libstdc++: Enable memset optimizations for distinct character types [PR93059]

Currently we only optimize std::fill to memset when the source and
destination types are the same byte-sized type. This means that we fail
to optimize cases like std::fill(buf. buf+n, 0) because the literal 0 is
not the same type as the character buffer.

Such cases can safely be optimized to use memset, because assigning an
int (or other integer) to a narrow character type has the same effects
as converting the integer to unsigned char then copying it with memset.

This patch enables the optimized code path when the fill character is a
memcpy-able integer (using the new __memcpyable_integer trait). We still
need to check is_same<U, T> to enable the memset optimization for
filling a range of std::byte with a std::byte value, because that isn't
a memcpyable integer.

libstdc++-v3/ChangeLog:

	PR libstdc++/93059
	* include/bits/stl_algobase.h (__fill_a1(T*, T*, const T&)):
	Change template parameters and enable_if condition to allow the
	fill value to be an integer.

diff --git a/libstdc++-v3/include/bits/stl_algobase.h b/libstdc++-v3/include/bits/stl_algobase.h
index 9e92211c12460949a40906695a5a76bc767efa6a..384e5fdcdc996ee15d1f131e87a2b0c4d4903410 100644 (file)
--- a/libstdc++-v3/include/bits/stl_algobase.h
+++ b/libstdc++-v3/include/bits/stl_algobase.h
@@ -967,23 +967,27 @@ _GLIBCXX_END_NAMESPACE_CONTAINER
 #pragma GCC diagnostic pop
 
   // Specialization: for char types we can use memset.
-  template<typename _Tp>
+  template<typename _Up, typename _Tp>
     _GLIBCXX20_CONSTEXPR
     inline typename
-    __gnu_cxx::__enable_if<__is_byte<_Tp>::__value, void>::__type
-    __fill_a1(_Tp* __first, _Tp* __last, const _Tp& __c)
-    {
-      const _Tp __tmp = __c;
+    __gnu_cxx::__enable_if<__is_byte<_Up>::__value
+                            && (__are_same<_Up, _Tp>::__value // for std::byte
+                                  || __memcpyable_integer<_Tp>::__value),
+                          void>::__type
+    __fill_a1(_Up* __first, _Up* __last, const _Tp& __x)
+    {
+      // This hoists the load out of the loop and also ensures that we don't
+      // use memset for cases where the assignment would be ill-formed.
+      const _Up __val = __x;
 #if __cpp_lib_is_constant_evaluated
       if (std::is_constant_evaluated())
        {
          for (; __first != __last; ++__first)
-           *__first = __tmp;
-         return;
+           *__first = __val;
        }
 #endif
       if (const size_t __len = __last - __first)
-       __builtin_memset(__first, static_cast<unsigned char>(__tmp), __len);
+       __builtin_memset(__first, static_cast<unsigned char>(__val), __len);
     }
 
   template<typename _Ite, typename _Cont, typename _Tp>