diff mbox

[v2,08/16] Improve generic memrchr

Message ID 20161221230605.28638-9-rth@twiddle.net
State New
Headers show

Commit Message

Richard Henderson Dec. 21, 2016, 11:05 p.m. UTC
[BZ #5806]
	* string/memrchr.c: Use string-fzb.h, string-fzi.h.
---
 string/memrchr.c | 205 +++++++++++++++----------------------------------------
 1 file changed, 55 insertions(+), 150 deletions(-)
diff mbox

Patch

diff --git a/string/memrchr.c b/string/memrchr.c
index b9b0c9e..ed9ceaf 100644
--- a/string/memrchr.c
+++ b/string/memrchr.c
@@ -21,180 +21,85 @@ 
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-#include <stdlib.h>
-
-#ifdef HAVE_CONFIG_H
-# include <config.h>
-#endif
-
-#undef __ptr_t
-#define __ptr_t void *
-
-#if defined _LIBC
-# include <string.h>
-# include <memcopy.h>
-#endif
-
-#if defined HAVE_LIMITS_H || defined _LIBC
-# include <limits.h>
-#endif
-
-#define LONG_MAX_32_BITS 2147483647
-
-#ifndef LONG_MAX
-# define LONG_MAX LONG_MAX_32_BITS
-#endif
-
-#include <sys/types.h>
+#include <string.h>
+#include <stdint.h>
+#include <limits.h>
+#include <string-fzb.h>
+#include <string-fzi.h>
+#include <string-opthr.h>
 
 #undef __memrchr
 #undef memrchr
 
-#ifndef weak_alias
-# define __memrchr memrchr
-#endif
-
 /* Search no more than N bytes of S for C.  */
-__ptr_t
-#ifndef MEMRCHR
-__memrchr
-#else
-MEMRCHR
+
+#ifdef MEMRCHR
+# define __memrchr MEMRCHR
 #endif
-     (const __ptr_t s, int c_in, size_t n)
+
+void *
+__memrchr (const void *s, int c_in, size_t n)
 {
-  const unsigned char *char_ptr;
-  const unsigned long int *longword_ptr;
-  unsigned long int longword, magic_bits, charmask;
+  const unsigned char *char_ptr = (const unsigned char *) s + n;
+  const op_t *word_ptr;
+  op_t word, repeated_c;
+  uintptr_t i, align;
   unsigned char c;
 
   c = (unsigned char) c_in;
 
   /* Handle the last 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 + n;
-       n > 0 && ((unsigned long int) char_ptr
-		 & (sizeof (longword) - 1)) != 0;
-       --n)
+     Do this until CHAR_PTR is aligned on a word boundary, or
+     the entirety of small inputs.  */
+  align = (uintptr_t)char_ptr % sizeof (word);
+  if (n < OP_T_THRES || align > n)
+    align = n;
+  for (i = 0; i < align; ++i)
     if (*--char_ptr == c)
-      return (__ptr_t) char_ptr;
-
-  /* All these elucidatory comments refer to 4-byte longwords,
-     but the theory applies equally well to 8-byte longwords.  */
-
-  longword_ptr = (const 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:
+      return (void *) char_ptr;
 
-     bits:  01111110 11111110 11111110 11111111
-     bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
+  /* Set up a word, each of whose bytes is C.  */
+  repeated_c = ((op_t)-1 / 0xff) * c;
 
-     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;
+  word_ptr = (const op_t *) char_ptr;
+  n -= align;
+  if (__glibc_unlikely (n == 0))
+    return NULL;
 
-  /* Set up a longword, each of whose bytes is C.  */
-  charmask = c | (c << 8);
-  charmask |= charmask << 16;
-#if LONG_MAX > LONG_MAX_32_BITS
-  charmask |= charmask << 32;
-#endif
-
-  /* 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.  */
-  while (n >= sizeof (longword))
+  /* Loop while we have at least one word remaining.  */
+  while (n >= sizeof (word))
     {
-      /* 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, not 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 ^ charmask;
-
-      /* 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)
+      word = *--word_ptr;
+      if (has_eq (word, repeated_c))
 	{
-	  /* Which of the bytes was C?  If none of them were, it was
-	     a misfire; continue the search.  */
-
-	  const unsigned char *cp = (const unsigned char *) longword_ptr;
-
-#if LONG_MAX > 2147483647
-	  if (cp[7] == c)
-	    return (__ptr_t) &cp[7];
-	  if (cp[6] == c)
-	    return (__ptr_t) &cp[6];
-	  if (cp[5] == c)
-	    return (__ptr_t) &cp[5];
-	  if (cp[4] == c)
-	    return (__ptr_t) &cp[4];
-#endif
-	  if (cp[3] == c)
-	    return (__ptr_t) &cp[3];
-	  if (cp[2] == c)
-	    return (__ptr_t) &cp[2];
-	  if (cp[1] == c)
-	    return (__ptr_t) &cp[1];
-	  if (cp[0] == c)
-	    return (__ptr_t) cp;
+	  word ^= repeated_c;
+	  goto found;
 	}
-
-      n -= sizeof (longword);
+      n -= sizeof (word);
     }
 
-  char_ptr = (const unsigned char *) longword_ptr;
-
-  while (n-- > 0)
+  /* Handle any remaining portion of a word.  */
+  if (n > 0)
     {
-      if (*--char_ptr == c)
-	return (__ptr_t) char_ptr;
-    }
+      word = *--word_ptr ^ repeated_c;
 
-  return 0;
+      /* Mask out the garbage bytes at the front of WORD.  */
+      op_t m = -1;
+      if (__BYTE_ORDER == __LITTLE_ENDIAN)
+	m >>= n * CHAR_BIT;
+      else
+	m <<= n * CHAR_BIT;
+      word |= m;
+
+      if (has_zero (word))
+	{
+	found:
+	  return (char *) word_ptr + index_last_zero (word);
+	}
+    }
+  return NULL;
 }
+
 #ifndef MEMRCHR
-# ifdef weak_alias
 weak_alias (__memrchr, memrchr)
-# endif
 #endif