD3iEuyqi7RJIiKgeFU3qGiRhvX7DB/rKeJy1gwoUgiz rfbMufCzaP+QbFWvrxjEScY/7TeAtmW0I/EkiTrAsXpG+k7/M93huJ/5vyx210HxNKMx qzGderCMMTgzZHiQhIdyblG5d+xJNrNunkhbxQPInEN0JOhv4pafyj8anjUy7lBC0E7r 0bKZyXanoPKfi5tSAdV09U0Stcng+mkaFOnNkGATftllNld9zgAQowYfeaFAIrL7fzFJ ZZPQ== X-Gm-Message-State: AKaTC03s/LkFa9FiEGBritjjcGdhGhF0SdiCh6RERKLk98s/d/uanMWkBRPPEei1CTdhCw== X-Received: by 10.84.214.1 with SMTP id h1mr15131439pli.47.1481957861793; Fri, 16 Dec 2016 22:57:41 -0800 (PST) From: Richard Henderson To: libc-alpha@sourceware.org Subject: [PATCH 04/11] Improve generic strchrnul Date: Fri, 16 Dec 2016 22:57:22 -0800 Message-Id: <20161217065729.28561-5-rth@twiddle.net> In-Reply-To: <20161217065729.28561-1-rth@twiddle.net> References: <20161217065729.28561-1-rth@twiddle.net> * string/strchrnul.c: Use haszero.h, whichzero.h. --- string/strchrnul.c | 126 +++++++---------------------------------------------- 1 file changed, 15 insertions(+), 111 deletions(-) diff --git a/string/strchrnul.c b/string/strchrnul.c index 629db46..fb2d1a4 100644 --- a/string/strchrnul.c +++ b/string/strchrnul.c @@ -21,8 +21,10 @@ . */ #include -#include #include +#include +#include +#include #undef __strchrnul #undef strchrnul @@ -37,130 +39,32 @@ STRCHRNUL (const char *s, int c_in) { const unsigned char *char_ptr; const unsigned long int *longword_ptr; - unsigned long int longword, magic_bits, charmask; + unsigned long int longword, 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) + align = -(uintptr_t)char_ptr % sizeof(longword); + for (i = 0; i < align; ++i, ++char_ptr) if (*char_ptr == c || *char_ptr == '\0') - return (void *) 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; + return (char *) char_ptr; /* 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 (); + repeated_c = (-1ul / 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 (;;) + longword_ptr = (unsigned long int *) 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 || *cp == '\0') - return (char *) cp; - if (*++cp == c || *cp == '\0') - return (char *) cp; - if (*++cp == c || *cp == '\0') - return (char *) cp; - if (*++cp == c || *cp == '\0') - return (char *) cp; - if (sizeof (longword) > 4) - { - if (*++cp == c || *cp == '\0') - return (char *) cp; - if (*++cp == c || *cp == '\0') - return (char *) cp; - if (*++cp == c || *cp == '\0') - return (char *) cp; - if (*++cp == c || *cp == '\0') - return (char *) cp; - } - } } + while (!haszero2(longword, longword ^ repeated_c)); - /* This should never happen. */ - return NULL; + found = whichzero2(longword, longword ^ repeated_c); + return (char *) (longword_ptr - 1) + found; } weak_alias (__strchrnul, strchrnul)