src/parallel_clscr.src at master · LucAlexander/src · GitHub

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
comp
	mul r1 !6 !8
	mul r2 r1 !2
	mul r3 r1 !3
	add 0  !r0 r1
	add 8  !r1 r1
	add 10 !r2 r1
	add 18 !r3 r1
	add 20 !r0 r2
	add 28 !r1 r2
	add 30 !r2 r2
	add 38 !r3 r2
	add 40 !r0 r3
	add 48 !r1 r3
	add 50 !r2 r3
	add 58 !r3 r3
	mov 60 !r0
	mov 68 !r1
	mov 70 !r2
	mov 78 !r3
run
bind r01 0
bind r11 8
bind r21 10
bind r31 18
bind r02 20
bind r12 28
bind r22 30
bind r32 38
bind r03 40
bind r13 48
bind r23 50
bind r33 58
bind save_r0 60
bind save_r1 68
bind save_r2 70
bind save_r3 78

pass
	movw 0 !literal_bytes
	mov 8 r1
	bind loop ip
		cmp [r0] 0
		jne next
		add r0 r0 !8
		bind change ip
			cmp [r0] 0
			jeq break
			movw [r1] mov  add r1 r1 !8
			movw [r1] \[   add r1 r1 !8
			movw [r1] !r1  add r1 r1 !8
			movw [r1] \]   add r1 r1 !8
			movw [r1] \[   add r1 r1 !8
			movw [r1] [r0] add r1 r1 !8
			movw [r1] \]   add r1 r1 !8
			add r0 r0 !8
			jmp change
		bind break ip
		add r0 r0 !8
		cmp r0 8
		jeq exit
		jmp loop
		bind next ip
		mov [r1] [r0]
		add r0 r0 !8
		add r1 r1 !8
		cmp r0 8
		jne loop
	bind exit ip
	mov r0 !1
	int
end

pass
	mov 0 !core_agnostic
	mov 8 r1
	bind loop ip
		cmp [r0] 0
		jne next
		add r0 r0 !8
		mov r2 r1
		bytes
			bind core0 ip
		bytes
		bind inner ip
			cmp r0 0
			jeq core1
			mov [r1] [r0]
			add r0 r0 !8
			mov r1 r1 !8
			jmp inner
		bind core1 ip
		mov r0 r2
		bytes
			bind core1 ip
			bind r0 !r01
			bind r1 !r11
			bind r2 !r21
			bind r3 !r31
		bytes
		bind inner ip
			cmp r0 0
			jeq core2
			mov [r1] [r0]
			add r0 r0 !8
			mov r1 r1 !8
			jmp inner
		bind core2 ip
		mov r0 r2
		bytes
			bind core2 ip
			bind r0 !r02
			bind r1 !r12
			bind r2 !r22
			bind r3 !r32
		bytes
		bind inner ip
			cmp r0 0
			jeq core3
			mov [r1] [r0]
			add r0 r0 !8
			mov r1 r1 !8
			jmp inner
		bind core3 ip
		mov r0 r2
		bytes
			bind core3 ip
			bind r0 !r03
			bind r1 !r13
			bind r2 !r23
			bind r3 !r33
		bytes
		bind inner ip
			cmp r0 0
			jeq break
			jmp inner
		bind break ip
		bytes
			bind r0 save_r0
			bind r1 save_r1
			bind r2 save_r2
			bind r3 save_r3
		bytes
		add r0 r0 !8
		cmp r0 !8
		jeq exit
		jmp loop
		bind next ip
		mov [r1] [r0]
		add r0 r0 !8
		add r1 r1 !8
		cmp r0 8
		jne loop
	bind exit ip
	mov r0 !1
	int
end

mov r0 !9
mov r1 two
int
mov r0 !9
mov r1 three
int
mov r0 !9
mov r1 four
int
jmp one

core_agnostic
bind worker ip
	bind loop ip
		cmp r2 !0
		jne skip
		mov r0 !0
		int
		bind skip ip
		mov r0 r2
		bind inner ip
			cmp r0 r1
			jge loop
			movw [r0] !ff808080ff808080
			add r0 r0 !8
			jmp inner
	unbind loop
	unbind skip
	unbind inner
core_agnostic

bind one ip
	mov r1 !mbm
	div r1 r1 !4
	mov r2 !0
	jmp core0

bind two ip
	mov r1 !mbm
	div r1 r1 !4
	mov r2 r1
	mul r1 r1 !2
	jmp core1

bind three ip
	mov r1 !mbm
	div r1 r1 !4
	mul r2 r1 !2
	mul r1 r1 !3
	jmp core2

bind four ip
	mov r1 !mbm
	div r1 r1 !4
	mul r2 r1 !3
	mov r1 !mbm
	jmp core3