diff mbox

[2/*,v2] Optimize generic strchrnul and strchr

Message ID 20150527091148.GB27814@domone
State New
Headers show

Commit Message

Ondrej Bilka May 27, 2015, 9:11 a.m. UTC
On Wed, May 27, 2015 at 08:35:44AM +0200, Ondřej Bílka wrote:
> This is my generic strchr algorithm resubmitted to use skeleton.
> 
> Idea to split into cases c<128 and c>128 didn't change.
> 
> So comments? How this perform on different architectures?
> 
This also needed to change as I used older strchr wrapper. Here is
correct one.

 	* string/strchr.c: Use skeleton.
 	* string/strchrnul.c: Likewise.
diff mbox

Patch

diff --git a/string/strchr.c b/string/strchr.c
index 5f90075..e7c2e4c 100644
--- a/string/strchr.c
+++ b/string/strchr.c
@@ -1,10 +1,5 @@ 
 /* Copyright (C) 1991-2015 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
-   Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
-   with help from Dan Sahlin (dan@sics.se) and
-   bug fix and commentary by Jim Blandy (jimb@ai.mit.edu);
-   adaptation to strchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
-   and implemented by Roland McGrath (roland@ai.mit.edu).
 
    The GNU C Library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Lesser General Public
@@ -21,166 +16,21 @@ 
    <http://www.gnu.org/licenses/>.  */
 
 #include <string.h>
-#include <stdlib.h>
-
 #undef strchr
+#undef index
+
+#define AS_STRCHR
+#define STRCHRNUL strchrnul_static
+#include "string/strchrnul.c"
+
 
-/* Find the first occurrence of C in S.  */
 char *
 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.  */
-  switch (sizeof (longword))
-    {
-    case 4: magic_bits = 0x7efefeffL; break;
-    case 8: magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL; break;
-    default:
-      abort ();
-    }
-
-  /* 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.
-
-	 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;
-	    }
-	}
-    }
-
-  return NULL;
+  unsigned char c = (unsigned char) c_in;
+  unsigned char *r = (unsigned char *) STRCHRNUL (s, c);
+  return (*r == c) ? (char *) r : NULL;
 }
 
-#ifdef weak_alias
-#undef index
 weak_alias (strchr, index)
-#endif
 libc_hidden_builtin_def (strchr)
diff --git a/string/strchrnul.c b/string/strchrnul.c
index 2678f1d..95fa11d 100644
--- a/string/strchrnul.c
+++ b/string/strchrnul.c
@@ -1,10 +1,5 @@ 
 /* Copyright (C) 1991-2015 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
-   Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
-   with help from Dan Sahlin (dan@sics.se) and
-   bug fix and commentary by Jim Blandy (jimb@ai.mit.edu);
-   adaptation to strchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
-   and implemented by Roland McGrath (roland@ai.mit.edu).
 
    The GNU C Library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Lesser General Public
@@ -21,153 +16,63 @@ 
    <http://www.gnu.org/licenses/>.  */
 
 #include <string.h>
-#include <memcopy.h>
 #include <stdlib.h>
 
-#undef __strchrnul
 #undef strchrnul
+#undef __strchrnul
+
+/* Return the length of the null-terminated string STR.  Scan for
+   the null terminator quickly by testing four bytes at a time.  */
+
+/* Here idea is still use the result of expression
+   contains_zero (*p) | contains_zero (*p ^ cmask)
+   but we can optimize it by using commutativity of operations.  */
+
+#include "string/common.h"
+/* #define EXPRESSION(s, cmask) (((((s & add) + add) & (((s & add) ^ cmask) + add)) | s) ^ high_bits) & high_bits */
+
+#define EXPRESSION(s, cmask) (contains_zero(s) | contains_zero (s ^ cmask))
+#include "string/skeleton.h"
 
 #ifndef STRCHRNUL
 # define STRCHRNUL __strchrnul
 #endif
 
-/* Find the first occurrence of C in S or the final NUL byte.  */
+#ifdef AS_STRCHR
+static __always_inline
+#endif
 char *
-STRCHRNUL (s, c_in)
-     const char *s;
-     int c_in;
+STRCHRNUL (const char *s_in, 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 || *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.  */
-  switch (sizeof (longword))
-    {
-    case 4: magic_bits = 0x7efefeffL; break;
-    case 8: magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL; break;
-    default:
-      abort ();
-    }
-
-  /* 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 (;;)
+  char *s_aligned;
+  unsigned long int mask;
+  const unsigned long int *lptr;
+  char *s = (char *) s_in;
+  unsigned char c = (unsigned char) c_in;
+  unsigned long int cmask = c * ones;
+  if (__glibc_unlikely (c > 127))
     {
-      /* 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;
-	    }
-	}
+      s_aligned = PTR_ALIGN_DOWN (s, LSIZE);
+      lptr = (const unsigned long int *) s_aligned;
+      mask = (contains_zero(*lptr) | contains_zero (*lptr ^ cmask))
+             >> (8 * (s - s_aligned));
+
+      if (mask)
+        return s + first_nonzero_byte (mask);
+
+      while (1)
+        {
+          s_aligned += LSIZE;
+          lptr = (const unsigned long int *) s_aligned;
+          mask = contains_zero(*lptr) | contains_zero (*lptr ^ cmask);
+          if (mask)
+            return s_aligned + first_nonzero_byte (mask);
+        }
     }
-
-  /* This should never happen.  */
-  return NULL;
+  else
+    return string_skeleton (s, c, 0);
 }
 
+#ifndef AS_STRCHR
 weak_alias (__strchrnul, strchrnul)
+#endif