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 2B0BA385841D; Mon, 26 Dec 2022 09:20:18 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2B0BA385841D
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1672046418;
	bh=03CUIXvhR08SoyF0IOBJvPw/R+DLcSJnCF7iZobEEWM=;
	h=From:To:Subject:Date:From;
	b=mau357kxluOHh5qb5UUlPn+9X4deyXC0MpOT2Z5pnYUJseu6R8b4UeDlyoKerPuCn
	 web32UubiadXYYYkwusi8+F21zklERrnVbsr1Ga9qtGemS7z13RHD6c/05W4Mm1/gZ
	 4T2ShJfVq1L+LlW/LxdUNq+UWn5VFyXL+c1yVND8=
From: "tkoenig at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/108227] New: Unnecessary division when
 looping over array with size of elements not a power of two
Date: Mon, 26 Dec 2022 09:20:16 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 13.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: tkoenig 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-108227-4@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=3D108227

            Bug ID: 108227
           Summary: Unnecessary division when looping over array with size
                    of elements not a power of two
           Product: gcc
           Version: 13.0
            Status: UNCONFIRMED
          Severity: enhancement
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: tkoenig at gcc dot gnu.org
  Target Milestone: ---

Consider

typedef struct coord {
  double x, y, z;
} coord;

void foo(coord *from, coord *to)
{
  unsigned long int n =3D to - from;
  for (unsigned long int i=3D0; i < n; i++)
    {
      from[i].x =3D from[i].x + 1.0;
    }
}

void bar (coord *from, coord *to)
{
  char *c_from =3D (char *) from, *c_to =3D (char *) to;
  coord *p =3D from;
  long int c_n =3D c_to - c_from;
  for (long int i=3D0; i < c_n; i+=3D sizeof(coord))
    {
      p->x =3D p->x + 1.0;
      p++;
    }
}

The code is functionally equivalent, but the assembly somewhat different:

foo has

foo:
.LFB0:
        .cfi_startproc
        movabsq $-6148914691236517205, %rax
        movq    %rsi, %rdx
        subq    %rdi, %rdx
        sarq    $3, %rdx
        imulq   %rax, %rdx
        cmpq    %rdi, %rsi
        je      .L1
        movsd   .LC0(%rip), %xmm1
        xorl    %eax, %eax
        .p2align 4,,10
        .p2align 3
.L3:
        movsd   (%rdi), %xmm0
        addq    $1, %rax
        addq    $24, %rdi
        addsd   %xmm1, %xmm0
        movsd   %xmm0, -24(%rdi)
        cmpq    %rdx, %rax
        jb      .L3
.L1:
        ret

so it first divides by 12 (efficiently) to determine n. There are 7
instructions in the loop itself.

bar has

bar:
.LFB1:
        .cfi_startproc
        subq    %rdi, %rsi
        testq   %rsi, %rsi
        jle     .L6
        movsd   .LC0(%rip), %xmm1
        xorl    %eax, %eax
        .p2align 4,,10
        .p2align 3
.L8:
        movsd   (%rdi,%rax), %xmm0
        addsd   %xmm1, %xmm0
        movsd   %xmm0, (%rdi,%rax)
        addq    $24, %rax
        cmpq    %rax, %rsi
        jg      .L8
.L6:
        ret

no need to divide, and one instruction less in the loop.

I would expect foo to match bar.=