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
|
//===-- comparesf2.S - Implement single-precision soft-float comparisons --===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements the following soft-fp_t comparison routines:
//
// __eqsf2 __gesf2 __unordsf2
// __lesf2 __gtsf2
// __ltsf2
// __nesf2
//
// The semantics of the routines grouped in each column are identical, so there
// is a single implementation for each, with multiple names.
//
// The routines behave as follows:
//
// __lesf2(a,b) returns -1 if a < b
// 0 if a == b
// 1 if a > b
// 1 if either a or b is NaN
//
// __gesf2(a,b) returns -1 if a < b
// 0 if a == b
// 1 if a > b
// -1 if either a or b is NaN
//
// __unordsf2(a,b) returns 0 if both a and b are numbers
// 1 if either a or b is NaN
//
// Note that __lesf2( ) and __gesf2( ) are identical except in their handling of
// NaN values.
//
//===----------------------------------------------------------------------===//
#include "../assembly.h"
.syntax unified
.align 2
DEFINE_COMPILERRT_FUNCTION(__eqsf2)
DEFINE_COMPILERRT_FUNCTION(__lesf2)
DEFINE_COMPILERRT_FUNCTION(__ltsf2)
DEFINE_COMPILERRT_FUNCTION(__nesf2)
// Make copies of a and b with the sign bit shifted off the top. These will
// be used to detect zeros and NaNs.
mov r2, r0, lsl #1
mov r3, r1, lsl #1
// We do the comparison in three stages (ignoring NaN values for the time
// being). First, we orr the absolute values of a and b; this sets the Z
// flag if both a and b are zero (of either sign). The shift of r3 doesn't
// effect this at all, but it *does* make sure that the C flag is clear for
// the subsequent operations.
orrs r12, r2, r3, lsr #1
// Next, we check if a and b have the same or different signs. If they have
// opposite signs, this eor will set the N flag.
it ne
eorsne r12, r0, r1
// If a and b are equal (either both zeros or bit identical; again, we're
// ignoring NaNs for now), this subtract will zero out r0. If they have the
// same sign, the flags are updated as they would be for a comparison of the
// absolute values of a and b.
it pl
subspl r0, r2, r3
// If a is smaller in magnitude than b and both have the same sign, place
// the negation of the sign of b in r0. Thus, if both are negative and
// a > b, this sets r0 to 0; if both are positive and a < b, this sets
// r0 to -1.
//
// This is also done if a and b have opposite signs and are not both zero,
// because in that case the subtract was not performed and the C flag is
// still clear from the shift argument in orrs; if a is positive and b
// negative, this places 0 in r0; if a is negative and b positive, -1 is
// placed in r0.
it lo
mvnlo r0, r1, asr #31
// If a is greater in magnitude than b and both have the same sign, place
// the sign of b in r0. Thus, if both are negative and a < b, -1 is placed
// in r0, which is the desired result. Conversely, if both are positive
// and a > b, zero is placed in r0.
it hi
movhi r0, r1, asr #31
// If you've been keeping track, at this point r0 contains -1 if a < b and
// 0 if a >= b. All that remains to be done is to set it to 1 if a > b.
// If a == b, then the Z flag is set, so we can get the correct final value
// into r0 by simply or'ing with 1 if Z is clear.
it ne
orrne r0, r0, #1
// Finally, we need to deal with NaNs. If either argument is NaN, replace
// the value in r0 with 1.
cmp r2, #0xff000000
ite ls
cmpls r3, #0xff000000
movhi r0, #1
bx lr
.align 2
DEFINE_COMPILERRT_FUNCTION(__gesf2)
DEFINE_COMPILERRT_FUNCTION(__gtsf2)
// Identical to the preceeding except in that we return -1 for NaN values.
// Given that the two paths share so much code, one might be tempted to
// unify them; however, the extra code needed to do so makes the code size
// to performance tradeoff very hard to justify for such small functions.
mov r2, r0, lsl #1
mov r3, r1, lsl #1
orrs r12, r2, r3, lsr #1
it ne
eorsne r12, r0, r1
it pl
subspl r0, r2, r3
it lo
mvnlo r0, r1, asr #31
it hi
movhi r0, r1, asr #31
it ne
orrne r0, r0, #1
cmp r2, #0xff000000
ite ls
cmpls r3, #0xff000000
movhi r0, #-1
bx lr
.align 2
DEFINE_COMPILERRT_FUNCTION(__unordsf2)
// Return 1 for NaN values, 0 otherwise.
mov r2, r0, lsl #1
mov r3, r1, lsl #1
mov r0, #0
cmp r2, #0xff000000
ite ls
cmpls r3, #0xff000000
movhi r0, #1
bx lr
|
