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 85F753858C2B; Mon, 15 May 2023 09:31:09 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 85F753858C2B
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1684143069;
	bh=s2Zfx2hCeJqDbi0SArVej2b5dRYP+ejMqjVGBK0tNm0=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=MhjyAw/GFSkvK+HMG39JrBB4GgtuVw3rPSMzcqD3wcphGR9tp1kqvSPxiGKEU2Z+e
	 gCXcwqRHC1lBwTZQQS+UpfxOdo+7gly4VU3/qy1OR6KOdxPPdMsk4w2ylzTa8ngDoB
	 YRhk76XesTNZealULML7soCwGNXHmCCnBkXVP3QQ=
From: "burnus at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug libgomp/109837] [OpenMP] despite 'requires unified_address'
 there is segfault when 'is_device_ptr' is not used
Date: Mon, 15 May 2023 09:31:08 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: libgomp
X-Bugzilla-Version: 13.0
X-Bugzilla-Keywords: wrong-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: burnus at gcc dot gnu.org
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: 
Message-ID: <bug-109837-4-Eqz5Jsyiyi@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-109837-4@http.gcc.gnu.org/bugzilla/>
References: <bug-109837-4@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=3D109837

--- Comment #1 from Tobias Burnus <burnus at gcc dot gnu.org> ---
Minor correction/clarification:

  (B) omp_target_is_accessible - will properly work for such pointers.

While it might be useful to handle also (C/C++) code like:
  ptr =3D omp_target_alloc (...);
  ...
  is_accessible =3D omp_target_is_accessible(ptr, ...);

The OpenMP spec only requires:
"The *omp_target_is_accessible* routine tests whether host memory is access=
ible
from a given device."

And "ptr" is a device pointer. Thus, returning FALSE for all such pointers,
unless in shared memory, is OK.

=E2=86=92 Still, we might consider to add checking for memory that is both =
host and
device accessible - or is a device pointer in the unified-address case.
(Quality of Implementation Feature).

* * *

Besides 'is_device_ptr', the same is required for has_device_addr like in
(Fortran):

  c_ptr =3D omp_alloc(...)
  call c_f_pointer (c_ptr, fptr)
  !$omp target
    fptr =3D ...

[That has_device_addr is not mentioned for 'requires unified_addr' is the
OpenMP Spec Issue #3606.]=