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 CD216385772E; Thu, 23 Nov 2023 14:41:21 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org CD216385772E
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1700750481;
	bh=/L4CEbid4ZgCdrPkzDCVqZvCMF4a3BLxpCqawWliytA=;
	h=From:To:Subject:Date:From;
	b=IFTWoVNIRY0TUohaj5fqbD8IiHTl+Co7+lKwIuLXw0APwHoTZyblsWxI3snRe9auj
	 Y6urbUtLVcQgy8IAhn1bQo8IzS6v2p0TviwH19IZwuwCT3jQY4KNkuTPBnRE7BZhds
	 JwmRnw/QCfmHeuyMfCsIWVIDhqQW0o0Qmz51zm3M=
From: "antoshkka at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/112683] New: Optimizing memcpy range by
 extending to word bounds
Date: Thu, 23 Nov 2023 14:41:21 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: antoshkka at gmail dot com
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: bug_id short_desc product version bug_status
 keywords bug_severity priority component assigned_to reporter
 target_milestone
Message-ID: <bug-112683-4@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=3D112683

            Bug ID: 112683
           Summary: Optimizing memcpy range by extending to word bounds
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: antoshkka at gmail dot com
  Target Milestone: ---

Consider the minimized source code from libstdc++

```
struct string {
    unsigned long _M_string_length;
    enum { _S_local_capacity =3D 15 };
    char _M_local_buf[_S_local_capacity + 1];
};

string copy(const string& __str) noexcept {
    string result;

    if (__str._M_string_length > __str._S_local_capacity)
        __builtin_unreachable();

    result._M_string_length =3D __str._M_string_length;
    __builtin_memcpy(result._M_local_buf, __str._M_local_buf,
                     __str._M_string_length + 1);

    return result;
}
```

Right now GCC with -O2 emits a long assembly with ~50 instructions
https://godbolt.org/z/a89bh17hd

However, note that
* the `result._M_local_buf` is uninitialized,
* there's at most 16 bytes to copy to `result._M_local_buf` which is of siz=
e 16
bytes

So the compiler could optimize the code to always copy 16 bytes. The behavi=
or
change is not observable by user as the uninitialized bytes could contain a=
ny
data, including the same bytes as `_str._M_local_buf`.

As a result of always copying 16 bytes, the assembly becomes more than 7 ti=
mes
shorter, conditional jumps go away: https://godbolt.org/z/r5GPYTs4Y=