github.com/aergoio/aergo@v1.3.1/libtool/src/gmp-6.1.2/mpn/powerpc64/mode32/submul_1.asm (about)

     1  dnl  PowerPC-64 mpn_submul_1 -- Multiply a limb vector with a limb and subtract
     2  dnl  the result from a second limb vector.
     3  
     4  dnl  Copyright 1999-2001, 2003, 2005 Free Software Foundation, Inc.
     5  
     6  dnl  This file is part of the GNU MP Library.
     7  dnl
     8  dnl  The GNU MP Library is free software; you can redistribute it and/or modify
     9  dnl  it under the terms of either:
    10  dnl
    11  dnl    * the GNU Lesser General Public License as published by the Free
    12  dnl      Software Foundation; either version 3 of the License, or (at your
    13  dnl      option) any later version.
    14  dnl
    15  dnl  or
    16  dnl
    17  dnl    * the GNU General Public License as published by the Free Software
    18  dnl      Foundation; either version 2 of the License, or (at your option) any
    19  dnl      later version.
    20  dnl
    21  dnl  or both in parallel, as here.
    22  dnl
    23  dnl  The GNU MP Library is distributed in the hope that it will be useful, but
    24  dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
    25  dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
    26  dnl  for more details.
    27  dnl
    28  dnl  You should have received copies of the GNU General Public License and the
    29  dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
    30  dnl  see https://www.gnu.org/licenses/.
    31  
    32  include(`../config.m4')
    33  
    34  C		cycles/limb
    35  C POWER3/PPC630:     ?
    36  C POWER4/PPC970:     16
    37  
    38  C INPUT PARAMETERS
    39  C rp	r3
    40  C up	r4
    41  C n	r5
    42  C v	r6,r7  or  r7,r8
    43  
    44  ASM_START()
    45  PROLOGUE(mpn_submul_1)
    46  
    47  ifdef(`BROKEN_LONGLONG_PARAM',
    48  `	rldimi	r8, r7, 32,0	C assemble vlimb from separate 32-bit arguments
    49  	mr	r6, r8
    50  ',`
    51  	rldimi	r7, r6, 32,0	C assemble vlimb from separate 32-bit arguments
    52  	mr	r6, r7
    53  ')
    54  	li	r7, 0		C cy_limb = 0
    55  	mtctr	r5
    56  	addic	r0, r0, 0
    57  	addi	r3, r3, -8
    58  	addi	r4, r4, -8
    59  
    60  L(oop):	ldu	r0, 8(r4)
    61  	mulld	r9, r0, r6
    62  	adde	r12, r9, r7	C add old high limb and new low limb
    63  	srdi	r5, r9, 32
    64  	srdi	r11, r7, 32
    65  	adde	r5, r5, r11	C add high limb parts, set cy
    66  	mulhdu	r7, r0, r6
    67  	addze	r7, r7
    68  	ld	r10, 8(r3)
    69  	subfc	r9, r12, r10
    70  	srdi	r5, r12, 32
    71  	srdi	r11, r10, 32
    72  	subfe	r5, r5, r11	C subtract high limb parts, set cy
    73  	stdu	r9, 8(r3)
    74  	subfe	r11, r11, r11	C invert ...
    75  	addic	r11, r11, 1	C ... carry
    76  	bdnz	L(oop)
    77  
    78  	addze	r4, r7
    79  	srdi	r3, r4, 32
    80  	blr
    81  EPILOGUE()
    82