From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id A15BC3858D37; Wed, 31 May 2023 03:11:46 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org A15BC3858D37 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1685502706; bh=ckSIvSNFthSOqHDv87b3z4UnsncV3JglLS/StRgFvpY=; h=From:To:Subject:Date:In-Reply-To:References:From; b=Da4cN8gO22cJSteSABT29jCFrOyC5zyvfbvDXZs1fng+F3neDCDqFZXM+9xUuceRo d/qaLpOOIA6PgPRg6me0DNIuP45xBN37HFiJZ2qVAGHLbLJHe2IpaqKdujJMCjg72O cS9av0rTHVWCPBriFGPSmN6LH/DkqOqtrKQNFXR8= From: "linkw at gcc dot gnu.org" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/109971] [14 regression] Several powerpc64 vector test cases fail after r14-1242-gf574e2dfae7905 Date: Wed, 31 May 2023 03:11:46 +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: 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: P1 X-Bugzilla-Assigned-To: juzhe.zhong at rivai dot ai X-Bugzilla-Target-Milestone: 14.0 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 #10 from Kewen Lin --- (In reply to JuzheZhong from comment #9) > (In reply to Kewen Lin from comment #8) > > I did SPEC2017 int/fp evaluation on Power10 at Ofast and an extra expli= cit > > --param=3Dvect-partial-vector-usage=3D2 (the default is 1 on Power), ba= seline > > r14-1241 vs. new r14-1242, the results showed that it can offer some > > speedups for 500.perlbench_r 1.12%, 525.x264_r 1.96%, 544.nab_r 1.91%, > > 549.fotonik3d_r 1.25%, but it degraded 510.parest_r by 5.01%. > >=20 > > I just tested Juzhe's new proposed fix which makes the loop closing iv > > SCEV-ed, it can fix the degradation of 510.parest_r, also the miss > > optimization on cunroll (in #c5), the test failures are gone as well. O= ne > > SPEC2017 re-evaluation with that fix is ongoing, I'd expect it won't de= grade > > anything. >=20 > Thanks so much. You mean you are trying this patch: > https://gcc.gnu.org/pipermail/gcc-patches/2023-May/620086.html ? Yes, it means that Richi's concern (niter analysis but all analyses relying= on SCEV are pessimized) does affect the exposed degradation and failures. Than= ks for looking into it. >=20 > I believe it can improve even more for IBM's target. Hope so, I'll post the new SPEC2017 results once the run finishes. btw, the SPEC2017 run with --param=3Dvect-partial-vector-usage=3D2 here is = mainly to verify the expectation on the decrement IV change, the normal SPEC2017 r= uns still use --param=3Dvect-partial-vector-usage=3D1 which isn't affected by t= his change and it beats the former in general as the cost for length setting up= .=