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 2FB4A3858C5F; Tue, 21 Mar 2023 20:07:21 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2FB4A3858C5F
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1679429241;
	bh=tAXbeY/JHf7mGPPzriF9/DicLPsT38TcudAguvslYYA=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=vhLk1/O/2W6yUA/G2RGOrrZhLGGXwzZDJUXLXdMqMjxVs38zbGOz/1rhLLaV3P2SI
	 L4EaCptPmwKcpsFHQWRiYn0N+7sBj+KtMYM9xzqNMnH5rQP9Ufzz7I/+S4Hk3W2zCy
	 SHqlJm7DFHEY/lktbEDmerPc1eYBUkRzUEpOzNvY=
From: "mkretz at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/85048] [missed optimization] vector conversions
Date: Tue, 21 Mar 2023 20:07:20 +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: 8.0.1
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: mkretz 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: 
Message-ID: <bug-85048-4-puzadR5kR8@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-85048-4@http.gcc.gnu.org/bugzilla/>
References: <bug-85048-4@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=3D85048

--- Comment #6 from Matthias Kretz (Vir) <mkretz at gcc dot gnu.org> ---
Most of the conversions are optimized perfectly now. Only the following
conversions are still missing for AVX-512:
https://godbolt.org/z/9afWbYod6

#include <cstdint>

template <class T, int N, int Size =3D N * sizeof(T)>
using V [[gnu::vector_size(Size)]] =3D T;

template <class From, class To> V<To, 4> cvt4(V<From, 4> x) {
    return V<To, 4>{To(x[0]), To(x[1]), To(x[2]), To(x[3])};
}
template <class From, class To> V<To, 8> cvt8(V<From, 8> x) {
    return V<To, 8>{
        To(x[0]), To(x[1]), To(x[2]), To(x[3]),
        To(x[4]), To(x[5]), To(x[6]), To(x[7])
    };
}
template <class From, class To> V<To, 16> cvt16(V<From, 16> x) {
    return V<To, 16>{
        To(x[0]), To(x[1]), To(x[2]), To(x[3]),
        To(x[4]), To(x[5]), To(x[6]), To(x[7]),
        To(x[8]), To(x[9]), To(x[10]), To(x[11]),
        To(x[12]), To(x[13]), To(x[14]), To(x[15])
    };
}

#define _(name, from, to, size) \
auto name(V<from, size> x) { return cvt##size<from, to>(x); }
// integral -> double
_(vcvtudq2pd, uint32_t, double, 4)
_(vcvtudq2pd, uint32_t, double, 8)

// integral -> float
_(vcvtqq2ps ,  int64_t, float, 16)
_(vcvtuqq2ps, uint64_t, float, 16)

// float -> integral
_(vcvttps2qq, float, int64_t, 16)

_( cvttps2udq, float, uint32_t,  4)
_(vcvttps2udq, float, uint32_t,  8)
_(vcvttps2uqq, float, uint64_t, 16)

// double -> integral
_(vcvttpd2udq, double, uint32_t, 4)=