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 670433858D38; Tue, 17 Oct 2023 11:03:14 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 670433858D38
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1697540594;
	bh=Wjv6FAhdVFQ+XZkFD/xwknvw9ZcOf8eRdfzeOie2Hh8=;
	h=From:To:Subject:Date:From;
	b=t4cYEECy7KI9i0XbR5NT97/gkmuZ40LzzV0DcayQi5WmTDV/noAuSA0DKblacolLt
	 aDfI6hVuP13nRh9AcHOFvEwqpBsxrTv/6CpqZrMqEKkniXJdsexnnPuknfiqlBA9be
	 ivvX1eFpkWbNSm2CQmzlTNHfVlz4354ug7srRmU4=
From: "juzhe.zhong at rivai dot ai" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug c/111848] New: RISC-V: RVV cost model pick unexpected big LMUL
Date: Tue, 17 Oct 2023 11:03:14 +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-111848-4@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=3D111848

            Bug ID: 111848
           Summary: RISC-V: RVV cost model pick unexpected big LMUL
           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 <stdint.h>
void
f3 (uint8_t *restrict a, uint8_t *restrict b,
   uint8_t *restrict c, uint8_t *restrict d,
   int n)
{
  for (int i =3D 0; i < n; ++i)
    {
      a[i * 8] =3D c[i * 8] + d[i * 8];
      a[i * 8 + 1] =3D c[i * 8] + d[i * 8 + 1];
      a[i * 8 + 2] =3D c[i * 8 + 2] + d[i * 8 + 2];
      a[i * 8 + 3] =3D c[i * 8 + 2] + d[i * 8 + 3];
      a[i * 8 + 4] =3D c[i * 8 + 4] + d[i * 8 + 4];
      a[i * 8 + 5] =3D c[i * 8 + 4] + d[i * 8 + 5];
      a[i * 8 + 6] =3D c[i * 8 + 6] + d[i * 8 + 6];
      a[i * 8 + 7] =3D c[i * 8 + 6] + d[i * 8 + 7];
      b[i * 8] =3D c[i * 8 + 1] + d[i * 8];
      b[i * 8 + 1] =3D c[i * 8 + 1] + d[i * 8 + 1];
      b[i * 8 + 2] =3D c[i * 8 + 3] + d[i * 8 + 2];
      b[i * 8 + 3] =3D c[i * 8 + 3] + d[i * 8 + 3];
      b[i * 8 + 4] =3D c[i * 8 + 5] + d[i * 8 + 4];
      b[i * 8 + 5] =3D c[i * 8 + 5] + d[i * 8 + 5];
      b[i * 8 + 6] =3D c[i * 8 + 7] + d[i * 8 + 6];
      b[i * 8 + 7] =3D c[i * 8 + 7] + d[i * 8 + 7];
    }
}

This case pick LMUL =3D 8 which causes horrible vector register spillings.

After experiment, the ideal LMUL should be 2.=