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 582A03858D28; Thu,  6 Apr 2023 18:40:22 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 582A03858D28
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1680806422;
	bh=OLqL+aP4+VcWZeWF0dqT1Z6JfKdquyyBAfEuh3H/MEI=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=X2MZHyodMbqSdIr5Ctc1RLNBriWpSNwHyD/YoaAfJG0R7g40zmaYCnvvw8rwyldqk
	 AQvti/+KOXqFY/IsgkmYlyrffDxUWxbRNTYjMx+47V153POaT1YN1cBhTFx4n1KbyZ
	 mp+kWazu3e0Vs/LmMEdL6WlqkWsrLqKI5pxOlHSA=
From: "hiraditya at msn dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/109441] missed optimization when all elements
 of vector are known
Date: Thu, 06 Apr 2023 18:40:22 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: unknown
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: hiraditya at msn dot com
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-109441-4-tB3LZp2PVx@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-109441-4@http.gcc.gnu.org/bugzilla/>
References: <bug-109441-4@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=3D109441

--- Comment #1 from AK <hiraditya at msn dot com> ---
I guess a better test case is this:

#include<vector>
using namespace std;

using T =3D int;


T v(std::vector<T> v) {
    T s;
    std::fill(v.begin(), v.end(), T());
    for (auto i =3D 0; i < v.size(); ++i) {
        s +=3D v[i];
    }

    return s;
}

which has similar effect.

$ g++ -O3 -std=3Dc++17

v(std::vector<int, std::allocator<int> >):
        push    rbp
        push    rbx
        sub     rsp, 8
        mov     rbp, QWORD PTR [rdi+8]
        mov     rcx, QWORD PTR [rdi]
        cmp     rcx, rbp
        je      .L7
        sub     rbp, rcx
        mov     rdi, rcx
        xor     esi, esi
        mov     rbx, rcx
        mov     rdx, rbp
        call    memset
        mov     rdi, rbp
        mov     edx, 1
        mov     rcx, rbx
        sar     rdi, 2
        test    rbp, rbp
        cmovne  rdx, rdi
        cmp     rbp, 12
        jbe     .L8
        mov     rax, rdx
        pxor    xmm0, xmm0
        shr     rax, 2
        sal     rax, 4
        add     rax, rbx
.L4:
        movdqu  xmm2, XMMWORD PTR [rbx]
        add     rbx, 16
        paddd   xmm0, xmm2
        cmp     rbx, rax
        jne     .L4
        movdqa  xmm1, xmm0
        psrldq  xmm1, 8
        paddd   xmm0, xmm1
        movdqa  xmm1, xmm0
        psrldq  xmm1, 4
        paddd   xmm0, xmm1
        movd    eax, xmm0
        test    dl, 3
        je      .L1
        and     rdx, -4
        mov     esi, edx
.L3:
        add     eax, DWORD PTR [rcx+rdx*4]
        lea     edx, [rsi+1]
        movsx   rdx, edx
        cmp     rdx, rdi
        jnb     .L1
        add     esi, 2
        lea     r8, [0+rdx*4]
        add     eax, DWORD PTR [rcx+rdx*4]
        movsx   rsi, esi
        cmp     rsi, rdi
        jnb     .L1
        add     eax, DWORD PTR [rcx+4+r8]
.L1:
        add     rsp, 8
        pop     rbx
        pop     rbp
        ret
.L7:
        add     rsp, 8
        xor     eax, eax
        pop     rbx
        pop     rbp
        ret
.L8:
        xor     eax, eax
        xor     esi, esi
        xor     edx, edx
        jmp     .L3=