DirectXShaderCompiler/tools/clang/test/CodeGenHLSL/Samples/DX11/ComputeShaderSort11.hlsl

// RUN: %dxc -E main -T cs_6_0 %s | FileCheck %s

// CHECK: threadId
// CHECK: flattenedThreadIdInGroup
// CHECK: bufferLoad
// CHECK: addrspace(3)
// CHECK: barrier
// CHECK: addrspace(3)
// CHECK: barrier
// CHECK: addrspace(3)
// CHECK: barrier
// CHECK: addrspace(3)
// CHECK: bufferStore

//--------------------------------------------------------------------------------------
// 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 main( 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];
}