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 6F5663858014; Fri, 28 Oct 2022 05:22:22 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 6F5663858014
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1666934542;
	bh=d+BiKbTXSd2GIAGMkdgGJKkdfy7ZdAB//rZE9FrG+mE=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=ldrOf9QPIGBRe8xBPUOreNFgiVK3y0RYL0CTDlu2EZuK3dhvZ8HuBiRWb/dXPW51p
	 8JWkni6ifujmQG3vuBs2oSbCqg2MiprOIedbtUFqC9nOoiYq6P5PDPbjE0bv2OxYFu
	 GrkprgUwstTkgh7zlWtcEJCV9hKC0bW3uCTZESno=
From: "crazylht at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/107432] __builtin_convertvector generates inefficient
 code
Date: Fri, 28 Oct 2022 05:22:22 +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: unknown
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: crazylht at gmail 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-107432-4-jl3g5M1nlj@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-107432-4@http.gcc.gnu.org/bugzilla/>
References: <bug-107432-4@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=3D107432

--- Comment #5 from Hongtao.liu <crazylht at gmail dot com> ---

> It's lowered by pass_lower_vector, ideally, can we use truncmn2 in
> expand_VEC_CONVERT if src is bigger integer mode than dest.

Currently, expand_vector_conversion uses VEC_PACK_TRUNC_EXPR

---------------cut begins------------------------
  else if (modifier =3D=3D NARROW)
    {
      switch (code)
        {
        CASE_CONVERT:
          code1 =3D VEC_PACK_TRUNC_EXPR;
          optab1 =3D optab_for_tree_code (code1, arg_type, optab_default);
          break;

---------------Cut ends------------------------

But BB vectorizer can do the right thing for=20

void
foo (long long* a, int* b)
{
    b[0] =3D a[0];
    b[1] =3D a[1];
    b[2] =3D a[2];
    b[3] =3D a[3];
}



        vmovdqu ymm0, YMMWORD PTR [rdi]
        vpmovqd XMMWORD PTR [rsi], ymm0
        vzeroupper
        ret


  vect__1.5_16 =3D MEM <vector(4) long long int> [(long long int *)a_10(D)];
  vect__2.6_18 =3D (vector(4) int) vect__1.5_16;
  # DEBUG BEGIN_STMT
  # DEBUG BEGIN_STMT
  # DEBUG BEGIN_STMT
  MEM <vector(4) int> [(int *)b_11(D)] =3D vect__2.6_18;
  return;


Guess expand_vector_conversion can be optimized.=