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
|
#include "../../prelude/slang-cpp-prelude.h"
#ifdef SLANG_PRELUDE_NAMESPACE
using namespace SLANG_PRELUDE_NAMESPACE;
#endif
Vector<uint32_t, 3> operator+(Vector<uint32_t, 3> a, Vector<uint32_t, 3> b)
{
Vector<uint32_t, 3> r;
r.x = a.x + b.x;
r.y = a.y + b.y;
r.z = a.z + b.z;
return r;
}
Vector<uint32_t, 3> operator*(Vector<uint32_t, 3> a, Vector<uint32_t, 3> b)
{
Vector<uint32_t, 3> r;
r.x = a.x * b.x;
r.y = a.y * b.y;
r.z = a.z * b.z;
return r;
}
Vector<uint32_t, 3> make_VecU3(uint32_t a, uint32_t b, uint32_t c)
{
return Vector<uint32_t, 3>{ a, b, c};
}
size_t __computeMainSize = 668;
unsigned char __computeMain[] = {68, 88, 66, 67, 87, 111, 81, 164, 2, 29, 72, 42, 151, 28, 13, 217, 55, 37, 7, 95, 1,
0, 0, 0, 156, 2, 0, 0, 5, 0, 0, 0, 52, 0, 0, 0, 8, 1, 0, 0, 24,
1, 0, 0, 40, 1, 0, 0, 32, 2, 0, 0, 82, 68, 69, 70, 204, 0, 0, 0, 1,
0, 0, 0, 88, 0, 0, 0, 1, 0, 0, 0, 28, 0, 0, 0, 0, 4, 83, 67, 0,
9, 16, 0, 164, 0, 0, 0, 60, 0, 0, 0, 6, 0, 0, 0, 6, 0, 0, 0, 1,
0, 0, 0, 4, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 101,
110, 116, 114, 121, 80, 111, 105, 110, 116, 80, 97, 114, 97, 109, 115, 95, 105, 111, 66, 117,
102, 102, 101, 114, 95, 48, 0, 60, 0, 0, 0, 1, 0, 0, 0, 112, 0, 0, 0, 4,
0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 136, 0, 0, 0, 0, 0, 0, 0, 4,
0, 0, 0, 2, 0, 0, 0, 148, 0, 0, 0, 0, 0, 0, 0, 36, 69, 108, 101, 109,
101, 110, 116, 0, 171, 171, 171, 0, 0, 3, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0,
0, 0, 0, 77, 105, 99, 114, 111, 115, 111, 102, 116, 32, 40, 82, 41, 32, 72, 76, 83,
76, 32, 83, 104, 97, 100, 101, 114, 32, 67, 111, 109, 112, 105, 108, 101, 114, 32, 49, 48,
46, 49, 0, 73, 83, 71, 78, 8, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 79,
83, 71, 78, 8, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 83, 72, 69, 88, 240,
0, 0, 0, 64, 0, 5, 0, 60, 0, 0, 0, 106, 8, 0, 1, 158, 0, 0, 4, 0,
224, 17, 0, 0, 0, 0, 0, 4, 0, 0, 0, 95, 0, 0, 2, 18, 0, 2, 0, 104,
0, 0, 2, 1, 0, 0, 0, 155, 0, 0, 4, 4, 0, 0, 0, 1, 0, 0, 0, 1,
0, 0, 0, 167, 0, 0, 8, 18, 0, 16, 0, 0, 0, 0, 0, 10, 0, 2, 0, 1,
64, 0, 0, 0, 0, 0, 0, 6, 224, 17, 0, 0, 0, 0, 0, 49, 0, 0, 7, 34,
0, 16, 0, 0, 0, 0, 0, 10, 0, 16, 0, 0, 0, 0, 0, 1, 64, 0, 0, 0,
0, 0, 63, 0, 0, 0, 7, 66, 0, 16, 0, 0, 0, 0, 0, 10, 0, 16, 0, 0,
0, 0, 0, 10, 0, 16, 0, 0, 0, 0, 0, 75, 0, 0, 5, 18, 0, 16, 0, 0,
0, 0, 0, 10, 0, 16, 0, 0, 0, 0, 0, 55, 0, 0, 9, 18, 0, 16, 0, 0,
0, 0, 0, 26, 0, 16, 0, 0, 0, 0, 0, 42, 0, 16, 0, 0, 0, 0, 0, 10,
0, 16, 0, 0, 0, 0, 0, 168, 0, 0, 8, 18, 224, 17, 0, 0, 0, 0, 0, 10,
0, 2, 0, 1, 64, 0, 0, 0, 0, 0, 0, 10, 0, 16, 0, 0, 0, 0, 0, 62,
0, 0, 1, 83, 84, 65, 84, 116, 0, 0, 0, 7, 0, 0, 0, 1, 0, 0, 0, 0,
0, 0, 0, 1, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, };
void computeMain_wrapper(gfx_Device_0* device, Vector<uint32_t, 3> gridDims,
RWStructuredBuffer<float> buffer)
{
gfx_ShaderProgram_0* shaderProgram = loadShaderProgram_0(device);
gfx_TransientResourceHeap_0* transientHeap = buildTransientHeap_0(device);
gfx_PipelineState_0* pipelineState = buildPipelineState_0(device, shaderProgram);
gfx_ResourceView_0* bufferView = createBufferView_0(device, unconvertBuffer_0(buffer));
dispatchComputation_0(device, transientHeap, pipelineState, bufferView, gridDims.x, gridDims.y, gridDims.z);
}
#line 8 "../../../examples/heterogeneous-hello-world/shader.slang"
struct EntryPointParams_0
{
RWStructuredBuffer<float> ioBuffer_0;
};
#line 21
struct gfx_Device_0
{
};
#line 22
struct gfx_BufferResource_0
{
};
#line 23
struct gfx_ResourceView_0
{
};
#line 8
void _computeMain(void* _S1, void* entryPointParams_0, void* _S2)
{
#line 8
ComputeThreadVaryingInput* _S3 = (slang_bit_cast<ComputeThreadVaryingInput*>(_S1));
uint32_t tid_0 = (*(&_S3->groupID) * make_VecU3(4U, 1U, 1U) + *(&_S3->groupThreadID)).x;
float* _S4 = &(*(&(slang_bit_cast<EntryPointParams_0*>(entryPointParams_0))->ioBuffer_0))[tid_0];
#line 12
float i_0 = *_S4;
bool _S5 = i_0 < 0.50000000000000000000f;
#line 13
float _S6 = i_0 + i_0;
#line 13
float _S7 = (F32_sqrt((i_0)));
#line 13
float o_0 = _S5 ? _S6 : _S7;
float* _S8 = &(*(&(slang_bit_cast<EntryPointParams_0*>(entryPointParams_0))->ioBuffer_0))[tid_0];
#line 15
*_S8 = o_0;
return;
}
#line 31
gfx_Device_0* createDevice_0();
gfx_BufferResource_0* createStructuredBuffer_0(gfx_Device_0* _0, FixedArray<float, 4> _1);
gfx_ResourceView_0* createBufferView_0(gfx_Device_0* _0, gfx_BufferResource_0* _1);
#line 4
RWStructuredBuffer<float> convertBuffer_0(gfx_BufferResource_0* _0);
#line 44
void printInitialValues_0(FixedArray<float, 4> _0, int32_t _1);
#line 50
bool printOutputValues_0(gfx_Device_0* _0, gfx_BufferResource_0* _1, int32_t _2);
bool executeComputation_0()
{
FixedArray<float, 4> initialArray_0 = { 3.00000000000000000000f, -20.00000000000000000000f, -6.00000000000000000000f, 8.00000000000000000000f };
gfx_Device_0* _S9 = createDevice_0();
gfx_BufferResource_0* _S10 = createStructuredBuffer_0(_S9, initialArray_0);
gfx_ResourceView_0* _S11 = createBufferView_0(_S9, _S10);
Vector<uint32_t, 3> _S12 = make_VecU3(uint32_t(int(4)), uint32_t(int(1)), uint32_t(int(1)));
RWStructuredBuffer<float> _S13 = convertBuffer_0(_S10);
#line 64
computeMain_wrapper(_S9, _S12, _S13);
printInitialValues_0(initialArray_0, int(4));
bool _S14 = printOutputValues_0(_S9, _S10, int(4));
return true;
}
// [numthreads(4, 1, 1)]
SLANG_PRELUDE_EXPORT
void computeMain_Thread(ComputeThreadVaryingInput* varyingInput, void* entryPointParams, void* globalParams)
{
_computeMain(varyingInput, entryPointParams, globalParams);
}
// [numthreads(4, 1, 1)]
SLANG_PRELUDE_EXPORT
void computeMain_Group(ComputeVaryingInput* varyingInput, void* entryPointParams, void* globalParams)
{
ComputeThreadVaryingInput threadInput = {};
threadInput.groupID = varyingInput->startGroupID;
for (uint32_t x = 0; x < 4; ++x)
{
threadInput.groupThreadID.x = x;
_computeMain(&threadInput, entryPointParams, globalParams);
}
}
// [numthreads(4, 1, 1)]
SLANG_PRELUDE_EXPORT
void computeMain(ComputeVaryingInput* varyingInput, void* entryPointParams, void* globalParams)
{
ComputeVaryingInput vi = *varyingInput;
ComputeVaryingInput groupVaryingInput = {};
for (uint32_t z = vi.startGroupID.z; z < vi.endGroupID.z; ++z)
{
groupVaryingInput.startGroupID.z = z;
for (uint32_t y = vi.startGroupID.y; y < vi.endGroupID.y; ++y)
{
groupVaryingInput.startGroupID.y = y;
for (uint32_t x = vi.startGroupID.x; x < vi.endGroupID.x; ++x)
{
groupVaryingInput.startGroupID.x = x;
computeMain_Group(&groupVaryingInput, entryPointParams, globalParams);
}
}
}
}
|
