135 lines
3.2 KiB
ArmAsm
135 lines
3.2 KiB
ArmAsm
! sparc __mpn_add_n -- Add two limb vectors of the same length > 0 and store
|
|
! sum in a third limb vector.
|
|
|
|
! Copyright (C) 1992, 1994 Free Software Foundation, Inc.
|
|
|
|
! This file is part of the GNU MP Library.
|
|
|
|
! The GNU MP Library is free software; you can redistribute it and/or modify
|
|
! it under the terms of the GNU Library General Public License as published by
|
|
! the Free Software Foundation; either version 2 of the License, or (at your
|
|
! option) any later version.
|
|
|
|
! The GNU MP 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 Library General Public
|
|
! License for more details.
|
|
|
|
! You should have received a copy of the GNU Library General Public License
|
|
! along with the GNU MP Library; see the file COPYING.LIB. If not, write to
|
|
! the Free Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
|
|
|
|
! INPUT PARAMETERS
|
|
! res_ptr %o0
|
|
! s1_ptr %o1
|
|
! s2_ptr %o2
|
|
! size %o3
|
|
|
|
#include "sysdep.h"
|
|
|
|
.text
|
|
.align 4
|
|
.global C_SYMBOL_NAME(__mpn_add_n)
|
|
C_SYMBOL_NAME(__mpn_add_n):
|
|
ld [%o1+0],%o4 ! read first limb from s1_ptr
|
|
srl %o3,4,%g1
|
|
ld [%o2+0],%o5 ! read first limb from s2_ptr
|
|
|
|
sub %g0,%o3,%o3
|
|
andcc %o3,(16-1),%o3
|
|
be Lzero
|
|
nop
|
|
|
|
sll %o3,2,%o3 ! multiply by 4
|
|
sub %o0,%o3,%o0 ! adjust res_ptr
|
|
sub %o1,%o3,%o1 ! adjust s1_ptr
|
|
sub %o2,%o3,%o2 ! adjust s2_ptr
|
|
|
|
mov %o4,%g2
|
|
|
|
sethi %hi(Lbase),%g3
|
|
or %g3,%lo(Lbase),%g3
|
|
sll %o3,2,%o3 ! multiply by 4
|
|
jmp %g3+%o3
|
|
mov %o5,%g3
|
|
|
|
Loop: addxcc %g2,%g3,%o3
|
|
add %o1,64,%o1
|
|
st %o3,[%o0+60]
|
|
add %o2,64,%o2
|
|
ld [%o1+0],%o4
|
|
add %o0,64,%o0
|
|
ld [%o2+0],%o5
|
|
Lzero: sub %g1,1,%g1 ! add 0 + 16r limbs (adjust loop counter)
|
|
Lbase: ld [%o1+4],%g2
|
|
addxcc %o4,%o5,%o3
|
|
ld [%o2+4],%g3
|
|
st %o3,[%o0+0]
|
|
ld [%o1+8],%o4 ! add 15 + 16r limbs
|
|
addxcc %g2,%g3,%o3
|
|
ld [%o2+8],%o5
|
|
st %o3,[%o0+4]
|
|
ld [%o1+12],%g2 ! add 14 + 16r limbs
|
|
addxcc %o4,%o5,%o3
|
|
ld [%o2+12],%g3
|
|
st %o3,[%o0+8]
|
|
ld [%o1+16],%o4 ! add 13 + 16r limbs
|
|
addxcc %g2,%g3,%o3
|
|
ld [%o2+16],%o5
|
|
st %o3,[%o0+12]
|
|
ld [%o1+20],%g2 ! add 12 + 16r limbs
|
|
addxcc %o4,%o5,%o3
|
|
ld [%o2+20],%g3
|
|
st %o3,[%o0+16]
|
|
ld [%o1+24],%o4 ! add 11 + 16r limbs
|
|
addxcc %g2,%g3,%o3
|
|
ld [%o2+24],%o5
|
|
st %o3,[%o0+20]
|
|
ld [%o1+28],%g2 ! add 10 + 16r limbs
|
|
addxcc %o4,%o5,%o3
|
|
ld [%o2+28],%g3
|
|
st %o3,[%o0+24]
|
|
ld [%o1+32],%o4 ! add 9 + 16r limbs
|
|
addxcc %g2,%g3,%o3
|
|
ld [%o2+32],%o5
|
|
st %o3,[%o0+28]
|
|
ld [%o1+36],%g2 ! add 8 + 16r limbs
|
|
addxcc %o4,%o5,%o3
|
|
ld [%o2+36],%g3
|
|
st %o3,[%o0+32]
|
|
ld [%o1+40],%o4 ! add 7 + 16r limbs
|
|
addxcc %g2,%g3,%o3
|
|
ld [%o2+40],%o5
|
|
st %o3,[%o0+36]
|
|
ld [%o1+44],%g2 ! add 6 + 16r limbs
|
|
addxcc %o4,%o5,%o3
|
|
ld [%o2+44],%g3
|
|
st %o3,[%o0+40]
|
|
ld [%o1+48],%o4 ! add 5 + 16r limbs
|
|
addxcc %g2,%g3,%o3
|
|
ld [%o2+48],%o5
|
|
st %o3,[%o0+44]
|
|
ld [%o1+52],%g2 ! add 4 + 16r limbs
|
|
addxcc %o4,%o5,%o3
|
|
ld [%o2+52],%g3
|
|
st %o3,[%o0+48]
|
|
ld [%o1+56],%o4 ! add 3 + 16r limbs
|
|
addxcc %g2,%g3,%o3
|
|
ld [%o2+56],%o5
|
|
st %o3,[%o0+52]
|
|
ld [%o1+60],%g2 ! add 2 + 16r limbs
|
|
addxcc %o4,%o5,%o3
|
|
ld [%o2+60],%g3
|
|
st %o3,[%o0+56]
|
|
addx %g0,%g0,%o4
|
|
tst %g1
|
|
bne Loop
|
|
subcc %g0,%o4,%g0 ! restore cy (delay slot)
|
|
|
|
addxcc %g2,%g3,%o3
|
|
st %o3,[%o0+60] ! store most significant limb
|
|
|
|
retl
|
|
addx %g0,%g0,%o0 ! return carry-out from most sign. limb
|