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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
|
#include <xmmintrin.h>
#include "math.h"
#include "interfaces.h"
using _m128 = __m128;
namespace math
{
uint32_t md5_pseudorandom( uint32_t seed ) {
using fn = uint32_t( __thiscall * )( uint32_t seed );
static auto func = pattern::first_code_match< fn >( cl.m_chl.dll( ), xors( "55 8B EC 83 E4 F8 83 EC 70 6A 58" ) );
if( !func ) {
return 0;
}
return func( seed );
}
static const __declspec( align( 16 ) ) uint32_t g_simd_component_mask[ 4 ][ 4 ] = {
{ 0xFFFFFFFF, 0, 0, 0 },
{ 0, 0xFFFFFFFF, 0, 0 },
{ 0, 0, 0xFFFFFFFF, 0 },
{ 0, 0, 0, 0xFFFFFFFF }
};
void concat_transforms( const matrix3x4& in, const matrix3x4& in2, matrix3x4& out ) {
//SSE concat transforms - turbo mode engaged
_m128 last_mask = *( _m128* )( &g_simd_component_mask[ 3 ] );
_m128 row_a0 = _mm_loadu_ps( in[ 0 ] );
_m128 row_a1 = _mm_loadu_ps( in[ 1 ] );
_m128 row_a2 = _mm_loadu_ps( in[ 2 ] );
_m128 row_b0 = _mm_loadu_ps( in2[ 0 ] );
_m128 row_b1 = _mm_loadu_ps( in2[ 1 ] );
_m128 row_b2 = _mm_loadu_ps( in2[ 2 ] );
_m128 a0 = _mm_shuffle_ps( row_a0, row_a0, _MM_SHUFFLE( 0, 0, 0, 0 ) );
_m128 a1 = _mm_shuffle_ps( row_a0, row_a0, _MM_SHUFFLE( 1, 1, 1, 1 ) );
_m128 a2 = _mm_shuffle_ps( row_a0, row_a0, _MM_SHUFFLE( 2, 2, 2, 2 ) );
_m128 mul00 = _mm_mul_ps( a0, row_b0 );
_m128 mul01 = _mm_mul_ps( a1, row_b1 );
_m128 mul02 = _mm_mul_ps( a2, row_b2 );
_m128 out0 = _mm_add_ps( mul00, _mm_add_ps( mul01, mul02 ) );
a0 = _mm_shuffle_ps( row_a2, row_a2, _MM_SHUFFLE( 0, 0, 0, 0 ) );
a1 = _mm_shuffle_ps( row_a2, row_a2, _MM_SHUFFLE( 1, 1, 1, 1 ) );
a2 = _mm_shuffle_ps( row_a2, row_a2, _MM_SHUFFLE( 2, 2, 2, 2 ) );
_m128 mul10 = _mm_mul_ps( a0, row_b0 );
_m128 mul11 = _mm_mul_ps( a1, row_b1 );
_m128 mul12 = _mm_mul_ps( a2, row_b2 );
_m128 out1 = _mm_add_ps( mul10, _mm_add_ps( mul11, mul12 ) );
a0 = _mm_shuffle_ps( row_a2, row_a2, _MM_SHUFFLE( 0, 0, 0, 0 ) );
a1 = _mm_shuffle_ps( row_a2, row_a2, _MM_SHUFFLE( 1, 1, 1, 1 ) );
a2 = _mm_shuffle_ps( row_a2, row_a2, _MM_SHUFFLE( 2, 2, 2, 2 ) );
_m128 mul20 = _mm_mul_ps( a0, row_b0 );
_m128 mul21 = _mm_mul_ps( a0, row_b1 );
_m128 mul22 = _mm_mul_ps( a0, row_b2 );
_m128 out2 = _mm_add_ps( mul20, _mm_add_ps( mul21, mul22 ) );
a0 = _mm_and_ps( row_a0, last_mask );
a1 = _mm_and_ps( row_a1, last_mask );
a2 = _mm_and_ps( row_a2, last_mask );
out0 = _mm_add_ps( out0, a0 );
out1 = _mm_add_ps( out1, a1 );
out2 = _mm_add_ps( out2, a2 );
*( _m128* )( out[ 0 ] ) = out0;
*( _m128* )( out[ 1 ] ) = out1;
*( _m128* )( out[ 2 ] ) = out2;
}
void math::set_matrix_position( vec3_t pos, matrix3x4& matrix ) {
for( size_t i{ }; i < 3; ++i ) {
matrix[ i ][ 3 ] = pos[ i ];
}
}
vec3_t math::get_matrix_position( const matrix3x4& src ) {
return vec3_t( src[ 0 ][ 3 ], src[ 1 ][ 3 ], src[ 2 ][ 3 ] );
}
void angle_matrix( vec3_t angles, matrix3x4& matrix ) {
float sr, sp, sy, cr, cp, cy;
sp = sinf( angles.x * M_PIRAD );
cp = cosf( angles.x * M_PIRAD );
sy = sinf( angles.y * M_PIRAD );
cy = cosf( angles.y * M_PIRAD );
sr = sinf( angles.z * M_PIRAD );
cr = cosf( angles.z * M_PIRAD );
matrix[ 0 ][ 0 ] = cp * cy;
matrix[ 1 ][ 0 ] = cp * sy;
matrix[ 2 ][ 0 ] = -sp;
float crcy = cr * cy;
float crsy = cr * sy;
float srcy = sr * cy;
float srsy = sr * sy;
matrix[ 0 ][ 1 ] = sp * srcy - crsy;
matrix[ 1 ][ 1 ] = sp * srsy + crcy;
matrix[ 2 ][ 1 ] = sr * cp;
matrix[ 0 ][ 2 ] = ( sp*crcy + srsy );
matrix[ 1 ][ 2 ] = ( sp*crsy - srcy );
matrix[ 2 ][ 2 ] = cr * cp;
matrix[ 0 ][ 3 ] = 0.f;
matrix[ 1 ][ 3 ] = 0.f;
matrix[ 2 ][ 3 ] = 0.f;
}
void angle_imatrix( vec3_t angles, matrix3x4& matrix ) {
float sr, sp, sy, cr, cp, cy;
sp = sinf( angles.x * M_PIRAD );
cp = cosf( angles.x * M_PIRAD );
sy = sinf( angles.y * M_PIRAD );
cy = cosf( angles.y * M_PIRAD );
sr = sinf( angles.z * M_PIRAD );
cr = cosf( angles.z * M_PIRAD );
matrix[ 0 ][ 0 ] = cp * cy;
matrix[ 0 ][ 1 ] = cp * sy;
matrix[ 0 ][ 2 ] = -sp;
matrix[ 1 ][ 0 ] = sr * sp*cy + cr * -sy;
matrix[ 1 ][ 1 ] = sr * sp*sy + cr * cy;
matrix[ 1 ][ 2 ] = sr * cp;
matrix[ 2 ][ 0 ] = ( cr*sp*cy + -sr * -sy );
matrix[ 2 ][ 1 ] = ( cr*sp*sy + -sr * cy );
matrix[ 2 ][ 2 ] = cr * cp;
matrix[ 0 ][ 3 ] = 0.f;
matrix[ 1 ][ 3 ] = 0.f;
matrix[ 2 ][ 3 ] = 0.f;
}
void angle_matrix( vec3_t angles, matrix3x4& matrix, vec3_t origin ) {
angle_matrix( angles, matrix );
set_matrix_position( origin, matrix );
}
vec3_t matrix_angles( const matrix3x4& matrix ) {
//thx strackoverflow
vec3_t angles;
float forward[ 3 ];
float left[ 3 ];
float up[ 3 ];
forward[ 0 ] = matrix[ 0 ][ 0 ];
forward[ 1 ] = matrix[ 1 ][ 0 ];
forward[ 2 ] = matrix[ 2 ][ 0 ];
left[ 0 ] = matrix[ 0 ][ 1 ];
left[ 1 ] = matrix[ 1 ][ 1 ];
left[ 2 ] = matrix[ 2 ][ 1 ];
up[ 2 ] = matrix[ 2 ][ 2 ];
float xy_dist = sqrtf( forward[ 0 ] * forward[ 0 ] + forward[ 1 ] * forward[ 1 ] );
if( xy_dist > 0.001f ) {
angles.y = RAD2DEG( atan2f( forward[ 1 ], forward[ 0 ] ) );
angles.x = RAD2DEG( atan2f( -forward[ 2 ], xy_dist ) );
angles.z = RAD2DEG( atan2f( left[ 2 ], up[ 2 ] ) );
}
else {
angles.y = RAD2DEG( atan2f( -left[ 0 ], left[ 1 ] ) );
angles.x = RAD2DEG( atan2f( -forward[ 2 ], xy_dist ) );
angles.z = 0;
}
return angles;
}
void rotate_matrix( vec3_t angles, vec3_t origin, float degrees, matrix3x4& matrix ) {
angles.y += degrees;
angles.clamp( );
vec3_t rotated( 0, degrees, 0 );
matrix3x4 rotated_matrix;
angle_matrix( rotated, rotated_matrix );
vec3_t delta = get_matrix_position( matrix ) - origin;
vec3_t out = vector_transform( delta, rotated_matrix );
matrix3x4 bone_rotation, matrix_out;
memcpy( &bone_rotation, &matrix, sizeof( matrix3x4 ) );
set_matrix_position( vec3_t( ), bone_rotation );
concat_transforms( rotated_matrix, bone_rotation, matrix_out );
auto angles_out = matrix_angles( matrix_out );
angle_matrix( angles_out, matrix, out );
}
float __vectorcall dist_segment_to_segment( vec3_t s1, vec3_t s2, vec3_t k1, vec3_t k2 ) {
vec3_t u = s2 - s1;
vec3_t v = k2 - k1;
vec3_t w = s1 - k1;
float a = u.dot( u );
float b = u.dot( v );
float c = v.dot( v );
float d = u.dot( w );
float e = v.dot( w );
float D = a * c - b * b;
float sc, sN, sD = D;
float tc, tN, tD = D;
if( D < SMALL_NUM ) {
sN = 0.0f;
sD = 1.0f;
tN = e;
tD = c;
}
else {
sN = ( b*e - c * d );
tN = ( a*e - b * d );
if( sN < 0.0f ) {
sN = 0.0f;
tN = e;
tD = c;
}
else if( sN > sD ) {
sN = sD;
tN = e + b;
tD = c;
}
}
if( tN < 0.0f ) {
tN = 0.0;
if( -d < 0.0f )
sN = 0.0;
else if( -d > a )
sN = sD;
else {
sN = -d;
sD = a;
}
}
else if( tN > tD ) {
tN = tD;
if( ( -d + b ) < 0.0f )
sN = 0;
else if( ( -d + b ) > a )
sN = sD;
else {
sN = ( -d + b );
sD = a;
}
}
sc = ( abs( sN ) < SMALL_NUM ? 0.0f : sN / sD );
tc = ( abs( tN ) < SMALL_NUM ? 0.0f : tN / tD );
vec3_t dP = w + ( u * sc ) - ( v * tc );
return dP.length( );
}
}
|
