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 3C5303858D37; Mon, 12 Feb 2024 14:41:34 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 3C5303858D37
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1707748894;
	bh=IYtefXdp194ydYEbedy8iwTuKyUkU+xtyA8AHVxNQl8=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=tBPff0IdHnN9pL/XP19oR4uP5XxB1Sh7Qjm8R6EUc0CkMvzhcbj1MAZ1NULKn//bw
	 ComShFSLXwouwkkra9IDte8yEnEn/IyOTqVG3vs/KsyjTpdYX11BzaOAeZ/KE/n0U4
	 thEFO1bE4BEQ7TMJCsiLXr1Ua7rCoEVOodC8XhI4=
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/113847] [14 Regression] 10% slowdown of 462.libquantum
 on AMD Ryzen 7700X and Ryzen 7900X
Date: Mon, 12 Feb 2024 14:41:33 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
X-Bugzilla-Status: ASSIGNED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: rguenth at gcc dot gnu.org
X-Bugzilla-Target-Milestone: 14.0
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: cc
Message-ID: <bug-113847-4-W0mOQ5fasp@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-113847-4@http.gcc.gnu.org/bugzilla/>
References: <bug-113847-4@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=3D113847

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |hubicka at gcc dot gnu.org

--- Comment #4 from Richard Biener <rguenth at gcc dot gnu.org> ---
Hmm, the important one is actually MEM[ptr + CST] vs MEM[ptr].component.  B=
ut
those are not semantically equivalent, even when the same TBAA type is in
effect.

  _31 =3D MEM <int> [(struct quantum_reg *)reg_3(D)];
  _33 =3D MEM <int> [(struct quantum_reg *)reg_3(D) + 8B];
  _34 =3D MEM <struct quantum_reg_node *> [(struct quantum_reg *)reg_3(D) +=
 16B];
  _35 =3D MEM <int *> [(struct quantum_reg *)reg_3(D) + 24B];
  out =3D quantum_state_collapse.isra (pos_1(D), result_22, _31, _32, _33, =
_34,
_35); [return slot optimization]

this is from inlined quantum_state_collapse where IPA SRA is eventually
applied producing the above.

That we do produce those might hint at that we can't really assume the
dynamic type quantum_reg is at offset 8 but that was the original intent.
What we are left with is the special-case where typeof (MEM[ptr + CST])
=3D=3D typeof (alias-pointed-to-type) (with CST =3D=3D 0).  For any other c=
ase
what we know is only that the access MEM[ptr + CST] is to somewhere
inside an object of dynamic type quantum_reg?

I'm not sure that's not less than we make use of in the alias-oracle,
esp. aliasing_component_refs_walk and friends?  We might be fine in
practice for "bare" MEM_REFs like the above, but if we ever fold only
part of the access path into the constant offset funny things may happen?

So I think IPA SRA does wrong here (and maybe GCC in other places as well),
possibly only pessimizing and possibly creating latent wrong-code.
Note quantum_state_collapse has

  reg$size_62 =3D reg.size;
  reg$node_75 =3D reg.node;
...

pre-IPA.

Honza, any opinion?=