From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 2AC083858D38; Sun, 28 May 2023 19:15:02 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2AC083858D38 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1685301302; bh=ek7sjgi93XgkOsRkgNKie+tz6VfkACokCGbIiI/uj24=; h=From:To:Subject:Date:From; b=KXreiqghD+qNGpmEzRpr7n4nf+L+HNUZU9vLScPAMnj7BOybiHFdM0szjrNbJhQDF 2NRbVp9NLkG/vpWjN+E5qDCRXAx8/KErb+YJwbMPewh+2rpiWCHEsKKZNsL6SYsIc+ aNQu9oXMZoJeSZYIYNJe2LxxLJv+qQBoWlTNHEmo= From: "hubicka at gcc dot gnu.org" To: gcc-bugs@gcc.gnu.org Subject: [Bug middle-end/110015] New: openjpeg is slower when built with gcc13 compared to clang16 Date: Sun, 28 May 2023 19:15:01 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: new X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: gcc X-Bugzilla-Component: middle-end X-Bugzilla-Version: unknown X-Bugzilla-Keywords: X-Bugzilla-Severity: normal X-Bugzilla-Who: hubicka 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 List-Id: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D110015 Bug ID: 110015 Summary: openjpeg is slower when built with gcc13 compared to clang16 Product: gcc Version: unknown Status: UNCONFIRMED Severity: normal Priority: P3 Component: middle-end Assignee: unassigned at gcc dot gnu.org Reporter: hubicka at gcc dot gnu.org Target Milestone: --- I tried to reproduce openjpeg benchmarks from Phoronix https://www.phoronix.com/review/gcc13-clang16-raptorlake/5 On zen3 hardware I get 42607ms for clang build and 45702ms for gcc build th= at is a 7% difference (Phoronix reports 10% on RaptorLake) perf of clang build: 88.64% opj_t1_cblk_encode_processor 6.68% opj_dwt_encode_and_deinterleave_v 1.30% opj_dwt_encode_and_deinterleave_h_one_row opj_t1_cblk_encode_processor is huge with no obvious hot spots. perf of gcc build: 70.36% opj_t1_cblk_encode_processor=20=20=20=20=20=20=20=20=20=20=20=20= =20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20= =20=20=20=20=20=20 16.12% opj_t1_enc_refpass.lto_priv.0=20=20=20=20=20=20=20=20=20=20=20=20= =20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20= =20=20=20=20=20 3.88% opj_dwt_encode_and_deinterleave_v=20=20=20=20=20=20=20=20=20=20=20= =20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20= =20=20 2.46% pj_dwt_fetch_cols_vertical_pass=20=20=20=20=20=20=20=20=20=20=20= =20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20= =20=20=20=20 2.35% opj_mqc_byteout=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20= =20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20= =20=20=20=20=20=20=20=20=20=20=20=20=20=20 So we apparently inline less even at -O3=