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 C234E385840E; Thu, 30 Nov 2023 10:08:57 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org C234E385840E
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1701338937;
	bh=50E2BFgBLsO6jTg3zeh+UuYGzvg9M8uYU6WWjf7AbnI=;
	h=From:To:Subject:Date:From;
	b=Ft3F+75/8MZBOjff19LF3EGYJrH7nUEsLDVrmpm3I0sA4KqaTfiO2WxM4aXa6ZSwV
	 tmeiCJA21HVhZbhOMN0Lvx5YM3ScvWR/UdtUSKaS8J7aTElMKRX9LL3zU88GFn0tFS
	 wF9YmIM+90rXvrvpFb6GrvIx0adJVGDKFgxYvgjo=
From: "juzhe.zhong at rivai dot ai" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug c/112776] New: RISC-V Regression: Missed optimization of VSETVL
 PASS
Date: Thu, 30 Nov 2023 10:08:57 +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-112776-4@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=3D112776

            Bug ID: 112776
           Summary: RISC-V Regression: Missed optimization of VSETVL PASS
           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: ---

#include "riscv_vector.h"

void
foo_vec(float *r, const float *x)
{
int i, k;

vfloat32m4_t x_vec;
vfloat32m4_t x_forward_vec;
vfloat32m4_t temp_vec;

/**
 * I have to use m1 to complicat intrisic
 */
vfloat32m1_t dst_vec;
vfloat32m1_t src_vec;

float result =3D 0.0f;
float shift_prev =3D 0.0f;

size_t n =3D 64;
for(size_t vl; n>0; n -=3Dvl){
    vl =3D __riscv_vsetvl_e32m4(n); //LMUL=3D4
    x_vec =3D __riscv_vle32_v_f32m4(&x[0], vl);
    x_forward_vec =3D __riscv_vle32_v_f32m4(&x[0], vl);
    temp_vec =3D __riscv_vfmul_vv_f32m4(x_vec, x_forward_vec, vl);

    /**
     * I have to use m1 to complicat intrisic
     */
    //vfloat32m1_t __riscv_vfmv_s_tu(vfloat32m1_t vd, float rs1, size_t vl);
    src_vec =3D __riscv_vfmv_s_tu(src_vec, 0.0f, vl);                 //ini=
tial
src_vec
    //dst_vec =3D __riscv_vfmv_s_f_f32m1_tu(dst_vec, 0.0f, vl);         //c=
lean
for vfredosum
    dst_vec =3D __riscv_vfmv_s_tu(dst_vec, 0.0f, vl);         //clean for
vfredosum
    dst_vec =3D __riscv_vfredosum_tu(dst_vec, temp_vec, src_vec, vl);

    r[0] =3D __riscv_vfmv_f_s_f32m1_f32(dst_vec);

   }
}

ASM:

GCC-14 foo_vec:
        li      a4,64
.L2:
        vsetvli a5,a4,e8,m1,ta,ma   --->=20
        vsetvli zero,a5,e32,m1,tu,ma
        vmv.s.x v2,zero
        vmv.s.x v1,zero
        vsetvli zero,a5,e32,m4,tu,ma
        vle32.v v4,0(a1)
        vfmul.vv        v4,v4,v4
        vfredosum.vs    v1,v4,v2
        vfmv.f.s        fa5,v1
        fsw     fa5,0(a0)
        sub     a4,a4,a5
        bne     a4,zero,.L2
        ret

GCC-13:

foo_vec(float*, float const*):
        fmv.s.x fa5,zero
        li      a4,64
.L2:
        vsetvli a5,a4,e32,m4,ta,ma
        vle32.v v28,0(a1)
        vfmv.s.f        v25,fa5
        vfmul.vv        v28,v28,v28
        vfmv.s.f        v24,fa5
        sub     a4,a4,a5
        vfredosum.vs    v24,v28,v25
        vfmv.f.s        fa4,v24
        fsw     fa4,0(a0)
        bne     a4,zero,.L2
        ret=