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 ED3EA3858408; Mon, 20 Feb 2023 11:14:28 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org ED3EA3858408
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1676891668;
	bh=Smn1VwLFFNE9alDs2v8crf0DkrKaxGYJ3MG9++NtX5Y=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=wGpWpMGBZn9AbdnUaFvCz+i2uK/tDd0r/9W5jPS323AFL430h91HXZm3Rbwyqeoex
	 yLoOn9TsXbWGBut+fRy5AerTKCRb05DajUYrNMlbSJCLgdGv7vCZu5dOGLsyh8lGWq
	 eLPOmzt2e76vRV/1xB9gSAAqSEuAH5LH8rOWWHxc=
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/108804] missed vectorization in presence of conversion
 from uint64_t to float
Date: Mon, 20 Feb 2023 11:14:28 +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: 12.2.1
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: rguenth at gcc dot gnu.org
X-Bugzilla-Status: NEW
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: cf_gcctarget bug_status everconfirmed keywords
 cf_reconfirmed_on
Message-ID: <bug-108804-4-sCki0ZiAvs@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-108804-4@http.gcc.gnu.org/bugzilla/>
References: <bug-108804-4@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=3D108804

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Target|                            |x86_64-*-*
             Status|UNCONFIRMED                 |NEW
     Ever confirmed|0                           |1
           Keywords|                            |missed-optimization
   Last reconfirmed|                            |2023-02-20

--- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> ---
EVRP does

@@ -38,16 +61,18 @@
   k_12 =3D k_10 >> 23;
   _2 =3D k_12 & 8388607;
   y_13 =3D _2 | 1065353216;
-  _3 =3D (float) x_11;
+  _17 =3D (signed long) x_11;
+  _3 =3D (float) _17;
   f[i_6] =3D _3;
   _4 =3D i_6 + 128;
-  _5 =3D (float) y_13;
+  _18 =3D (signed long) y_13;
+  _5 =3D (float) _18;
   f[_4] =3D _5;

because unsigned long -> float is even more difficult.  With -fno-tree-vrp
the conversion is still from uint64_t but that's not supported either.

So it's a target issue.  Shorter testcase:

#include<stdint.h>

uint64_t d[512];
float f[1024];

void foo() {
    for (int i=3D0; i<512; ++i) {
        uint64_t k =3D d[i];
        f[i]=3Dk;
    }
}=