-
Notifications
You must be signed in to change notification settings - Fork 6
/
mult64.a
280 lines (242 loc) · 6.13 KB
/
mult64.a
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
; mult64.a
; based on Dr Jefyll, http://forum.6502.org/viewtopic.php?f=9&t=689&start=0#p19958
; - adjusted to use fixed zero page addresses
; - removed 'decrement to avoid clc' as this is slower on average
; - rearranged memory use to remove final memory copy and give LSB first order to result
; - removed temp zp storage bytes
; - unrolled the outer loop
; - unrolled the two inner loops fully
;
; 16 bit x 16 bit unsigned multiply, 32 bit result
; Average cycles: 386.00
; 279 bytes
multiplicand = $02 ; 2 bytes
multiplier = $04 ; 2 bytes
result = $04 ; 4 bytes (note: shares memory with multiplier)
* = $0200
; 16 bit x 16 bit unsigned multiply, 32 bit result
;
; On Entry:
; (multiplier, multiplier+1): two byte multiplier, four bytes needed for result
; (multiplicand, multiplicand+1): two byte multiplicand
; On Exit:
; (result, result+1, result+2, result+3): product
mult
ldy multiplicand ; Y is 'multiplicand' (low byte) throughout
; To avoid using Y, just 'lda multiplicand' instead of 'tya' throughout.
; This increases the average cycle count of the routine by only 4.5 cycles.
lda #0 ;
sta result+2 ; 16 bits of zero in A, result+2
; Note: First 8 shifts are A -> result+2 -> result
; Final 8 shifts are A -> result+2 -> result+1
; --- 1st byte ---
lsr result
; first time
bcc +
sty result+2
lda multiplicand+1
lsr ; shift
ror result+2
+ ; normally this should be two instructions earlier but as this
; is the first iteration we know A=result+2=0 and carry clear
; so those shift instructions have no effect.
ror result
; second time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result
; third time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result
; fourth time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result
; fifth time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result
; sixth time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result
; seventh time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result
; eighth time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result
; --- 2nd byte ---
lsr result+1
; first time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result+1
; second time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result+1
; third time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result+1
; fourth time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result+1
; fifth time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result+1
; sixth time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result+1
; seventh time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result+1
; eighth time
bcc +
tax ; retain A
tya ; equivalent to lda multiplicand
clc
adc result+2
sta result+2
txa ; recall A
adc multiplicand+1
+
ror ; shift
ror result+2
ror result+1
sta result+3 ; ms byte of hi-word of result
rts