From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-oa1-x2b.google.com (mail-oa1-x2b.google.com [IPv6:2001:4860:4864:20::2b]) by sourceware.org (Postfix) with ESMTPS id A05C83858286 for ; Mon, 19 Sep 2022 19:59:36 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org A05C83858286 Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=linaro.org Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=linaro.org Received: by mail-oa1-x2b.google.com with SMTP id 586e51a60fabf-11e9a7135easo998605fac.6 for ; Mon, 19 Sep 2022 12:59:36 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date; bh=XlqHG16NRT1osbFpKxurgn+W1gihN2MPoNSOHcDHg18=; b=dTNvtcIBYZn0TrqssaWTtSSZE4VD/vlWeqTQVF9QJthE+VQUre4ARCBC2JO67xuAnh 94YaASu4sYch2slPD+PF86GwF01BDK9UWs/WYxASgeyNRx8ZW9oPvxbncvq5/1vqISW+ MkOhPmRQqYjE0kP9xdBh6zTthNYInlFCuAcJeDXf3NqsJGMmB+vKoWh5pWFqLkm8bY+t d3KHCPxf468rPviI4efdP2XwjK2R/+9Z7/2/dnCFG8l2MPrFLmXyDvcufp5lq6XU/K9t kSyWNu2WqAY3ggUJSDakUt/iTNVrfn2tcmRm/d4Kp3Qkd7pIlm8qHndosmLdLXk80uzq fnaQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date; bh=XlqHG16NRT1osbFpKxurgn+W1gihN2MPoNSOHcDHg18=; b=wTxsw0R2Ydbw6LDlhZrTkkQ8xTglYDrhAiB7q4ovdtUWuIeg22n1o+q4nuXXS4ExPR IZlbbXxwUEMY5HHNBqlpqRBqfDnC+Fq8f/DC91MZI2JzZSD1r5mqXrgbjdxkqaxoU4gm rEQ0/SUDNk4qS3aLp48sXaU8EbFd0iNNKu2DNLIFztc8KIO9DSJM53ine2mabr+fnrVH OZoszzaea5siu11F4byJIAsA3Y8IF7uOiJaEktRQ23dHJ5DQG3D/Mx/GQGKBSaTgX2IL CLSoumNhNiVaGOfmMoznrd4aCDt8h9j8hpJ1hcyYl91o5HNRyt46oPeatxNslmtBQhcY mrBA== X-Gm-Message-State: ACgBeo1kHS15eo8q8AcYkshnPIl5wPM0t2AhcomI2nUgyC9R7ssb8AIY K7d21cH7XKcSNLVNCvMn0Oemjtr/MGBpYc8R X-Google-Smtp-Source: AA6agR6F0G1l6S+g8i6sb1T8dhC6GxZqnxCnXaOKxar44qM+C93juFRCOBkgugQyPcF6N3fT0SxH6Q== X-Received: by 2002:a05:6870:4783:b0:118:81e3:27ec with SMTP id c3-20020a056870478300b0011881e327ecmr15974191oaq.146.1663617575650; Mon, 19 Sep 2022 12:59:35 -0700 (PDT) Received: from mandiga.. ([2804:1b3:a7c1:c266:b3ad:a56d:1ca:d6ea]) by smtp.gmail.com with ESMTPSA id l7-20020a4ab0c7000000b00475dc6c6f31sm4532291oon.45.2022.09.19.12.59.34 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 19 Sep 2022 12:59:35 -0700 (PDT) From: Adhemerval Zanella To: libc-alpha@sourceware.org Cc: Richard Henderson Subject: [PATCH v5 07/17] string: Improve generic strchr Date: Mon, 19 Sep 2022 16:59:10 -0300 Message-Id: <20220919195920.956393-8-adhemerval.zanella@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20220919195920.956393-1-adhemerval.zanella@linaro.org> References: <20220919195920.956393-1-adhemerval.zanella@linaro.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=-12.7 required=5.0 tests=BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,GIT_PATCH_0,RCVD_IN_DNSWL_NONE,SPF_HELO_NONE,SPF_PASS,TXREP autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: 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-extbyte function. 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 --- string/strchr.c | 172 +++++++--------------------------------- sysdeps/s390/strchr-c.c | 11 +-- 2 files changed, 34 insertions(+), 149 deletions(-) diff --git a/string/strchr.c b/string/strchr.c index bfd0c4e4bc..6bbee7f79d 100644 --- a/string/strchr.c +++ b/string/strchr.c @@ -22,164 +22,48 @@ #include #include +#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; - unsigned char c; - - c = (unsigned char) c_in; - - /* 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) - if (*char_ptr == c) - return (void *) 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 (); - - /* 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 (;;) - { - /* 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. + /* Set up a word, each of whose bytes is C. */ + unsigned char c = (unsigned char) c_in; + op_t repeated_c = repeat_bytes (c_in); - 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. + /* Align the input address to op_t. */ + uintptr_t s_int = (uintptr_t) s; + const op_t *word_ptr = word_containing (s); - 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! + /* Read the first aligned word, but force bytes before the string to + match neither zero nor goal (we make sure the high bit of each byte + is 1, and the low 7 bits are all the opposite of the goal byte). */ + op_t bmask = create_mask (s_int); + op_t word = (*word_ptr | bmask) ^ (repeated_c & highbit_mask (bmask)); - So it ignores everything except 128's, when they're aligned - properly. + while (! has_zero_eq (word, repeated_c)) + word = *++word_ptr; - 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; - } - } - } + op_t found = index_first_zero_eq (word, repeated_c); + if (extractbyte (word, found) == c) + return (char *) (word_ptr) + found; return NULL; } - -#ifdef weak_alias -# undef index +#ifndef STRCHR weak_alias (strchr, index) -#endif libc_hidden_builtin_def (strchr) +#endif diff --git a/sysdeps/s390/strchr-c.c b/sysdeps/s390/strchr-c.c index 4ac3a62fba..a5a1781b1c 100644 --- a/sysdeps/s390/strchr-c.c +++ b/sysdeps/s390/strchr-c.c @@ -21,13 +21,14 @@ #if HAVE_STRCHR_C # if HAVE_STRCHR_IFUNC # define STRCHR STRCHR_C -# undef weak_alias +# endif + +# include + +# if HAVE_STRCHR_IFUNC # if defined SHARED && IS_IN (libc) -# undef libc_hidden_builtin_def -# define libc_hidden_builtin_def(name) \ - __hidden_ver1 (__strchr_c, __GI_strchr, __strchr_c); +__hidden_ver1 (__strchr_c, __GI_strchr, __strchr_c); # endif # endif -# include #endif -- 2.34.1