blob: db7bd51366fb13c1fd87a87ebf8f5ad3303abd73 (
plain)
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
|
//TEST_IGNORE_FILE: Currently failing due to Spire compiler issues.
//TEST:COMPARE_HLSL: -target dxbc-assembly -profile cs_4_0 -entry BitonicSort -entry MatrixTranspose
//--------------------------------------------------------------------------------------
// File: ComputeShaderSort11.hlsl
//
// This file contains the compute shaders to perform GPU sorting using DirectX 11.
//
// Copyright (c) Microsoft Corporation. All rights reserved.
//--------------------------------------------------------------------------------------
#define BITONIC_BLOCK_SIZE 512
#define TRANSPOSE_BLOCK_SIZE 16
//--------------------------------------------------------------------------------------
// Constant Buffers
//--------------------------------------------------------------------------------------
cbuffer CB : register( b0 )
{
unsigned int g_iLevel;
unsigned int g_iLevelMask;
unsigned int g_iWidth;
unsigned int g_iHeight;
};
//--------------------------------------------------------------------------------------
// Structured Buffers
//--------------------------------------------------------------------------------------
StructuredBuffer<unsigned int> Input : register( t0 );
RWStructuredBuffer<unsigned int> Data : register( u0 );
//--------------------------------------------------------------------------------------
// Bitonic Sort Compute Shader
//--------------------------------------------------------------------------------------
groupshared unsigned int shared_data[BITONIC_BLOCK_SIZE];
[numthreads(BITONIC_BLOCK_SIZE, 1, 1)]
void BitonicSort( uint3 Gid : SV_GroupID,
uint3 DTid : SV_DispatchThreadID,
uint3 GTid : SV_GroupThreadID,
uint GI : SV_GroupIndex )
{
// Load shared data
shared_data[GI] = Data[DTid.x];
GroupMemoryBarrierWithGroupSync();
// Sort the shared data
for (unsigned int j = g_iLevel >> 1 ; j > 0 ; j >>= 1)
{
unsigned int result = ((shared_data[GI & ~j] <= shared_data[GI | j]) == (bool)(g_iLevelMask & DTid.x))? shared_data[GI ^ j] : shared_data[GI];
GroupMemoryBarrierWithGroupSync();
shared_data[GI] = result;
GroupMemoryBarrierWithGroupSync();
}
// Store shared data
Data[DTid.x] = shared_data[GI];
}
//--------------------------------------------------------------------------------------
// Matrix Transpose Compute Shader
//--------------------------------------------------------------------------------------
groupshared unsigned int transpose_shared_data[TRANSPOSE_BLOCK_SIZE * TRANSPOSE_BLOCK_SIZE];
[numthreads(TRANSPOSE_BLOCK_SIZE, TRANSPOSE_BLOCK_SIZE, 1)]
void MatrixTranspose( uint3 Gid : SV_GroupID,
uint3 DTid : SV_DispatchThreadID,
uint3 GTid : SV_GroupThreadID,
uint GI : SV_GroupIndex )
{
transpose_shared_data[GI] = Input[DTid.y * g_iWidth + DTid.x];
GroupMemoryBarrierWithGroupSync();
uint2 XY = DTid.yx - GTid.yx + GTid.xy;
Data[XY.y * g_iHeight + XY.x] = transpose_shared_data[GTid.x * TRANSPOSE_BLOCK_SIZE + GTid.y];
}
|
