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 D8A713858298; Fri, 17 Nov 2023 09:28:39 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org D8A713858298
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1700213319;
	bh=MkksJxRJu6z8QUP+yxUQikAKK3ddcQyuyZAziN3DRmE=;
	h=From:To:Subject:Date:From;
	b=OjJrAbiKfC++5FmQvPgVp3lL0WdEmVOoQp42uiS8l6Hgx9bWykmZPLDvJ5EoopI3Z
	 thqmq4Pg0m5dXvLnHJPq/RkLg4/tNlPAEvyhtRGjLQRGz+KUYk2Ed6GZ7K+/0UQkG5
	 TQCjoyXNIqNEhWeiemYlSa4mh1w2TSecC4fWqeqg=
From: "antoshkka at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/112584] New: Suboptimal stack usage on third
 memcpy
Date: Fri, 17 Nov 2023 09:28:39 +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: 13.2.1
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-112584-4@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=3D112584

            Bug ID: 112584
           Summary: Suboptimal stack usage on third memcpy
           Product: gcc
           Version: 13.2.1
            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 example:


struct string_view {
    const char* data;
    unsigned long size;
};

void AppendToCharArray(char*& data, string_view s1, string_view s2, string_=
view
s3) {
  __builtin_memcpy(data, s1.data, s1.size);
  data +=3D s1.size;

  __builtin_memcpy(data, s2.data, s2.size);
  data +=3D s2.size;

  __builtin_memcpy(data, s3.data, s3.size);
  data +=3D s3.size;
}


With -O2 it generates an assembly with 6 push and 6 pop instructions. Howev=
er,
there's a better assembly possible:

  push r15
  push r14
  push r12
  push rbx
  push rax
  mov rbx, r8
  mov r14, rcx
  mov r15, rdx
  mov r12, rdi
  mov rdi, qword ptr [rdi]
  call memcpy
  add r15, qword ptr [r12]
  mov qword ptr [r12], r15
  mov rdi, r15
  mov rsi, r14
  mov rdx, rbx
  call memcpy
  add rbx, qword ptr [r12]
  mov qword ptr [r12], rbx
  mov rsi, qword ptr [rsp + 48]
  mov r14, qword ptr [rsp + 56]
  mov rdi, rbx
  mov rdx, r14
  call memcpy
  add qword ptr [r12], r14
  add rsp, 8
  pop rbx
  pop r12
  pop r14
  pop r15
  ret

Godbolt playground: https://godbolt.org/z/EY8E1GGPz=