Use long long builtins of zero counting for x86-64.

gcc/longlong.h

 /* longlong.h -- definitions for mixed size 32/64 bit arithmetic.
    Copyright (C) 1991, 1992, 1994, 1995, 1996, 1997, 1998, 1999, 2000,
-   2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009
+   2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
    Free Software Foundation, Inc.
 
    This file is part of the GNU C Library.
 
    The GNU C Library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Lesser General Public
    License as published by the Free Software Foundation; either
    version 2.1 of the License, or (at your option) any later version.
 
    In addition to the permissions in the GNU Lesser General Public
@@ skipping 386 matching lines @@
              "=d" ((UDItype) (w1))                                      \
            : "%0" ((UDItype) (u)),                                      \
              "rm" ((UDItype) (v)))
 #define udiv_qrnnd(q, r, n1, n0, dv) \
   __asm__ ("div{q} %4"                                                  \
            : "=a" ((UDItype) (q)),                                      \
              "=d" ((UDItype) (r))                                       \
            : "0" ((UDItype) (n0)),                                      \
              "1" ((UDItype) (n1)),                                      \
              "rm" ((UDItype) (dv)))
-#define count_leading_zeros(count, x)   ((count) = __builtin_clzl (x))
-#define count_trailing_zeros(count, x)  ((count) = __builtin_ctzl (x))
+#define count_leading_zeros(count, x)   ((count) = __builtin_clzll (x))
+#define count_trailing_zeros(count, x)  ((count) = __builtin_ctzll (x))
 #define UMUL_TIME 40
 #define UDIV_TIME 40
 #endif /* x86_64 */
 
 #if defined (__i960__) && W_TYPE_SIZE == 32
 #define umul_ppmm(w1, w0, u, v) \
   ({union {UDItype __ll;                                                \
            struct {USItype __l, __h;} __i;                              \
           } __xx;                                                       \
   __asm__ ("emul        %2,%1,%0"                                       \
@@ skipping 1094 matching lines @@
     UWtype __ctz_x = (x);                                               \
     UWtype __ctz_c;                                                     \
     count_leading_zeros (__ctz_c, __ctz_x & -__ctz_x);                  \
     (count) = W_TYPE_SIZE - 1 - __ctz_c;                                \
   } while (0)
 #endif
 
 #ifndef UDIV_NEEDS_NORMALIZATION
 #define UDIV_NEEDS_NORMALIZATION 0
 #endif