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 2A27D3858405; Wed, 25 Aug 2021 06:22:53 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2A27D3858405
From: "crazylht at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/77287] Much worse code generated compared to clang
 (stack alignment and spills)
Date: Wed, 25 Aug 2021 06:22:52 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 6.1.0
X-Bugzilla-Keywords: missed-optimization, ra
X-Bugzilla-Severity: normal
X-Bugzilla-Who: crazylht at gmail dot com
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: <bug-77287-4-nW5p7HIBMy@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-77287-4@http.gcc.gnu.org/bugzilla/>
References: <bug-77287-4@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: Wed, 25 Aug 2021 06:22:53 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D77287

--- Comment #13 from Hongtao.liu <crazylht at gmail dot com> ---
;; Function fn (fn, funcdef_no=3D5484, decl_uid=3D32317, cgraph_uid=3D5485,
symbol_order=3D5484)

int fn (const int * px, const int * py, const int * pz, const int * pw, con=
st
int * pa, const int * pb, const int * pc, const int * pd)
{
  vector(16) short unsigned int _3;
  vector(16) short unsigned int _5;
  vector(16) short int _7;
  vector(16) short int _9;
  vector(32) char _12;
  vector(32) unsigned char _14;
  vector(16) short unsigned int _16;
  vector(16) short unsigned int _17;
  vector(16) short int _18;
  vector(16) short int _19;
  vector(32) char _20;
  vector(32) unsigned char _21;
  vector(16) short unsigned int _22;
  vector(16) short unsigned int _23;
  vector(16) short int _24;
  vector(16) short int _25;
  vector(32) char _26;
  vector(32) unsigned char _27;
  vector(16) short unsigned int _28;
  vector(16) short unsigned int _29;
  vector(16) short int _30;
  vector(16) short int _31;
  int _32;
  vector(4) int _33;
  vector(8) int _34;
  vector(32) unsigned char _35;
  vector(32) char _36;
  vector(16) short unsigned int _37;
  vector(16) short unsigned int _38;
  vector(16) short unsigned int _39;
  vector(16) short unsigned int _40;
  vector(16) short unsigned int _41;
  vector(16) short unsigned int _42;
  vector(16) short unsigned int _43;
  vector(16) short unsigned int _44;
  vector(16) short unsigned int _45;
  vector(16) short unsigned int _46;
  vector(16) short unsigned int _47;
  vector(16) short unsigned int _48;
  vector(16) short unsigned int _50;
  vector(16) short unsigned int _51;
  vector(16) short unsigned int _53;
  vector(16) short unsigned int _54;
  vector(16) short unsigned int _56;
  vector(16) short unsigned int _57;
  vector(16) short unsigned int _59;
  vector(16) short unsigned int _60;
  vector(16) short int _62;
  vector(16) short int _63;
  vector(16) short unsigned int _64;
  vector(16) short unsigned int _65;
  vector(32) unsigned char _66;
  vector(32) char _67;
  vector(16) short int _68;
  vector(16) short int _69;
  vector(16) short unsigned int _70;
  vector(16) short unsigned int _71;
  vector(32) unsigned char _72;
  vector(32) char _73;
  vector(16) short int _74;
  vector(16) short int _75;
  vector(16) short unsigned int _76;
  vector(16) short unsigned int _77;
  vector(32) unsigned char _78;
  vector(32) char _79;
  vector(16) short int _80;
  vector(16) short int _81;
  vector(16) short unsigned int _82;
  vector(16) short unsigned int _83;
  vector(32) unsigned char _84;
  vector(32) char _85;
  vector(16) short int _86;
  vector(16) short int _87;
  vector(16) short unsigned int _88;
  vector(16) short unsigned int _89;
  vector(32) unsigned char _90;
  vector(32) char _91;
  vector(4) long long int _92;
  vector(4) long long int _93;
  vector(4) long long int _94;
  vector(4) long long int _95;
  vector(4) long long int _96;
  vector(4) long long int _97;
  vector(4) long long int _98;
  vector(4) long long int _99;
  vector(4) long long int _100;
  vector(4) long long int _101;
  vector(16) short unsigned int _107;
  vector(16) short unsigned int _108;
  vector(16) short unsigned int _109;
  vector(16) short unsigned int _110;
  vector(16) short unsigned int _111;

  <bb 2> [local count: 1073741824]:
  _101 =3D MEM[(const __m256i_u * {ref-all})px_2(D)];
  _100 =3D MEM[(const __m256i_u * {ref-all})py_4(D)];
  _99 =3D MEM[(const __m256i_u * {ref-all})pz_6(D)];
  _98 =3D MEM[(const __m256i_u * {ref-all})pw_8(D)];
  _97 =3D MEM[(const __m256i_u * {ref-all})pa_10(D)];
  _96 =3D MEM[(const __m256i_u * {ref-all})pb_11(D)];
  _95 =3D MEM[(const __m256i_u * {ref-all})pc_13(D)];
  _94 =3D MEM[(const __m256i_u * {ref-all})pd_15(D)];
  _93 =3D MEM[(const __m256i_u * {ref-all})pc_13(D) + 32B];
  _92 =3D MEM[(const __m256i_u * {ref-all})pd_15(D) + 32B];
  _86 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_96);
  _87 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_101);
  _88 =3D (vector(16) short unsigned int) _87;
  _89 =3D (vector(16) short unsigned int) _86;
  _90 =3D VEC_PACK_SAT_EXPR <_88, _89>;
  _91 =3D (vector(32) char) _90;
  _80 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_95);
  _81 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_100);
  _82 =3D (vector(16) short unsigned int) _81;
  _83 =3D (vector(16) short unsigned int) _80;
  _84 =3D VEC_PACK_SAT_EXPR <_82, _83>;
  _85 =3D (vector(32) char) _84;
  _74 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_94);
  _75 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_99);
  _76 =3D (vector(16) short unsigned int) _75;
  _77 =3D (vector(16) short unsigned int) _74;
  _78 =3D VEC_PACK_SAT_EXPR <_76, _77>;
  _79 =3D (vector(32) char) _78;
  _68 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_93);
  _69 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_98);
  _70 =3D (vector(16) short unsigned int) _69;
  _71 =3D (vector(16) short unsigned int) _68;
  _72 =3D VEC_PACK_SAT_EXPR <_70, _71>;
  _73 =3D (vector(32) char) _72;
  _62 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_92);
  _63 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_97);
  _64 =3D (vector(16) short unsigned int) _63;
  _65 =3D (vector(16) short unsigned int) _62;
  _66 =3D VEC_PACK_SAT_EXPR <_64, _65>;
  _67 =3D (vector(32) char) _66;
  _59 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_91);
  _60 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_101);
  _56 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_85);
  _57 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_100);
  _53 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_79);
  _54 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_99);
  _50 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_73);
  _51 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_98);
  _47 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_67);
  _48 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_97);
  _45 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_96);
  _111 =3D _60 - _45;
  _46 =3D _59 + _111;
  _43 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_95);
  _110 =3D _57 - _43;
  _44 =3D _56 + _110;
  _41 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_94);
  _109 =3D _54 - _41;
  _42 =3D _53 + _109;
  _39 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_93);
  _108 =3D _51 - _39;
  _40 =3D _50 + _108;
  _37 =3D VIEW_CONVERT_EXPR<vector(16) short unsigned int>(_92);
  _107 =3D _48 - _37;
  _38 =3D _47 + _107;
  _9 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_44);
  _7 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_46);
  _5 =3D (vector(16) short unsigned int) _7;
  _3 =3D (vector(16) short unsigned int) _9;
  _35 =3D VEC_PACK_SAT_EXPR <_5, _3>;
  _36 =3D (vector(32) char) _35;
  _19 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_42);
  _18 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_36);
  _17 =3D (vector(16) short unsigned int) _18;
  _16 =3D (vector(16) short unsigned int) _19;
  _14 =3D VEC_PACK_SAT_EXPR <_17, _16>;
  _12 =3D (vector(32) char) _14;
  _25 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_40);
  _24 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_12);
  _23 =3D (vector(16) short unsigned int) _24;
  _22 =3D (vector(16) short unsigned int) _25;
  _21 =3D VEC_PACK_SAT_EXPR <_23, _22>;
  _20 =3D (vector(32) char) _21;
  _31 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_38);
  _30 =3D VIEW_CONVERT_EXPR<vector(16) short int>(_20);
  _29 =3D (vector(16) short unsigned int) _30;
  _28 =3D (vector(16) short unsigned int) _31;
  _27 =3D VEC_PACK_SAT_EXPR <_29, _28>;
  _26 =3D (vector(32) char) _27;
  _34 =3D VIEW_CONVERT_EXPR<vector(8) int>(_26);
  _33 =3D __builtin_ia32_vextractf128_si256 (_34, 0);
  _32 =3D __builtin_ia32_vec_ext_v4si (_33, 1); [tail call]
  return _32;

}

After folding _mm256_packus_epi16, gimple still doesn't simplify it.
I guess gcc only functionally supports vec_pack_sat_expr, but does not opti=
mize
it=