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
|
#define UNITY_ASSEMBLER
#include "Configuration/PrefixConfigure.h"
#include "Runtime/Utilities/VFPUtility.h"
#if UNITY_SUPPORTS_VFP
.syntax unified
.set device,0
.set device,__arm__
.if device
//.code32
.globl _MultiplyMatrices4x4_VFP
.globl _MultiplyMatrixArray4x4_VFP
#if UNITY_ANDROID
.hidden _MultiplyMatrices4x4_VFP
.hidden _MultiplyMatrixArray4x4_VFP
#endif
//===========================================================================================================================================
// void MultiplyMatrices4x4_VFP(const Matrix4x4f* __restrict lhs, const Matrix4x4f* __restrict rhs, Matrix4x4f* __restrict res)
_MultiplyMatrices4x4_VFP:
// r0: A
// r1: B
// r2: dst
vpush {d8-d15}
mov ip, r0
// VFP_VECTOR_LENGTH(3)
mov r0, ip
vldmia.32 r0, {s8-s23}
vldmia.32 r1!, {s0-s7}
FMULS4 (24,25,26,27, 8,9,10,11, 0,0,0,0)
FMULS4 (28,29,30,31, 8,9,10,11, 4,4,4,4)
FMACS4 (24,25,26,27, 12,13,14,15, 1,1,1,1)
FMACS4 (28,29,30,31, 12,13,14,15, 5,5,5,5)
FMACS4 (24,25,26,27, 16,17,18,19, 2,2,2,2)
FMACS4 (28,29,30,31, 16,17,18,19, 6,6,6,6)
FMACS4 (24,25,26,27, 20,21,22,23, 3,3,3,3)
FMACS4 (28,29,30,31, 20,21,22,23, 7,7,7,7)
vstmia.32 r2!, {s24-s31}
vldmia.32 r1, {s0-s7}
FMULS4 (24,25,26,27, 8,9,10,11, 0,0,0,0)
FMULS4 (28,29,30,31, 8,9,10,11, 4,4,4,4)
FMACS4 (24,25,26,27, 12,13,14,15, 1,1,1,1)
FMACS4 (28,29,30,31, 12,13,14,15, 5,5,5,5)
FMACS4 (24,25,26,27, 16,17,18,19, 2,2,2,2)
FMACS4 (28,29,30,31, 16,17,18,19, 6,6,6,6)
FMACS4 (24,25,26,27, 20,21,22,23, 3,3,3,3)
FMACS4 (28,29,30,31, 20,21,22,23, 7,7,7,7)
vstmia.32 r2, {s24-s31}
// VFP_VECTOR_LENGTH_ZERO
vpop {d8-d15}
bx lr
//===========================================================================================================================================
// void MultiplyMatrixArray4x4_VFP(const Matrix4x4f* arrayA, const Matrix4x4f* arrayB, Matrix4x4f* arrayRes, size_t count)
_MultiplyMatrixArray4x4_VFP:
// r0: A
// r1: B
// r2: dst
// r3: A end
vpush {d8-d15}
mov ip, r0
// VFP_VECTOR_LENGTH(3)
mov r0, ip
add r3, r0, r3, lsl #6
.align 4
_MultiplyMatrixArray4x4_VFP_loop:
vldmia.32 r0!, {s16-s31}
vldmia.32 r1!, {s0-s7}
FMULS4 (8,9,10,11, 16,17,18,19, 0,0,0,0)
FMULS4 (12,13,14,15, 16,17,18,19, 4,4,4,4)
FMACS4 (8,9,10,11, 20,21,22,23, 1,1,1,1)
FMACS4 (12,13,14,15, 20,21,22,23, 5,5,5,5)
FMACS4 (8,9,10,11, 24,25,26,27, 2,2,2,2)
FMACS4 (12,13,14,15, 24,25,26,27, 6,6,6,6)
FMACS4 (8,9,10,11, 28,29,30,31, 3,3,3,3)
FMACS4 (12,13,14,15, 28,29,30,31, 7,7,7,7)
vldmia.32 r1!, {s0-s7}
vstmia.32 r2!, {s8-s15}
FMULS4 (8,9,10,11, 16,17,18,19, 0,0,0,0)
FMULS4 (12,13,14,15, 16,17,18,19, 4,4,4,4)
FMACS4 (8,9,10,11, 20,21,22,23, 1,1,1,1)
FMACS4 (12,13,14,15, 20,21,22,23, 5,5,5,5)
FMACS4 (8,9,10,11, 24,25,26,27, 2,2,2,2)
FMACS4 (12,13,14,15, 24,25,26,27, 6,6,6,6)
FMACS4 (8,9,10,11, 28,29,30,31, 3,3,3,3)
FMACS4 (12,13,14,15, 28,29,30,31, 7,7,7,7)
vstmia.32 r2!, {s8-s15}
cmp r0, r3
bcc _MultiplyMatrixArray4x4_VFP_loop
// VFP_VECTOR_LENGTH_ZERO
vpop {d8-d15}
bx lr
.endif
#endif
|
