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
|
#pragma clang diagnostic ignored "-Wmissing-prototypes"
#pragma clang diagnostic ignored "-Wmissing-braces"
#include <metal_stdlib>
#include <simd/simd.h>
using namespace metal;
template<typename T, size_t Num>
struct spvUnsafeArray
{
T elements[Num ? Num : 1];
thread T& operator [] (size_t pos) thread
{
return elements[pos];
}
constexpr const thread T& operator [] (size_t pos) const thread
{
return elements[pos];
}
device T& operator [] (size_t pos) device
{
return elements[pos];
}
constexpr const device T& operator [] (size_t pos) const device
{
return elements[pos];
}
constexpr const constant T& operator [] (size_t pos) const constant
{
return elements[pos];
}
threadgroup T& operator [] (size_t pos) threadgroup
{
return elements[pos];
}
constexpr const threadgroup T& operator [] (size_t pos) const threadgroup
{
return elements[pos];
}
};
struct main0_out
{
float4 gl_Position;
};
struct main0_patchOut
{
spvUnsafeArray<float4, 2> pFoo;
};
struct main0_in
{
spvUnsafeArray<float4, 2> iFoo;
float4 ipFoo;
};
template<typename T, uint A>
inline void spvArrayCopyFromConstantToStack1(thread T (&dst)[A], constant T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromConstantToThreadGroup1(threadgroup T (&dst)[A], constant T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromStackToStack1(thread T (&dst)[A], thread const T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromStackToThreadGroup1(threadgroup T (&dst)[A], thread const T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromThreadGroupToStack1(thread T (&dst)[A], threadgroup const T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromThreadGroupToThreadGroup1(threadgroup T (&dst)[A], threadgroup const T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromDeviceToDevice1(device T (&dst)[A], device const T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromConstantToDevice1(device T (&dst)[A], constant T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromStackToDevice1(device T (&dst)[A], thread const T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromThreadGroupToDevice1(device T (&dst)[A], threadgroup const T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromDeviceToStack1(thread T (&dst)[A], device const T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
template<typename T, uint A>
inline void spvArrayCopyFromDeviceToThreadGroup1(threadgroup T (&dst)[A], device const T (&src)[A])
{
for (uint i = 0; i < A; i++)
{
dst[i] = src[i];
}
}
kernel void main0(uint3 gl_GlobalInvocationID [[thread_position_in_grid]], device main0_out* spvOut [[buffer(28)]], constant uint* spvIndirectParams [[buffer(29)]], device main0_patchOut* spvPatchOut [[buffer(27)]], device MTLQuadTessellationFactorsHalf* spvTessLevel [[buffer(26)]], device main0_in* spvIn [[buffer(22)]])
{
device main0_out* gl_out = &spvOut[gl_GlobalInvocationID.x - gl_GlobalInvocationID.x % 4];
threadgroup float4 spvStorageFoo[8][4][2];
threadgroup float4 (&Foo)[4][2] = spvStorageFoo[(gl_GlobalInvocationID.x / 4) % 8];
device main0_patchOut& patchOut = spvPatchOut[gl_GlobalInvocationID.x / 4];
device main0_in* gl_in = &spvIn[min(gl_GlobalInvocationID.x / 4, spvIndirectParams[1] - 1) * spvIndirectParams[0]];
uint gl_InvocationID = gl_GlobalInvocationID.x % 4;
uint gl_PrimitiveID = min(gl_GlobalInvocationID.x / 4, spvIndirectParams[1]);
gl_out[gl_InvocationID].gl_Position = float4(1.0);
spvArrayCopyFromDeviceToThreadGroup1(Foo[gl_InvocationID], gl_in[gl_InvocationID].iFoo.elements);
if (gl_InvocationID == 0)
{
spvUnsafeArray<float4, 2> _56 = spvUnsafeArray<float4, 2>({ gl_in[0].ipFoo, gl_in[1].ipFoo });
patchOut.pFoo = _56;
}
}
|
