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
|
.file "__umoddi3.s"
// $FreeBSD$
//-
// Copyright (c) 2000, Intel Corporation
// All rights reserved.
//
// Contributed 2/15/2000 by Marius Cornea, John Harrison, Cristina Iordache,
// Ted Kubaska, Bob Norin, and Shane Story of the Computational Software Lab,
// Intel Corporation.
//
// WARRANTY DISCLAIMER
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL OR ITS
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY OR TORT (INCLUDING
// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
// SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Intel Corporation is the author of this code, and requests that all
// problem reports or change requests be submitted to it directly at
// http://developer.intel.com/opensource.
//
.section .text
// 64-bit unsigned integer remainder
.proc __umoddi3#
.align 32
.global __umoddi3#
.align 32
__umoddi3:
{ .mii
alloc r31=ar.pfs,3,0,0,0
nop.i 0
nop.i 0
} { .mmb
// 64-BIT UNSIGNED INTEGER REMAINDER BEGINS HERE
// general register used:
// r32 - 64-bit unsigned integer dividend, called a below
// r33 - 64-bit unsigned integer divisor, called b below
// r8 - 64-bit unsigned integer result
// floating-point registers used: f6, f7, f8, f9, f10, f11, f12
// predicate registers used: p6
setf.sig f12=r32 // holds a in integer form
setf.sig f7=r33
nop.b 0;;
} { .mfi
// get 2's complement of b
sub r33=r0,r33
fcvt.xuf.s1 f6=f12
nop.i 0
} { .mfi
nop.m 0
fcvt.xuf.s1 f7=f7
nop.i 0;;
} { .mfi
nop.m 0
// Step (1)
// y0 = 1 / b in f8
frcpa.s1 f8,p6=f6,f7
nop.i 0;;
} { .mfi
nop.m 0
// Step (2)
// q0 = a * y0 in f10
(p6) fma.s1 f10=f6,f8,f0
nop.i 0
} { .mfi
nop.m 0
// Step (3)
// e0 = 1 - b * y0 in f9
(p6) fnma.s1 f9=f7,f8,f1
nop.i 0;;
} { .mfi
nop.m 0
// Step (4)
// q1 = q0 + e0 * q0 in f10
(p6) fma.s1 f10=f9,f10,f10
nop.i 0
} { .mfi
nop.m 0
// Step (5)
// e1 = e0 * e0 in f11
(p6) fma.s1 f11=f9,f9,f0
nop.i 0;;
} { .mfi
nop.m 0
// Step (6)
// y1 = y0 + e0 * y0 in f8
(p6) fma.s1 f8=f9,f8,f8
nop.i 0;;
} { .mfi
nop.m 0
// Step (7)
// q2 = q1 + e1 * q1 in f9
(p6) fma.s1 f9=f11,f10,f10
nop.i 0;;
} { .mfi
nop.m 0
// Step (8)
// y2 = y1 + e1 * y1 in f8
(p6) fma.s1 f8=f11,f8,f8
nop.i 0;;
} { .mfi
nop.m 0
// Step (9)
// r2 = a - b * q2 in f10
(p6) fnma.s1 f10=f7,f9,f6
nop.i 0;;
} { .mfi
// f7=-b
setf.sig f7=r33
// Step (10)
// q3 = q2 + r2 * y2 in f8
(p6) fma.s1 f8=f10,f8,f9
nop.i 0;;
} { .mfi
nop.m 0
// (11) q = trunc(q3)
fcvt.fxu.trunc.s1 f8=f8
nop.i 0;;
} { .mfi
nop.m 0
// (12) r = a + (-b) * q
xma.l f8=f8,f7,f12
nop.i 0;;
} { .mib
getf.sig r8=f8
nop.i 0
nop.b 0
}
// 64-BIT UNSIGNED INTEGER REMAINDER ENDS HERE
{ .mib
nop.m 0
nop.i 0
br.ret.sptk b0;;
}
.endp __umoddi3
|