summaryrefslogtreecommitdiffstats
path: root/mdk-stage1/dietlibc/i386/libm2.S
blob: 91c4437cda4fc41e9d0b71ca42d507407da7adc2 (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
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
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
.text
#d.half:
#	.long	0x3f000000	# 1/2
#d.log1p:
#	.long	0x3ed413cc	# < sqrt(2)-1-2^(-25)

.global fabsf,fabs,fabsl
	.type	fabsf,@function
	.type	fabs,@function
	.type	fabsl,@function
fabsf:
	flds 4(%esp)
	fabs
	ret
fabs:
	fldl 4(%esp)
	fabs
	ret
fabsl:
	fldt 4(%esp)
	fabs
	ret

.global sincosf,sincos,sincosl
.type   sincosf,@function
.type   sincos,@function
.type   sincosl,@function
# void  sincos ( double x, double* sinx, double* cosx );

sincosf:
        flds     4(%esp)
	call	__fmod2pi
        movl    12(%esp),%eax
        movl    8(%esp),%ecx
        fsincos
        fstps   (%eax)
        fstps   (%ecx)
        ret
sincos:
        fldl     4(%esp)
	call	__fmod2pi
        movl    16(%esp),%eax
        movl    12(%esp),%ecx
        fsincos
        fstpl   (%eax)
        fstpl   (%ecx)
        ret
sincosl:
        fldt     4(%esp)
	call	__fmod2pi
        movl    20(%esp),%eax
        movl    16(%esp),%ecx
        fsincos
        fstpt   (%eax)
        fstpt   (%ecx)
        ret

.global tanf,tan,tanl
.type   tanf,@function
.type   tan,@function
.type   tanl,@function
tanf:
        flds    4(%esp)
	jmp __tan
tan:
        fldl    4(%esp)
__tan:
	call	__fmod2pi
        fsincos
        fdivrp
        ret
tanl:
        fldt    4(%esp)
	jmp __tan

.global atan2f,atan2,atan2l
	.type	 atan2f,@function
	.type	 atan2,@function
	.type	 atan2l,@function
atan2f:
	flds 4(%esp)
	flds 8(%esp)
	fpatan
	ret
atan2l:
	fldt 4(%esp)
	fldt 16(%esp)
	fpatan
	ret
atan2:
	fldl 4(%esp)
	fldl 12(%esp)
	fpatan
	ret

.global cbrtf,cbrt,cbrtl
	.type	cbrtf,@function
	.type	cbrt,@function
	.type	cbrtl,@function
cbrtf:
	flds 4(%esp)
	jmp __cbrt
cbrtl:
	fldt 4(%esp)
	jmp __cbrt
cbrt:
	fldl 4(%esp)
# fldt 1/3
__cbrt:
	pushl $0x00003ffd	# yes, this method of loading 1/3
	pushl $0xaaaaaaaa	# is shorter than keeping the data
	pushl $0xaaaaaaab	# separate
	fldt (%esp)
	addl $12,%esp
	fxch			# st(0)=x, st(1)=1/3
	ftst
	fstsw %ax
	sahf
	jz 1f
	jnc finpow
	fchs
	call finpow
	fchs
1:	ret

# x^y; st(0)=x, st(1)=y (x > 0)
finpow:
	fyl2x
	jmp __finexp

.global exp2f,exp2,exp2l
	.type	 exp2f,@function
	.type	 exp2,@function
	.type	 exp2l,@function
exp2f:
	flds 4(%esp)
	jmp __finexp
exp2:
	fldl 4(%esp)
	jmp __finexp
exp2l:
	fldt 4(%esp)
	jmp __finexp

.global exp10f,exp10,exp10l	#,pow10f,pow10,pow10l
	.type	 exp10f,@function
	.type	 exp10,@function
	.type	 exp10l,@function
#	.type	 pow10f,@function
#	.type	 pow10,@function
#	.type	 pow10l,@function
exp10f:
#pow10f:
	fldl2t
	fmuls 4(%esp)
	jmp __finexp
exp10:
#pow10:
	fldl2t
	fmull 4(%esp)
	jmp __finexp
exp10l:
#pow10l:
	fldl2t
	fldt 4(%esp)
	fmulp
	jmp __finexp

# exp(x)-1
.global expm1f,expm1,expm1l
	.type	 expm1f,@function
	.type	 expm1,@function
	.type	 expm1l,@function
expm1f:
	fldl2e
	fmuls 4(%esp)
	jmp finem1
expm1l:
	fldl2e
	fldt 4(%esp)
	fmulp
	jmp finem1
expm1:
	fldl2e
	fmull 4(%esp)
# -1 <= st <= 1 ?
finem1:
	fst %st(1)	# st(1)=st(0)
	fabs
	fld1
	fcompp
	fstsw %ax
	sahf
# |x| >= 1
	jc 1f
	f2xm1
	ret
1:	call __finexp
	fld1
	fsubrp
	ret

# sinh(x)=(exp(x)-exp(-x))/2
# cosh(x)=(exp(x)+exp(-x))/2
# tanh(x)=sinh(x)/cosh(x)
.global sinhf,sinh,sinhl
	.type	sinhf,@function
	.type	sinh,@function
	.type	sinhl,@function
sinhf:
	fldl2e
	fmuls 4(%esp)
	jmp finsinh
sinh:
	fldl2e
	fmull 4(%esp)
finsinh:
	call __finexp
	fld1
	fdiv %st(1),%st(0)	# st(0)=1/exp(x), st(1)=exp(x)
	fsubrp %st(0),%st(1)
	pushl $0x3f000000	# 1/2
	flds (%esp)
	popl %eax
	fmulp
	ret

sinhl:
	fldl2e
	fldt 4(%esp)
	fmulp
	jmp finsinh

.global coshf,cosh,coshl
	.type	coshf,@function
	.type	cosh,@function
	.type	coshl,@function
coshf:
	fldl2e
	fmuls 4(%esp)
	jmp fincosh
cosh:
	fldl2e
	fmull 4(%esp)
fincosh:
	call __finexp
	fld1
	fdiv %st(1),%st(0)	# st(0)=1/exp(x), st(1)=exp(x)
	faddp %st,%st(1)
	pushl $0x3f000000	# 1/2
	flds (%esp)
	popl %eax
	fmulp
	ret

coshl:
	fldl2e
	fldt 4(%esp)
	fmulp
	jmp fincosh

.global tanhf,tanh,tanhl
	.type	tanhf,@function
	.type	tanh,@function
	.type	tanhl,@function
tanhf:
	fldl2e
	fmuls 4(%esp)
	call __finexp
	jmp fintanh
tanh:
	fldl2e
	fmull 4(%esp)
	call __finexp
fintanh:
	fld1
	fdiv %st(1),%st	# st(0)=1/exp(x), st(1)=exp(x)
	fst %st(2)	# st(2)=1/exp(x)
	fadd %st(1),%st(0)
	fstp %st(3)	# st(2)=exp(x)+exp(-x), st(1)=exp(-x), st(0)=exp(x)
	fsubp		# st(1)=exp(x)+exp(-x), st(0)=exp(x)-exp(-x)
	fdivp
	ret

tanhl:
	fldl2e
	fldt 4(%esp)
	fmulp
	call __finexp
	jmp fintanh

.global hypotf,hypot,hypotl	# ,__hypot
	.type	 hypotf,@function
	.type	 hypot,@function
	.type	 hypotl,@function
#	.type	 __hypot,@function
hypotf:
	flds 8(%esp)
	flds 4(%esp)
	jmp __hypot
hypotl:
	fldt 16(%esp)
	fldt 4(%esp)
	jmp __hypot
hypot:
	fldl 12(%esp)
	fldl 4(%esp)
__hypot:
	fmul %st(0),%st(0)
	fxch
	fmul %st(0),%st(0)
	faddp
	fsqrt
	ret

.global log1pf,log1p,log1pl
	.type	 log1pf,@function
	.type	 log1p,@function
	.type	 log1pl,@function
log1pf:
	flds 4(%esp)
	jmp __log1p
log1pl:
	fldt 4(%esp)
	jmp __log1p
log1p:
	fldl 4(%esp)
__log1p:
# Sprawdzenie zakresu parametru
	fst %st(1)
	pushl	$0x3ed413cc	# sqrt(2)-1-2^(-25)
	fabs
	flds (%esp)
	popl %eax
	fcompp			# porownanie
	fstsw %ax
	fldln2
	fxch
	sahf
# |x| >= sqrt(2)-1
	jc 1f
	fyl2xp1
	ret
1:	fld1		# x = x + 1
	faddp
	fyl2x
	ret

.global log10f,log10,log10l
	.type	 log10f,@function
	.type	 log10,@function
	.type	 log10l,@function
log10f:
	fldlg2
	flds 4(%esp)
	fyl2x
	ret
log10l:
	fldlg2
	fldt 4(%esp)
	fyl2x
	ret
log10:
	fldlg2
	fldl 4(%esp)
	fyl2x
	ret

.global log2f,log2,log2l
	.type	 log2f,@function
	.type	 log2,@function
	.type	 log2l,@function
log2f:
	fld1
	flds 4(%esp)
	fyl2x
	ret
log2l:
	fld1
	fldt 4(%esp)
	fyl2x
	ret
log2:
	fld1
	fldl 4(%esp)
	fyl2x
	ret

.global fmaf,fma,fmal
	.type	fmaf,@function
	.type	fma,@function
	.type	fmal,@function
fmaf:
	flds 4(%esp)
	fmuls 8(%esp)
	fadds 12(%esp)
	ret
fma:
	fldl 4(%esp)
	fmull 12(%esp)
	faddl 20(%esp)
	ret
fmal:
	fldt 4(%esp)
	fldt 16(%esp)
	fmulp %st,%st(1)
	fldt 28(%esp)
	faddp %st,%st(1)
	ret

.global asinhf,asinh,asinhl
	.type	asinhf,@function
	.type	asinh,@function
	.type	asinhl,@function
asinhf:
	flds 4(%esp)
	jmp __asinh
asinh:
	fldl 4(%esp)
__asinh:
	fld %st(0)
	fmul %st(0),%st(0)
	fld1
	faddp %st(0),%st(1)
finasch:
	fsqrt
	faddp %st(0),%st(1)
	fldln2
	fxch
	fyl2x
	ret
asinhl:
	fldt 4(%esp)
	jmp __asinh

.global acoshf,acosh,acoshl
	.type	acoshf,@function
	.type	acosh,@function
	.type	acoshl,@function
acoshf:
	flds 4(%esp)
	jmp __acosh
acosh:
	fldl 4(%esp)
__acosh:
	fld %st(0)
	fmul %st(0),%st(0)
	fld1
	fsubrp %st(0),%st(1)	# st1=st1-st0; pop
	jmp finasch
acoshl:
	fldt 4(%esp)
	jmp __acosh

.global atanhf,atanh,atanhl
	.type	atanhf,@function
	.type	atanh,@function
	.type	atanhl,@function
atanhf:
	flds 4(%esp)
	jmp __atanh
atanh:
	fldl 4(%esp)
__atanh:
	fst %st(1)
	fld1			# st0=1, st1=x, st2=x
	fadd %st(0),%st(2)	# st0=1, st1=x, st2=x+1
	fsubp %st(0),%st(1)	# st0=1-x, st1=x+1
	fdivrp %st(0),%st(1)
	fsqrt
	fldln2
	fxch
	fyl2x
	ret
atanhl:
	fldt 4(%esp)
	jmp __atanh

.global dremf,drem,dreml
	.type	dremf,@function
	.type	drem,@function
	.type	dreml,@function
dremf:
	flds 8(%esp)		# y
	flds 4(%esp)		# x
	jmp __drem
drem:
	fldl 12(%esp)
	fldl 4(%esp)
__drem:
	fprem1
	fstsw %ax
	sahf
	jp __drem
	ret

dreml:
	fldt 16(%esp)
	fldt 4(%esp)
	jmp __drem

# |ret| = |x|, sign(ret) = sign(y)
.global copysignf,copysign,copysignl
	.type	copysignf,@function
	.type	copysign,@function
	.type	copysignl,@function
copysignf:
	flds 4(%esp)		# x
	flds 8(%esp)		# y
	jmp __copysign
copysign:
	fldl 4(%esp)
	fldl 12(%esp)
__copysign:
	fmul %st(1),%st		# st = x*y
	ftst
	fstsw %ax
	fincstp
	sahf
	jnc 1f
	fchs
1:	ret

copysignl:
	fldt 4(%esp)
	fldt 16(%esp)
	jmp __copysign

.global fdimf,fdim,fdiml
	.type	 fdimf,@function
	.type	 fdim,@function
	.type	 fdiml,@function
fdimf:
	flds 4(%esp)
	fsubl 12(%esp)
	jmp __fdim
fdim:
	fldl 4(%esp)
	fsubl 12(%esp)
__fdim:
	fstsw %ax
	sahf
	jnc 1f
	fldz
1:	ret
fdiml:
	fldt 4(%esp)
	fldt 16(%esp)
	fsubp
	jmp __fdim


.global truncf,trunc,truncl
	.type truncf,@function
	.type trunc,@function
	.type truncl,@function

truncf:
	flds 4(%esp)
	movb $0x0c,%ah
	jmp __flcetr

trunc:
	fldl 4(%esp)
	movb $0x0c,%ah
	jmp __flcetr

truncl:
	fldt 4(%esp)
	movb $0x0c,%ah
	jmp __flcetr

.global frexpf,frexp,frexpl
	.type frexpf,@function
	.type frexp,@function
	.type frexpl,@function

frexpf:
	flds 4(%esp)
	movl 8(%esp),%eax
	jmp __frexp

frexp:
	fldl 4(%esp)
	movl 12(%esp),%eax
__frexp:
	fxtract
	fxch
	fistpl (%eax)
	pushl $0x3f000000	# 1/2
	fmuls (%esp)
	incl (%eax)
	popl %eax
	ret

frexpl:
	fldt 4(%esp)
	movl 16(%esp),%eax
	jmp __frexp

.global logbf,logb,logbl
	.type logbf,@function
	.type logb,@function
	.type logbl,@function

#logbf:	flds 4(%esp)
#	fxtract
#	fxch
#	ret

#logb:	fldl 4(%esp)
#	fxtract
#	fxch
#	ret

#logbl:	fldt 4(%esp)
#	fxtract
#	fxch
#	ret

.global ilogbf,ilogb,ilogbl
	.type ilogbf,@function
	.type ilogb,@function
	.type ilogbl,@function

logbf:
ilogbf:	flds 4(%esp)
	jmp __ilogb

logb:
ilogb:	fldl 4(%esp)
__ilogb:
	fxtract
	pushl %eax
	fxch
	fistl (%esp)
	popl %eax
	ret

logbl:
ilogbl:	fldt 4(%esp)
	jmp __ilogb