From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugzilla@gcc.gnu.org>
Received: by sourceware.org (Postfix, from userid 48)
	id E8B223858D38; Tue, 23 Apr 2024 08:52:29 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org E8B223858D38
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1713862349;
	bh=pCVBOf1YWHkFJSpO0s61gu7PUpTFptLCBM/RgK8b5UM=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=CBYmAJsfal67JAuIKazLe1/2dgg078ZRF0EJfg7FqZxAPBdQExByzRfiykZEShUE4
	 B92xJzHBfzDG4wj5hOJArNda0dMAwKF4PwxKGvOkQ74JddwLcMTGojx5L8g+uNJ/ia
	 tYlaMLXwhByOUAz+/OXDIVi4gR5jlvoWG9ZrrYtk=
From: "hubicka at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug libstdc++/114821] _M_realloc_append should use memcpy instead
 of loop to copy data when possible
Date: Tue, 23 Apr 2024 08:52:29 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: libstdc++
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: hubicka at gcc dot gnu.org
X-Bugzilla-Status: UNCONFIRMED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-114821-4-XBpBevNS6Y@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-114821-4@http.gcc.gnu.org/bugzilla/>
References: <bug-114821-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
List-Id: <gcc-bugs.sourceware.org>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D114821

--- Comment #2 from Jan Hubicka <hubicka at gcc dot gnu.org> ---
What I am shooting for is to optimize it later in loop distribution. We can
recognize memcpy loop if we can figure out that source and destination memo=
ry
are different.

We can help here with restrict, but I was bit lost in how to get them done.

This seems to do the trick, but for some reason I get memmove

diff --git a/libstdc++-v3/include/bits/stl_uninitialized.h
b/libstdc++-v3/include/bits/stl_uninitialized.h
index 7f84da31578..1a6223ea892 100644
--- a/libstdc++-v3/include/bits/stl_uninitialized.h
+++ b/libstdc++-v3/include/bits/stl_uninitialized.h
@@ -1130,7 +1130,58 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
        }
       return __result + __count;
     }
+
+  template <typename _Tp, typename _Allocator>
+    _GLIBCXX20_CONSTEXPR
+    inline __enable_if_t<std::__is_bitwise_relocatable<_Tp>::value, _Tp*>
+    __relocate_a(_Tp * __restrict __first, _Tp *__last,
+                _Tp * __restrict __result, _Allocator& __alloc) noexcept
+    {
+      ptrdiff_t __count =3D __last - __first;
+      if (__count > 0)
+       {
+#ifdef __cpp_lib_is_constant_evaluated
+         if (std::is_constant_evaluated())
+           {
+             for (; __first !=3D __last; ++__first, (void)++__result)
+               {
+                 // manually inline relocate_object_a to not lose restrict
qualifiers
+                 typedef std::allocator_traits<_Allocator> __traits;
+                 __traits::construct(__alloc, __result, std::move(*__first=
));
+                 __traits::destroy(__alloc, std::__addressof(*__first));
+               }
+             return __result;
+           }
 #endif
+         __builtin_memcpy(__result, __first, __count * sizeof(_Tp));
+       }
+      return __result + __count;
+    }
+#endif
+
+  template <typename _Tp, typename _Allocator>
+    _GLIBCXX20_CONSTEXPR
+#if _GLIBCXX_HOSTED
+    inline __enable_if_t<!std::__is_bitwise_relocatable<_Tp>::value, _Tp*>
+#else
+    inline _Tp *
+#endif
+    __relocate_a(_Tp * __restrict __first, _Tp *__last,
+                _Tp * __restrict __result, _Allocator& __alloc)
+    noexcept(noexcept(std::allocator_traits<_Allocator>::construct(__alloc,
+                        __result, std::move(*__first)))
+            && noexcept(std::allocator_traits<_Allocator>::destroy(
+                           __alloc, std::__addressof(*__first))))
+    {
+      for (; __first !=3D __last; ++__first, (void)++__result)
+       {
+         // manually inline relocate_object_a to not lose restrict qualifi=
ers
+         typedef std::allocator_traits<_Allocator> __traits;
+         __traits::construct(__alloc, __result, std::move(*__first));
+         __traits::destroy(__alloc, std::__addressof(*__first));
+       }
+      return __result;
+    }

   template <typename _InputIterator, typename _ForwardIterator,
            typename _Allocator>=