glibc/sysdeps/sparc/sparc64/multiarch/sub_n-vis3.S
David S. Miller 32fcb36dbf Add 64-bit VIS3 optimized GMP routines for sparc.
* math/Makefile: Recognize gmp-sysdep_routines.
	* sysdeps/sparc/sparc64/multiarch/Makefile: Add VIS3 optimized GMP routines
	to sysdeps.
	* sysdeps/sparc/sparc64/multiarch/add_n-vis3.S: New file.
	* sysdeps/sparc/sparc64/multiarch/add_n.S: New file.
	* sysdeps/sparc/sparc64/multiarch/addmul_1-vis3.S: New file.
	* sysdeps/sparc/sparc64/multiarch/addmul_1.S: New file.
	* sysdeps/sparc/sparc64/multiarch/mul_1-vis3.S: New file.
	* sysdeps/sparc/sparc64/multiarch/mul_1.S: New file.
	* sysdeps/sparc/sparc64/multiarch/sub_n-vis3.S: New file.
	* sysdeps/sparc/sparc64/multiarch/sub_n.S: New file.
	* sysdeps/sparc/sparc64/multiarch/submul_1-vis3.S: New file.
	* sysdeps/sparc/sparc64/multiarch/submul_1.S: New file.
2013-01-11 23:39:02 -08:00

72 lines
1.8 KiB
ArmAsm

! SPARC v9 64-bit VIS3 __mpn_sub_n -- Subtract two limb vectors of the same length > 0
! and store difference in a third limb vector.
!
! Copyright (C) 2013 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 %o0
#define s1_ptr %o1
#define s2_ptr %o2
#define sz %o3
#define tmp1 %g1
#define tmp2 %g2
#define tmp3 %g3
#define tmp4 %o4
.register %g2,#scratch
.register %g3,#scratch
ENTRY(__mpn_sub_n_vis3)
subcc sz, 1, sz
be .Lfinal_limb
cmp %g0, 1
.Lloop:
ldx [s2_ptr + 0x00], tmp1
add s2_ptr, 0x10, s2_ptr
ldx [s1_ptr + 0x00], tmp2
add s1_ptr, 0x10, s1_ptr
ldx [s2_ptr - 0x08], tmp3
add res_ptr, 0x10, res_ptr
ldx [s1_ptr - 0x08], tmp4
sub sz, 2, sz
xnor tmp1, %g0, tmp1
addxccc tmp1, tmp2, tmp1
stx tmp1, [res_ptr - 0x10]
xnor tmp3, %g0, tmp3
addxccc tmp3, tmp4, tmp3
brgz sz, .Lloop
stx tmp3, [res_ptr - 0x08]
brlz,pt sz, .Lfinish
nop
.Lfinal_limb:
ldx [s2_ptr + 0x00], tmp1
ldx [s1_ptr + 0x00], tmp2
xnor tmp1, %g0, tmp1
addxccc tmp1, tmp2, tmp1
stx tmp1, [res_ptr + 0x00]
.Lfinish:
clr %o0
retl
movcc %xcc, 1, %o0
END(__mpn_sub_n_vis3)