Return to addmul_1.s CVS log

Up to [local] / OpenXM_contrib / gmp / mpn / a29k

Annotation of OpenXM_contrib/gmp/mpn/a29k/addmul_1.s, Revision 1.1.1.3

1.1.1.2   maekawa     1: ; 29000 __gmpn_addmul_1 -- Multiply a limb vector with a single limb and
1.1       maekawa     2: ; add the product to a second limb vector.
                      3:
1.1.1.3 ! ohara       4: ; Copyright 1992, 1994, 2000 Free Software Foundation, Inc.
1.1       maekawa     5:
                      6: ; This file is part of the GNU MP Library.
                      7:
                      8: ; The GNU MP Library is free software; you can redistribute it and/or modify
1.1.1.2   maekawa     9: ; it under the terms of the GNU Lesser General Public License as published by
                     10: ; the Free Software Foundation; either version 2.1 of the License, or (at your
1.1       maekawa    11: ; option) any later version.
                     12:
                     13: ; The GNU MP Library is distributed in the hope that it will be useful, but
                     14: ; WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
1.1.1.2   maekawa    15: ; or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
1.1       maekawa    16: ; License for more details.
                     17:
1.1.1.2   maekawa    18: ; You should have received a copy of the GNU Lesser General Public License
1.1       maekawa    19: ; along with the GNU MP Library; see the file COPYING.LIB.  If not, write to
                     20: ; the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
                     21: ; MA 02111-1307, USA.
                     22:
                     23:
                     24: ; INPUT PARAMETERS
                     25: ; res_ptr      lr2
                     26: ; s1_ptr       lr3
                     27: ; size         lr4
                     28: ; s2_limb      lr5
                     29:
                     30:        .cputype 29050
                     31:        .sect .lit,lit
                     32:        .text
                     33:        .align  4
1.1.1.2   maekawa    34:        .global ___gmpn_addmul_1
1.1       maekawa    35:        .word   0x60000
1.1.1.2   maekawa    36: ___gmpn_addmul_1:
1.1       maekawa    37:        sub     lr4,lr4,8
                     38:        jmpt    lr4,Ltail
                     39:         const  gr120,0                 ; init cylimb reg
                     40:
                     41:        srl     gr117,lr4,3             ; divide by 8
                     42:        sub     gr117,gr117,1           ; count for jmpfdec
                     43:
                     44: Loop:  mtsrim  cr,(8-1)
                     45:        loadm   0,0,gr96,lr3
                     46:        add     lr3,lr3,32
                     47:
                     48:        multiplu gr104,gr96,lr5
                     49:        multmu   gr96,gr96,lr5
                     50:        multiplu gr105,gr97,lr5
                     51:        multmu   gr97,gr97,lr5
                     52:        multiplu gr106,gr98,lr5
                     53:        multmu   gr98,gr98,lr5
                     54:        multiplu gr107,gr99,lr5
                     55:        multmu   gr99,gr99,lr5
                     56:        multiplu gr108,gr100,lr5
                     57:        multmu   gr100,gr100,lr5
                     58:        multiplu gr109,gr101,lr5
                     59:        multmu   gr101,gr101,lr5
                     60:        multiplu gr110,gr102,lr5
                     61:        multmu   gr102,gr102,lr5
                     62:        multiplu gr111,gr103,lr5
                     63:        multmu   gr103,gr103,lr5
                     64:
                     65:        add     gr104,gr104,gr120
                     66:        addc    gr105,gr105,gr96
                     67:        addc    gr106,gr106,gr97
                     68:        addc    gr107,gr107,gr98
                     69:        addc    gr108,gr108,gr99
                     70:        addc    gr109,gr109,gr100
                     71:        addc    gr110,gr110,gr101
                     72:        addc    gr111,gr111,gr102
                     73:        addc    gr120,gr103,0
                     74:
                     75:        mtsrim  cr,(8-1)
                     76:        loadm   0,0,gr96,lr2
                     77:
                     78:        add     gr104,gr96,gr104
                     79:        addc    gr105,gr97,gr105
                     80:        addc    gr106,gr98,gr106
                     81:        addc    gr107,gr99,gr107
                     82:        addc    gr108,gr100,gr108
                     83:        addc    gr109,gr101,gr109
                     84:        addc    gr110,gr102,gr110
                     85:        addc    gr111,gr103,gr111
                     86:        addc    gr120,gr120,0
                     87:
                     88:        mtsrim  cr,(8-1)
                     89:        storem  0,0,gr104,lr2
                     90:        jmpfdec gr117,Loop
                     91:         add    lr2,lr2,32
                     92:
                     93: Ltail: and     lr4,lr4,(8-1)
                     94:        sub     gr118,lr4,1             ; count for CR
                     95:        jmpt    gr118,Lend
                     96:         sub    lr4,lr4,2
                     97:        sub     lr2,lr2,4               ; offset res_ptr by one limb
                     98:
                     99: Loop2: load    0,0,gr116,lr3
                    100:        add     lr3,lr3,4
                    101:        multiplu gr117,gr116,lr5
                    102:        multmu  gr118,gr116,lr5
                    103:        add     lr2,lr2,4
                    104:        load    0,0,gr119,lr2
                    105:        add     gr117,gr117,gr120
                    106:        addc    gr118,gr118,0
                    107:        add     gr117,gr117,gr119
                    108:        store   0,0,gr117,lr2
                    109:        jmpfdec lr4,Loop2
                    110:         addc   gr120,gr118,0
                    111:
                    112: Lend:  jmpi    lr0
                    113:         or     gr96,gr120,0            ; copy