From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 6B07B3857827; Wed, 27 Apr 2022 12:02:05 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 6B07B3857827 From: "rguenth at gcc dot gnu.org" To: gcc-bugs@gcc.gnu.org Subject: [Bug tree-optimization/105219] [12 Regression] SVE: Wrong code with -O3 -msve-vector-bits=128 -mtune=thunderx Date: Wed, 27 Apr 2022 12:02:04 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: gcc X-Bugzilla-Component: tree-optimization X-Bugzilla-Version: 12.0 X-Bugzilla-Keywords: wrong-code X-Bugzilla-Severity: normal X-Bugzilla-Who: rguenth at gcc dot gnu.org X-Bugzilla-Status: NEW X-Bugzilla-Resolution: X-Bugzilla-Priority: P1 X-Bugzilla-Assigned-To: avieira at gcc dot gnu.org X-Bugzilla-Target-Milestone: 12.0 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 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, 27 Apr 2022 12:02:05 -0000 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D105219 --- Comment #14 from Richard Biener --- (In reply to Martin Li=C5=A1ka from comment #13) > (In reply to Richard Biener from comment #11) > > int data[128]; > >=20 > > void __attribute((noipa)) > > foo (int *data, int n) > > { > > for (int i =3D 0; i < n; ++i) > > data[i] =3D i; > > } > >=20 > > int main() > > { > > for (int start =3D 0; start < 16; ++start) > > for (int n =3D 1; n < 3*16; ++n) > > { > > __builtin_memset (data, 0, sizeof (data)); > > foo (&data[start], n); > > for (int j =3D 0; j < n; ++j) > > if (data[start + j] !=3D j) > > __builtin_abort (); > > } > > return 0; > > } > >=20 > > for example aborts with -O3 -mtune=3Dintel -fno-vect-cost-model on x86_= 64, > > the cost model disabling is necessary to have the epilogue vectorized. > > Without a cost model we peel for the maximum number of aligned refs > > but still use the target cost to decide whether peeling is worth at all. >=20 > This one started with r12-1181-g7ed1cd9665d8ca0f. So the following fixes the x86 failure for me. Can somebody check if that also fixes the aarch64 issue observed? diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index d7bc34636bd..3b63ab7b669 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -9977,7 +9981,7 @@ vect_transform_loop (loop_vec_info loop_vinfo, gimple *loop_vectorized_call) lowest_vf) - 1 : wi::udiv_floor (loop->nb_iterations_upper_bound + bias_for_low= est, lowest_vf) - 1); - if (main_vinfo) + if (main_vinfo && !main_vinfo->peeling_for_alignment) { unsigned int bound; poly_uint64 main_iters=