Return to add_n.s CVS log

Up to [local] / OpenXM_contrib / gmp / mpn / hppa / hppa1_1 / pa7100

Annotation of OpenXM_contrib/gmp/mpn/hppa/hppa1_1/pa7100/add_n.s, Revision 1.1.1.1

1.1       maekawa     1: ; HP-PA  __mpn_add_n -- Add two limb vectors of the same length > 0 and store
                      2: ; sum in a third limb vector.
                      3: ; This is optimized for the PA7100, where is runs at 4.25 cycles/limb
                      4:
                      5: ; Copyright (C) 1992, 1994 Free Software Foundation, Inc.
                      6:
                      7: ; This file is part of the GNU MP Library.
                      8:
                      9: ; The GNU MP Library is free software; you can redistribute it and/or modify
                     10: ; it under the terms of the GNU Library General Public License as published by
                     11: ; the Free Software Foundation; either version 2 of the License, or (at your
                     12: ; option) any later version.
                     13:
                     14: ; The GNU MP Library is distributed in the hope that it will be useful, but
                     15: ; WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
                     16: ; or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Library General Public
                     17: ; License for more details.
                     18:
                     19: ; You should have received a copy of the GNU Library General Public License
                     20: ; along with the GNU MP Library; see the file COPYING.LIB.  If not, write to
                     21: ; the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
                     22: ; MA 02111-1307, USA.
                     23:
                     24:
                     25: ; INPUT PARAMETERS
                     26: ; res_ptr      gr26
                     27: ; s1_ptr       gr25
                     28: ; s2_ptr       gr24
                     29: ; size         gr23
                     30:
                     31:        .code
                     32:        .export         __mpn_add_n
                     33: __mpn_add_n
                     34:        .proc
                     35:        .callinfo       frame=0,no_calls
                     36:        .entry
                     37:
                     38:        ldws,ma         4(0,%r25),%r20
                     39:        ldws,ma         4(0,%r24),%r19
                     40:
                     41:        addib,<=        -5,%r23,L$rest
                     42:         add            %r20,%r19,%r28  ; add first limbs ignoring cy
                     43:
                     44: L$loop ldws,ma         4(0,%r25),%r20
                     45:        ldws,ma         4(0,%r24),%r19
                     46:        stws,ma         %r28,4(0,%r26)
                     47:        addc            %r20,%r19,%r28
                     48:        ldws,ma         4(0,%r25),%r20
                     49:        ldws,ma         4(0,%r24),%r19
                     50:        stws,ma         %r28,4(0,%r26)
                     51:        addc            %r20,%r19,%r28
                     52:        ldws,ma         4(0,%r25),%r20
                     53:        ldws,ma         4(0,%r24),%r19
                     54:        stws,ma         %r28,4(0,%r26)
                     55:        addc            %r20,%r19,%r28
                     56:        ldws,ma         4(0,%r25),%r20
                     57:        ldws,ma         4(0,%r24),%r19
                     58:        stws,ma         %r28,4(0,%r26)
                     59:        addib,>         -4,%r23,L$loop
                     60:        addc            %r20,%r19,%r28
                     61:
                     62: L$rest addib,=         4,%r23,L$end
                     63:        nop
                     64: L$eloop        ldws,ma         4(0,%r25),%r20
                     65:        ldws,ma         4(0,%r24),%r19
                     66:        stws,ma         %r28,4(0,%r26)
                     67:        addib,>         -1,%r23,L$eloop
                     68:        addc            %r20,%r19,%r28
                     69:
                     70: L$end  stws            %r28,0(0,%r26)
                     71:        bv              0(%r2)
                     72:         addc           %r0,%r0,%r28
                     73:
                     74:        .exit
                     75:        .procend