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
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
|
/*
* ulong
* _udiv(ulong num, ulong den)
* {
* int i;
* ulong quo;
*
* if(den == 0)
* *(ulong*)-1 = 0;
* quo = num;
* if(quo > 1<<(32-1))
* quo = 1<<(32-1);
* for(i=0; den<quo; i++)
* den <<= 1;
* quo = 0;
* for(; i>=0; i--) {
* quo <<= 1;
* if(num >= den) {
* num -= den;
* quo |= 1;
* }
* den >>= 1;
* }
* return quo::num;
* }
*/
#define NOPROF 1
/*
* calling sequence:
* num: 4(R1)
* den: 8(R1)
* returns
* quo: 4(R1)
* rem: 8(R1)
*/
TEXT _udivmod(SB), NOPROF, $-4
MOVW $(1<<31), R11
MOVW 4(R1), R13 /* numerator */
MOVW 8(R1), R10 /* denominator */
CMP R10, R0
BNE udm20
MOVW R0, -1(R0) /* fault -- divide by zero */
udm20:
MOVW R13, R12
CMP R13, R11
BLEU udm34
MOVW R11, R12
udm34:
MOVW R0, R11
udm38:
CMP R10, R12
BCC udm54
SLL $1, R10
ADD $1, R11
BA udm38
udm54:
MOVW R0, R12
udm58:
CMP R11, R0
BL udm8c
SLL $1, R12
CMP R13, R10
BCS udm7c
SUB R10, R13
OR $1, R12
udm7c:
SRL $1, R10
SUB $1, R11
BA udm58
udm8c:
MOVW R12, 4(R1) /* quotent */
MOVW R13, 8(R1) /* remainder */
JMPL 8(R15)
/*
* save working registers
* and bring in num/den parameters
*/
TEXT _unsarg(SB), NOPROF, $-4
MOVW R10, 12(R1)
MOVW R11, 16(R1)
MOVW R12, 20(R1)
MOVW R13, 24(R1)
MOVW R14, 4(R1)
MOVW 32(R1), R14
MOVW R14, 8(R1)
JMPL 8(R15)
/*
* save working registers
* and bring in absolute value
* of num/den parameters
*/
TEXT _absarg(SB), NOPROF, $-4
MOVW R10, 12(R1)
MOVW R11, 16(R1)
MOVW R12, 20(R1)
MOVW R13, 24(R1)
MOVW R14, 28(R1)
CMP R14, R0
BGE ab1
SUB R14, R0, R14
ab1:
MOVW R14, 4(R1) /* numerator */
MOVW 32(R1), R14
CMP R14, R0
BGE ab2
SUB R14, R0, R14
ab2:
MOVW R14, 8(R1) /* denominator */
JMPL 8(R15)
/*
* restore registers and
* return to original caller
* answer is in R14
*/
TEXT _retarg(SB), NOPROF, $-4
MOVW 12(R1), R10
MOVW 16(R1), R11
MOVW 20(R1), R12
MOVW 24(R1), R13
MOVW 0(R1), R15
ADD $28, R1
JMP 8(R15) /* back to main sequence */
/*
* calling sequence
* num: R14
* den: 8(R1)
* returns
* quo: R14
*/
TEXT _div(SB), NOPROF, $-4
SUB $28, R1 /* 4 reg save, 2 parameters, link */
MOVW R15, 0(R1)
JMPL _absarg(SB)
JMPL _udivmod(SB)
MOVW 4(R1), R14
MOVW 28(R1), R10 /* clean up the sign */
MOVW 32(R1), R11
XORCC R11, R10, R0
BGE div1
SUB R14, R0, R14
div1:
JMPL _retarg(SB)
JMP 8(R15) /* not executed */
/*
* calling sequence
* num: R14
* den: 8(R1)
* returns
* quo: R14
*/
TEXT _divl(SB), NOPROF, $-4
SUB $((4+2+1)*4), R1 /* 4 reg save, 2 parameters, link */
MOVW R15, 0(R1)
JMPL _unsarg(SB)
JMPL _udivmod(SB)
MOVW 4(R1), R14
JMPL _retarg(SB)
JMP 8(R15) /* not executed */
/*
* calling sequence
* num: R14
* den: 8(R1)
* returns
* rem: R14
*/
TEXT _mod(SB), NOPROF, $-4
SUB $28, R1 /* 4 reg save, 2 parameters, link */
MOVW R15, 0(R1)
JMPL _absarg(SB)
JMPL _udivmod(SB)
MOVW 8(R1), R14
MOVW 28(R1), R10 /* clean up the sign */
CMP R10, R0
BGE mod1
SUB R14, R0, R14
mod1:
JMPL _retarg(SB)
JMP 8(R15) /* not executed */
/*
* calling sequence
* num: R14
* den: 8(R1)
* returns
* rem: R14
*/
TEXT _modl(SB), NOPROF, $-4
SUB $28, R1 /* 4 reg save, 2 parameters, link */
MOVW R15, 0(R1)
JMPL _unsarg(SB)
JMPL _udivmod(SB)
MOVW 8(R1), R14
JMPL _retarg(SB)
JMP 8(R15) /* not executed */
/*
* special calling sequence:
* arg1 in R14
* arg2 in 4(R1), will save R9
* nothing in 0(R1), will save R8
* result in R14
*/
TEXT _mul+0(SB), NOPROF, $-4
/*
* exchange stack and registers
*/
MOVW R8, 0(R1)
MOVW 4(R1), R8
MOVW R9, 4(R1)
CMP R14, R8
BLE mul1
MOVW R14, R9
MOVW R8, R14
MOVW R9, R8
mul1:
MOVW R14, Y
ANDNCC $0xFFF, R14, R0
BE mul_shortway
ANDCC R0, R0, R9 /* zero partial product and clear N and V cond's */
/* long multiply */
MULSCC R8, R9, R9 /* 0 */
MULSCC R8, R9, R9 /* 1 */
MULSCC R8, R9, R9 /* 2 */
MULSCC R8, R9, R9 /* 3 */
MULSCC R8, R9, R9 /* 4 */
MULSCC R8, R9, R9 /* 5 */
MULSCC R8, R9, R9 /* 6 */
MULSCC R8, R9, R9 /* 7 */
MULSCC R8, R9, R9 /* 8 */
MULSCC R8, R9, R9 /* 9 */
MULSCC R8, R9, R9 /* 10 */
MULSCC R8, R9, R9 /* 11 */
MULSCC R8, R9, R9 /* 12 */
MULSCC R8, R9, R9 /* 13 */
MULSCC R8, R9, R9 /* 14 */
MULSCC R8, R9, R9 /* 15 */
MULSCC R8, R9, R9 /* 16 */
MULSCC R8, R9, R9 /* 17 */
MULSCC R8, R9, R9 /* 18 */
MULSCC R8, R9, R9 /* 19 */
MULSCC R8, R9, R9 /* 20 */
MULSCC R8, R9, R9 /* 21 */
MULSCC R8, R9, R9 /* 22 */
MULSCC R8, R9, R9 /* 23 */
MULSCC R8, R9, R9 /* 24 */
MULSCC R8, R9, R9 /* 25 */
MULSCC R8, R9, R9 /* 26 */
MULSCC R8, R9, R9 /* 27 */
MULSCC R8, R9, R9 /* 28 */
MULSCC R8, R9, R9 /* 29 */
MULSCC R8, R9, R9 /* 30 */
MULSCC R8, R9, R9 /* 31 */
MULSCC R0, R9, R9 /* 32; shift only */
MOVW Y, R14 /* get low part */
BA mul_return
mul_shortway:
ANDCC R0, R0, R9 /* zero partial product and clear N and V cond's */
MULSCC R8, R9, R9 /* 0 */
MULSCC R8, R9, R9 /* 1 */
MULSCC R8, R9, R9 /* 2 */
MULSCC R8, R9, R9 /* 3 */
MULSCC R8, R9, R9 /* 4 */
MULSCC R8, R9, R9 /* 5 */
MULSCC R8, R9, R9 /* 6 */
MULSCC R8, R9, R9 /* 7 */
MULSCC R8, R9, R9 /* 8 */
MULSCC R8, R9, R9 /* 9 */
MULSCC R8, R9, R9 /* 10 */
MULSCC R8, R9, R9 /* 11 */
MULSCC R0, R9, R9 /* 12; shift only */
MOVW Y, R8
SLL $12, R9
SRL $20, R8
OR R8, R9, R14
mul_return:
MOVW 0(R1), R8
MOVW 4(R1), R9
JMP 8(R15)
|
