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
|
; $Id: tan.asm $
;; @file
; IPRT - No-CRT tan - AMD64 & X86.
;
;
; Copyright (C) 2006-2023 Oracle and/or its affiliates.
;
; This file is part of VirtualBox base platform packages, as
; available from https://www.virtualbox.org.
;
; This program is free software; you can redistribute it and/or
; modify it under the terms of the GNU General Public License
; as published by the Free Software Foundation, in version 3 of the
; License.
;
; This program 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
; General Public License for more details.
;
; You should have received a copy of the GNU General Public License
; along with this program; if not, see <https://www.gnu.org/licenses>.
;
; The contents of this file may alternatively be used under the terms
; of the Common Development and Distribution License Version 1.0
; (CDDL), a copy of it is provided in the "COPYING.CDDL" file included
; in the VirtualBox distribution, in which case the provisions of the
; CDDL are applicable instead of those of the GPL.
;
; You may elect to license modified versions of this file under the
; terms and conditions of either the GPL or the CDDL or both.
;
; SPDX-License-Identifier: GPL-3.0-only OR CDDL-1.0
;
%define RT_ASM_WITH_SEH64
%include "iprt/asmdefs.mac"
%include "iprt/x86.mac"
BEGINCODE
;;
; Compute the sine of rd
; @returns st(0) / xmm0
; @param rd [xSP + xCB*2] / xmm0
RT_NOCRT_BEGINPROC tan
push xBP
SEH64_PUSH_xBP
mov xBP, xSP
SEH64_SET_FRAME_xBP 0
sub xSP, 20h
SEH64_ALLOCATE_STACK 20h
SEH64_END_PROLOGUE
%ifdef RT_OS_WINDOWS
;
; Make sure we use full precision and not the windows default of 53 bits.
;
fnstcw [xBP - 20h]
mov ax, [xBP - 20h]
or ax, X86_FCW_PC_64 ; includes both bits, so no need to clear the mask.
mov [xBP - 1ch], ax
fldcw [xBP - 1ch]
%endif
;
; Load the input into st0.
;
%ifdef RT_ARCH_AMD64
movsd [xBP - 10h], xmm0
fld qword [xBP - 10h]
%else
fld qword [xBP + xCB*2]
%endif
;
; Calculate the tangent.
;
fptan
fnstsw ax
test ah, (X86_FSW_C2 >> 8) ; C2 is set if the input was out of range.
jz .return_val
;
; Input was out of range, perform reduction to +/-2pi.
;
fldpi
fadd st0
fxch st1
.again:
fprem1
fnstsw ax
test ah, (X86_FSW_C2 >> 8) ; C2 is set if partial result.
jnz .again ; Loop till C2 == 0 and we have a final result.
fstp st1
fptan
;
; Run st0.
;
.return_val:
ffreep st0 ; ignore the 1.0 fptan pushed
%ifdef RT_ARCH_AMD64
fstp qword [xBP - 10h]
movsd xmm0, [xBP - 10h]
%endif
%ifdef RT_OS_WINDOWS
fldcw [xBP - 20h] ; restore original
%endif
.return:
leave
ret
ENDPROC RT_NOCRT(tan)
|
