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
|
#ifndef JMATH_H
#define JMATH_H
#include "dolphin/mtx/quat.h"
#include "math.h"
bool JMANewSinTable(u8 numBits);
void JMAEulerToQuat(s16 x, s16 y, s16 z, Quaternion* out);
void JMAQuatLerp(Quaternion* a, Quaternion* b, f32 t, Quaternion* out);
f32 JMAHermiteInterpolation(f32 frame, f32 time0, f32 value0, f32 tangent0, f32 time1, f32 value1, f32 tangent1);
inline f32 JMAFastReciprocal(f32 value) {
return __fres(value);
}
inline float __frsqrtes(register double f) {
register float out;
// clang-format off
#ifdef __MWERKS__
asm {
frsqrte out, f
}
#endif
// clang-format on
return out;
}
inline f32 JMAFastSqrt(register f32 input) {
if (input > 0.0f) {
register f32 out;
#ifdef __MWERKS__
asm {
frsqrte out, input
}
#endif
return out * input;
} else {
return input;
}
}
namespace JMath {
inline f32 fastReciprocal(f32 value) {
return JMAFastReciprocal(value);
}
inline void gekko_ps_copy3(register void* dst, register const void* src) {
register f32 src0;
register f32 src1;
#ifdef __MWERKS__
asm {
psq_l src0, 0(src), 0, 0
lfs src1, 8(src)
psq_st src0, 0(dst), 0, 0
stfs src1, 8(dst)
};
#endif
}
inline void gekko_ps_copy6(register void* dst, register const void* src) {
register f32 src0;
register f32 src1;
register f32 src2;
#ifdef __MWERKS__
asm {
psq_l src0, 0(src), 0, 0
psq_l src1, 8(src), 0, 0
psq_l src2, 16(src), 0, 0
psq_st src0, 0(dst), 0, 0
psq_st src1, 8(dst), 0, 0
psq_st src2, 16(dst), 0, 0
};
#endif
}
inline void gekko_ps_copy12(register void* dst, register const void* src) {
register f32 src0;
register f32 src1;
register f32 src2;
register f32 src3;
register f32 src4;
register f32 src5;
#ifdef __MWERKS__
asm {
psq_l src0, 0(src), 0, 0
psq_l src1, 8(src), 0, 0
psq_l src2, 16(src), 0, 0
psq_l src3, 24(src), 0, 0
psq_l src4, 32(src), 0, 0
psq_l src5, 40(src), 0, 0
psq_st src0, 0(dst), 0, 0
psq_st src1, 8(dst), 0, 0
psq_st src2, 16(dst), 0, 0
psq_st src3, 24(dst), 0, 0
psq_st src4, 32(dst), 0, 0
psq_st src5, 40(dst), 0, 0
};
#endif
}
inline void gekko_ps_copy16(register void* dst, register const void* src) {
register f32 src0;
register f32 src1;
register f32 src2;
register f32 src3;
register f32 src4;
register f32 src5;
register f32 src6;
register f32 src7;
#ifdef __MWERKS__
asm {
psq_l src0, 0(src), 0, 0
psq_l src1, 8(src), 0, 0
psq_l src2, 16(src), 0, 0
psq_l src3, 24(src), 0, 0
psq_l src4, 32(src), 0, 0
psq_l src5, 40(src), 0, 0
psq_l src6, 48(src), 0, 0
psq_l src7, 56(src), 0, 0
psq_st src0, 0(dst), 0, 0
psq_st src1, 8(dst), 0, 0
psq_st src2, 16(dst), 0, 0
psq_st src3, 24(dst), 0, 0
psq_st src4, 32(dst), 0, 0
psq_st src5, 40(dst), 0, 0
psq_st src6, 48(dst), 0, 0
psq_st src7, 56(dst), 0, 0
};
#endif
}
}; // namespace JMath
#endif /* JMATH_H */
|
