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 BB6723858402; Thu, 22 Feb 2024 08:10:30 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org BB6723858402
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1708589430;
	bh=AaQHwZwluZV36Zy6BaIThpmMGsuCME/Top9DIaNxJLc=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=SToSgfM5gvia2XKwXaFXatvz848oDuLSansgSOHxuBUbWec8pRjTOe4iTWW8UK7PL
	 yyZBfE8IGSvuQ7UdXsElBNS5Fx2u26D0XIWHFQ3XCTpm5+1Ld3ON+oD8hA8VXtuQww
	 05CuBMHPo48prrL7gH4mIkJZBIFZunYFlldcJgM8=
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/111770] predicated loads inactive lane values
 not modelled
Date: Thu, 22 Feb 2024 08:10:29 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
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: rguenth at gcc dot gnu.org
X-Bugzilla-Status: NEW
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-111770-4-tIK4qYwgiB@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-111770-4@http.gcc.gnu.org/bugzilla/>
References: <bug-111770-4@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=3D111770

--- Comment #3 from Richard Biener <rguenth at gcc dot gnu.org> ---
As said X + 0. -> X is an invalid transform with FP unless there are no sig=
ned
zeros (maybe also problematic with sign-dependent rounding).

I think we agree to define .MASK_LOAD to zero masked elements.  When we need
something else we need to add an explicit ELSE value.  That needs documenti=
ng
of course and also possibly testsuite coverage - I _think_ you should be ab=
le
to do a GIMPLE frontend testcase for this.

Note this behavior would extend to .MASK_GATHER_LOAD as well as
the load-lanes and -len variants.

Unfortunately we do not have _any_ internals manual documentation for
internal functions - but you can backtrack to the optabs documentation
where this would need documenting.

Now, if-conversion could indeed elide the .COND_ADD for integers.  It's
problematic there only because of signed overflow undefinedness, so
you shouldn't see it for 'unsigned' already, and adding zero is safe.
if-conversion would need to have an idea of all the ranges involved here
so it might be a bit sophisticated to get it right.=