From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 59CAE3858D37; Thu, 25 May 2023 22:32:17 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 59CAE3858D37 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1685053937; bh=wI5ofL16A53AY5JtUiwOmjuzJXitF3/yqBL1KElFjtg=; h=From:To:Subject:Date:In-Reply-To:References:From; b=Sh9u2AQJ7gUMA/kjasi4mQjWkAMINQVD97VbFvrpI9Kk6YyBtEG10gKonJCVq7PWZ rEoOj1/LoFcqB9IUqsRT+eZpTi6wKRYP/e8GMmpQzYnrT/KHz+IA4Epmemy0Zk8eP0 fQ+rMd/kedv0oSURrA3tond0o0YQrITLeQygjfMQ= From: "juzhe.zhong at rivai dot ai" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/109971] [14 regression] Several powerpc64 vector test cases fail after r14-1242-gf574e2dfae7905 Date: Thu, 25 May 2023 22:32:17 +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: X-Bugzilla-Severity: normal X-Bugzilla-Who: juzhe.zhong at rivai dot ai 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: In-Reply-To: References: 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: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D109971 --- Comment #1 from JuzheZhong --- It seems this condition: + /* If we're vectorizing a loop that uses length "controls" and + can iterate more than once, we apply decrementing IV approach + in loop control. */ + if (LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo) + && !LOOP_VINFO_LENS (loop_vinfo).is_empty () + && LOOP_VINFO_PARTIAL_LOAD_STORE_BIAS (loop_vinfo) =3D=3D 0 + && !(LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo) + && known_le (LOOP_VINFO_INT_NITERS (loop_vinfo), + LOOP_VINFO_VECT_FACTOR (loop_vinfo)))) + LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo) =3D true; dit not disable decrement IV in powerPC.=20 Sorry for creating this issue since I only tested on X86. Should I add target hook for decrement IV? I am waiting for Richard's comments.=