re PR libstdc++/58625 (std::signbit always converts to double)

2013-10-06  Oleg Endo  <olegendo@gcc.gnu.org>
	    Paolo Carlini  <paolo.carlini@oracle.com>

	PR libstdc++/58625
	* include/c_global/cmath (signbit): Use __builtin_signbitf and
	__builtin_signbitl.

Co-Authored-By: Paolo Carlini <paolo.carlini@oracle.com>

From-SVN: r203228

libstdc++-v3/ChangeLog

+2013-10-06  Oleg Endo  <olegendo@gcc.gnu.org>
+	    Paolo Carlini  <paolo.carlini@oracle.com>
+
+	PR libstdc++/58625
+	* include/c_global/cmath (signbit): Use __builtin_signbitf and
+	__builtin_signbitl.
+
 2013-10-03  Tim Shen  <timshen91@gmail.com>
 
 	* include/bits/regex_executor.tcc (_DFSExecutor<>::_M_dfs): Fix wrong

libstdc++-v3/include/c_global/cmath

@@ -650,9 +650,10 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
     isnormal(_Tp __x)
     { return __x != 0 ? true : false; }
 
+  // The front-end doesn't provide a type generic builtin (libstdc++/58625).
   constexpr bool
   signbit(float __x)
-  { return __builtin_signbit(__x); }
+  { return __builtin_signbitf(__x); }
 
   constexpr bool
   signbit(double __x)
@@ -660,7 +661,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
 
   constexpr bool
   signbit(long double __x)
-  { return __builtin_signbit(__x); }
+  { return __builtin_signbitl(__x); }
 
   template<typename _Tp>
     constexpr typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value,