From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 242903857803; Wed, 10 Nov 2021 09:17:22 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 242903857803 From: "cvs-commit at gcc dot gnu.org" To: gcc-bugs@gcc.gnu.org Subject: [Bug middle-end/102566] [i386] GCC should emit LOCK BTS for simple bit-test-and-set operations with std::atomic Date: Wed, 10 Nov 2021 09:17:21 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: gcc X-Bugzilla-Component: middle-end X-Bugzilla-Version: 12.0 X-Bugzilla-Keywords: missed-optimization X-Bugzilla-Severity: enhancement X-Bugzilla-Who: cvs-commit at gcc dot gnu.org X-Bugzilla-Status: NEW 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 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: Wed, 10 Nov 2021 09:17:22 -0000 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D102566 --- Comment #30 from CVS Commits --- The master branch has been updated by hongtao Liu : https://gcc.gnu.org/g:fb161782545224f55ba26ba663889c5e6e9a04d1 commit r12-5102-gfb161782545224f55ba26ba663889c5e6e9a04d1 Author: liuhongt Date: Mon Oct 25 13:59:51 2021 +0800 Improve integer bit test on __atomic_fetch_[or|and]_* returns commit adedd5c173388ae505470df152b9cb3947339566 Author: Jakub Jelinek Date: Tue May 3 13:37:25 2016 +0200 re PR target/49244 (__sync or __atomic builtins will not emit 'lock bts/btr/btc') optimized bit test on __atomic_fetch_or_* and __atomic_fetch_and_* retu= rns with lock bts/btr/btc by turning mask_2 =3D 1 << cnt_1; _4 =3D __atomic_fetch_or_* (ptr_6, mask_2, _3); _5 =3D _4 & mask_2; into _4 =3D ATOMIC_BIT_TEST_AND_SET (ptr_6, cnt_1, 0, _3); _5 =3D _4; and mask_6 =3D 1 << bit_5(D); _1 =3D ~mask_6; _2 =3D __atomic_fetch_and_4 (v_8(D), _1, 0); _3 =3D _2 & mask_6; _4 =3D _3 !=3D 0; into mask_6 =3D 1 << bit_5(D); _1 =3D ~mask_6; _11 =3D .ATOMIC_BIT_TEST_AND_RESET (v_8(D), bit_5(D), 1, 0); _4 =3D _11 !=3D 0; But it failed to optimize many equivalent, but slighly different cases: 1. _1 =3D __atomic_fetch_or_4 (ptr_6, 1, _3); _4 =3D (_Bool) _1; 2. _1 =3D __atomic_fetch_and_4 (ptr_6, ~1, _3); _4 =3D (_Bool) _1; 3. _1 =3D __atomic_fetch_or_4 (ptr_6, 1, _3); _7 =3D ~_1; _5 =3D (_Bool) _7; 4. _1 =3D __atomic_fetch_and_4 (ptr_6, ~1, _3); _7 =3D ~_1; _5 =3D (_Bool) _7; 5. _1 =3D __atomic_fetch_or_4 (ptr_6, 1, _3); _2 =3D (int) _1; _7 =3D ~_2; _5 =3D (_Bool) _7; 6. _1 =3D __atomic_fetch_and_4 (ptr_6, ~1, _3); _2 =3D (int) _1; _7 =3D ~_2; _5 =3D (_Bool) _7; 7. _1 =3D __atomic_fetch_or_4 (ptr_6, 0x80000000, _3); _5 =3D (signed int) _1; _4 =3D _5 < 0; 8. _1 =3D __atomic_fetch_and_4 (ptr_6, 0x7fffffff, _3); _5 =3D (signed int) _1; _4 =3D _5 < 0; 9. _1 =3D 1 << bit_4(D); mask_5 =3D (unsigned int) _1; _2 =3D __atomic_fetch_or_4 (v_7(D), mask_5, 0); _3 =3D _2 & mask_5; 10. mask_7 =3D 1 << bit_6(D); _1 =3D ~mask_7; _2 =3D (unsigned int) _1; _3 =3D __atomic_fetch_and_4 (v_9(D), _2, 0); _4 =3D (int) _3; _5 =3D _4 & mask_7; We make mask_2 =3D 1 << cnt_1; _4 =3D __atomic_fetch_or_* (ptr_6, mask_2, _3); _5 =3D _4 & mask_2; and mask_6 =3D 1 << bit_5(D); _1 =3D ~mask_6; _2 =3D __atomic_fetch_and_4 (v_8(D), _1, 0); _3 =3D _2 & mask_6; _4 =3D _3 !=3D 0; the canonical forms for this optimization and transform cases 1-9 to the equivalent canonical form. For cases 10 and 11, we simply remove the c= ast before __atomic_fetch_or_4/__atomic_fetch_and_4 with _1 =3D 1 << bit_4(D); _2 =3D __atomic_fetch_or_4 (v_7(D), _1, 0); _3 =3D _2 & _1; and mask_7 =3D 1 << bit_6(D); _1 =3D ~mask_7; _3 =3D __atomic_fetch_and_4 (v_9(D), _1, 0); _6 =3D _3 & mask_7; _5 =3D (int) _6; 2021-11-04 H.J. Lu Hongtao Liu gcc/ PR middle-end/102566 * match.pd (nop_atomic_bit_test_and_p): New match. * tree-ssa-ccp.c (convert_atomic_bit_not): New function. (gimple_nop_atomic_bit_test_and_p): New prototype. (optimize_atomic_bit_test_and): Transform equivalent, but sligh= ly different cases to their canonical forms. gcc/testsuite/ PR middle-end/102566 * g++.target/i386/pr102566-1.C: New test. * g++.target/i386/pr102566-2.C: Likewise. * g++.target/i386/pr102566-3.C: Likewise. * g++.target/i386/pr102566-4.C: Likewise. * g++.target/i386/pr102566-5a.C: Likewise. * g++.target/i386/pr102566-5b.C: Likewise. * g++.target/i386/pr102566-6a.C: Likewise. * g++.target/i386/pr102566-6b.C: Likewise. * gcc.target/i386/pr102566-1a.c: Likewise. * gcc.target/i386/pr102566-1b.c: Likewise. * gcc.target/i386/pr102566-2.c: Likewise. * gcc.target/i386/pr102566-3a.c: Likewise. * gcc.target/i386/pr102566-3b.c: Likewise. * gcc.target/i386/pr102566-4.c: Likewise. * gcc.target/i386/pr102566-5.c: Likewise. * gcc.target/i386/pr102566-6.c: Likewise. * gcc.target/i386/pr102566-7.c: Likewise. * gcc.target/i386/pr102566-8a.c: Likewise. * gcc.target/i386/pr102566-8b.c: Likewise. * gcc.target/i386/pr102566-9a.c: Likewise. * gcc.target/i386/pr102566-9b.c: Likewise. * gcc.target/i386/pr102566-10a.c: Likewise. * gcc.target/i386/pr102566-10b.c: Likewise. * gcc.target/i386/pr102566-11.c: Likewise. * gcc.target/i386/pr102566-12.c: Likewise. * gcc.target/i386/pr102566-13.c: New test. * gcc.target/i386/pr102566-14.c: New test.=