aboutsummaryrefslogtreecommitdiff
path: root/sysdeps/i386/fpu/s_expm1.S
blob: 05e5285d7bb560ffde57424c6ca6210676450cb3 (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
/* ix87 specific implementation of exp(x)-1.
   Copyright (C) 1996-2015 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Ulrich Drepper <drepper@cygnus.com>, 1996.
   Based on code by John C. Bowman <bowman@ipp-garching.mpg.de>.
   Corrections by H.J. Lu (hjl@gnu.ai.mit.edu), 1997.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; if not, see
   <http://www.gnu.org/licenses/>.  */

	/* Using: e^x - 1 = 2^(x * log2(e)) - 1 */

#include <sysdep.h>
#include <machine/asm.h>

	.section .rodata

	.align ALIGNARG(4)
	.type minus1,@object
minus1:	.double -1.0
	ASM_SIZE_DIRECTIVE(minus1)
	.type one,@object
one:	.double 1.0
	ASM_SIZE_DIRECTIVE(one)
	.type l2e,@object
l2e:	.tfloat 1.442695040888963407359924681002
	ASM_SIZE_DIRECTIVE(l2e)

	.section .rodata.cst8,"aM",@progbits,8

	.p2align 3
	.type dbl_min,@object
dbl_min:	.byte 0, 0, 0, 0, 0, 0, 0x10, 0
	ASM_SIZE_DIRECTIVE(dbl_min)

#ifdef PIC
#define MO(op) op##@GOTOFF(%edx)
#else
#define MO(op) op
#endif

	.text
ENTRY(__expm1)
	movzwl	4+6(%esp), %eax
	xorb	$0x80, %ah	// invert sign bit (now 1 is "positive")
	cmpl	$0xc086, %eax	// is num >= 704?
	jae	HIDDEN_JUMPTARGET (__exp)

	fldl	4(%esp)		// x
	fxam			// Is NaN, +-Inf or +-0?
	xorb	$0x80, %ah
	cmpl	$0xc043, %eax	// is num <= -38.0?
	fstsw	%ax
	movb	$0x45, %ch
	jb	4f

	// Below -38.0 (may be -NaN or -Inf).
	andb	%ah, %ch
#ifdef	PIC
	LOAD_PIC_REG (dx)
#endif
	cmpb	$0x01, %ch
	je	5f		// If -NaN, jump.
	jmp	2f		// -large, possibly -Inf.

4:	// In range -38.0 to 704.0 (may be +-0 but not NaN or +-Inf).
	andb	%ah, %ch
	cmpb	$0x40, %ch
	je	3f		// If +-0, jump.
#ifdef	PIC
	LOAD_PIC_REG (dx)
#endif
	fld	%st
	fabs
	fcoml	MO(dbl_min)
	fstp	%st
	fnstsw
	sahf
	jae	5f
	subl	$8, %esp
	cfi_adjust_cfa_offset (8)
	fld	%st(0)
	fmul	%st(0)
	fstpl	(%esp)
	addl	$8, %esp
	cfi_adjust_cfa_offset (-8)
	ret

5:	fldt	MO(l2e)		// log2(e) : x
	fmulp			// log2(e)*x
	fld	%st		// log2(e)*x : log2(e)*x
	// Set round-to-nearest temporarily.
	subl	$8, %esp
	cfi_adjust_cfa_offset (8)
	fstcw	4(%esp)
	movl	$0xf3ff, %ecx
	andl	4(%esp), %ecx
	movl	%ecx, (%esp)
	fldcw	(%esp)
	frndint			// int(log2(e)*x) : log2(e)*x
	fldcw	4(%esp)
	addl	$8, %esp
	cfi_adjust_cfa_offset (-8)
	fsubr	%st, %st(1)	// int(log2(e)*x) : fract(log2(e)*x)
	fxch			// fract(log2(e)*x) : int(log2(e)*x)
	f2xm1			// 2^fract(log2(e)*x)-1 : int(log2(e)*x)
	fscale			// 2^(log2(e)*x)-2^int(log2(e)*x) : int(log2(e)*x)
	fxch			// int(log2(e)*x) : 2^(log2(e)*x)-2^int(log2(e)*x)
	fldl	MO(one)		// 1 : int(log2(e)*x) : 2^(log2(e)*x)-2^int(log2(e)*x)
	fscale			// 2^int(log2(e)*x) : int(log2(e)*x) : 2^(log2(e)*x)-2^int(log2(e)*x)
	fsubrl	MO(one)		// 1-2^int(log2(e)*x) : int(log2(e)*x) : 2^(log2(e)*x)-2^int(log2(e)*x)
	fstp	%st(1)		// 1-2^int(log2(e)*x) : 2^(log2(e)*x)-2^int(log2(e)*x)
	fsubrp	%st, %st(1)	// 2^(log2(e)*x)
	ret

2:	fstp	%st
	fldl	MO(minus1)	// Set result to -1.0.
3:	ret
END(__expm1)
weak_alias (__expm1, expm1)