From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 5649C384B110; Thu, 8 Oct 2020 16:14:18 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 5649C384B110 From: "vries at gcc dot gnu.org" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/97338] New: [nvptx] Convergence checking Date: Thu, 08 Oct 2020 16:14:18 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: new X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: gcc X-Bugzilla-Component: target X-Bugzilla-Version: 11.0 X-Bugzilla-Keywords: X-Bugzilla-Severity: enhancement X-Bugzilla-Who: vries 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: bug_id short_desc product version bug_status bug_severity priority component assigned_to reporter target_milestone Message-ID: 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 X-BeenThere: gcc-bugs@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gcc-bugs mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 08 Oct 2020 16:14:18 -0000 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D97338 Bug ID: 97338 Summary: [nvptx] Convergence checking Product: gcc Version: 11.0 Status: UNCONFIRMED Severity: enhancement Priority: P3 Component: target Assignee: unassigned at gcc dot gnu.org Reporter: vries at gcc dot gnu.org Target Milestone: --- With ptx, we have insns that need to be executed in convergent mode, that i= s, all threads in the warp active. We can unfortunately not enforce this, but we could check it, which could h= elp pinpoint problems. A ptx insn: ... vote.ballot.b32 %rbla, 1; ... gives us the regmask of active threads, so we could check: ... { .reg .u32 %rwarp_active_mask; vote.ballot.b32 %rwarp_active_mask, 1; .reg .pred %pconvergent; setp.eq.u32 %pconvergent,%rwarp_active_mask,-1; @ ! %pconvergent trap; } ...=