! SPARC v9 64-bit VIS3 __mpn_addmul_1 -- Multiply a limb vector with a

! limb and add the result to a second limb vector.

!

! Copyright (C) 2013-2018 Free Software Foundation, Inc.

! This file is part of the GNU C Library.

! Contributed by David S. Miller <davem@davemloft.net>

!

! The GNU C Library is free software; you can redistribute it and/or

! modify it under the terms of the GNU Lesser General Public

! License as published by the Free Software Foundation; either

! version 2.1 of the License, or (at your option) any later version.

!

! The GNU C Library is distributed in the hope that it will be useful,

! but WITHOUT ANY WARRANTY; without even the implied warranty of

! MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU

! Lesser General Public License for more details.

!

! You should have received a copy of the GNU Lesser General Public

! License along with the GNU C Library; if not, see

! <http://www.gnu.org/licenses/>.

#include <sysdep.h>

#define res_ptr	%i0

#define s1_ptr	%i1

#define sz	%i2

#define s2_limb	%i3

#define carry	%o5

#define tmp1	%g1

#define tmp2	%g2

#define tmp3	%g3

#define tmp4	%o4

#define tmp5	%l0

#define tmp6	%l1

#define tmp7	%l2

#define tmp8	%l3

	.register	%g2,#scratch

	.register	%g3,#scratch

ENTRY(__mpn_addmul_1_vis3)

	save	%sp, -176, %sp

	subcc	sz, 1, sz

	be	.Lfinal_limb

	 clr	carry

.Lloop:

	ldx	[s1_ptr  + 0x00], tmp1

	ldx	[res_ptr + 0x00], tmp3

	ldx	[s1_ptr  + 0x08], tmp2

	ldx	[res_ptr + 0x08], tmp4

	mulx	tmp1, s2_limb, tmp5

	add	s1_ptr, 0x10, s1_ptr

	umulxhi	tmp1, s2_limb, tmp6

	add	res_ptr, 0x10, res_ptr

	mulx	tmp2, s2_limb, tmp7

	sub	sz, 2, sz

	umulxhi	tmp2, s2_limb, tmp8

	addcc	carry, tmp5, tmp5

	addxc	%g0, tmp6, carry

	addcc	tmp3, tmp5, tmp5

	addxc	%g0, carry, carry

	stx	tmp5, [res_ptr - 0x10]

	addcc	carry, tmp7, tmp7

	addxc	%g0, tmp8, carry

	addcc	tmp4, tmp7, tmp7

	addxc	%g0, carry, carry

	brgz	sz, .Lloop

	 stx	tmp7, [res_ptr - 0x08]

	brlz,pt	sz, .Lfinish

	 nop

.Lfinal_limb:

	ldx	[s1_ptr  + 0x00], tmp1

	ldx	[res_ptr + 0x00], tmp3

	mulx	tmp1, s2_limb, tmp5

	umulxhi	tmp1, s2_limb, tmp6

	addcc	carry, tmp5, tmp5

	addxc	%g0, tmp6, carry

	addcc	tmp3, tmp5, tmp5

	addxc	%g0, carry, carry

	stx	tmp5, [res_ptr + 0x00]

.Lfinish:

	jmpl	%i7 + 8, %g0

	 restore carry, 0, %o0

END(__mpn_addmul_1_vis3)