From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugzilla@gcc.gnu.org>
Received: by sourceware.org (Postfix, from userid 48)
 id E68F73858025; Fri,  5 Mar 2021 14:54:32 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org E68F73858025
From: "hubicka at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug middle-end/99412] New: s352 benchmark of TSVC is vectorized by
 clang and not by gcc
Date: Fri, 05 Mar 2021 14:54:32 +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: 11.0
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: <bug-99412-4@http.gcc.gnu.org/bugzilla/>
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 <gcc-bugs.gcc.gnu.org>
List-Unsubscribe: <https://gcc.gnu.org/mailman/options/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=unsubscribe>
List-Archive: <https://gcc.gnu.org/pipermail/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-request@gcc.gnu.org?subject=help>
List-Subscribe: <https://gcc.gnu.org/mailman/listinfo/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=subscribe>
X-List-Received-Date: Fri, 05 Mar 2021 14:54:33 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D99412

            Bug ID: 99412
           Summary: s352 benchmark of TSVC is vectorized by clang and not
                    by gcc
           Product: gcc
           Version: 11.0
            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: ---

typedef float real_t;

#define iterations 100000
#define LEN_1D 32000
#define LEN_2D 256

real_t a[LEN_1D],b[LEN_1D];
int main ()
{

//    loop rerolling
//    unrolled dot product

    real_t dot;
    for (int nl =3D 0; nl < 8*iterations; nl++) {
        dot =3D (real_t)0.;
        for (int i =3D 0; i < LEN_1D; i +=3D 5) {
            dot =3D dot + a[i] * b[i] + a[i + 1] * b[i + 1] + a[i + 2]
                * b[i + 2] + a[i + 3] * b[i + 3] + a[i + 4] * b[i + 4];
        }
    }

    return dot;
}


clang does:
main:                                   # @main
        .cfi_startproc
# %bb.0:
        xorl    %eax, %eax
        .p2align        4, 0x90
.LBB0_1:                                # =3D>This Loop Header: Depth=3D1
                                        #     Child Loop BB0_2 Depth 2
        vxorps  %xmm0, %xmm0, %xmm0
        movq    $-5, %rcx
        .p2align        4, 0x90
.LBB0_2:                                #   Parent Loop BB0_1 Depth=3D1
                                        # =3D>  This Inner Loop Header: Dep=
th=3D2
        vmovups b+20(,%rcx,4), %xmm1
        vmovss  b+36(,%rcx,4), %xmm2            # xmm2 =3D mem[0],zero,zero=
,zero
        vmulps  a+20(,%rcx,4), %xmm1, %xmm1
        vpermilpd       $1, %xmm1, %xmm3        # xmm3 =3D xmm1[1,0]
        vaddps  %xmm3, %xmm1, %xmm1
        vmovshdup       %xmm1, %xmm3            # xmm3 =3D xmm1[1,1,3,3]
        vaddss  %xmm3, %xmm1, %xmm1
        vfmadd231ss     a+36(,%rcx,4), %xmm2, %xmm1 # xmm1 =3D (xmm2 * mem)=
 +
xmm1
        addq    $5, %rcx
        vaddss  %xmm0, %xmm1, %xmm0
        cmpq    $31995, %rcx                    # imm =3D 0x7CFB
        jb      .LBB0_2
# %bb.3:                                #   in Loop: Header=3DBB0_1 Depth=
=3D1
        incl    %eax
        cmpl    $800000, %eax                   # imm =3D 0xC3500
        jne     .LBB0_1
# %bb.4:
        vcvttss2si      %xmm0, %eax
        retq=