[BACK]Return to aorsmul_1.asm CVS log [TXT][DIR] Up to [local] / OpenXM_contrib / gmp / mpn / x86

Annotation of OpenXM_contrib/gmp/mpn/x86/aorsmul_1.asm, Revision 1.1.1.1

1.1       maekawa     1: dnl  x86 __gmpn_addmul_1 (for 386 and 486) -- Multiply a limb vector with a
                      2: dnl  limb and add the result to a second limb vector.
                      3:
                      4:
                      5: dnl  Copyright (C) 1992, 1994, 1997, 1999, 2000 Free Software Foundation,
                      6: dnl  Inc.
                      7: dnl
                      8: dnl  This file is part of the GNU MP Library.
                      9: dnl
                     10: dnl  The GNU MP Library is free software; you can redistribute it and/or
                     11: dnl  modify it under the terms of the GNU Lesser General Public License as
                     12: dnl  published by the Free Software Foundation; either version 2.1 of the
                     13: dnl  License, or (at your option) any later version.
                     14: dnl
                     15: dnl  The GNU MP Library is distributed in the hope that it will be useful,
                     16: dnl  but WITHOUT ANY WARRANTY; without even the implied warranty of
                     17: dnl  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
                     18: dnl  Lesser General Public License for more details.
                     19: dnl
                     20: dnl  You should have received a copy of the GNU Lesser General Public
                     21: dnl  License along with the GNU MP Library; see the file COPYING.LIB.  If
                     22: dnl  not, write to the Free Software Foundation, Inc., 59 Temple Place -
                     23: dnl  Suite 330, Boston, MA 02111-1307, USA.
                     24:
                     25:
                     26: include(`../config.m4')
                     27:
                     28:
                     29: ifdef(`OPERATION_addmul_1',`
                     30:       define(M4_inst,        addl)
                     31:       define(M4_function_1,  mpn_addmul_1)
                     32:
                     33: ',`ifdef(`OPERATION_submul_1',`
                     34:       define(M4_inst,        subl)
                     35:       define(M4_function_1,  mpn_submul_1)
                     36:
                     37: ',`m4_error(`Need OPERATION_addmul_1 or OPERATION_submul_1
                     38: ')')')
                     39:
                     40: MULFUNC_PROLOGUE(mpn_addmul_1 mpn_submul_1)
                     41:
                     42:
                     43: C mp_limb_t M4_function_1 (mp_ptr dst, mp_srcptr src, mp_size_t size,
                     44: C                          mp_limb_t mult);
                     45:
                     46: define(PARAM_MULTIPLIER, `FRAME+16(%esp)')
                     47: define(PARAM_SIZE,       `FRAME+12(%esp)')
                     48: define(PARAM_SRC,        `FRAME+8(%esp)')
                     49: define(PARAM_DST,        `FRAME+4(%esp)')
                     50:
                     51:        TEXT
                     52:        ALIGN(8)
                     53:
                     54: PROLOGUE(M4_function_1)
                     55: deflit(`FRAME',0)
                     56:
                     57:        pushl   %edi
                     58:        pushl   %esi
                     59:        pushl   %ebx
                     60:        pushl   %ebp
                     61: deflit(`FRAME',16)
                     62:
                     63:        movl    PARAM_DST,%edi
                     64:        movl    PARAM_SRC,%esi
                     65:        movl    PARAM_SIZE,%ecx
                     66:
                     67:        xorl    %ebx,%ebx
                     68:        andl    $3,%ecx
                     69:        jz      L(end0)
                     70:
                     71: L(oop0):
                     72:        movl    (%esi),%eax
                     73:        mull    PARAM_MULTIPLIER
                     74:        leal    4(%esi),%esi
                     75:        addl    %ebx,%eax
                     76:        movl    $0,%ebx
                     77:        adcl    %ebx,%edx
                     78:        M4_inst %eax,(%edi)
                     79:        adcl    %edx,%ebx       C propagate carry into cylimb
                     80:
                     81:        leal    4(%edi),%edi
                     82:        decl    %ecx
                     83:        jnz     L(oop0)
                     84:
                     85: L(end0):
                     86:        movl    PARAM_SIZE,%ecx
                     87:        shrl    $2,%ecx
                     88:        jz      L(end)
                     89:
                     90:        ALIGN(8)
                     91: L(oop):        movl    (%esi),%eax
                     92:        mull    PARAM_MULTIPLIER
                     93:        addl    %eax,%ebx
                     94:        movl    $0,%ebp
                     95:        adcl    %edx,%ebp
                     96:
                     97:        movl    4(%esi),%eax
                     98:        mull    PARAM_MULTIPLIER
                     99:        M4_inst %ebx,(%edi)
                    100:        adcl    %eax,%ebp       C new lo + cylimb
                    101:        movl    $0,%ebx
                    102:        adcl    %edx,%ebx
                    103:
                    104:        movl    8(%esi),%eax
                    105:        mull    PARAM_MULTIPLIER
                    106:        M4_inst %ebp,4(%edi)
                    107:        adcl    %eax,%ebx       C new lo + cylimb
                    108:        movl    $0,%ebp
                    109:        adcl    %edx,%ebp
                    110:
                    111:        movl    12(%esi),%eax
                    112:        mull    PARAM_MULTIPLIER
                    113:        M4_inst %ebx,8(%edi)
                    114:        adcl    %eax,%ebp       C new lo + cylimb
                    115:        movl    $0,%ebx
                    116:        adcl    %edx,%ebx
                    117:
                    118:        M4_inst %ebp,12(%edi)
                    119:        adcl    $0,%ebx         C propagate carry into cylimb
                    120:
                    121:        leal    16(%esi),%esi
                    122:        leal    16(%edi),%edi
                    123:        decl    %ecx
                    124:        jnz     L(oop)
                    125:
                    126: L(end):        movl    %ebx,%eax
                    127:
                    128:        popl    %ebp
                    129:        popl    %ebx
                    130:        popl    %esi
                    131:        popl    %edi
                    132:        ret
                    133:
                    134: EPILOGUE()

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>