| # Alpha 21064 __mpn_addmul_1 -- Multiply a limb vector with a limb and add |
| # the result to a second limb vector. |
| |
| # Copyright (C) 1992-2014 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 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 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 Lesser General Public |
| # License for more details. |
| |
| # You should have received a copy of the GNU Lesser General Public License |
| # along with the GNU MP Library. If not, see <http://www.gnu.org/licenses/>. |
| |
| |
| # INPUT PARAMETERS |
| # res_ptr r16 |
| # s1_ptr r17 |
| # size r18 |
| # s2_limb r19 |
| |
| # This code runs at 42 cycles/limb on EV4 and 18 cycles/limb on EV5. |
| |
| .set noreorder |
| .set noat |
| .text |
| .align 3 |
| .globl __mpn_addmul_1 |
| .ent __mpn_addmul_1 2 |
| __mpn_addmul_1: |
| .frame $30,0,$26 |
| |
| ldq $2,0($17) # $2 = s1_limb |
| addq $17,8,$17 # s1_ptr++ |
| subq $18,1,$18 # size-- |
| mulq $2,$19,$3 # $3 = prod_low |
| ldq $5,0($16) # $5 = *res_ptr |
| umulh $2,$19,$0 # $0 = prod_high |
| beq $18,.Lend1 # jump if size was == 1 |
| ldq $2,0($17) # $2 = s1_limb |
| addq $17,8,$17 # s1_ptr++ |
| subq $18,1,$18 # size-- |
| addq $5,$3,$3 |
| cmpult $3,$5,$4 |
| stq $3,0($16) |
| addq $16,8,$16 # res_ptr++ |
| beq $18,.Lend2 # jump if size was == 2 |
| |
| .align 3 |
| .Loop: mulq $2,$19,$3 # $3 = prod_low |
| ldq $5,0($16) # $5 = *res_ptr |
| addq $4,$0,$0 # cy_limb = cy_limb + 'cy' |
| subq $18,1,$18 # size-- |
| umulh $2,$19,$4 # $4 = cy_limb |
| ldq $2,0($17) # $2 = s1_limb |
| addq $17,8,$17 # s1_ptr++ |
| addq $3,$0,$3 # $3 = cy_limb + prod_low |
| cmpult $3,$0,$0 # $0 = carry from (cy_limb + prod_low) |
| addq $5,$3,$3 |
| cmpult $3,$5,$5 |
| stq $3,0($16) |
| addq $16,8,$16 # res_ptr++ |
| addq $5,$0,$0 # combine carries |
| bne $18,.Loop |
| |
| .Lend2: mulq $2,$19,$3 # $3 = prod_low |
| ldq $5,0($16) # $5 = *res_ptr |
| addq $4,$0,$0 # cy_limb = cy_limb + 'cy' |
| umulh $2,$19,$4 # $4 = cy_limb |
| addq $3,$0,$3 # $3 = cy_limb + prod_low |
| cmpult $3,$0,$0 # $0 = carry from (cy_limb + prod_low) |
| addq $5,$3,$3 |
| cmpult $3,$5,$5 |
| stq $3,0($16) |
| addq $5,$0,$0 # combine carries |
| addq $4,$0,$0 # cy_limb = prod_high + cy |
| ret $31,($26),1 |
| .Lend1: addq $5,$3,$3 |
| cmpult $3,$5,$5 |
| stq $3,0($16) |
| addq $0,$5,$0 |
| ret $31,($26),1 |
| |
| .end __mpn_addmul_1 |
