From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <SRS0=GGgE=IF=oss.cipunited.com=zhujunxian@sourceware.org>
Received: from va-2-33.ptr.blmpb.com (va-2-33.ptr.blmpb.com [209.127.231.33])
	by sourceware.org (Postfix) with ESMTPS id 2BD303858CD1
	for <libc-alpha@sourceware.org>; Tue, 26 Dec 2023 02:48:47 +0000 (GMT)
DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 2BD303858CD1
Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=oss.cipunited.com
Authentication-Results: sourceware.org; spf=none smtp.mailfrom=oss.cipunited.com
ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 2BD303858CD1
Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=209.127.231.33
ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1703558933; cv=none;
	b=eYiFWl0UB1bz5zQGYNy7hWMPdNc5OGvNzXCwIObCQSqWWbi3AS+BheLWzHwyvRV9XtahH/Lqe+nWOUybqM0LT18aDgNzGY/NJjCQJWXvcdlQCJKIxXxEsRDJfhSuRN1KT0jWkgu9hloq8xa46b5DBZOMbVjTPGkTdZuZkF16yZU=
ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key;
	t=1703558933; c=relaxed/simple;
	bh=3tSmRQaMzmVEDjL1WqXyd0KSraLrMC2GOU6i7YMWYVw=;
	h=DKIM-Signature:To:Date:From:Message-Id:Mime-Version:Subject; b=QW+RStIKdE0kvT55SWcvZbdEXfoRQi36dNUVmKp4QCNpyk90jAb0KwlZKm4Pd3gzdgyzoh7JotFRS70QX/GPoebygs8rwBEPAu8HjyoPkNyfpbK9NmzvUwaGL9ECNwQ8EvJgD104CGLz4WsylH5fHiD1C7ItX6y4k1OKpXSP7lU=
ARC-Authentication-Results: i=1; server2.sourceware.org
DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed;
 s=feishu2303200042; d=oss.cipunited.com; t=1703558920;
  h=from:subject:mime-version:from:date:message-id:subject:to:cc:
 reply-to:content-type:mime-version:in-reply-to:message-id;
 bh=5FQT+YeXTdrWrC4bKq7B+fMIQmUr74czWuDpVZVq6B0=;
 b=18V80YuL8oMxsOkZKKJQSQQZyVqwx0g8+mzCInCZvwVk6EcD5hQecOvbR+WgoJzrSnCQXt
 6CEp4mLu/Q75M8argxOnC7zlfleGdQECBZEaWAgc6GgYcDFoqzN++6W7MxOMzt2XtXhVDs
 dX2ebzk6IhLQr8WacwmluTPrMzBt25kfen9ZpozLNtAHw/T53Tp8eKARSJEZqfGm3Aoa/g
 8//4ImX+Fy4F7eAvzvCo6J5KDzJEqzhWWbwe1jXDIA6i5ACqa9qU1JwuRQR3cEhd4KdOaT
 Ke0LwMDqKHVvBSxz9dnYlXky2tFxTeqRfly+3YEfxY34cZWBcbfWaaNUqi7hlw==
In-Reply-To: <CAKcpw6Wt8xcx0Lvz1k3EkDaJVjKnm_AwFNnCpMA139GO+nYnJw@mail.gmail.com>
To: "YunQiang Su" <wzssyqa@gmail.com>
Date: Tue, 26 Dec 2023 10:48:38 +0800
Received: from [192.168.8.110] ([1.192.71.159]) by smtp.feishu.cn with ESMTPS; Tue, 26 Dec 2023 10:48:39 +0800
X-Original-From: Junxian Zhu <zhujunxian@oss.cipunited.com>
From: "Junxian Zhu" <zhujunxian@oss.cipunited.com>
Content-Type: text/plain; charset=UTF-8
User-Agent: Mozilla Thunderbird
References: <20231225103548.1615-2-zhujunxian@oss.cipunited.com> <20231225103548.1615-4-zhujunxian@oss.cipunited.com> <CAKcpw6Wt8xcx0Lvz1k3EkDaJVjKnm_AwFNnCpMA139GO+nYnJw@mail.gmail.com>
X-Lms-Return-Path: <lba+2658a3f07+ca705f+sourceware.org+zhujunxian@oss.cipunited.com>
Cc: <libc-alpha@sourceware.org>
Message-Id: <c8c2f5c0-d6f3-4011-afbd-db54122b57b3@oss.cipunited.com>
Mime-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Subject: Re: [PATCH 2/2] MIPS: Hard-float rounding instructions support
X-Spam-Status: No, score=-9.3 required=5.0 tests=BAYES_00,BODY_8BITS,DKIM_INVALID,DKIM_SIGNED,GIT_PATCH_0,KAM_DMARC_STATUS,KAM_SHORT,SPF_HELO_NONE,SPF_NONE,TXREP,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org
List-Id: <libc-alpha.sourceware.org>

=E5=9C=A8 2023/12/25 20:36, YunQiang Su =E5=86=99=E9=81=93:
>
>
> Junxian Zhu <zhujunxian@oss.cipunited.com> =E4=BA=8E 2023=E5=B9=B412=E6=
=9C=8825=E6=97=A5=E5=91=A8=E4=B8=80=20
> 18:38=E5=86=99=E9=81=93=EF=BC=9A
>
>     From: Junxian Zhu <zhujunxian@oss.cipunited.com>
>
>     Use hardware floating-point rounding instructions to implement
>     roundeven, trunc, ceil and floor.
>
>     * sysdeps/mips/mips32/Implies: Add source path.
>     * sysdeps/mips/mips64/Implies: Likewise.
>     * sysdeps/mips/fpu/Makefile: Newfile.
>     * sysdeps/mips/fpu/s_ceil.c: Likewise.
>     * sysdeps/mips/fpu/s_ceil_fpu.S: Likewise.
>     * sysdeps/mips/fpu/s_ceilf.c: Likewise.
>     * sysdeps/mips/fpu/s_ceilf_fpu.S: Likewise.
>     * sysdeps/mips/fpu/s_floor.c: Likewise.
>     * sysdeps/mips/fpu/s_floor_fpu.S: Likewise.
>     * sysdeps/mips/fpu/s_floorf.c: Likewise.
>     * sysdeps/mips/fpu/s_floorf_fpu.S: Likewise.
>     * sysdeps/mips/fpu/s_roundeven.c: Likewise.
>     * sysdeps/mips/fpu/s_roundeven_fpu.S: Likewise.
>     * sysdeps/mips/fpu/s_roundevenf.c: Likewise.
>     * sysdeps/mips/fpu/s_roundevenf_fpu.S: Likewise.
>     * sysdeps/mips/fpu/s_trunc.c: Likewise.
>     * sysdeps/mips/fpu/s_trunc_fpu.S: Likewise.
>     * sysdeps/mips/fpu/s_truncf.c: Likewise.
>     * sysdeps/mips/fpu/s_truncf_fpu.S: Likewise.
>
>     Signed-off-by: Rong Zhang <rongrong@oss.cipunited.com>
>     Signed-off-by: Junxian Zhu <zhujunxian@oss.cipunited.com>
>     ---
>     =C2=A0sysdeps/mips/fpu/Makefile=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0| 12 ++++
>     =C2=A0sysdeps/mips/fpu/s_ceil.c=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0| 30 ++++++++++
>     =C2=A0sysdeps/mips/fpu/s_ceil_fpu.S=C2=A0 =C2=A0 =C2=A0 =C2=A0| 90
>     +++++++++++++++++++++++++++++
>     =C2=A0sysdeps/mips/fpu/s_ceilf.c=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 | =
30 ++++++++++
>     =C2=A0sysdeps/mips/fpu/s_ceilf_fpu.S=C2=A0 =C2=A0 =C2=A0 | 82 +++++++=
+++++++++++++++++++
>     =C2=A0sysdeps/mips/fpu/s_floor.c=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 | =
24 ++++++++
>     =C2=A0sysdeps/mips/fpu/s_floor_fpu.S=C2=A0 =C2=A0 =C2=A0 | 88 +++++++=
+++++++++++++++++++++
>     =C2=A0sysdeps/mips/fpu/s_floorf.c=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0| =
24 ++++++++
>     =C2=A0sysdeps/mips/fpu/s_floorf_fpu.S=C2=A0 =C2=A0 =C2=A0| 80 +++++++=
++++++++++++++++++
>     =C2=A0sysdeps/mips/fpu/s_roundeven.c=C2=A0 =C2=A0 =C2=A0 | 24 +++++++=
+
>     =C2=A0sysdeps/mips/fpu/s_roundeven_fpu.S=C2=A0 | 87 +++++++++++++++++=
+++++++++++
>     =C2=A0sysdeps/mips/fpu/s_roundevenf.c=C2=A0 =C2=A0 =C2=A0| 24 +++++++=
+
>     =C2=A0sysdeps/mips/fpu/s_roundevenf_fpu.S | 79 ++++++++++++++++++++++=
+++
>     =C2=A0sysdeps/mips/fpu/s_trunc.c=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 | =
24 ++++++++
>     =C2=A0sysdeps/mips/fpu/s_trunc_fpu.S=C2=A0 =C2=A0 =C2=A0 | 84 +++++++=
++++++++++++++++++++
>     =C2=A0sysdeps/mips/fpu/s_truncf.c=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0| =
24 ++++++++
>     =C2=A0sysdeps/mips/fpu/s_truncf_fpu.S=C2=A0 =C2=A0 =C2=A0| 76 +++++++=
+++++++++++++++++
>     =C2=A0sysdeps/mips/mips32/Implies=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0|=
=C2=A0 1 +
>     =C2=A0sysdeps/mips/mips64/Implies=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0|=
=C2=A0 1 +
>     =C2=A019 files changed, 884 insertions(+)
>     =C2=A0create mode 100644 sysdeps/mips/fpu/Makefile
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_ceil.c
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_ceil_fpu.S
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_ceilf.c
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_ceilf_fpu.S
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_floor.c
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_floor_fpu.S
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_floorf.c
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_floorf_fpu.S
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_roundeven.c
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_roundeven_fpu.S
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_roundevenf.c
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_roundevenf_fpu.S
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_trunc.c
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_trunc_fpu.S
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_truncf.c
>     =C2=A0create mode 100644 sysdeps/mips/fpu/s_truncf_fpu.S
>
>     diff --git a/sysdeps/mips/fpu/Makefile b/sysdeps/mips/fpu/Makefile
>     new file mode 100644
>     index 0000000000..ad537d6bf1
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/Makefile
>     @@ -0,0 +1,12 @@
>     +ifeq ($(subdir),math)
>     +sysdep_routines +=3D s_floor_fpu s_floorf_fpu \
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0 =C2=A0 =C2=A0s_ceil_fpu s_ceilf_fpu \
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0 =C2=A0 =C2=A0s_trunc_fpu s_truncf_fpu \
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0 =C2=A0 =C2=A0s_roundeven_fpu s_roundevenf_fpu
>     +
>     +libm-sysdep_routines +=3D s_floor_fpu s_floorf_fpu \
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0 =C2=A0 =C2=A0s_ceil_fpu s_ceilf_fpu \
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0 =C2=A0 =C2=A0s_trunc_fpu s_truncf_fpu \
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0 =C2=A0 =C2=A0s_roundeven_fpu s_roundevenf_fpu
>     +
>     +endif
>     diff --git a/sysdeps/mips/fpu/s_ceil.c b/sysdeps/mips/fpu/s_ceil.c
>     new file mode 100644
>     index 0000000000..91a90a70c5
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_ceil.c
>     @@ -0,0 +1,30 @@
>     +/* Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library.=C2=A0 If not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +/*
>     + * ceil(x)
>     + * Return x rounded toward -inf to integral value
>     + * Method:
>     + *=C2=A0 =C2=A0 =C2=A0Bit twiddling.
>     + */
>     +
>     +#if !((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1)=C2=A0 =
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
>     =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 \
>     +=C2=A0 =C2=A0 =C2=A0 && ((__mips =3D=3D 32 && __mips_isa_rev > 1) ||=
 __mips =3D=3D 64))
>     +
>
>
> __mips_fpr =3D=3D 64
> this condition should not be here.
> it means fp64.
> In fact your code should also support fp32 and fpxx.
>
>     +#=C2=A0 include <sysdeps/ieee754/dbl-64/s_ceil.c>
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_ceil_fpu.S
>     b/sysdeps/mips/fpu/s_ceil_fpu.S
>     new file mode 100644
>     index 0000000000..13d4f85ad3
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_ceil_fpu.S
>     @@ -0,0 +1,90 @@
>     +/* Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library.=C2=A0 If not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +/*
>     + * ceil(x)
>     + * Return x rounded toward -inf to integral value
>     + * Method:
>     + *=C2=A0 =C2=A0 =C2=A0Bit twiddling.
>     + */
>     +
>     +#if ((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1) && ((__m=
ips
>     =3D=3D 32 && __mips_isa_rev > 1) || __mips =3D=3D 64))
>     +#include <sys/regdef.h>
>     +#include <sysdep.h>
>     +#include <libm-alias-double.h>
>     +
>     +ENTRY(__ceil)
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set push
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noreorder
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noat
>     +# $f0=3Dret, $f12=3Ddouble, a0=3Dint64/int32_h, a1=3Dint32_l, a2=3Ds=
ign, a3=3Dexp
>     +#if __mips =3D=3D 64
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dmfc1=C2=A0 =C2=A0a0, $f12 # assign int64
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfhc1=C2=A0 =C2=A0a0, $f12 # assign int64
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cfc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ceil.l.d=C2=A0 =C2=A0 $f0, $f12
>     +#if __mips =3D=3D 64
>     +#if __mips_isa_rev > 1
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dext=C2=A0 =C2=A0 a3, a0, 52, 11 # assign=
 exp
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a3, a0, 52
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0andi=C2=A0 =C2=A0 a3, a3, 0x7ff
>     +#endif
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ext=C2=A0 =C2=A0 =C2=A0a3, a0, 20, 11 # a=
ssign exp
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 1023
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 AT, SMALL # exp < 1023
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ctc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 1023+54
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 AT, BIG # exp >=3D 1023=
+54
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0x7ff
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.d.l $f0, $f0
>     +BIG:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bne=C2=A0 =C2=A0 =C2=A0AT, a3, RETURN_AS_=
IS # exp !=3D 0x7ff, no frac
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +NAN_INF:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0add.d=C2=A0 =C2=A0$f0, $f12, $f12 # retur=
n double + double
>     +SMALL:
>     +#if __mips =3D=3D 64
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a2, a0, 63
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0srl=C2=A0 =C2=A0 =C2=A0a2, a0, 31
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 a2, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +SMALL_NEGATIVE: # return -0.0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0neg.d=C2=A0 =C2=A0$f0, $f0
>     +SMALL_POSITIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.d.l $f0, $f0
>     +RETURN_AS_IS:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mov.d=C2=A0 =C2=A0$f0, $f12
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set pop
>     +
>     +END (__ceil)
>     +libm_alias_double (__ceil, ceil)
>     +
>     +#endif
>     +
>     diff --git a/sysdeps/mips/fpu/s_ceilf.c b/sysdeps/mips/fpu/s_ceilf.c
>     new file mode 100644
>     index 0000000000..a7f81c7539
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_ceilf.c
>     @@ -0,0 +1,30 @@
>     +/* Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library.=C2=A0 If not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +/*
>     + * ceil(x)
>     + * Return x rounded toward -inf to integral value
>     + * Method:
>     + *=C2=A0 =C2=A0 =C2=A0Bit twiddling.
>     + */
>     +
>     +#if !((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1)=C2=A0 =
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
>     =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 \
>     +=C2=A0 =C2=A0 =C2=A0 && ((__mips =3D=3D 32 && __mips_isa_rev > 1) ||=
 __mips =3D=3D 64))
>     +
>     +#=C2=A0 include <sysdeps/ieee754/flt-32/s_ceilf.c>
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_ceilf_fpu.S
>     b/sysdeps/mips/fpu/s_ceilf_fpu.S
>     new file mode 100644
>     index 0000000000..7952894f73
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_ceilf_fpu.S
>     @@ -0,0 +1,82 @@
>     +/* Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library.=C2=A0 If not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +/*
>     + * ceil(x)
>     + * Return x rounded toward -inf to integral value
>     + * Method:
>     + *=C2=A0 =C2=A0 =C2=A0Bit twiddling.
>     + */
>     +
>     +#if ((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1) && ((__m=
ips
>     =3D=3D 32 && __mips_isa_rev > 1) || __mips =3D=3D 64))
>     +#include <sys/regdef.h>
>     +#include <sysdep.h>
>     +#include <libm-alias-float.h>
>     +
>     +ENTRY(__ceilf)
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set push
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noreorder
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noat
>     +# f0=3Dret, f12=3Dfloat, a0=3Dint32, a2=3Dsign, a3=3Dexp
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfc1=C2=A0 =C2=A0 a0, $f12 # assign int32
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cfc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ceil.l.s=C2=A0 =C2=A0 $f0, $f12
>     +#if __mips =3D=3D 64
>     +#if __mips_isa_rev > 1
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dext=C2=A0 =C2=A0 a3, a0, 23, 8 # assign =
exp
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a3, a0, 23
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0andi=C2=A0 =C2=A0 a3, a3, 0x1ff
>     +#endif
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ext=C2=A0 =C2=A0 =C2=A0a3, a0, 23, 8 # as=
sign exp
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 127
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 AT, SMALL # exp < 127
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ctc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 127+25
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 AT, BIG # exp >=3D 127+=
25
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0xff
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.s.l $f0, $f0
>     +BIG:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bne=C2=A0 =C2=A0 =C2=A0AT, a3, RETURN_AS_=
IS # exp !=3D 0xff, no frac
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +NAN_INF:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0add.s=C2=A0 =C2=A0$f0, $f12, $f12 # retur=
n double + double
>     +SMALL:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0srl=C2=A0 =C2=A0 =C2=A0a2, a0, 31
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 a2, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +SMALL_NEGATIVE: # return -0.0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0neg.s=C2=A0 =C2=A0$f0, $f0
>     +SMALL_POSITIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.s.l $f0, $f0
>     +RETURN_AS_IS:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mov.s=C2=A0 =C2=A0$f0, $f12
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set pop
>     +
>     +END (__ceilf)
>     +libm_alias_float (__ceil, ceil)
>     +
>     +#endif
>     +
>     diff --git a/sysdeps/mips/fpu/s_floor.c b/sysdeps/mips/fpu/s_floor.c
>     new file mode 100644
>     index 0000000000..4b43dc9ad9
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_floor.c
>     @@ -0,0 +1,24 @@
>     +/* Round double to integer away from zero.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if !((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1)=C2=A0 =
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
>     =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 \
>     +=C2=A0 =C2=A0 =C2=A0 && ((__mips =3D=3D 32 && __mips_isa_rev > 1) ||=
 __mips =3D=3D 64))
>     +
>     +#=C2=A0 include <sysdeps/ieee754/dbl-64/s_floor.c>
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_floor_fpu.S
>     b/sysdeps/mips/fpu/s_floor_fpu.S
>     new file mode 100644
>     index 0000000000..fda661fd3a
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_floor_fpu.S
>     @@ -0,0 +1,88 @@
>     +/* Round double to integer away from zero.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if ((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1) && ((__m=
ips
>     =3D=3D 32 && __mips_isa_rev > 1) || __mips =3D=3D 64))
>     +#include <sys/regdef.h>
>     +#include <sysdep.h>
>     +#include <libm-alias-double.h>
>     +
>     +ENTRY(__floor)
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set push
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noreorder
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noat
>     +# f0=3Dret, f12=3Ddouble, a0=3Dint64/int32_h, a1=3Dint32_l, a2=3Dsig=
n, a3=3Dexp
>     +#if __mips =3D=3D 64
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dmfc1=C2=A0 =C2=A0a0, $f12 # assign int64
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfhc1=C2=A0 =C2=A0a0, $f12 # assign int64
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cfc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0floor.l.d=C2=A0 =C2=A0 $f0, $f12
>     +#if __mips =3D=3D 64
>     +#if __mips_isa_rev > 1
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dext=C2=A0 =C2=A0 a3, a0, 52, 11 # assign=
 exp
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a3, a0, 52
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0andi=C2=A0 =C2=A0 a3, a3, 0x7ff
>     +#endif
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ext=C2=A0 =C2=A0 =C2=A0a3, a0, 20, 11 # a=
ssign exp
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 1023
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 AT, SMALL # exp < 1023
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ctc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 1023+54
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 AT, BIG # exp >=3D 1023=
+54
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0x7ff
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.d.l $f0, $f0
>     +BIG:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bne=C2=A0 =C2=A0 =C2=A0AT, a3, RETURN_AS_=
IS # exp !=3D 0x7ff, no frac
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +NAN_INF:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0add.d=C2=A0 =C2=A0$f0, $f12, $f12 # retur=
n double + double
>     +SMALL:
>     +#if __mips =3D=3D 64
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a2, a0, 63
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0srl=C2=A0 =C2=A0 =C2=A0a2, a0, 31
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 a2, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0xbff # used b=
y SMALL_NEGATIVE
>     +SMALL_NEGATIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfhc1=C2=A0 =C2=A0t1, $f0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 t1, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0neg.d=C2=A0 =C2=A0$f0, $f0
>     +SMALL_POSITIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.d.l $f0, $f0
>     +RETURN_AS_IS:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mov.d=C2=A0 =C2=A0$f0, $f12
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set pop
>     +
>     +END (__floor)
>     +libm_alias_double (__floor, floor)
>     +
>     +#endif
>     +
>     diff --git a/sysdeps/mips/fpu/s_floorf.c b/sysdeps/mips/fpu/s_floorf.=
c
>     new file mode 100644
>     index 0000000000..30cfda7820
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_floorf.c
>     @@ -0,0 +1,24 @@
>     +/* Round double to integer away from zero.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if !((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1)=C2=A0 =
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
>     =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 \
>     +=C2=A0 =C2=A0 =C2=A0 && ((__mips =3D=3D 32 && __mips_isa_rev > 1) ||=
 __mips =3D=3D 64))
>     +
>     +#=C2=A0 include <sysdeps/ieee754/flt-32/s_floorf.c>
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_floorf_fpu.S
>     b/sysdeps/mips/fpu/s_floorf_fpu.S
>     new file mode 100644
>     index 0000000000..8edd234dbc
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_floorf_fpu.S
>     @@ -0,0 +1,80 @@
>     +/* Round double to integer away from zero.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if ((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1) && ((__m=
ips
>     =3D=3D 32 && __mips_isa_rev > 1) || __mips =3D=3D 64))
>     +#include <sys/regdef.h>
>     +#include <sysdep.h>
>     +#include <libm-alias-float.h>
>     +
>     +ENTRY(__floorf)
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set push
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noreorder
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noat
>     +# f0=3Dret, f12=3Dfloat, a0=3Dint32, a2=3Dsign, a3=3Dexp
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfc1=C2=A0 =C2=A0 a0, $f12 # assign int32
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cfc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0floor.l.s=C2=A0 =C2=A0 $f0, $f12
>     +#if __mips =3D=3D 64
>     +#if __mips_isa_rev > 1
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dext=C2=A0 =C2=A0 a3, a0, 23, 8 # assign =
exp
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a3, a0, 23
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0andi=C2=A0 =C2=A0 a3, a3, 0x1ff
>     +#endif
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ext=C2=A0 =C2=A0 =C2=A0a3, a0, 23, 8 # as=
sign exp
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 127
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 AT, SMALL # exp < 127
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ctc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 127+25
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 AT, BIG # exp >=3D 127+=
25
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0xff
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.s.l $f0, $f0
>     +BIG:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bne=C2=A0 =C2=A0 =C2=A0AT, a3, RETURN_AS_=
IS # exp !=3D 0xff, no frac
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +NAN_INF:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0add.s=C2=A0 =C2=A0$f0, $f12, $f12 # retur=
n double + double
>     +SMALL:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0srl=C2=A0 =C2=A0 =C2=A0a2, a0, 31
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 a2, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0xbff # used b=
y SMALL_NEGATIVE
>     +SMALL_NEGATIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfhc1=C2=A0 =C2=A0t1, $f0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 t1, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0neg.s=C2=A0 =C2=A0$f0, $f0
>     +SMALL_POSITIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.s.l $f0, $f0
>     +RETURN_AS_IS:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mov.s=C2=A0 =C2=A0$f0, $f12
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set pop
>     +
>     +END (__floorf)
>     +libm_alias_float (__floor, floor)
>     +
>     +#endif
>     +
>     diff --git a/sysdeps/mips/fpu/s_roundeven.c
>     b/sysdeps/mips/fpu/s_roundeven.c
>     new file mode 100644
>     index 0000000000..dace85a70b
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_roundeven.c
>     @@ -0,0 +1,24 @@
>     +/* Round to nearest integer value, rounding halfway cases to even.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if !((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1)=C2=A0 =
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
>     =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 \
>     +=C2=A0 =C2=A0 =C2=A0 && ((__mips =3D=3D 32 && __mips_isa_rev > 1) ||=
 __mips =3D=3D 64))
>     +
>     +#=C2=A0 include <sysdeps/ieee754/dbl-64/s_roundeven.c>
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_roundeven_fpu.S
>     b/sysdeps/mips/fpu/s_roundeven_fpu.S
>     new file mode 100644
>     index 0000000000..aef6434886
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_roundeven_fpu.S
>     @@ -0,0 +1,87 @@
>     +/* Round to nearest integer value, rounding halfway cases to even.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if ((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1) && ((__m=
ips
>     =3D=3D 32 && __mips_isa_rev > 1) || __mips =3D=3D 64))
>     +#include <sys/regdef.h>
>     +#include <sysdep.h>
>     +#include <libm-alias-double.h>
>     +
>     +ENTRY(__roundeven)
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set push
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noreorder
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noat
>     +# f0=3Dret, f12=3Ddouble, a0=3Dint64/int32_h, a1=3Dint32_l, a2=3Dsig=
n, a3=3Dexp
>     +#if __mips =3D=3D 64
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dmfc1=C2=A0 =C2=A0a0, $f12 # assign int64
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfhc1=C2=A0 =C2=A0a0, $f12 # assign int64
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cfc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0round.l.d=C2=A0 =C2=A0 =C2=A0 =C2=A0$f0, =
$f12
>     +#if __mips =3D=3D 64
>     +#if __mips_isa_rev > 1
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dext=C2=A0 =C2=A0 a3, a0, 52, 11 # assign=
 exp
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a3, a0, 52
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0andi=C2=A0 =C2=A0 a3, a3, 0x7ff
>     +#endif
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ext=C2=A0 =C2=A0 =C2=A0a3, a0, 20, 11 # a=
ssign exp
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 1023
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 AT, SMALL # exp < 1023
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ctc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 1023+54
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 AT, BIG # exp >=3D 1023=
+54
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0x7ff
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.d.l $f0, $f0
>     +BIG:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bne=C2=A0 =C2=A0 =C2=A0AT, a3, RETURN_AS_=
IS # exp !=3D 0x7ff, no frac
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +NAN_INF:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0add.d=C2=A0 =C2=A0$f0, $f12, $f12 # retur=
n double + double
>     +SMALL:
>     +#if __mips =3D=3D 64
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a2, a0, 63
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0srl=C2=A0 =C2=A0 =C2=A0a2, a0, 31
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 a2, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +SMALL_NEGATIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfhc1=C2=A0 =C2=A0t1, $f0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 t1, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0neg.d=C2=A0 =C2=A0$f0, $f0
>     +SMALL_POSITIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.d.l $f0, $f0
>     +RETURN_AS_IS:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mov.d=C2=A0 =C2=A0$f0, $f12
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set pop
>     +
>     +END (__roundeven)
>     +libm_alias_double (__roundeven, roundeven)
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_roundevenf.c
>     b/sysdeps/mips/fpu/s_roundevenf.c
>     new file mode 100644
>     index 0000000000..5bb35901db
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_roundevenf.c
>     @@ -0,0 +1,24 @@
>     +/* Round to nearest integer value, rounding halfway cases to even.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if !((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1)=C2=A0 =
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
>     =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 \
>     +=C2=A0 =C2=A0 =C2=A0 && ((__mips =3D=3D 32 && __mips_isa_rev > 1) ||=
 __mips =3D=3D 64))
>     +
>     +#=C2=A0 include <sysdeps/ieee754/flt-32/s_roundevenf.c>
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_roundevenf_fpu.S
>     b/sysdeps/mips/fpu/s_roundevenf_fpu.S
>     new file mode 100644
>     index 0000000000..e946e50d8f
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_roundevenf_fpu.S
>     @@ -0,0 +1,79 @@
>     +/* Round to nearest integer value, rounding halfway cases to even.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if ((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1) && ((__m=
ips
>     =3D=3D 32 && __mips_isa_rev > 1) || __mips =3D=3D 64))
>     +#include <sys/regdef.h>
>     +#include <sysdep.h>
>     +#include <libm-alias-float.h>
>     +
>     +ENTRY(__roundevenf)
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set push
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noreorder
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noat
>     +# f0=3Dret, f12=3Dfloat, a0=3Dint32, a2=3Dsign, a3=3Dexp
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfc1=C2=A0 =C2=A0 a0, $f12 # assign int32
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cfc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0round.l.s=C2=A0 =C2=A0 =C2=A0 =C2=A0$f0, =
$f12
>     +#if __mips =3D=3D 64
>     +#if __mips_isa_rev > 1
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dext=C2=A0 =C2=A0 a3, a0, 23, 8 # assign =
exp
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a3, a0, 23
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0andi=C2=A0 =C2=A0 a3, a3, 0x1ff
>     +#endif
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ext=C2=A0 =C2=A0 =C2=A0a3, a0, 23, 8 # as=
sign exp
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 127
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 AT, SMALL # exp < 127
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ctc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 127+25
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 AT, BIG # exp >=3D 127+=
25
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0xff
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.s.l $f0, $f0
>     +BIG:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bne=C2=A0 =C2=A0 =C2=A0AT, a3, RETURN_AS_=
IS # exp !=3D 0xff, no frac
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +NAN_INF:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0add.s=C2=A0 =C2=A0$f0, $f12, $f12 # retur=
n double + double
>     +SMALL:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0srl=C2=A0 =C2=A0 =C2=A0a2, a0, 31
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 a2, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +SMALL_NEGATIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfhc1=C2=A0 =C2=A0t1, $f0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 t1, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0neg.s=C2=A0 =C2=A0$f0, $f0
>     +SMALL_POSITIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.s.l $f0, $f0
>     +RETURN_AS_IS:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mov.s=C2=A0 =C2=A0$f0, $f12
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set pop
>     +
>     +END (__roundevenf)
>     +libm_alias_float (__roundeven, roundeven)
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_trunc.c b/sysdeps/mips/fpu/s_trunc.c
>     new file mode 100644
>     index 0000000000..3865026c70
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_trunc.c
>     @@ -0,0 +1,24 @@
>     +/* Truncate argument to nearest integral value not larger than
>     the argument.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if !((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1)=C2=A0 =
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
>     =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 \
>     +=C2=A0 =C2=A0 =C2=A0 && ((__mips =3D=3D 32 && __mips_isa_rev > 1) ||=
 __mips =3D=3D 64))
>     +
>     +#=C2=A0 include <sysdeps/ieee754/dbl-64/s_trunc.c>
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_trunc_fpu.S
>     b/sysdeps/mips/fpu/s_trunc_fpu.S
>     new file mode 100644
>     index 0000000000..3a7947507f
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_trunc_fpu.S
>     @@ -0,0 +1,84 @@
>     +/* Truncate argument to nearest integral value not larger than
>     the argument.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if ((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1) && ((__m=
ips
>     =3D=3D 32 && __mips_isa_rev > 1) || __mips =3D=3D 64))
>     +#include <sys/regdef.h>
>     +#include <sysdep.h>
>     +#include <libm-alias-double.h>
>     +
>     +ENTRY(__trunc)
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set push
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noreorder
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noat
>     +# f0=3Dret, f12=3Ddouble, a0=3Dint64/int32_h, a1=3Dint32_l, a2=3Dsig=
n, a3=3Dexp
>     +#if __mips =3D=3D 64
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dmfc1=C2=A0 =C2=A0a0, $f12 # assign int64
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfhc1=C2=A0 =C2=A0a0, $f12 # assign int64
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cfc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0trunc.l.d=C2=A0 =C2=A0 $f0, $f12
>     +#if __mips =3D=3D 64
>     +#if __mips_isa_rev > 1
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dext=C2=A0 =C2=A0 a3, a0, 52, 11 # assign=
 exp
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a3, a0, 52
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0andi=C2=A0 =C2=A0 a3, a3, 0x7ff
>     +#endif
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ext=C2=A0 =C2=A0 =C2=A0a3, a0, 20, 11 # a=
ssign exp
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 1023
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 AT, SMALL # exp < 1023
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ctc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 1023+54
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 AT, BIG # exp >=3D 1023=
+54
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0x7ff
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.d.l $f0, $f0
>     +BIG:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bne=C2=A0 =C2=A0 =C2=A0AT, a3, RETURN_AS_=
IS # exp !=3D 0x7ff, no frac
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +NAN_INF:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0add.d=C2=A0 =C2=A0$f0, $f12, $f12 # retur=
n double + double
>     +SMALL:
>     +#if __mips =3D=3D 64
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a2, a0, 63
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0srl=C2=A0 =C2=A0 =C2=A0a2, a0, 31
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 a2, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +SMALL_NEGATIVE: # return -0.0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0neg.d=C2=A0 =C2=A0$f0, $f0
>     +SMALL_POSITIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.d.l $f0, $f0
>     +RETURN_AS_IS:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mov.d=C2=A0 =C2=A0$f0, $f12
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set pop
>     +
>     +END (__trunc)
>     +libm_alias_double (__trunc, trunc)
>     +
>     +#endif
>     +
>     diff --git a/sysdeps/mips/fpu/s_truncf.c b/sysdeps/mips/fpu/s_truncf.=
c
>     new file mode 100644
>     index 0000000000..59ef17bf74
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_truncf.c
>     @@ -0,0 +1,24 @@
>     +/* Truncate argument to nearest integral value not larger than
>     the argument.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if !((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1)=C2=A0 =
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0
>     =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 \
>     +=C2=A0 =C2=A0 =C2=A0 && ((__mips =3D=3D 32 && __mips_isa_rev > 1) ||=
 __mips =3D=3D 64))
>     +
>     +#=C2=A0 include <sysdeps/ieee754/flt-32/s_truncf.c>
>     +
>     +#endif
>     diff --git a/sysdeps/mips/fpu/s_truncf_fpu.S
>     b/sysdeps/mips/fpu/s_truncf_fpu.S
>     new file mode 100644
>     index 0000000000..1878d88e3c
>     --- /dev/null
>     +++ b/sysdeps/mips/fpu/s_truncf_fpu.S
>     @@ -0,0 +1,76 @@
>     +/* Truncate argument to nearest integral value not larger than
>     the argument.
>     +=C2=A0 =C2=A0Copyright (C) 2023 Free Software Foundation, Inc.
>     +=C2=A0 =C2=A0This file is part of the GNU C Library.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is free software; you can redistribut=
e it and/or
>     +=C2=A0 =C2=A0modify it under the terms of the GNU Lesser General Pub=
lic
>     +=C2=A0 =C2=A0License as published by the Free Software Foundation; e=
ither
>     +=C2=A0 =C2=A0version 2.1 of the License, or (at your option) any lat=
er version.
>     +
>     +=C2=A0 =C2=A0The GNU C Library is distributed in the hope that it wi=
ll be
>     useful,
>     +=C2=A0 =C2=A0but WITHOUT ANY WARRANTY; without even the implied warr=
anty of
>     +=C2=A0 =C2=A0MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Se=
e the GNU
>     +=C2=A0 =C2=A0Lesser General Public License for more details.
>     +
>     +=C2=A0 =C2=A0You should have received a copy of the GNU Lesser Gener=
al Public
>     +=C2=A0 =C2=A0License along with the GNU C Library; if not, see
>     +=C2=A0 =C2=A0<https://www.gnu.org/licenses/>. */
>     +
>     +#if ((__mips_fpr =3D=3D 64) && (__mips_hard_float =3D=3D 1) && ((__m=
ips
>     =3D=3D 32 && __mips_isa_rev > 1) || __mips =3D=3D 64))
>     +#include <sys/regdef.h>
>     +#include <sysdep.h>
>     +#include <libm-alias-float.h>
>     +
>     +ENTRY(__truncf)
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set push
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noreorder
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set noat
>     +# f0=3Dret, f12=3Dfloat, a0=3Dint32, a2=3Dsign, a3=3Dexp
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mfc1=C2=A0 =C2=A0 a0, $f12 # assign int32
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cfc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0trunc.l.s=C2=A0 =C2=A0 $f0, $f12
>     +#if __mips =3D=3D 64
>     +#if __mips_isa_rev > 1
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dext=C2=A0 =C2=A0 a3, a0, 23, 8 # assign =
exp
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0dsrl=C2=A0 =C2=A0 a3, a0, 23
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0andi=C2=A0 =C2=A0 a3, a3, 0x1ff
>     +#endif
>     +#else
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ext=C2=A0 =C2=A0 =C2=A0a3, a0, 23, 8 # as=
sign exp
>     +#endif
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 127
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bnez=C2=A0 =C2=A0 AT, SMALL # exp < 127
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0ctc1=C2=A0 =C2=A0 t0, $f26
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0sltiu=C2=A0 =C2=A0AT, a3, 127+25
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 AT, BIG # exp >=3D 127+=
25
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0li=C2=A0 =C2=A0 =C2=A0 AT, 0xff
>     +
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.s.l $f0, $f0
>     +BIG:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0bne=C2=A0 =C2=A0 =C2=A0AT, a3, RETURN_AS_=
IS # exp !=3D 0xff, no frac
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +NAN_INF:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0add.s=C2=A0 =C2=A0$f0, $f12, $f12 # retur=
n double + double
>     +SMALL:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0srl=C2=A0 =C2=A0 =C2=A0a2, a0, 31
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0beqz=C2=A0 =C2=A0 a2, SMALL_POSITIVE # si=
gn =3D=3D 0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0nop
>     +SMALL_NEGATIVE: # return -0.0
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0neg.s=C2=A0 =C2=A0$f0, $f0
>     +SMALL_POSITIVE:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0cvt.s.l $f0, $f0
>     +RETURN_AS_IS:
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0jr=C2=A0 =C2=A0 =C2=A0 ra
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0mov.s=C2=A0 =C2=A0$f0, $f12
>     +=C2=A0 =C2=A0 =C2=A0 =C2=A0.set pop
>     +
>     +END (__truncf)
>     +libm_alias_float (__trunc, trunc)
>     +
>     +#endif
>     +
>     diff --git a/sysdeps/mips/mips32/Implies b/sysdeps/mips/mips32/Implie=
s
>     index 6473f2517c..71b3678c6c 100644
>     --- a/sysdeps/mips/mips32/Implies
>     +++ b/sysdeps/mips/mips32/Implies
>     @@ -1,3 +1,4 @@
>     +mips/fpu
>     =C2=A0mips/ieee754
>     =C2=A0mips
>     =C2=A0wordsize-32
>     diff --git a/sysdeps/mips/mips64/Implies b/sysdeps/mips/mips64/Implie=
s
>     index 826ff1541f..8885ebd564 100644
>     --- a/sysdeps/mips/mips64/Implies
>     +++ b/sysdeps/mips/mips64/Implies
>     @@ -1,4 +1,5 @@
>     =C2=A0# MIPS uses IEEE 754 floating point.
>     +mips/fpu
>     =C2=A0mips/ieee754
>     =C2=A0ieee754/flt-32
>     =C2=A0ieee754/dbl-64
>     --=20
>     2.43.0.windows.1
>

According to restrictions about rounding instructions in MIPS=20
instructions manual, "The result of this instruction is UNPREDICTABLE if=20
the processor is executing in the FR=3D0 32-bit FPU register model; it is=
=20
predictable if executing on a 64-bit FPU in the FR=3D1 mode, but not with=
=20
FR=3D0, and not on a 32-bit FPU.".

It means that such MIPS rounding instruction could only work correct in=20
the FR=3D1 mode, and fp64 is the only ABI can make sure MIPS FPU running=20
at FR=3D1 mode. If we support fp32 or fpxx, the result will be UNPREDICTABL=
E.