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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
|
dnl x86-64 mpn_divrem_1 -- mpn by limb division.
dnl Copyright 2004, 2005, 2007-2010, 2012, 2014 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 norm unorm frac
C AMD K8,K9 15 15 12
C AMD K10 15 15 12
C Intel P4 44 44 43
C Intel core2 24 24 19.5
C Intel corei 19 19 18
C Intel atom 51 51 36
C VIA nano 46 44 22.5
C mp_limb_t
C mpn_divrem_1 (mp_ptr qp, mp_size_t fn,
C mp_srcptr np, mp_size_t nn, mp_limb_t d)
C mp_limb_t
C mpn_preinv_divrem_1 (mp_ptr qp, mp_size_t fn,
C mp_srcptr np, mp_size_t nn, mp_limb_t d,
C mp_limb_t dinv, int cnt)
C INPUT PARAMETERS
define(`qp', `%rdi')
define(`fn_param', `%rsi')
define(`up_param', `%rdx')
define(`un_param', `%rcx')
define(`d', `%r8')
define(`dinv', `%r9') C only for mpn_preinv_divrem_1
C shift passed on stack C only for mpn_preinv_divrem_1
define(`cnt', `%rcx')
define(`up', `%rsi')
define(`fn', `%r12')
define(`un', `%rbx')
C rax rbx rcx rdx rsi rdi rbp r8 r9 r10 r11 r12 r13 r14 r15
C cnt qp d dinv
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)
IFSTD(`define(`CNTOFF', `40($1)')')
IFDOS(`define(`CNTOFF', `104($1)')')
ASM_START()
TEXT
ALIGN(16)
PROLOGUE(mpn_preinv_divrem_1)
FUNC_ENTRY(4)
IFDOS(` mov 56(%rsp), %r8 ')
IFDOS(` mov 64(%rsp), %r9 ')
xor R32(%rax), R32(%rax)
push %r13
push %r12
push %rbp
push %rbx
mov fn_param, fn
mov un_param, un
add fn_param, un_param
mov up_param, up
lea -8(qp,un_param,8), qp
mov CNTOFF(%rsp), R8(cnt)
shl R8(cnt), d
jmp L(ent)
EPILOGUE()
ALIGN(16)
PROLOGUE(mpn_divrem_1)
FUNC_ENTRY(4)
IFDOS(` mov 56(%rsp), %r8 ')
xor R32(%rax), R32(%rax)
push %r13
push %r12
push %rbp
push %rbx
mov fn_param, fn
mov un_param, un
add fn_param, un_param
mov up_param, up
je L(ret)
lea -8(qp,un_param,8), qp
xor R32(%rbp), R32(%rbp)
L(unnormalized):
test un, un
je L(44)
mov -8(up,un,8), %rax
cmp d, %rax
jae L(44)
mov %rbp, (qp)
mov %rax, %rbp
lea -8(qp), qp
je L(ret)
dec un
L(44):
bsr d, %rcx
not R32(%rcx)
sal R8(%rcx), d
sal R8(%rcx), %rbp
push %rcx
IFSTD(` push %rdi ')
IFSTD(` push %rsi ')
push %r8
IFSTD(` sub $8, %rsp ')
IFSTD(` mov d, %rdi ')
IFDOS(` sub $40, %rsp ')
IFDOS(` mov d, %rcx ')
ASSERT(nz, `test $15, %rsp')
CALL( mpn_invert_limb)
IFSTD(` add $8, %rsp ')
IFDOS(` add $40, %rsp ')
pop %r8
IFSTD(` pop %rsi ')
IFSTD(` pop %rdi ')
pop %rcx
mov %rax, dinv
mov %rbp, %rax
test un, un
je L(frac)
L(ent): mov -8(up,un,8), %rbp
shr R8(%rcx), %rax
shld R8(%rcx), %rbp, %rax
sub $2, un
js L(end)
ALIGN(16)
L(top): lea 1(%rax), %r11
mul dinv
mov (up,un,8), %r10
shld R8(%rcx), %r10, %rbp
mov %rbp, %r13
add %rax, %r13
adc %r11, %rdx
mov %rdx, %r11
imul d, %rdx
sub %rdx, %rbp
lea (d,%rbp), %rax
sub $8, qp
cmp %r13, %rbp
cmovc %rbp, %rax
adc $-1, %r11
cmp d, %rax
jae L(ufx)
L(uok): dec un
mov %r11, 8(qp)
mov %r10, %rbp
jns L(top)
L(end): lea 1(%rax), %r11
sal R8(%rcx), %rbp
mul dinv
add %rbp, %rax
adc %r11, %rdx
mov %rax, %r11
mov %rdx, %r13
imul d, %rdx
sub %rdx, %rbp
mov d, %rax
add %rbp, %rax
cmp %r11, %rbp
cmovc %rbp, %rax
adc $-1, %r13
cmp d, %rax
jae L(efx)
L(eok): mov %r13, (qp)
sub $8, qp
jmp L(frac)
L(ufx): sub d, %rax
inc %r11
jmp L(uok)
L(efx): sub d, %rax
inc %r13
jmp L(eok)
L(frac):mov d, %rbp
neg %rbp
jmp L(fent)
ALIGN(16) C K8-K10 P6-CNR P6-NHM P4
L(ftop):mul dinv C 0,12 0,17 0,17
add %r11, %rdx C 5 8 10
mov %rax, %r11 C 4 8 3
mov %rdx, %r13 C 6 9 11
imul %rbp, %rdx C 6 9 11
mov d, %rax C
add %rdx, %rax C 10 14 14
cmp %r11, %rdx C 10 14 14
cmovc %rdx, %rax C 11 15 15
adc $-1, %r13 C
mov %r13, (qp) C
sub $8, qp C
L(fent):lea 1(%rax), %r11 C
dec fn C
jns L(ftop) C
shr R8(%rcx), %rax
L(ret): pop %rbx
pop %rbp
pop %r12
pop %r13
FUNC_EXIT()
ret
EPILOGUE()
|