Initial import of code.

1 files changed, 75 insertions, 0 deletions

diff --git a/tests/hlsl/dxsdk/ComputeShaderSort11/ComputeShaderSort11.hlsl b/tests/hlsl/dxsdk/ComputeShaderSort11/ComputeShaderSort11.hlsl
new file mode 100644
index 000000000..db7bd5136
--- /dev/null
+++ b/tests/hlsl/dxsdk/ComputeShaderSort11/ComputeShaderSort11.hlsl
@@ -0,0 +1,75 @@
+//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];
+}