mirror of
https://review.haiku-os.org/buildtools
synced 2025-02-12 08:47:41 +01:00
f133d007f9
Old version was from 2012-05-06, 6.1.2 is from 2016-12-16 A lot of support for newer processors and speedups since then See gmp/NEWS for details
157 lines
3.4 KiB
NASM
157 lines
3.4 KiB
NASM
dnl x86 __gmpn_addmul_1 (for 386 and 486) -- Multiply a limb vector with a
|
|
dnl limb and add the result to a second limb vector.
|
|
|
|
dnl Copyright 1992, 1994, 1997, 1999-2002, 2005 Free Software Foundation, Inc.
|
|
|
|
dnl This file is part of the GNU MP Library.
|
|
dnl
|
|
dnl The GNU MP Library is free software; you can redistribute it and/or modify
|
|
dnl it under the terms of either:
|
|
dnl
|
|
dnl * the GNU Lesser General Public License as published by the Free
|
|
dnl Software Foundation; either version 3 of the License, or (at your
|
|
dnl option) any later version.
|
|
dnl
|
|
dnl or
|
|
dnl
|
|
dnl * the GNU General Public License as published by the Free Software
|
|
dnl Foundation; either version 2 of the License, or (at your option) any
|
|
dnl later version.
|
|
dnl
|
|
dnl or both in parallel, as here.
|
|
dnl
|
|
dnl The GNU MP Library is distributed in the hope that it will be useful, but
|
|
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
|
|
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
dnl for more details.
|
|
dnl
|
|
dnl You should have received copies of the GNU General Public License and the
|
|
dnl GNU Lesser General Public License along with the GNU MP Library. If not,
|
|
dnl see https://www.gnu.org/licenses/.
|
|
|
|
include(`../config.m4')
|
|
|
|
C cycles/limb
|
|
C P5 14.75
|
|
C P6 model 0-8,10-12 7.5
|
|
C P6 model 9 (Banias) 6.7
|
|
C P6 model 13 (Dothan) 6.75
|
|
C P4 model 0 (Willamette) 24.0
|
|
C P4 model 1 (?) 24.0
|
|
C P4 model 2 (Northwood) 24.0
|
|
C P4 model 3 (Prescott)
|
|
C P4 model 4 (Nocona)
|
|
C Intel Atom
|
|
C AMD K6 12.5
|
|
C AMD K7 5.25
|
|
C AMD K8
|
|
C AMD K10
|
|
|
|
|
|
ifdef(`OPERATION_addmul_1',`
|
|
define(M4_inst, addl)
|
|
define(M4_function_1, mpn_addmul_1)
|
|
|
|
',`ifdef(`OPERATION_submul_1',`
|
|
define(M4_inst, subl)
|
|
define(M4_function_1, mpn_submul_1)
|
|
|
|
',`m4_error(`Need OPERATION_addmul_1 or OPERATION_submul_1
|
|
')')')
|
|
|
|
MULFUNC_PROLOGUE(mpn_addmul_1 mpn_submul_1)
|
|
|
|
|
|
C mp_limb_t M4_function_1 (mp_ptr dst, mp_srcptr src, mp_size_t size,
|
|
C mp_limb_t mult);
|
|
|
|
define(PARAM_MULTIPLIER, `FRAME+16(%esp)')
|
|
define(PARAM_SIZE, `FRAME+12(%esp)')
|
|
define(PARAM_SRC, `FRAME+8(%esp)')
|
|
define(PARAM_DST, `FRAME+4(%esp)')
|
|
|
|
TEXT
|
|
ALIGN(8)
|
|
|
|
PROLOGUE(M4_function_1)
|
|
deflit(`FRAME',0)
|
|
|
|
pushl %edi
|
|
pushl %esi
|
|
pushl %ebx
|
|
pushl %ebp
|
|
deflit(`FRAME',16)
|
|
|
|
movl PARAM_DST,%edi
|
|
movl PARAM_SRC,%esi
|
|
movl PARAM_SIZE,%ecx
|
|
|
|
xorl %ebx,%ebx
|
|
andl $3,%ecx
|
|
jz L(end0)
|
|
|
|
L(oop0):
|
|
movl (%esi),%eax
|
|
mull PARAM_MULTIPLIER
|
|
leal 4(%esi),%esi
|
|
addl %ebx,%eax
|
|
movl $0,%ebx
|
|
adcl %ebx,%edx
|
|
M4_inst %eax,(%edi)
|
|
adcl %edx,%ebx C propagate carry into cylimb
|
|
|
|
leal 4(%edi),%edi
|
|
decl %ecx
|
|
jnz L(oop0)
|
|
|
|
L(end0):
|
|
movl PARAM_SIZE,%ecx
|
|
shrl $2,%ecx
|
|
jz L(end)
|
|
|
|
ALIGN(8)
|
|
L(oop): movl (%esi),%eax
|
|
mull PARAM_MULTIPLIER
|
|
addl %eax,%ebx
|
|
movl $0,%ebp
|
|
adcl %edx,%ebp
|
|
|
|
movl 4(%esi),%eax
|
|
mull PARAM_MULTIPLIER
|
|
M4_inst %ebx,(%edi)
|
|
adcl %eax,%ebp C new lo + cylimb
|
|
movl $0,%ebx
|
|
adcl %edx,%ebx
|
|
|
|
movl 8(%esi),%eax
|
|
mull PARAM_MULTIPLIER
|
|
M4_inst %ebp,4(%edi)
|
|
adcl %eax,%ebx C new lo + cylimb
|
|
movl $0,%ebp
|
|
adcl %edx,%ebp
|
|
|
|
movl 12(%esi),%eax
|
|
mull PARAM_MULTIPLIER
|
|
M4_inst %ebx,8(%edi)
|
|
adcl %eax,%ebp C new lo + cylimb
|
|
movl $0,%ebx
|
|
adcl %edx,%ebx
|
|
|
|
M4_inst %ebp,12(%edi)
|
|
adcl $0,%ebx C propagate carry into cylimb
|
|
|
|
leal 16(%esi),%esi
|
|
leal 16(%edi),%edi
|
|
decl %ecx
|
|
jnz L(oop)
|
|
|
|
L(end): movl %ebx,%eax
|
|
|
|
popl %ebp
|
|
popl %ebx
|
|
popl %esi
|
|
popl %edi
|
|
ret
|
|
|
|
EPILOGUE()
|