Hello guys,

I am working on implementing deferred texturing tecnique.

I have screen-space material ID texture from render G-Buffer pass for which I would like to calculate screen space rectangles encompasing material IDs used for the same mesh type. By mesh type I refer to one pipeline state object permutation used for G-Buffer shading pass. Those screen space rectangles are later used to shade G-Buffer based on mesh type as described in article Deferred+ from GPU Zen. 

My compute shader pass for calculating encompasing rectangles does not produce expected results.

I did some debugging with PIX and I can see that PIX for some reason does not show g_MaterialIDTexture and g_MeshTypePerMaterialIDBuffer in the list of binded resources.

When I step with debugger through the shader code,  reading g_MaterialIDTexture and MeshTypePerMaterialIDBuffer is skipped.  You can see the shader below.

groupshared uint2 g_ScreenMinPoints[NUM_MESH_TYPES];
groupshared uint2 g_ScreenMaxPoints[NUM_MESH_TYPES];

#define NUM_THREADS_PER_GROUP (NUM_THREADS_X * NUM_THREADS_Y)

cbuffer AppDataBuffer : register(b0)
{
	AppData g_AppData;
}

RWStructuredBuffer<uint2> g_ShadingRectangleMinPointBuffer : register(u0);
RWStructuredBuffer<uint2> g_ShadingRectangleMaxPointBuffer : register(u1);

Texture2D<uint> g_MaterialIDTexture : register(t0);
Buffer<uint> g_MeshTypePerMaterialIDBuffer : register(t1);

[numthreads(NUM_THREADS_X, NUM_THREADS_Y, 1)]
void Main(uint3 globalThreadId : SV_DispatchThreadID, uint localThreadIndex : SV_GroupIndex)
{
	for (uint index = localThreadIndex; index < NUM_MESH_TYPES; index += NUM_THREADS_PER_GROUP)
	{
		g_ScreenMinPoints[index] = uint2(0xffffffff, 0xffffffff);
		g_ScreenMaxPoints[index] = uint2(0, 0);
	}
	GroupMemoryBarrierWithGroupSync();

	if ((globalThreadId.x < g_AppData.screenSize.x) && (globalThreadId.y < g_AppData.screenSize.y))
	{
		uint materialID = g_MaterialIDTexture[globalThreadId.xy];
		uint meshType = g_MeshTypePerMaterialIDBuffer[materialID];
				
		InterlockedMin(g_ScreenMinPoints[meshType].x, globalThreadId.x);
		InterlockedMin(g_ScreenMinPoints[meshType].y, globalThreadId.y);

		InterlockedMax(g_ScreenMaxPoints[meshType].x, globalThreadId.x);
		InterlockedMax(g_ScreenMaxPoints[meshType].y, globalThreadId.y);
	}
	GroupMemoryBarrierWithGroupSync();

	for (uint index = localThreadIndex; index < NUM_MESH_TYPES; index += NUM_THREADS_PER_GROUP)
	{
		InterlockedMin(g_ShadingRectangleMinPointBuffer[index].x, g_ScreenMinPoints[index].x);
		InterlockedMin(g_ShadingRectangleMinPointBuffer[index].y, g_ScreenMinPoints[index].y);

		InterlockedMax(g_ShadingRectangleMaxPointBuffer[index].x, g_ScreenMaxPoints[index].x);
		InterlockedMax(g_ShadingRectangleMaxPointBuffer[index].y, g_ScreenMaxPoints[index].y);
	}
}

I checked DXBC output and it does not include them either. 

//
// Generated by Microsoft (R) HLSL Shader Compiler 10.1
//
//
// Buffer Definitions: 
//
// cbuffer AppDataBuffer
// {
//
//   struct AppData
//   {
//       
//       float4x4 viewMatrix;           // Offset:    0
//       float4x4 viewInvMatrix;        // Offset:   64
//       float4x4 projMatrix;           // Offset:  128
//       float4x4 projInvMatrix;        // Offset:  192
//       float4x4 viewProjMatrix;       // Offset:  256
//       float4x4 viewProjInvMatrix;    // Offset:  320
//       float4x4 prevViewProjMatrix;   // Offset:  384
//       float4x4 prevViewProjInvMatrix;// Offset:  448
//       float4x4 notUsed1;             // Offset:  512
//       float4 cameraWorldSpacePos;    // Offset:  576
//       float4 cameraWorldFrustumPlanes[6];// Offset:  592
//       float cameraNearPlane;         // Offset:  688
//       float cameraFarPlane;          // Offset:  692
//       float2 notUsed2;               // Offset:  696
//       uint2 screenSize;              // Offset:  704
//       float2 rcpScreenSize;          // Offset:  712
//       uint2 screenHalfSize;          // Offset:  720
//       float2 rcpScreenHalfSize;      // Offset:  728
//       uint2 screenQuarterSize;       // Offset:  736
//       float2 rcpScreenQuarterSize;   // Offset:  744
//       float4 sunWorldSpaceDir;       // Offset:  752
//       float4 sunLightColor;          // Offset:  768
//       float4 notUsed3[15];           // Offset:  784
//
//   } g_AppData;                       // Offset:    0 Size:  1024
//
// }
//
// Resource bind info for g_ShadingRectangleMinPointBuffer
// {
//
//   uint2 $Element;                    // Offset:    0 Size:     8
//
// }
//
// Resource bind info for g_ShadingRectangleMaxPointBuffer
// {
//
//   uint2 $Element;                    // Offset:    0 Size:     8
//
// }
//
//
// Resource Bindings:
//
// Name                                 Type  Format         Dim      HLSL Bind  Count
// ------------------------------ ---------- ------- ----------- -------------- ------
// g_ShadingRectangleMinPointBuffer        UAV  struct         r/w             u0      1 
// g_ShadingRectangleMaxPointBuffer        UAV  struct         r/w             u1      1 
// AppDataBuffer                     cbuffer      NA          NA            cb0      1 
//
//
//
// Input signature:
//
// Name                 Index   Mask Register SysValue  Format   Used
// -------------------- ----- ------ -------- -------- ------- ------
// no Input
//
// Output signature:
//
// Name                 Index   Mask Register SysValue  Format   Used
// -------------------- ----- ------ -------- -------- ------- ------
// no Output
      0x00000000: cs_5_0
      0x00000008: dcl_globalFlags refactoringAllowed | skipOptimization
      0x0000000C: dcl_constantbuffer CB0[45], immediateIndexed
      0x0000001C: dcl_uav_structured u0, 8
      0x0000002C: dcl_uav_structured u1, 8
      0x0000003C: dcl_input vThreadIDInGroupFlattened
      0x00000044: dcl_input vThreadID.xy
      0x0000004C: dcl_temps 2
      0x00000054: dcl_tgsm_structured g0, 8, 1
      0x00000068: dcl_tgsm_structured g1, 8, 1
      0x0000007C: dcl_thread_group 16, 16, 1
//
// Initial variable locations:
//   vThreadID.x <- globalThreadId.x; vThreadID.y <- globalThreadId.y; vThreadID.z <- globalThreadId.z; 
//   vThreadIDInGroupFlattened.x <- localThreadIndex
//
#line 22 "D:\GitHub\RenderSDK\Samples\Bin\DynamicGI\Shaders\CalcShadingRectanglesCS.hlsl"
   0  0x0000008C: mov r0.x, vThreadIDInGroupFlattened.x
   1  0x0000009C: mov r0.y, r0.x
   2  0x000000B0: loop 
   3  0x000000B4:   mov r0.z, l(1)
   4  0x000000C8:   ult r0.z, r0.y, r0.z
   5  0x000000E4:   breakc_z r0.z

#line 24
   6  0x000000F0:   store_structured g0.x, l(0), l(0), l(-1)
   7  0x00000114:   store_structured g0.x, l(0), l(4), l(-1)

#line 25
   8  0x00000138:   mov r0.zw, l(0,0,0,0)
   9  0x00000158:   store_structured g1.x, l(0), l(0), r0.z
  10  0x0000017C:   store_structured g1.x, l(0), l(4), r0.w

#line 26
  11  0x000001A0:   mov r0.z, l(256)
  12  0x000001B4:   iadd r0.y, r0.z, r0.y
  13  0x000001D0: endloop 

#line 27
  14  0x000001D4: sync_g_t

#line 29
  15  0x000001D8: ult r0.x, vThreadID.x, cb0[44].x
  16  0x000001F4: ult r0.y, vThreadID.y, cb0[44].y
  17  0x00000210: and r0.x, r0.y, r0.x
  18  0x0000022C: if_nz r0.x

#line 34
  19  0x00000238:   atomic_umin g0, l(0, 0, 0, 0), vThreadID.x

#line 35
  20  0x0000025C:   atomic_umin g0, l(0, 4, 0, 0), vThreadID.y

#line 37
  21  0x00000280:   atomic_umax g1, l(0, 0, 0, 0), vThreadID.x

#line 38
  22  0x000002A4:   atomic_umax g1, l(0, 4, 0, 0), vThreadID.y

#line 39
  23  0x000002C8: endif 

#line 40
  24  0x000002CC: sync_g_t

#line 42
  25  0x000002D0: mov r0.x, vThreadIDInGroupFlattened.x  // r0.x <- index
  26  0x000002E0: mov r1.x, r0.x  // r1.x <- index
  27  0x000002F4: loop 
  28  0x000002F8:   mov r0.y, l(1)
  29  0x0000030C:   ult r0.y, r1.x, r0.y
  30  0x00000328:   breakc_z r0.y

#line 44
  31  0x00000334:   ld_structured r0.y, l(0), l(0), g0.xxxx
  32  0x00000358:   mov r1.y, l(0)
  33  0x0000036C:   atomic_umin u0, r1.xyxx, r0.y

#line 45
  34  0x00000388:   ld_structured r0.y, l(0), l(4), g0.xxxx
  35  0x000003AC:   mov r1.z, l(4)
  36  0x000003C0:   atomic_umin u0, r1.xzxx, r0.y

#line 47
  37  0x000003DC:   ld_structured r0.y, l(0), l(0), g1.xxxx
  38  0x00000400:   atomic_umax u1, r1.xyxx, r0.y

#line 48
  39  0x0000041C:   ld_structured r0.y, l(0), l(4), g1.xxxx
  40  0x00000440:   atomic_umax u1, r1.xzxx, r0.y

#line 49
  41  0x0000045C:   mov r0.y, l(256)
  42  0x00000470:   iadd r1.x, r0.y, r1.x
  43  0x0000048C: endloop 

#line 50
  44  0x00000490: ret 
// Approximately 45 instruction slots used

Looks like compiler optimizes them away but I do not understand why. Any ideas? :-)

Thanks,

You didn't provide a fully compilable repro, so I had to guess the missing bits, but on the compiler I have here there's references to g_MaterialIDTexture and g_MeshTypePerMaterialIDBuffer in the DXBC. Can you provide something that compiles?

@ajmiles Updated shader

struct AppData
{
	float4x4 viewMatrix;
	float4x4 viewInvMatrix;
	float4x4 projMatrix;
	float4x4 projInvMatrix;

	float4x4 viewProjMatrix;
	float4x4 viewProjInvMatrix;
	float4x4 prevViewProjMatrix;
	float4x4 prevViewProjInvMatrix;

	float4x4 notUsed1;
	float4 cameraWorldSpacePos;
	float4 cameraWorldFrustumPlanes[6];
	float cameraNearPlane;
	float cameraFarPlane;
	float2 notUsed2;
	uint2 screenSize;
	float2 rcpScreenSize;
	uint2 screenHalfSize;
	float2 rcpScreenHalfSize;
	uint2 screenQuarterSize;
	float2 rcpScreenQuarterSize;
	float4 sunWorldSpaceDir;

	float4 sunLightColor;
	float4 notUsed3[15];
};

#define NUM_MESH_TYPES 1
#define NUM_THREADS_X 16
#define NUM_THREADS_Y 16

groupshared uint2 g_ScreenMinPoints[NUM_MESH_TYPES];
groupshared uint2 g_ScreenMaxPoints[NUM_MESH_TYPES];

#define NUM_THREADS_PER_GROUP (NUM_THREADS_X * NUM_THREADS_Y)

cbuffer AppDataBuffer : register(b0)
{
	AppData g_AppData;
}

RWStructuredBuffer<uint2> g_ShadingRectangleMinPointBuffer : register(u0);
RWStructuredBuffer<uint2> g_ShadingRectangleMaxPointBuffer : register(u1);

Texture2D<uint> g_MaterialIDTexture : register(t0);
Buffer<uint> g_MeshTypePerMaterialIDBuffer : register(t1);

[numthreads(NUM_THREADS_X, NUM_THREADS_Y, 1)]
void main(uint3 globalThreadId : SV_DispatchThreadID, uint localThreadIndex : SV_GroupIndex)
{
	for (uint index = localThreadIndex; index < NUM_MESH_TYPES; index += NUM_THREADS_PER_GROUP)
	{
		g_ScreenMinPoints[index] = uint2(0xffffffff, 0xffffffff);
		g_ScreenMaxPoints[index] = uint2(0, 0);
	}
	GroupMemoryBarrierWithGroupSync();

	if ((globalThreadId.x < g_AppData.screenSize.x) && (globalThreadId.y < g_AppData.screenSize.y))
	{
		uint materialID = g_MaterialIDTexture[globalThreadId.xy];
		uint meshType = g_MeshTypePerMaterialIDBuffer[materialID];
				
		InterlockedMin(g_ScreenMinPoints[meshType].x, globalThreadId.x);
		InterlockedMin(g_ScreenMinPoints[meshType].y, globalThreadId.y);

		InterlockedMax(g_ScreenMaxPoints[meshType].x, globalThreadId.x);
		InterlockedMax(g_ScreenMaxPoints[meshType].y, globalThreadId.y);
	}
	GroupMemoryBarrierWithGroupSync();

	for (uint index = localThreadIndex; index < NUM_MESH_TYPES; index += NUM_THREADS_PER_GROUP)
	{
		InterlockedMin(g_ShadingRectangleMinPointBuffer[index].x, g_ScreenMinPoints[index].x);
		InterlockedMin(g_ShadingRectangleMinPointBuffer[index].y, g_ScreenMinPoints[index].y);

		InterlockedMax(g_ShadingRectangleMaxPointBuffer[index].x, g_ScreenMaxPoints[index].x);
		InterlockedMax(g_ShadingRectangleMaxPointBuffer[index].y, g_ScreenMaxPoints[index].y);
	}
}

The compiler has deduced that since the size of the g_ScreenMinPoints and g_ScreenMaxPoints array is 1, the only valid index must be 0. If the only valid index is 0, it can infer that "meshType" must be 0. If it can infer meshType is 0 then there's no point in reading g_MaterialIDTexture or g_MeshTypePerMaterialIDBuffer.

The compiler can InterlockedMin/Max on g_Screen[Min|Max]Points[0] and not bother reading either of your input textures.

@ajmilesNow I understand :-)

I am using MAX_INT as meshType for those pixels in the screen where geometry is missing.

I was hoping that writes out of the array boundaries at index MAX_INT will be ignored.

But in this case compiler just optimized away the code.

I have added explicit check against MAX_INT and everything works now. Thanks a million!

if (meshType != MAX_INT)
{
  InterlockedMin(g_ScreenMinPoints[meshType].x, globalThreadId.x);
  InterlockedMin(g_ScreenMinPoints[meshType].y, globalThreadId.y);

  InterlockedMax(g_ScreenMaxPoints[meshType].x, globalThreadId.x);
  InterlockedMax(g_ScreenMaxPoints[meshType].y, globalThreadId.y);
}

13 minutes ago, _void_ said:

I was hoping that writes out of the array boundaries at index MAX_INT will be ignored.

I'm afraid not. Out of bounds writes to group shared memory cause the entire contents of shared memory to become undefined. You might be thinking of UAV writes which do discard out of bound writes.