Return to mul_1.S CVS log

Up to [local] / OpenXM_contrib / gmp / mpn / sparc32 / v8

Annotation of OpenXM_contrib/gmp/mpn/sparc32/v8/mul_1.S, Revision 1.1.1.1

1.1       maekawa     1: ! SPARC v8 __mpn_mul_1 -- Multiply a limb vector with a single limb and
                      2: ! store the product in a second limb vector.
                      3:
                      4: ! Copyright (C) 1992, 1994, 1995 Free Software Foundation, Inc.
                      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
                      9: ! it under the terms of the GNU Library General Public License as published by
                     10: ! the Free Software Foundation; either version 2 of the License, or (at your
                     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
                     15: ! or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Library General Public
                     16: ! License for more details.
                     17:
                     18: ! You should have received a copy of the GNU Library General Public License
                     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      o0
                     26: ! s1_ptr       o1
                     27: ! size         o2
                     28: ! s2_limb      o3
                     29:
                     30: #include "sysdep.h"
                     31:
                     32: .text
                     33:        .align  8
                     34:        .global C_SYMBOL_NAME(__mpn_mul_1)
                     35: C_SYMBOL_NAME(__mpn_mul_1):
                     36:        sll     %o2,4,%g1
                     37:        and     %g1,(4-1)<<4,%g1
                     38: #if PIC
                     39:        mov     %o7,%g4                 ! Save return address register
                     40:        call    1f
                     41:        add     %o7,LL-1f,%g3
                     42: 1:     mov     %g4,%o7                 ! Restore return address register
                     43: #else
                     44:        sethi   %hi(LL),%g3
                     45:        or      %g3,%lo(LL),%g3
                     46: #endif
                     47:        jmp     %g3+%g1
                     48:        ld      [%o1+0],%o4     ! 1
                     49: LL:
                     50: LL00:  add     %o0,-4,%o0
                     51:        add     %o1,-4,%o1
                     52:        b       Loop00          /* 4, 8, 12, ... */
                     53:        orcc    %g0,%g0,%g2
                     54: LL01:  b       Loop01          /* 1, 5, 9, ... */
                     55:        orcc    %g0,%g0,%g2
                     56:        nop
                     57:        nop
                     58: LL10:  add     %o0,-12,%o0     /* 2, 6, 10, ... */
                     59:        add     %o1,4,%o1
                     60:        b       Loop10
                     61:        orcc    %g0,%g0,%g2
                     62:        nop
                     63: LL11:  add     %o0,-8,%o0      /* 3, 7, 11, ... */
                     64:        add     %o1,-8,%o1
                     65:        b       Loop11
                     66:        orcc    %g0,%g0,%g2
                     67:
                     68: Loop:  addcc   %g3,%g2,%g3     ! 1
                     69:        ld      [%o1+4],%o4     ! 2
                     70:        st      %g3,[%o0+0]     ! 1
                     71:        rd      %y,%g2          ! 1
                     72: Loop00:        umul    %o4,%o3,%g3     ! 2
                     73:        addxcc  %g3,%g2,%g3     ! 2
                     74:        ld      [%o1+8],%o4     ! 3
                     75:        st      %g3,[%o0+4]     ! 2
                     76:        rd      %y,%g2          ! 2
                     77: Loop11:        umul    %o4,%o3,%g3     ! 3
                     78:        addxcc  %g3,%g2,%g3     ! 3
                     79:        ld      [%o1+12],%o4    ! 4
                     80:        add     %o1,16,%o1
                     81:        st      %g3,[%o0+8]     ! 3
                     82:        rd      %y,%g2          ! 3
                     83: Loop10:        umul    %o4,%o3,%g3     ! 4
                     84:        addxcc  %g3,%g2,%g3     ! 4
                     85:        ld      [%o1+0],%o4     ! 1
                     86:        st      %g3,[%o0+12]    ! 4
                     87:        add     %o0,16,%o0
                     88:        rd      %y,%g2          ! 4
                     89:        addx    %g0,%g2,%g2
                     90: Loop01:        addcc   %o2,-4,%o2
                     91:        bg      Loop
                     92:        umul    %o4,%o3,%g3     ! 1
                     93:
                     94:        addcc   %g3,%g2,%g3     ! 4
                     95:        st      %g3,[%o0+0]     ! 4
                     96:        rd      %y,%g2          ! 4
                     97:
                     98:        retl
                     99:        addx    %g0,%g2,%o0