From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 90D3B3858C83; Wed, 11 Jan 2023 22:28:15 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 90D3B3858C83 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1673476095; bh=fmVY6/7+xJhYVr8PENpRmXiUWFzVNW9Sc/6aVhGANgU=; h=From:To:Subject:Date:In-Reply-To:References:From; b=RbLiZEZ60BT/JwKjrTGbsOmBbLSeyUz9n+2RwPqU2FAt8jHlv9vOOZy3jd9RWOB3h YcpBLRVOrmFN1HcvZq4lN7BQIhApwRFVWMKxhqnrzMYrd4W8T1oic0ru45j7mHqhSG XCtxEY+PwZCgd8dLNnmSAoFMGM5byvXg2KLmUXOk= From: "hubicka at gcc dot gnu.org" To: gcc-bugs@gcc.gnu.org Subject: [Bug middle-end/99634] s2102 benchmarks of TSVC is vectorized better by icc than gcc, interchange is missing Date: Wed, 11 Jan 2023 22:28:14 +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: 11.0 X-Bugzilla-Keywords: X-Bugzilla-Severity: normal X-Bugzilla-Who: hubicka 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 List-Id: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D99634 --- Comment #2 from Jan Hubicka --- AOCC produced code is: .LBB0_2: # %vector.body # Parent Loop BB0_1 Depth=3D1 # =3D> This Inner Loop Header: Dep= th=3D2 vpbroadcastq %rdx, %zmm4 kxnorw %k0, %k0, %k1 incq %rdx vpsllq $2, %zmm4, %zmm4 vpaddq %zmm4, %zmm0, %zmm4 vpaddq %zmm7, %zmm4, %zmm5 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq .LCPI0_0(%rip), %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq .LCPI0_3(%rip), %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq .LCPI0_2(%rip), %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm11, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq .LCPI0_4(%rip), %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm13, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm12, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm15, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm14, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm17, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm16, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm19, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm18, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm21, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm20, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm23, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm22, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm25, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm24, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm27, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm26, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm29, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm28, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm31, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm30, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm2, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm1, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm8, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm6, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm5) {%k1} vpaddq %zmm10, %zmm4, %zmm5 kxnorw %k0, %k0, %k1 vpaddq %zmm9, %zmm4, %zmm4 vscatterqps %ymm3, (,%zmm5) {%k1} kxnorw %k0, %k0, %k1 vscatterqps %ymm3, (,%zmm4) {%k1} movl $1065353216, (%rcx) # imm =3D 0x3F800000 addq $1028, %rcx # imm =3D 0x404 cmpq $256, %rdx # imm =3D 0x100 jne .LBB0_2 # %bb.3: # %for.cond.cleanup3=