Return to addmul_1.asm CVS log

Up to [local] / OpenXM_contrib / gmp / mpn / powerpc64

Annotation of OpenXM_contrib/gmp/mpn/powerpc64/addmul_1.asm, Revision 1.1.1.2

1.1.1.2 ! ohara       1: dnl  PowerPC-64 mpn_addmul_1 -- Multiply a limb vector with a limb and add
        !             2: dnl  the result to a second limb vector.
1.1       maekawa     3:
1.1.1.2 ! ohara       4: dnl  Copyright 1999, 2000, 2001 Free Software Foundation, Inc.
1.1       maekawa     5:
1.1.1.2 ! ohara       6: dnl  This file is part of the GNU MP Library.
1.1       maekawa     7:
1.1.1.2 ! ohara       8: dnl  The GNU MP Library is free software; you can redistribute it and/or modify
        !             9: dnl  it under the terms of the GNU Lesser General Public License as published
        !            10: dnl  by the Free Software Foundation; either version 2.1 of the License, or (at
        !            11: dnl  your option) any later version.
        !            12:
        !            13: dnl  The GNU MP Library is distributed in the hope that it will be useful, but
        !            14: dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
        !            15: dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
        !            16: dnl  License for more details.
        !            17:
        !            18: dnl  You should have received a copy of the GNU Lesser General Public License
        !            19: dnl  along with the GNU MP Library; see the file COPYING.LIB.  If not, write to
        !            20: dnl  the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
        !            21: dnl  MA 02111-1307, USA.
1.1       maekawa    22:
                     23: include(`../config.m4')
                     24:
1.1.1.2 ! ohara      25: C INPUT PARAMETERS
        !            26: C res_ptr      r3
        !            27: C s1_ptr       r4
        !            28: C size         r5
        !            29: C s2_limb      r6
        !            30: C cy_limb      r7
        !            31:
        !            32: C PPC630: 6 to 18 cycles/limb, depending on multiplier.  This cannot be
        !            33: C improved unless floating-point operations are used instead of the slow
        !            34: C mulld/mulhdu.
        !            35:
1.1       maekawa    36: ASM_START()
                     37: PROLOGUE(mpn_addmul_1)
1.1.1.2 ! ohara      38:        li      r7,0                    C cy_limb = 0
        !            39:
        !            40: PROLOGUE(mpn_addmul_1c)
        !            41:        mtctr   r5
        !            42:        addic   r0,r0,0
        !            43:        cal     r3,-8(r3)
        !            44:        cal     r4,-8(r4)
1.1       maekawa    45: .Loop:
1.1.1.2 ! ohara      46:        ldu     r0,8(r4)
        !            47:        ld      r10,8(r3)
        !            48:        mulld   r9,r0,r6
        !            49:        adde    r9,r9,r7
        !            50:        mulhdu  r7,r0,r6
        !            51:        addze   r7,r7
        !            52:        addc    r9,r9,r10
        !            53:        stdu    r9,8(r3)
1.1       maekawa    54:        bdnz    .Loop
                     55:
1.1.1.2 ! ohara      56:        addze   r3,r7
1.1       maekawa    57:        blr
                     58: EPILOGUE(mpn_addmul_1)
1.1.1.2 ! ohara      59: EPILOGUE(mpn_addmul_1c)