[PATCH 1/4] Improve generic strcspn performance

[Adhemerval Zanella]

From: Wilco Dijkstra <wdijkstr@arm.com>

Improve strcspn performance using a much faster algorithm.  It is kept simple
so it works well on most targets.  It is generally at least 10 times faster
than the existing implementation on bench-strcspn on a few AArch64
implementations, and for some tests 100 times as fast (repeatedly calling
strchr on a small string is extremely slow...).

In fact the string/bits/string2.h inlines make no longer sense, as GCC
already uses strlen if reject is an empty string, strchrnul is 5 times as
fast as __strcspn_c1, while __strcspn_c2 and __strcspn_c3 are slower than
the strcspn main loop for large strings (though reject length 2-4 could be
special cased in the future to gain even more performance).

Tested on x86_64, i686, and aarch64.

	* string/strcspn.c (strcspn): Rewrite function.
	* string/bits/string2.h (strcspn): Use __builtin_strcspn.
---
 ChangeLog             |  6 ++++++
 string/bits/string2.h | 41 ++++++-----------------------------------
 string/strcspn.c      | 44 ++++++++++++++++++++++++++++++++++++--------
 3 files changed, 48 insertions(+), 43 deletions(-)

diff --git a/string/bits/string2.h b/string/bits/string2.h
index 8200ef1..1b87686 100644
--- a/string/bits/string2.h
+++ b/string/bits/string2.h
@@ -905,43 +905,14 @@ __stpcpy_small (char *__dest,
 
 /* Return the length of the initial segment of S which
    consists entirely of characters not in REJECT.  */
-#if !defined _HAVE_STRING_ARCH_strcspn || defined _FORCE_INLINES
-# ifndef _HAVE_STRING_ARCH_strcspn
-#  if __GNUC_PREREQ (3, 2)
-#   define strcspn(s, reject) \
-  __extension__								      \
-  ({ char __r0, __r1, __r2;						      \
-     (__builtin_constant_p (reject) && __string2_1bptr_p (reject)	      \
-      ? ((__builtin_constant_p (s) && __string2_1bptr_p (s))		      \
-	 ? __builtin_strcspn (s, reject)				      \
-	 : ((__r0 = ((const char *) (reject))[0], __r0 == '\0')		      \
-	    ? strlen (s)						      \
-	    : ((__r1 = ((const char *) (reject))[1], __r1 == '\0')	      \
-	       ? __strcspn_c1 (s, __r0)					      \
-	       : ((__r2 = ((const char *) (reject))[2], __r2 == '\0')	      \
-		  ? __strcspn_c2 (s, __r0, __r1)			      \
-		  : (((const char *) (reject))[3] == '\0'		      \
-		     ? __strcspn_c3 (s, __r0, __r1, __r2)		      \
-		     : __builtin_strcspn (s, reject))))))		      \
-      : __builtin_strcspn (s, reject)); })
-#  else
-#   define strcspn(s, reject) \
-  __extension__								      \
-  ({ char __r0, __r1, __r2;						      \
-     (__builtin_constant_p (reject) && __string2_1bptr_p (reject)	      \
-      ? ((__r0 = ((const char *) (reject))[0], __r0 == '\0')		      \
-	 ? strlen (s)							      \
-	 : ((__r1 = ((const char *) (reject))[1], __r1 == '\0')		      \
-	    ? __strcspn_c1 (s, __r0)					      \
-	    : ((__r2 = ((const char *) (reject))[2], __r2 == '\0')	      \
-	       ? __strcspn_c2 (s, __r0, __r1)				      \
-	       : (((const char *) (reject))[3] == '\0'			      \
-		  ? __strcspn_c3 (s, __r0, __r1, __r2)			      \
-		  : strcspn (s, reject)))))				      \
-      : strcspn (s, reject)); })
-#  endif
+#ifndef _HAVE_STRING_ARCH_strcspn
+# if __GNUC_PREREQ (3, 2)
+#  define strcspn(s, reject) __builtin_strcspn (s, reject)
 # endif
 
+ /* The inline functions are not used from GLIBC 2.24 and forward, however
+    they are required to provide the symbols through string-inlines.c
+    (if inlining is not possible for compatibility reasons).  */
 __STRING_INLINE size_t __strcspn_c1 (const char *__s, int __reject);
 __STRING_INLINE size_t
 __strcspn_c1 (const char *__s, int __reject)
diff --git a/string/strcspn.c b/string/strcspn.c
index 8888919..89ba4ca 100644
--- a/string/strcspn.c
+++ b/string/strcspn.c
@@ -26,16 +26,44 @@
 /* Return the length of the maximum initial segment of S
    which contains no characters from REJECT.  */
 size_t
-STRCSPN (const char *s, const char *reject)
+STRCSPN (const char *str, const char *reject)
 {
-  size_t count = 0;
+  if (reject[0] == '\0' || reject[1] == '\0')
+    return __strchrnul (str, reject [0]) - str;
 
-  while (*s != '\0')
-    if (strchr (reject, *s++) == NULL)
-      ++count;
-    else
-      return count;
+  /* Use multiple small memsets to enable inlining on most targets.  */
+  unsigned char table[256];
+  unsigned char *p = memset (table, 0, 64);
+  memset (p + 64, 0, 64);
+  memset (p + 128, 0, 64);
+  memset (p + 192, 0, 64);
 
-  return count;
+  unsigned char *s = (unsigned char*) reject;
+  unsigned char tmp;
+  do
+    p[tmp = *s++] = 1;
+  while (tmp);
+
+  s = (unsigned char*) str;
+  if (p[s[0]]) return 0;
+  if (p[s[1]]) return 1;
+  if (p[s[2]]) return 2;
+  if (p[s[3]]) return 3;
+
+  s = (unsigned char *) ((size_t)s & ~3);
+
+  unsigned int c0, c1, c2, c3;
+  do
+    {
+      s += 4;
+      c0 = p[s[0]];
+      c1 = p[s[1]];
+      c2 = p[s[2]];
+      c3 = p[s[3]];
+    }
+  while ((c0 | c1 | c2 | c3) == 0);
+
+  size_t count = s - (unsigned char *) str;
+  return (c0 | c1) != 0 ? count - c0 + 1 : count - c2 + 3;
 }
 libc_hidden_builtin_def (strcspn)
-- 
1.9.1