1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
|
dnl x86 mpn_bdiv_dbm1.
dnl Copyright 2008 Free Software Foundation, Inc.
dnl This file is part of the GNU MP Library.
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of the GNU Lesser General Public License as published
dnl by the Free Software Foundation; either version 3 of the License, or (at
dnl your option) any later version.
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 Lesser General Public
dnl License for more details.
dnl You should have received a copy of the GNU Lesser General Public License
dnl along with the GNU MP Library. If not, see http://www.gnu.org/licenses/.
include(`../config.m4')
C cycles/limb
C K7: 3.5
C P4 m0: ?
C P4 m1: ?
C P4 m2: 13.67
C P4 m3: ?
C P4 m4: ?
C P6-13: 5.1
C TODO
C * Optimize for more x86 processors
ASM_START()
TEXT
ALIGN(16)
PROLOGUE(mpn_bdiv_dbm1c)
mov 16(%esp), %ecx C d
push %esi
mov 12(%esp), %esi C ap
push %edi
mov 12(%esp), %edi C qp
push %ebp
mov 24(%esp), %ebp C n
push %ebx
mov (%esi), %eax
mul %ecx
mov 36(%esp), %ebx
sub %eax, %ebx
mov %ebx, (%edi)
sbb %edx, %ebx
mov %ebp, %eax
and $3, %eax
jz L(b0)
cmp $2, %eax
jc L(b1)
jz L(b2)
jmp L(b3)
L(b0): mov 4(%esi), %eax
lea -4(%esi), %esi
lea 12(%edi), %edi
add $-4, %ebp
jmp L(0)
L(b3):
lea -8(%esi), %esi
lea 8(%edi), %edi
add $-3, %ebp
jmp L(3)
L(b2): mov 4(%esi), %eax
lea 4(%esi), %esi
lea 4(%edi), %edi
add $-2, %ebp
jmp L(2)
ALIGN(8)
L(top):
mov 4(%esi), %eax
mul %ecx
lea 16(%edi), %edi
sub %eax, %ebx
mov 8(%esi), %eax
mov %ebx, -12(%edi)
sbb %edx, %ebx
L(0): mul %ecx
sub %eax, %ebx
mov %ebx, -8(%edi)
sbb %edx, %ebx
L(3): mov 12(%esi), %eax
mul %ecx
sub %eax, %ebx
mov %ebx, -4(%edi)
mov 16(%esi), %eax
lea 16(%esi), %esi
sbb %edx, %ebx
L(2): mul %ecx
sub %eax, %ebx
mov %ebx, 0(%edi)
sbb %edx, %ebx
L(b1): add $-4, %ebp
jns L(top)
mov %ebx, %eax
pop %ebx
pop %ebp
pop %edi
pop %esi
ret
EPILOGUE()
|
