github.com/aergoio/aergo@v1.3.1/libtool/src/gmp-6.1.2/mpn/sparc32/v8/mul_1.asm (about)

     1  dnl  SPARC v8 mpn_mul_1 -- Multiply a limb vector with a single limb and
     2  dnl  store the product in a second limb vector.
     3  
     4  dnl  Copyright 1992, 1994, 1995, 2000 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  
    33  include(`../config.m4')
    34  
    35  C INPUT PARAMETERS
    36  C res_ptr	o0
    37  C s1_ptr	o1
    38  C size		o2
    39  C s2_limb	o3
    40  
    41  ASM_START()
    42  PROLOGUE(mpn_mul_1)
    43  	sll	%o2,4,%g1
    44  	and	%g1,(4-1)<<4,%g1
    45  ifdef(`PIC',
    46  `	mov	%o7,%g4		C Save return address register
    47  0:	call	1f
    48  	add	%o7,L(1)-0b,%g3
    49  1:	mov	%g4,%o7		C Restore return address register
    50  ',
    51  `	sethi	%hi(L(1)),%g3
    52  	or	%g3,%lo(L(1)),%g3
    53  ')
    54  	jmp	%g3+%g1
    55  	ld	[%o1+0],%o4	C 1
    56  L(1):
    57  L(L00):	add	%o0,-4,%o0
    58  	add	%o1,-4,%o1
    59  	b	L(loop00)	C 4, 8, 12, ...
    60  	orcc	%g0,%g0,%g2
    61  L(L01):	b	L(loop01)	C 1, 5, 9, ...
    62  	orcc	%g0,%g0,%g2
    63  	nop
    64  	nop
    65  L(L10):	add	%o0,-12,%o0	C 2, 6, 10, ...
    66  	add	%o1,4,%o1
    67  	b	L(loop10)
    68  	orcc	%g0,%g0,%g2
    69  	nop
    70  L(L11):	add	%o0,-8,%o0	C 3, 7, 11, ...
    71  	add	%o1,-8,%o1
    72  	b	L(loop11)
    73  	orcc	%g0,%g0,%g2
    74  
    75  L(loop):
    76  	addcc	%g3,%g2,%g3	C 1
    77  	ld	[%o1+4],%o4	C 2
    78  	st	%g3,[%o0+0]	C 1
    79  	rd	%y,%g2		C 1
    80  L(loop00):
    81  	umul	%o4,%o3,%g3	C 2
    82  	addxcc	%g3,%g2,%g3	C 2
    83  	ld	[%o1+8],%o4	C 3
    84  	st	%g3,[%o0+4]	C 2
    85  	rd	%y,%g2		C 2
    86  L(loop11):
    87  	umul	%o4,%o3,%g3	C 3
    88  	addxcc	%g3,%g2,%g3	C 3
    89  	ld	[%o1+12],%o4	C 4
    90  	add	%o1,16,%o1
    91  	st	%g3,[%o0+8]	C 3
    92  	rd	%y,%g2		C 3
    93  L(loop10):
    94  	umul	%o4,%o3,%g3	C 4
    95  	addxcc	%g3,%g2,%g3	C 4
    96  	ld	[%o1+0],%o4	C 1
    97  	st	%g3,[%o0+12]	C 4
    98  	add	%o0,16,%o0
    99  	rd	%y,%g2		C 4
   100  	addx	%g0,%g2,%g2
   101  L(loop01):
   102  	addcc	%o2,-4,%o2
   103  	bg	L(loop)
   104  	umul	%o4,%o3,%g3	C 1
   105  
   106  	addcc	%g3,%g2,%g3	C 4
   107  	st	%g3,[%o0+0]	C 4
   108  	rd	%y,%g2		C 4
   109  
   110  	retl
   111  	addx	%g0,%g2,%o0
   112  EPILOGUE(mpn_mul_1)