libstdc++: Allow Lemire's algorithm to be used in more cases

This extends the fast path to also work when the URBG's range of
possible values is not the entire range of its result_type. Previously,
the slow path would be used for engines with a uint_fast32_t result type
if that type is actually a typedef for uint64_t rather than uint32_t.
After this change, the generator's result_type is not important, only
the range of possible value that generator can produce. If the
generator's range is exactly UINT64_MAX then the calculation will be
done using 128-bit and 64-bit integers, and if the range is UINT32_MAX
it will be done using 64-bit and 32-bit integers.

In practice, this benefits most of the engines and engine adaptors
defined in [rand.predef] on x86_64-linux and other 64-bit targets. This
is because std::minstd_rand0 and std::mt19937 and others use
uint_fast32_t, which is a typedef for uint64_t.

The code now makes use of the recently-clarified requirement that the
generator's min() and max() functions are usable in constant
expressions (see LWG 2154).

libstdc++-v3/ChangeLog:

	* include/bits/uniform_int_dist.h (_Power_of_two): Add
	constexpr.
	(uniform_int_distribution::_S_nd): Add static_assert to ensure
	the wider type is twice as wide as the result type.
	(uniform_int_distribution::__generate_impl): Add static_assert
	and declare variables as constexpr where appropriate.
	(uniform_int_distribution:operator()): Likewise. Only consider
	the uniform random bit generator's range of possible results
	when deciding whether _S_nd can be used, not the __uctype type.

diff --git a/libstdc++-v3/include/bits/uniform_int_dist.h b/libstdc++-v3/include/bits/uniform_int_dist.h
index cf6ba35c675675ac85eda490716e4be487c8e7e7..524593bb9847a0900240328f6c348016c288c68b 100644 (file)
--- a/libstdc++-v3/include/bits/uniform_int_dist.h
+++ b/libstdc++-v3/include/bits/uniform_int_dist.h
@@ -58,7 +58,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
   {
     /* Determine whether number is a power of 2.  */
     template<typename _Tp>
-      inline bool
+      constexpr bool
       _Power_of_2(_Tp __x)
       {
        return ((__x - 1) & __x) == 0;
@@ -242,9 +242,12 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
        static _Up
        _S_nd(_Urbg& __g, _Up __range)
        {
-         using __gnu_cxx::__int_traits;
-         static_assert(!__int_traits<_Up>::__is_signed, "U must be unsigned");
-         static_assert(!__int_traits<_Wp>::__is_signed, "W must be unsigned");
+         using _Up_traits = __gnu_cxx::__int_traits<_Up>;
+         using _Wp_traits = __gnu_cxx::__int_traits<_Wp>;
+         static_assert(!_Up_traits::__is_signed, "U must be unsigned");
+         static_assert(!_Wp_traits::__is_signed, "W must be unsigned");
+         static_assert(_Wp_traits::__digits == (2 * _Up_traits::__digits),
+                       "W must be twice as wide as U");
 
          // reference: Fast Random Integer Generation in an Interval
          // ACM Transactions on Modeling and Computer Simulation 29 (1), 2019
@@ -260,7 +263,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
                  __low = _Up(__product);
                }
            }
-         return __product >> __gnu_cxx::__int_traits<_Up>::__digits;
+         return __product >> _Up_traits::__digits;
        }
     };
 
@@ -275,9 +278,12 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
        typedef typename make_unsigned<result_type>::type __utype;
        typedef typename common_type<_Gresult_type, __utype>::type __uctype;
 
-       const __uctype __urngmin = __urng.min();
-       const __uctype __urngmax = __urng.max();
-       const __uctype __urngrange = __urngmax - __urngmin;
+       static_assert( __urng.min() < __urng.max(),
+           "Uniform random bit generator must define min() < max()");
+
+       constexpr __uctype __urngmin = __urng.min();
+       constexpr __uctype __urngmax = __urng.max();
+       constexpr __uctype __urngrange = __urngmax - __urngmin;
        const __uctype __urange
          = __uctype(__param.b()) - __uctype(__param.a());
 
@@ -288,21 +294,26 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
 
            const __uctype __uerange = __urange + 1; // __urange can be zero
 
-           using __gnu_cxx::__int_traits;
+#if defined __UINT64_TYPE__ && defined __UINT32_TYPE__
 #if __SIZEOF_INT128__
-           if (__int_traits<__uctype>::__digits == 64
-               && __urngrange == __int_traits<__uctype>::__max)
+           if _GLIBCXX17_CONSTEXPR (__urngrange == __UINT64_MAX__)
              {
-               __ret = _S_nd<unsigned __int128>(__urng, __uerange);
+               // __urng produces values that use exactly 64-bits,
+               // so use 128-bit integers to downscale to desired range.
+               __UINT64_TYPE__ __u64erange = __uerange;
+               __ret = _S_nd<unsigned __int128>(__urng, __u64erange);
              }
            else
 #endif
-           if (__int_traits<__uctype>::__digits == 32
-               && __urngrange == __int_traits<__uctype>::__max)
+           if _GLIBCXX17_CONSTEXPR (__urngrange == __UINT32_MAX__)
              {
-               __ret = _S_nd<__UINT64_TYPE__>(__urng, __uerange);
+               // __urng produces values that use exactly 32-bits,
+               // so use 64-bit integers to downscale to desired range.
+               __UINT32_TYPE__ __u32erange = __uerange;
+               __ret = _S_nd<__UINT64_TYPE__>(__urng, __u32erange);
              }
            else
+#endif
              {
                // fallback case (2 divisions)
                const __uctype __scaling = __urngrange / __uerange;
@@ -361,9 +372,12 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
        typedef typename make_unsigned<result_type>::type __utype;
        typedef typename common_type<_Gresult_type, __utype>::type __uctype;
 
-       const __uctype __urngmin = __urng.min();
-       const __uctype __urngmax = __urng.max();
-       const __uctype __urngrange = __urngmax - __urngmin;
+       static_assert( __urng.min() < __urng.max(),
+           "Uniform random bit generator must define min() < max()");
+
+       constexpr __uctype __urngmin = __urng.min();
+       constexpr __uctype __urngmax = __urng.max();
+       constexpr __uctype __urngrange = __urngmax - __urngmin;
        const __uctype __urange
          = __uctype(__param.b()) - __uctype(__param.a());
 
@@ -417,7 +431,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
              {
                do
                  {
-                   const __uctype __uerngrange = __urngrange + 1;
+                   constexpr __uctype __uerngrange = __urngrange + 1;
                    __tmp = (__uerngrange * operator()
                             (__urng, param_type(0, __urange / __uerngrange)));
                    __ret = __tmp + (__uctype(__urng()) - __urngmin);