From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 076A83987C33; Fri, 25 Sep 2020 12:52:14 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 076A83987C33 From: "linkw at gcc dot gnu.org" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/96789] x264: sub4x4_dct() improves when vectorization is disabled Date: Fri, 25 Sep 2020 12:52:14 +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: 11.0 X-Bugzilla-Keywords: missed-optimization X-Bugzilla-Severity: normal X-Bugzilla-Who: linkw at gcc dot gnu.org X-Bugzilla-Status: ASSIGNED X-Bugzilla-Resolution: X-Bugzilla-Priority: P3 X-Bugzilla-Assigned-To: linkw 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 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: Fri, 25 Sep 2020 12:52:15 -0000 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D96789 --- Comment #19 from Kewen Lin --- (In reply to rguenther@suse.de from comment #17) > On Fri, 18 Sep 2020, linkw at gcc dot gnu.org wrote: >=20 > > https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D96789 > >=20 > > --- Comment #15 from Kewen Lin --- > > (In reply to rguenther@suse.de from comment #14) > > > On Fri, 18 Sep 2020, linkw at gcc dot gnu.org wrote: > > >=20 > > > > https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D96789 > > > >=20 > > > > --- Comment #13 from Kewen Lin --- > > > > > 2) on Power, the conversion from unsigned char to unsigned shor= t is nop > > > > > conversion, when we counting scalar cost, it's counted, then add = costs 32 > > > > > totally onto scalar cost. Meanwhile, the conversion from unsigned= short to > > > > > signed short should be counted but it's not (need to check why fu= rther).=20 > > > >=20 > > > > UH to SH conversion is true when calling vect_nop_conversion_p, so = it's not > > > > even put into the cost vector.=20 > > > >=20 > > > > tree_nop_conversion_p's comments saying: > > > >=20 > > > > /* Return true iff conversion from INNER_TYPE to OUTER_TYPE generat= es > > > > no instruction. */ > > > >=20 > > > > I may miss something here, but UH to SH conversion does need one ex= plicit > > > > extend instruction *extsh*, the precision/mode equality check looks= wrong for > > > > this conversion. > > >=20 > > > Well, it isn't a RTL predicate and it only needs extension because > > > there's never a HImode pseudo but always SImode subregs. > >=20 > > Thanks Richi! Should we take care of this case? or neglect this kind of > > extension as "no instruction"? I was intent to handle it in target spec= ific > > code, but it isn't recorded into cost vector while it seems too heavy t= o do the > > bb_info slp_instances revisits in finish_cost. >=20 > I think it's not something we should handle on GIMPLE. Got it! For=20 else if (vect_nop_conversion_p (stmt_info)) continue; Is it a good idea to change it to call record_stmt_cost like the others?=20 1) introduce one vect_cost_for_stmt enum type eg: nop_stmt 2) builtin_vectorization_cost return zero for it by default as before. 3) targets can adjust the cost according to its need=