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 B06E3386EC45; Fri, 16 Apr 2021 20:30:08 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org B06E3386EC45
From: "munroesj at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/100085] Bad code for union transfer from __float128 to
 vector types
Date: Fri, 16 Apr 2021 20:30:08 +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: 10.2.1
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: munroesj 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: <bug-100085-4-1KIHR9yeDz@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-100085-4@http.gcc.gnu.org/bugzilla/>
References: <bug-100085-4@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, 16 Apr 2021 20:30:08 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D100085

--- Comment #4 from Steven Munroe <munroesj at gcc dot gnu.org> ---
I am seeing this a similar problem with union transfers from __float128 to
__int128.


     static inline unsigned __int128
     vec_xfer_bin128_2_int128t (__binary128 f128)
     {
       __VF_128 vunion;

       vunion.vf1 =3D f128;

       return (vunion.ui1);
     }

and=20

unsigned __int128
test_xfer_bin128_2_int128 (__binary128 f128)
{
  return vec_xfer_bin128_2_int128t (f128);
}

generates:

0000000000000030 <test_xfer_bin128_2_int128>:
  30:   57 12 42 f0     xxswapd vs34,vs34
  34:   20 00 20 39     li      r9,32
  38:   d0 ff 41 39     addi    r10,r1,-48
  3c:   99 4f 4a 7c     stxvd2x vs34,r10,r9
  40:   f0 ff 61 e8     ld      r3,-16(r1)
  44:   f8 ff 81 e8     ld      r4,-8(r1)
  48:   20 00 80 4e     blr

For POWER8 should use mfvsrd/xxpermdi/mfvsrd.

This looks like the root cause of poor performance for __float128 soft-floa=
t on
POWER8. A simple benchmark using __float128 in C code calling libgcc for
-mcpu=3Dpower8 and then hardware instructions for -mcpu=3Dpower9.

P8 target P8AT14, Uses libgcc __addkf3_sw and __mulkf3_sw:
test_time_f128 f128 CC  tb delta =3D 52589, sec =3D 0.000102713

P9 Target P8AT14, Uses libgcc __addkf3_hw and __mulkf3_hw:
test_time_f128 f128 CC  tb delta =3D 18762, sec =3D 3.66445e-05

P9 Target P9AT14, inline hardware binary128 float:
test_time_f128 f128 CC  tb delta =3D 3809, sec =3D 7.43945e-06

I used Valgrind Itrace and Sim-ppc and perfstat analysis. Every call to lib=
gcc
__add/sub/mul/divkf3 takes a load-hit-store flush every call. This explains=
 why
__float128 is so 13.8 X slower on P8 then P9.=