summaryrefslogtreecommitdiff
path: root/gcc/config/sparc/lb1spl.asm
blob: 973401f801826421c4fd01641722348edabbf653 (plain)
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
/* This is an assembly language implementation of mulsi3, divsi3, and modsi3
   for the sparclite processor.

   These routines are all from the SPARClite User's Guide, slightly edited
   to match the desired calling convention, and also to optimize them.  */

#ifdef L_udivsi3
.text
	.align 4
	.global .udiv
	.proc	04
.udiv:
	wr	%g0,%g0,%y	! Not a delayed write for sparclite
	tst	%g0
	divscc	%o0,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	retl
	divscc	%g1,%o1,%o0
#endif

#ifdef L_umodsi3
.text
	.align 4
	.global .urem
	.proc	04
.urem:
	wr	%g0,%g0,%y	! Not a delayed write for sparclite
	tst	%g0
	divscc	%o0,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	divscc	%g1,%o1,%g1
	bl 1f
	rd	%y,%o0
	retl
	nop
1:	retl
	add	%o0,%o1,%o0
#endif

#ifdef L_divsi3
.text
	.align 4
	.global .div
	.proc	04
! ??? This routine could be made faster if was optimized, and if it was
! rewritten to only calculate the quotient.
.div:
	wr	%g0,%g0,%y	! Not a delayed write for sparclite
	mov	%o1,%o4
	tst	%o1
	bl,a	1f
	sub	%g0,%o4,%o4
1:	tst	%o0
	bl,a	2f
	mov	-1,%y
2:	divscc	%o0,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	be	6f
	mov	%y,%o3
	bg	4f
	addcc	%o3,%o4,%g0
	be,a	6f
	mov	%g0,%o3
	tst	%o0
	bl	5f
	tst	%g1
	ba	5f
	add	%o3,%o4,%o3
4:	subcc	%o3,%o4,%g0
	be,a	6f
	mov	%g0,%o3
	tst	%o0
	bge	5f
	tst	%g1
	sub	%o3,%o4,%o3
5:	bl,a	6f
	add	%g1,1,%g1
6:	tst	%o1
	bl,a	7f
	sub	%g0,%g1,%g1
7:	retl
	mov	%g1,%o0		! Quotient is in %g1.
#endif

#ifdef L_modsi3
.text
	.align 4
	.global .rem
	.proc	04
! ??? This routine could be made faster if was optimized, and if it was
! rewritten to only calculate the remainder.
.rem:
	wr	%g0,%g0,%y	! Not a delayed write for sparclite
	mov	%o1,%o4
	tst	%o1
	bl,a	1f
	sub	%g0,%o4,%o4
1:	tst	%o0
	bl,a	2f
	mov	-1,%y
2:	divscc	%o0,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	divscc	%g1,%o4,%g1
	be	6f
	mov	%y,%o3
	bg	4f
	addcc	%o3,%o4,%g0
	be,a	6f
	mov	%g0,%o3
	tst	%o0
	bl	5f
	tst	%g1
	ba	5f
	add	%o3,%o4,%o3
4:	subcc	%o3,%o4,%g0
	be,a	6f
	mov	%g0,%o3
	tst	%o0
	bge	5f
	tst	%g1
	sub	%o3,%o4,%o3
5:	bl,a	6f
	add	%g1,1,%g1
6:	tst	%o1
	bl,a	7f
	sub	%g0,%g1,%g1
7:	retl
	mov	%o3,%o0		! Remainder is in %o3.
#endif