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
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
|
# Externe Routinen zu ARILEV1.D
# Prozessor: MIPS
# Endianness: irrelevant
# Compiler: GNU-C oder ...
# Parameter-Übergabe:
# o32: in Registern $4,$5,$6,$7, und auf dem Stack 16($sp),...
# n32: in Registern $4,$5,$6,$7,$8,$9,$10,$11, und auf dem Stack 4($sp),...
# Rückgabewert: in Register $2
# Einstellungen: intCsize=32, intDsize=32.
# Besonderheiten: Nach jedem Ladebefehl ein Wartetakt nötig, bevor der
# geholte Wert benutzt werden darf.
#ifdef INCLUDED_FROM_C
#define COPY_LOOPS
#define FILL_LOOPS
#define CLEAR_LOOPS
#define LOG_LOOPS
#define TEST_LOOPS
#define ADDSUB_LOOPS
#else
# Strictly speaking, the MIPS ABI (-32 or -n32) is independent from the CPU
# identification (-mips[12] or -mips[34]). But -n32 is commonly used together
# with -mips3, and it's easier to test the CPU identification.
#if __mips >= 3
#define ABI_N32 1
#else
#define ABI_O32 1
#endif
.text
.globl copy_loop_up
.globl copy_loop_down
.globl fill_loop_up
.globl fill_loop_down
.globl clear_loop_up
.globl clear_loop_down
.globl or_loop_up
.globl xor_loop_up
.globl and_loop_up
.globl eqv_loop_up
.globl nand_loop_up
.globl nor_loop_up
.globl andc2_loop_up
.globl orc2_loop_up
.globl not_loop_up
.globl and_test_loop_up
.globl test_loop_up
.globl compare_loop_up
.globl add_loop_down
.globl addto_loop_down
.globl inc_loop_down
.globl sub_loop_down
.globl subx_loop_down
.globl subfrom_loop_down
.globl dec_loop_down
.globl neg_loop_down
#ifndef __GNUC__ /* mit GNU-C machen wir mulu32() als Macro, der inline multipliziert */
# extern struct { uint32 lo; uint32 hi; } mulu32_ (uint32 arg1, uint32 arg2);
# 2^32*hi+lo := arg1*arg2.
.globl mulu32_
.align 2
.ent mulu32_ # Input in $4,$5, Output in $2,mulu32_high
mulu32_:
multu $5,$4 # arg1 * arg2
mfhi $6 # hi
mflo $2 # lo
sw $6,mulu32_high # hi abspeichern # Adressierung?? Deklaration??
j $31 # return
.end mulu32_
#endif
# extern uintD* copy_loop_up (uintD* sourceptr, uintD* destptr, uintC count);
.align 2
.ent copy_loop_up # Input in $4,$5,$6, Output in $2
colu1: lw $12,($4) # d = *sourceptr
addu $4,4 # sourceptr++
sw $12,($5) # *destptr = d
addu $5,4 # destptr++
subu $6,1 # count--
copy_loop_up:
bnez $6,colu1 # until (count==0)
move $2,$5 # destptr
j $31 # return
.end copy_loop_up
# extern uintD* copy_loop_down (uintD* sourceptr, uintD* destptr, uintC count);
.align 2
.ent copy_loop_down # Input in $4,$5,$6, Output in $2
cold1: subu $4,4 # sourceptr--
lw $12,($4) # d = *sourceptr
subu $5,4 # destptr--
sw $12,($5) # *destptr = d
subu $6,1 # count--
copy_loop_down:
bnez $6,cold1 # until (count==0)
move $2,$5 # destptr
j $31 # return
.end copy_loop_down
# extern uintD* fill_loop_up (uintD* destptr, uintC count, uintD filler);
.align 2
.ent fill_loop_up # Input in $4,$5,$6, Output in $2
flu1: sw $6,($4) # *destptr = filler
addu $4,4 # destptr++
subu $5,1 # count--
fill_loop_up:
bnez $5,flu1 # until (count==0)
move $2,$4 # destptr
j $31 # return
.end fill_loop_up
# extern uintD* fill_loop_down (uintD* destptr, uintC count, uintD filler);
.align 2
.ent fill_loop_down # Input in $4,$5,$6, Output in $2
fld1: subu $4,4 # destptr--
sw $6,($4) # *destptr = filler
subu $5,1 # count--
fill_loop_down:
bnez $5,fld1 # until (count==0)
move $2,$4 # destptr
j $31 # return
.end fill_loop_down
# extern uintD* clear_loop_up (uintD* destptr, uintC count);
.align 2
.ent clear_loop_up # Input in $4,$5, Output in $2
cllu1: sw $0,($4) # *destptr = 0
addu $4,4 # destptr++
subu $5,1 # count--
clear_loop_up:
bnez $5,cllu1 # until (count==0)
move $2,$4 # destptr
j $31 # return
.end clear_loop_up
# extern uintD* clear_loop_down (uintD* destptr, uintC count);
.align 2
.ent clear_loop_down # Input in $4,$5, Output in $2
clld1: subu $4,4 # destptr--
sw $0,($4) # *destptr = 0
subu $5,1 # count--
clear_loop_down:
bnez $5,clld1 # until (count==0)
move $2,$4 # destptr
j $31 # return
.end clear_loop_down
# extern void or_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent or_loop_up # Input in $4,$5,$6
olu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
or $12,$13 # x |= y
sw $12,($4) # *xptr = x
addu $4,4 # xptr++
subu $6,1 # count--
or_loop_up:
bnez $6,olu1 # until (count==0)
j $31 # return
.end or_loop_up
# extern void xor_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent xor_loop_up # Input in $4,$5,$6
xlu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
xor $12,$13 # x ^= y
sw $12,($4) # *xptr = x
addu $4,4 # xptr++
subu $6,1 # count--
xor_loop_up:
bnez $6,xlu1 # until (count==0)
j $31 # return
.end xor_loop_up
# extern void and_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent and_loop_up # Input in $4,$5,$6
alu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
and $12,$13 # x &= y
sw $12,($4) # *xptr = x
addu $4,4 # xptr++
subu $6,1 # count--
and_loop_up:
bnez $6,alu1 # until (count==0)
j $31 # return
.end and_loop_up
# extern void eqv_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent eqv_loop_up # Input in $4,$5,$6
nxlu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
xor $12,$13 # x ^= y
nor $12,$0 # x = ~x
sw $12,($4) # *xptr = x
addu $4,4 # xptr++
subu $6,1 # count--
eqv_loop_up:
bnez $6,nxlu1 # until (count==0)
j $31 # return
.end eqv_loop_up
# extern void nand_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent nand_loop_up # Input in $4,$5,$6
nalu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
and $12,$13 # x &= y # Gibt es 'nand $12,$13' ??
nor $12,$0 # x = ~x
sw $12,($4) # *xptr = x
addu $4,4 # xptr++
subu $6,1 # count--
nand_loop_up:
bnez $6,nalu1 # until (count==0)
j $31 # return
.end nand_loop_up
# extern void nor_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent nor_loop_up # Input in $4,$5,$6
nolu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
nor $12,$13 # x = ~(x|y)
sw $12,($4) # *xptr = x
addu $4,4 # xptr++
subu $6,1 # count--
nor_loop_up:
bnez $6,nolu1 # until (count==0)
j $31 # return
.end nor_loop_up
# extern void andc2_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent andc2_loop_up # Input in $4,$5,$6
aclu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
nor $13,$0 # y = ~y
and $12,$13 # x &= y
sw $12,($4) # *xptr = x
addu $4,4 # xptr++
subu $6,1 # count--
andc2_loop_up:
bnez $6,aclu1 # until (count==0)
j $31 # return
.end andc2_loop_up
# extern void orc2_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent orc2_loop_up # Input in $4,$5,$6
oclu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
nor $13,$0 # y = ~y
or $12,$13 # x |= y
sw $12,($4) # *xptr = x
addu $4,4 # xptr++
subu $6,1 # count--
orc2_loop_up:
bnez $6,oclu1 # until (count==0)
j $31 # return
.end orc2_loop_up
# extern void not_loop_up (uintD* xptr, uintC count);
.align 2
.ent not_loop_up # Input in $4,$5
nlu1: lw $12,($4) # x = *xptr
subu $5,1 # count--
nor $12,$0 # x = ~x
sw $12,($4) # *xptr = x
addu $4,4 # xptr++
not_loop_up:
bnez $5,nlu1 # until (count==0)
j $31 # return
.end not_loop_up
# extern bool and_test_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent and_test_loop_up # Input in $4,$5,$6
atlu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
and $12,$13 # x &= y
bnez $12,atlu3 # if (x) ...
addu $4,4 # xptr++
subu $6,1 # count--
and_test_loop_up:
bnez $6,atlu1 # until (count==0)
move $2,$0 # 0
j $31 # return
atlu3: li $2,1 # 1
j $31 # return
.end and_test_loop_up
# extern bool test_loop_up (uintD* ptr, uintC count);
.align 2
.ent test_loop_up # Input in $4,$5
tlu1: lw $12,($4) # x = *ptr
addu $4,4 # ptr++
bnez $12,tlu3
subu $5,1 # count--
test_loop_up:
bnez $5,tlu1 # until (count==0)
move $2,$0 # 0
j $31 # return
tlu3: li $2,1 # 1
j $31 # return
.end test_loop_up
# extern signean compare_loop_up (uintD* xptr, uintD* yptr, uintC count);
.align 2
.ent compare_loop_up # Input in $4,$5,$6
cmlu1: lw $12,($4) # x = *xptr
lw $13,($5) # y = *yptr
addu $5,4 # yptr++
bne $12,$13,cmlu3 # if (!(x==y)) ...
addu $4,4 # xptr++
subu $6,1 # count--
compare_loop_up:
bnez $6,cmlu1 # until (count==0)
move $2,$0 # 0
j $31 # return
cmlu3: bltu $12,$13,cmlu4 # if (x<y) ...
li $2,1 # 1
j $31 # return
cmlu4: li $2,-1 # -1
j $31 # return
.end compare_loop_up
# extern uintD add_loop_down (uintD* sourceptr1, uintD* sourceptr2, uintD* destptr, uintC count);
.align 2
.ent add_loop_down # Input in $4,$5,$6,$7, Output in $2
ald1: # kein Carry
subu $4,4 # sourceptr1--
subu $5,4 # sourceptr2--
lw $12,($4) # source1 = *sourceptr1
lw $13,($5) # source2 = *sourceptr2
subu $6,4 # destptr--
addu $12,$13 # dest = source1 + source2
sw $12,($6) # *destptr = dest
bltu $12,$13,ald4 # if (dest < source2) [also Carry] ...
ald2:
subu $7,1 # count--
add_loop_down:
bnez $7,ald1 # until (count==0)
move $2,$0 # 0
j $31 # return
ald3: # Hier Carry
subu $4,4 # sourceptr1--
subu $5,4 # sourceptr2--
lw $12,($4) # source1 = *sourceptr1
lw $13,($5) # source2 = *sourceptr2
subu $6,4 # destptr--
addu $12,$13 # dest = source1 + source2
addu $12,1 # + 1
sw $12,($6) # *destptr = dest
bgtu $12,$13,ald2 # if (dest > source2) [also kein Carry] ...
ald4: subu $7,1 # count--
bnez $7,ald3 # until (count==0)
li $2,1 # 1
j $31 # return
.end add_loop_down
# extern uintD addto_loop_down (uintD* sourceptr, uintD* destptr, uintC count);
.align 2
.ent addto_loop_down # Input in $4,$5,$6, Output in $2
atld1: # kein Carry
subu $4,4 # sourceptr--
subu $5,4 # destptr--
lw $12,($4) # source1 = *sourceptr
lw $13,($5) # source2 = *destptr
subu $6,1 # count--
addu $12,$13 # dest = source1 + source2
sw $12,($5) # *destptr = dest
bltu $12,$13,atld4 # if (dest < source2) [also Carry] ...
addto_loop_down:
atld2: bnez $6,atld1 # until (count==0)
move $2,$0 # 0
j $31 # return
atld3: # Hier Carry
subu $4,4 # sourceptr--
subu $5,4 # destptr--
lw $12,($4) # source1 = *sourceptr
lw $13,($5) # source2 = *destptr
subu $6,1 # count--
addu $12,$13 # dest = source1 + source2
addu $12,1 # + 1
sw $12,($5) # *destptr = dest
bgtu $12,$13,atld2 # if (dest > source2) [also kein Carry] ...
atld4: bnez $6,atld3 # until (count==0)
li $2,1 # 1
j $31 # return
.end addto_loop_down
# extern uintD inc_loop_down (uintD* ptr, uintC count);
.align 2
.ent inc_loop_down # Input in $4,$5, Output in $2
ild1: subu $4,4 # ptr--
lw $12,($4) # x = *ptr
subu $5,1 # count--
addu $12,1 # x++;
sw $12,($4) # *ptr = x
bnez $12,ild3 # if (!(x==0)) ...
inc_loop_down:
bnez $5,ild1 # until (count==0)
li $2,1 # 1
j $31 # return
ild3: move $2,$0 # 0
j $31 # return
.end inc_loop_down
# extern uintD sub_loop_down (uintD* sourceptr1, uintD* sourceptr2, uintD* destptr, uintC count);
.align 2
.ent sub_loop_down # Input in $4,$5,$6,$7, Output in $2
sld1: # kein Carry
subu $4,4 # sourceptr1--
subu $5,4 # sourceptr2--
lw $12,($4) # source1 = *sourceptr1
lw $13,($5) # source2 = *sourceptr2
subu $6,4 # destptr--
bltu $12,$13,sld2 # if (source1 < source2) [also Carry] ...
subu $12,$13 # dest = source1 - source2
sw $12,($6) # *destptr = dest
subu $7,1 # count--
sub_loop_down:
bnez $7,sld1 # until (count==0)
move $2,$0 # 0
j $31 # return
sld2: subu $12,$13 # dest = source1 - source2
sw $12,($6) # *destptr = dest
subu $7,1 # count--
bnez $7,sld3 # until (count==0)
li $2,-1 # -1
j $31 # return
sld3: # Hier Carry
subu $4,4 # sourceptr1--
subu $5,4 # sourceptr2--
lw $12,($4) # source1 = *sourceptr1
lw $13,($5) # source2 = *sourceptr2
subu $6,4 # destptr--
bgtu $12,$13,sld4 # if (source1 > source2) [also kein Carry] ...
subu $12,$13 # dest = source1 - source2
subu $12,1 # - 1
sw $12,($6) # *destptr = dest
subu $7,1 # count--
bnez $7,sld3 # until (count==0)
li $2,-1 # -1
j $31 # return
sld4: subu $12,$13 # dest = source1 - source2
subu $12,1 # - 1
sw $12,($6) # *destptr = dest
subu $7,1 # count--
bnez $7,sld1 # until (count==0)
move $2,$0 # 0
j $31 # return
.end sub_loop_down
# extern uintD subx_loop_down (uintD* sourceptr1, uintD* sourceptr2, uintD* destptr, uintC count, uintD carry);
.align 2
.ent subx_loop_down # Input in $4,$5,$6,$7,$8, Output in $2
subx_loop_down:
#if ABI_N32
move $12,$8 # carry
#else
lw $12,16($sp) # carry
#endif
bnez $12,sxld5 # !(carry==0) ?
b sxld2
sxld1: # kein Carry
subu $4,4 # sourceptr1--
subu $5,4 # sourceptr2--
lw $12,($4) # source1 = *sourceptr1
lw $13,($5) # source2 = *sourceptr2
subu $6,4 # destptr--
bltu $12,$13,sxld3 # if (source1 < source2) [also Carry] ...
subu $12,$13 # dest = source1 - source2
sw $12,($6) # *destptr = dest
subu $7,1 # count--
sxld2: bnez $7,sxld1 # until (count==0)
move $2,$0 # 0
j $31 # return
sxld3: subu $12,$13 # dest = source1 - source2
sw $12,($6) # *destptr = dest
subu $7,1 # count--
bnez $7,sxld4 # until (count==0)
li $2,-1 # -1
j $31 # return
sxld4: # Hier Carry
subu $4,4 # sourceptr1--
subu $5,4 # sourceptr2--
lw $12,($4) # source1 = *sourceptr1
lw $13,($5) # source2 = *sourceptr2
subu $6,4 # destptr--
bgtu $12,$13,sxld6 # if (source1 > source2) [also kein Carry] ...
subu $12,$13 # dest = source1 - source2
subu $12,1 # - 1
sw $12,($6) # *destptr = dest
subu $7,1 # count--
sxld5: bnez $7,sxld4 # until (count==0)
li $2,-1 # -1
j $31 # return
sxld6: subu $12,$13 # dest = source1 - source2
subu $12,1 # - 1
sw $12,($6) # *destptr = dest
subu $7,1 # count--
bnez $7,sxld1 # until (count==0)
move $2,$0 # 0
j $31 # return
.end subx_loop_down
# extern uintD subfrom_loop_down (uintD* sourceptr, uintD* destptr, uintC count);
.align 2
.ent subfrom_loop_down # Input in $4,$5,$6,$7, Output in $2
sfld1: # kein Carry
subu $4,4 # sourceptr--
subu $5,4 # destptr--
lw $12,($5) # source1 = *destptr
lw $13,($4) # source2 = *sourceptr
subu $6,1 # count--
bltu $12,$13,sfld2 # if (source1 < source2) [also Carry] ...
subu $12,$13 # dest = source1 - source2
sw $12,($5) # *destptr = dest
subfrom_loop_down:
bnez $6,sfld1 # until (count==0)
move $2,$0 # 0
j $31 # return
sfld2: subu $12,$13 # dest = source1 - source2
sw $12,($5) # *destptr = dest
bnez $6,sfld3 # until (count==0)
li $2,-1 # -1
j $31 # return
sfld3: # Hier Carry
subu $4,4 # sourceptr--
subu $5,4 # destptr--
lw $12,($5) # source1 = *destptr
lw $13,($4) # source2 = *sourceptr
subu $6,1 # count--
bgtu $12,$13,sfld4 # if (source1 > source2) [also kein Carry] ...
subu $12,$13 # dest = source1 - source2
subu $12,1 # - 1
sw $12,($5) # *destptr = dest
bnez $6,sfld3 # until (count==0)
li $2,-1 # -1
j $31 # return
sfld4: subu $12,$13 # dest = source1 - source2
subu $12,1 # - 1
sw $12,($5) # *destptr = dest
bnez $6,sfld1 # until (count==0)
move $2,$0 # 0
j $31 # return
.end subfrom_loop_down
# extern uintD dec_loop_down (uintD* ptr, uintC count);
.align 2
.ent dec_loop_down # Input in $4,$5, Output in $2
dld1: subu $4,4 # ptr--
lw $12,($4) # x = *ptr
subu $5,1 # count--
bnez $12,dld3 # if (!(x==0)) ...
subu $12,1 # x--;
sw $12,($4) # *ptr = x
dec_loop_down:
bnez $5,dld1 # until (count==0)
li $2,-1 # -1
j $31 # return
dld3: subu $12,1 # x--;
sw $12,($4) # *ptr = x
move $2,$0 # 0
j $31 # return
.end dec_loop_down
# extern uintD neg_loop_down (uintD* ptr, uintC count);
.align 2
.ent neg_loop_down # Input in $4,$5, Output in $2
# erstes Digit /=0 suchen:
nld1: subu $4,4 # ptr--
lw $12,($4) # x = *ptr
subu $5,1 # count--
bnez $12,nld3 # if (!(x==0)) ...
neg_loop_down:
bnez $5,nld1 # until (count==0)
move $2,$0 # 0
j $31 # return
nld3: # erstes Digit /=0 gefunden, ab jetzt gibt's Carrys
# 1 Digit negieren:
subu $12,$0,$12 # x = -x
sw $12,($4) # *ptr = x
# alle anderen Digits invertieren:
b nld5
nld4: subu $4,4 # xptr--
lw $12,($4) # x = *xptr
subu $5,1 # count--
nor $12,$0 # x = ~x
sw $12,($4) # *xptr = x
nld5: bnez $5,nld4 # until (count==0)
li $2,-1 # -1
j $31 # return
.end neg_loop_down
#endif
|
