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 B76C23858D38; Mon, 18 Sep 2023 03:24:43 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org B76C23858D38
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1695007483;
	bh=UjnCLUs8Yw2Wgxdgmb4n3HJM9Pvpty7mYhUrKmUaNkE=;
	h=From:To:Subject:Date:From;
	b=ZRypwLuxKbQ8IjUXmwMXOx0Bwf0z24FZqzviuLD7wGxkUHuBRkbAO6Of1ZhgEfa9O
	 Pujr2cSO9U0SlrP4pzfj8ZT5CAcVEbyK4Q5pSluGy7bo3/AsOal529Jsv8HF2/JvWV
	 HOPjtL+VwI9dIeAxDhcWYmE6NP7QT3YNOHM13UkU=
From: "juzhe.zhong at rivai dot ai" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug c/111451] New: RISC-V: Missed optimization of vrgather.vv into
 vrgatherei16.vv
Date: Mon, 18 Sep 2023 03:24:42 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: c
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: juzhe.zhong at rivai dot ai
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-111451-4@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
List-Id: <gcc-bugs.sourceware.org>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D111451

            Bug ID: 111451
           Summary: RISC-V: Missed optimization of vrgather.vv into
                    vrgatherei16.vv
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c
          Assignee: unassigned at gcc dot gnu.org
          Reporter: juzhe.zhong at rivai dot ai
  Target Milestone: ---

Consider this following case:

#include <stdint.h>
typedef int32_t vnx32si __attribute__ ((vector_size (128)));

#define MASK_2(X, Y) (Y) - 1 - (X), (Y) - 2 - (X)
#define MASK_4(X, Y) MASK_2 (X, Y), MASK_2 (X + 2, Y)
#define MASK_8(X, Y) MASK_4 (X, Y), MASK_4 (X + 4, Y)
#define MASK_16(X, Y) MASK_8 (X, Y), MASK_8 (X + 8, Y)
#define MASK_32(X, Y) MASK_16 (X, Y), MASK_16 (X + 16, Y)
#define MASK_64(X, Y) MASK_32 (X, Y), MASK_32 (X + 32, Y)
#define MASK_128(X, Y) MASK_64 (X, Y), MASK_64 (X + 64, Y)

#define PERMUTE(TYPE, NUNITS)=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20
\
  __attribute__ ((noipa)) void permute_##TYPE (TYPE values1, TYPE values2,=
=20=20=20=20
\
                                               TYPE *out)=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
\
  {=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20
\
    TYPE v=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
\
      =3D __builtin_shufflevector (values1, values2, MASK_##NUNITS (0, NUNI=
TS));
\
    *(TYPE *) out =3D v;=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20
\
  }

#define TEST_ALL(T)=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
\
  T (vnx32si, 32)=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
\

TEST_ALL (PERMUTE)

ASM:

permute_vnx32si:
        li      a5,32
        li      a4,31
        vsetvli zero,a5,e32,m8,ta,ma
        vid.v   v8
        vle32.v v24,0(a0)
        vrsub.vx        v8,v8,a4
        vrgather.vv     v16,v24,v8
        vse32.v v16,0(a2)
        ret

https://godbolt.org/z/Mh77YY91r

Here we use:

vsetvli zero,a5,e32,m8,ta,ma
...
vrgather.vv     v16,v24,v8

The index vector register "v8" occupies 8 registers.
We should optimize it into vrgatherei16.vv which is using int16 as the inde=
x=20
elements.

Then with vrgatherei16.vv, the v8 will occupy 4 registers instead of 8.
Lower the register consuming and register pressure.=