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
|
!
! The contents of this file are subject to the Mozilla Public
! License Version 1.1 (the "License"); you may not use this file
! except in compliance with the License. You may obtain a copy of
! the License at http://www.mozilla.org/MPL/
!
! Software distributed under the License is distributed on an "AS
! IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
! implied. See the License for the specific language governing
! rights and limitations under the License.
!
! The Original Code is inline macros for SPARC Montgomery multiply functions.
!
! The Initial Developer of the Original Code is Sun Microsystems Inc.
! Portions created by Sun Microsystems Inc. are
! Copyright (C) 1999-2000 Sun Microsystems Inc. All Rights Reserved.
!
! Contributor(s):
!
! Alternatively, the contents of this file may be used under the
! terms of the GNU General Public License Version 2 or later (the
! "GPL"), in which case the provisions of the GPL are applicable
! instead of those above. If you wish to allow use of your
! version of this file only under the terms of the GPL and not to
! allow others to use your version of this file under the MPL,
! indicate your decision by deleting the provisions above and
! replace them with the notice and other provisions required by
! the GPL. If you do not delete the provisions above, a recipient
! may use your version of this file under either the MPL or the
! GPL.
!
! $Id$
!
!
! double upper32(double /*frs1*/);
!
.inline upper32,8
fdtox %f0,%f10
fitod %f10,%f0
.end
!
! double lower32(double /*frs1*/, double /* Zero */);
!
.inline lower32,8
fdtox %f0,%f10
fmovs %f2,%f10
fxtod %f10,%f0
.end
!
! double mod(double /*x*/, double /*1/m*/, double /*m*/);
!
.inline mod,12
fmuld %f0,%f2,%f2
fdtox %f2,%f2
fxtod %f2,%f2
fmuld %f2,%f4,%f2
fsubd %f0,%f2,%f0
.end
!
! void i16_to_d16_and_d32x4(double * /*1/(2^16)*/, double * /* 2^16*/,
! double * /* 0 */,
! double * /*result16*/, double * /* result32 */
! float * /*source - should be unsigned int*
! converted to float* */);
!
.inline i16_to_d16_and_d32x4,24
ldd [%o0],%f2 ! 1/(2^16)
ldd [%o1],%f4 ! 2^16
ldd [%o2],%f22
fmovd %f22,%f6
ld [%o5],%f7
fmovd %f22,%f10
ld [%o5+4],%f11
fmovd %f22,%f14
ld [%o5+8],%f15
fmovd %f22,%f18
ld [%o5+12],%f19
fxtod %f6,%f6
std %f6,[%o4]
fxtod %f10,%f10
std %f10,[%o4+8]
fxtod %f14,%f14
std %f14,[%o4+16]
fxtod %f18,%f18
std %f18,[%o4+24]
fmuld %f2,%f6,%f8
fmuld %f2,%f10,%f12
fmuld %f2,%f14,%f16
fmuld %f2,%f18,%f20
fdtox %f8,%f8
fdtox %f12,%f12
fdtox %f16,%f16
fdtox %f20,%f20
fxtod %f8,%f8
std %f8,[%o3+8]
fxtod %f12,%f12
std %f12,[%o3+24]
fxtod %f16,%f16
std %f16,[%o3+40]
fxtod %f20,%f20
std %f20,[%o3+56]
fmuld %f8,%f4,%f8
fmuld %f12,%f4,%f12
fmuld %f16,%f4,%f16
fmuld %f20,%f4,%f20
fsubd %f6,%f8,%f8
std %f8,[%o3]
fsubd %f10,%f12,%f12
std %f12,[%o3+16]
fsubd %f14,%f16,%f16
std %f16,[%o3+32]
fsubd %f18,%f20,%f20
std %f20,[%o3+48]
.end
|
