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 DBD9B3858D20; Tue, 30 May 2023 08:35:59 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org DBD9B3858D20
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1685435759;
	bh=bOHzGK97Z0rvCw/u4/VtyKZyaDPvRdnMxq6/dmorbwU=;
	h=From:To:Subject:Date:From;
	b=e9JFwWPVoHjwWUx/mN9vol5DEvhaR69YyWWY061VT1UuuL9nLqYtcPu1dKjOBXqEE
	 eN1Txxl3wPbpsSVqI87HbVVGzIiTejGGEA3FHIKgwhtoMS4dVgTsm3Y4g22gLniDJU
	 rNgUC/7fSE27xUaYWvY/4NVVmpN3WgCLziyurL4Q=
From: "ptk.prasertsuk at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/110035] New: Missed optimization for
 dependent assignment statements
Date: Tue, 30 May 2023 08:35:53 +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: 12.1.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: ptk.prasertsuk 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
 bug_severity priority component assigned_to reporter target_milestone
 attachments.created
Message-ID: <bug-110035-4@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=3D110035

            Bug ID: 110035
           Summary: Missed optimization for dependent assignment
                    statements
           Product: gcc
           Version: 12.1.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: ptk.prasertsuk at gmail dot com
  Target Milestone: ---

Created attachment 55212
  --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=3D55212&action=3Dedit
Test case, compiled with -stdc++=3D20 -O2

The test case, when compiled, produces additional move instructions:

movdqu  (%rdi), %xmm2
movdqu  16(%rdi), %xmm1
movdqu  32(%rdi), %xmm0
movl    $48, %edi
movaps  %xmm2, 32(%rsp)
movaps  %xmm1, 16(%rsp)
movaps  %xmm0, (%rsp)
call    _Znwm@PLT
movdqa  32(%rsp), %xmm2
movdqa  16(%rsp), %xmm1
movdqa  (%rsp), %xmm0
movq    %rax, %rdi
movups  %xmm2, (%rax)
movups  %xmm1, 16(%rax)
movups  %xmm0, 32(%rax)

compared to more optimized result using clang++ 14.0.0 with same flags:

callq   _Znwm@PLT
movups  (%rbx), %xmm0
movups  16(%rbx), %xmm1
movups  32(%rbx), %xmm2
movups  %xmm0, (%rax)
movups  %xmm1, 16(%rax)
movups  %xmm2, 32(%rax)
movq    %rax, %rdi

Clang has MemCpyOptPass which detects and removes memory dependency of the
second set of move instructions, which allows Dead Store Elimination pass to
remove the first set of move instructions.

g++-12 -v
Using built-in specs.
COLLECT_GCC=3Dg++-12
COLLECT_LTO_WRAPPER=3D/usr/lib/gcc/x86_64-linux-gnu/12/lto-wrapper
OFFLOAD_TARGET_NAMES=3Dnvptx-none:amdgcn-amdhsa
OFFLOAD_TARGET_DEFAULT=3D1
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion=3D'Ubuntu
12.1.0-2ubuntu1~22.04' --with-bugurl=3Dfile:///usr/share/doc/gcc-12/README.=
Bugs
--enable-languages=3Dc,ada,c++,go,d,fortran,objc,obj-c++,m2 --prefix=3D/usr
--with-gcc-major-version-only --program-suffix=3D-12
--program-prefix=3Dx86_64-linux-gnu- --enable-shared --enable-linker-build-=
id
--libexecdir=3D/usr/lib --without-included-gettext --enable-threads=3Dposix
--libdir=3D/usr/lib --enable-nls --enable-clocale=3Dgnu --enable-libstdcxx-=
debug
--enable-libstdcxx-time=3Dyes --with-default-libstdcxx-abi=3Dnew
--enable-gnu-unique-object --disable-vtable-verify --enable-plugin
--enable-default-pie --with-system-zlib --enable-libphobos-checking=3Drelea=
se
--with-target-system-zlib=3Dauto --enable-objc-gc=3Dauto --enable-multiarch
--disable-werror --enable-cet --with-arch-32=3Di686 --with-abi=3Dm64
--with-multilib-list=3Dm32,m64,mx32 --enable-multilib --with-tune=3Dgeneric
--enable-offload-targets=3Dnvptx-none=3D/build/gcc-12-sZcx2y/gcc-12-12.1.0/=
debian/tmp-nvptx/usr,amdgcn-amdhsa=3D/build/gcc-12-sZcx2y/gcc-12-12.1.0/deb=
ian/tmp-gcn/usr
--enable-offload-defaulted --without-cuda-driver --enable-checking=3Drelease
--build=3Dx86_64-linux-gnu --host=3Dx86_64-linux-gnu --target=3Dx86_64-linu=
x-gnu
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 12.1.0 (Ubuntu 12.1.0-2ubuntu1~22.04)=