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 5C3AD3858D37; Thu, 26 Oct 2023 06:51:48 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 5C3AD3858D37
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1698303108;
	bh=LloT5DNZTTiMXZj4sQvCFvQpOHkYpXARzKBnTvFNHMg=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=VQ/YId9MPh+R+Fm3XQNYUzF38S9j0qwb9OxZaH3gwh4cmjJVFC+62vLr8GgX5oWDQ
	 eFa+rIVnLf2oZvKhFvMtqNRm8DrgaHkQfF3i/FVNQVZ4ymqZAQuzFPfO81OYfHZGXO
	 3++wL2T4vyWjvTT+yiyA/eteimKqytHVfxqM8d0c=
From: "juzhe.zhong at rivai dot ai" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/112092] RISC-V: Wrong RVV code produced for vsetvl-11.c
 and vsetvlmax-8.c
Date: Thu, 26 Oct 2023 06:51:48 +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: 14.0
X-Bugzilla-Keywords: wrong-code
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: 
Message-ID: <bug-112092-4-0BDzIm8XL9@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-112092-4@http.gcc.gnu.org/bugzilla/>
References: <bug-112092-4@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=3D112092

--- Comment #5 from JuzheZhong <juzhe.zhong at rivai dot ai> ---
Yes. I am agree that some arch prefer agnostic than undisturbed even with m=
ore
vsetvls. That's why I have post PR for asking whether we can have a option =
like

-mprefer-agosnotic.

https://github.com/riscv-non-isa/riscv-toolchain-conventions/issues/37


But I think Maciej is worrying about why GCC fuse vsetvl, and change

e16mf2 vsetvl into e32m1.


For example:

https://godbolt.org/z/6G9G7Pbe9

No 'TU' included.

I think LLVM codegen looks more reasonable:

        beqz    a5, .LBB0_4
        vsetvli a1, a6, e32, m1, ta, ma
        beqz    a4, .LBB0_3
.LBB0_2:                                # =3D>This Inner Loop Header: Depth=
=3D1
        vsetvli zero, a1, e32, m1, ta, ma
        vle32.v v8, (a0)
        vadd.vv v8, v8, v8
        addi    a4, a4, -1
        vse32.v v8, (a3)
        bnez    a4, .LBB0_2
.LBB0_3:
        ret
.LBB0_4:
        srai    a1, a6, 2
        vsetvli a1, a1, e16, mf2, ta, ma
        bnez    a4, .LBB0_2
        j       .LBB0_3

But GCC is correct with optimizations:

foo(int*, int*, int*, int*, unsigned long, int, int):
        beq     a5,zero,.L2
        vsetvli a5,a6,e32,m1,ta,ma
.L3:
        beq     a4,zero,.L10
        li      a2,0
.L5:
        vle32.v v1,0(a0)
        addi    a2,a2,1
        vadd.vv v1,v1,v1
        vse32.v v1,0(a3)
        bne     a4,a2,.L5
.L10:
        ret
.L2:
        sraiw   a5,a6,2
        vsetvli zero,a5,e32,m1,ta,ma
        j       .L3=