From patchwork Wed Dec 21 23:05:59 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 18620 Received: (qmail 51363 invoked by alias); 21 Dec 2016 23:06:21 -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 51236 invoked by uid 89); 21 Dec 2016 23:06:20 -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=1632, ofs X-HELO: mail-pg0-f67.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=jiGBuYOGA06BMjBqP2JEIxX7g4VzGD8HGsy8Pejli5Q=; b=dUiJTecxvmYz7a5rAVEK7A2KWDZQZz/QUS6yBWLCFtCVHmadvTh2E5cO3Stf11uTyS jSGKSVBBv5TzWxFmlWswCEZNK/TDmMNanhbfEuaisQIbnMdwX7eHWxecliB/c7+SxBwR vxZ1FGuvHTVL9Jo3QyEW1eVMEMYs1CYIVARK+2YXP2wjTm0ppqUjBl+DPa0OxJW9LLT3 FHmWiYU9hn9vrr0648z8QipxxAaAA0SdAfd4mPJ6S9LqSqY8eNVzrXPetTYLmhUq8moB 6YuU7CXFAwg6fAtzuvA/uOh8DVSBbgBYUBAm5fvNqAm/sNjOinpd/pl+xpLFOlu0MQUr ZA7A== X-Gm-Message-State: AIkVDXLdbYc60c/45z0UV4y+HsYJ4GINekJ/TeKvFc38OqB71xNCfs4gDrN8aswjkfYZEQ== X-Received: by 10.84.215.152 with SMTP id l24mr13335373pli.10.1482361576022; Wed, 21 Dec 2016 15:06:16 -0800 (PST) From: Richard Henderson To: libc-alpha@sourceware.org Subject: [PATCH v2 10/16] Improve generic strcmp Date: Wed, 21 Dec 2016 15:05:59 -0800 Message-Id: <20161221230605.28638-11-rth@twiddle.net> In-Reply-To: <20161221230605.28638-1-rth@twiddle.net> References: <20161221230605.28638-1-rth@twiddle.net> * string/strcmp.c: Rewrite using memcopy.h, string-fzb.h, string-fzi.h. --- string/strcmp.c | 102 ++++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 91 insertions(+), 11 deletions(-) diff --git a/string/strcmp.c b/string/strcmp.c index 4b16f99..cb522ff 100644 --- a/string/strcmp.c +++ b/string/strcmp.c @@ -16,32 +16,112 @@ . */ #include +#include +#include +#include +#include +#include +#include #undef strcmp -#ifndef STRCMP -# define STRCMP strcmp +#ifdef STRCMP +# define strcmp STRCMP #endif /* Compare S1 and S2, returning less than, equal to or greater than zero if S1 is lexicographically less than, equal to or greater than S2. */ int -STRCMP (const char *p1, const char *p2) +strcmp (const char *p1, const char *p2) { - const unsigned char *s1 = (const unsigned char *) p1; - const unsigned char *s2 = (const unsigned char *) p2; + const op_t *x1, *x2; + op_t w1, w2; unsigned char c1, c2; + uintptr_t i, n, ofs; + int diff; + + /* Handle the unaligned bytes of p1 first. */ + n = -(uintptr_t)p1 % sizeof(op_t); + for (i = 0; i < n; ++i) + { + c1 = *p1++; + c2 = *p2++; + diff = c1 - c2; + if (c1 == '\0' || diff) + return diff; + } - do + /* P1 is now aligned to unsigned long. P2 may or may not be. */ + x1 = (const op_t *)p1; + w1 = *x1++; + ofs = (uintptr_t)p2 % sizeof(op_t); + if (ofs == 0) { - c1 = (unsigned char) *s1++; - c2 = (unsigned char) *s2++; - if (c1 == '\0') - return c1 - c2; + x2 = (const op_t *)p2; + w2 = *x2++; + /* Aligned loop. If a difference is found, exit to compare the + bytes. Else if a zero is found we have equal strings. */ + while (w1 == w2) + { + if (has_zero (w1)) + return 0; + w1 = *x1++; + w2 = *x2++; + } } - while (c1 == c2); + else + { + op_t w2a, w2b; + uintptr_t sh_1, sh_2; + + x2 = (const op_t *)(p2 - ofs); + w2a = *x2++; + sh_1 = ofs * CHAR_BIT; + sh_2 = sizeof(op_t) * CHAR_BIT - sh_1; + + /* Align the first partial of P2, with 0xff for the rest of the + bytes so that we can also apply the has_zero test to see if we + have already reached EOS. If we have, then we can simply fall + through to the final comparison. */ + w2 = MERGE (w2a, sh_1, (op_t)-1, sh_2); + if (!has_zero (w2)) + { + /* Unaligned loop. The invariant is that W2B, which is "ahead" + of W1, does not contain end-of-string. Therefore it is safe + (and necessary) to read another word from each while we do + not have a difference. */ + while (1) + { + w2b = *x2++; + w2 = MERGE (w2a, sh_1, w2b, sh_2); + if (w1 != w2) + goto final_cmp; + if (has_zero (w2b)) + break; + w1 = *x1++; + w2a = w2b; + } + /* Zero found in the second partial of P2. If we had EOS + in the aligned word, we have equality. */ + if (has_zero (w1)) + return 0; + + /* Load the final word of P1 and align the final partial of P2. */ + w1 = *x1++; + w2 = MERGE (w2b, sh_1, 0, sh_2); + } + } + + final_cmp: + /* We have two aligned words of data. */ + i = index_first_zero_ne (w1, w2); + c1 = extractbyte (w1, i); + c2 = extractbyte (w2, i); return c1 - c2; } + +#ifndef STRCMP libc_hidden_builtin_def (strcmp) +#endif