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 D9A933858C50; Tue, 18 Apr 2023 22:24:15 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org D9A933858C50
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1681856655;
	bh=MZEh1WaT95kbPBKQ9zVqUDNVzhq1J/S4wHLust1zlL0=;
	h=From:To:Subject:Date:From;
	b=kjKpf4HmiZ+ExVXuaptR2uGMpODvXca+7C0KeEYd4w5XxoaiKMGJAYZJPtys69rHd
	 Kfp2lIhHq96EsXarQNcZYWjXC+/OC5ohRvF6By5XPBCq40CganSN1WhSH+VaClx1+Y
	 4Qo7UyStTk70BooVn3ZpJ/fIPf600Zb0uNQFd2n4=
From: "palmer at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/109547] New: RISC-V: Multiple vsetvli for load/store
 loop
Date: Tue, 18 Apr 2023 22:24:15 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: palmer at gcc dot gnu.org
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-109547-4@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=3D109547

            Bug ID: 109547
           Summary: RISC-V: Multiple vsetvli for load/store loop
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: palmer at gcc dot gnu.org
  Target Milestone: ---

I was just poking around with a simple loop using the vector intrinsics and
found some odd generated code.  This is on the gcc-13 branch, but that's pr=
etty
close to trunk so I'm filing it for 14.  I'm probably not going to have tim=
e to
look for a bit, as it seems to just be a performance issue.

$ cat test.c
#include <riscv_vector.h>

void func(unsigned char *out, unsigned char *in, unsigned long len) {
  unsigned long i =3D 0;
  while (i < len) {
    unsigned long vl =3D __riscv_vsetvl_e8m1(len - i);
    vuint8m1_t r =3D __riscv_vle8_v_u8m1(in + i, vl);
    __riscv_vse8_v_u8m1(out + i, r, vl);
    i +=3D vl;
  }
}
$ ../toolchain/install/bin/riscv64-unknown-linux-gnu-gcc test.c -O3 -c -S -=
o-
-march=3Drv64gcv -fdump-rtl-all
        .file   "test.c"
        .option nopic
        .attribute arch,
"rv64i2p0_m2p0_a2p0_f2p0_d2p0_c2p0_v1p0_zve32f1p0_zve32x1p0_zve64d1p0_zve64=
f1p0_zve64x1p0_zvl128b1p0_zvl32b1p0_zvl64b1p0"
        .attribute unaligned_access, 0
        .attribute stack_align, 16
        .text
        .align  1
        .globl  func
        .type   func, @function
func:
.LFB2:
        .cfi_startproc
        beq     a2,zero,.L1
        li      a5,0
.L3:
        sub     a4,a2,a5
        add     a6,a1,a5
        add     a3,a0,a5
        vsetvli a4,a4,e8,m1,ta,mu
        vsetvli zero,a4,e8,m1,ta,ma
        add     a5,a5,a4
        vle8.v  v24,0(a6)
        vse8.v  v24,0(a3)
        bgtu    a2,a5,.L3
.L1:
        ret
        .cfi_endproc
.LFE2:
        .size   func, .-func
        .ident  "GCC: (g85b95ea729c) 13.0.1 20230417 (prerelease)"
        .section        .note.GNU-stack,"",@progbits=