fix spd err.

Packages/com.unity.render-pipelines.universal@14.0.11/Runtime/OcclusionCulling/HierarchicalZOcclusionCullFeature.cs

@@ -351,6 +351,7 @@ namespace X.Rendering.Feature
             {
                 var hizIndex = GetHizIndex();
                 RTHandle hizBuffer = depthPyramidTexs[hizIndex];
+                cmd.BeginSample("Depth-Downsample");
 
                 RenderingUtils.ReAllocateIfNeeded(ref hizBuffer, new RenderTextureDescriptor()
                 {
@@ -360,6 +361,7 @@ namespace X.Rendering.Feature
                     colorFormat = RenderTextureFormat.RFloat,
                     msaaSamples = 1,
                     enableRandomWrite = true,
+                    sRGB = false,
                 }, filterMode: FilterMode.Point, name: depthPyramidNames[hizIndex]);
                 depthPyramidTexs[hizIndex] = hizBuffer;
 
@@ -418,7 +420,10 @@ namespace X.Rendering.Feature
                     // cmd.SetExecutionFlags(CommandBufferExecutionFlags.AsyncCompute);
                     cmd.DispatchCompute(settings.ComputeShader, kernelId, Mathf.CeilToInt(outputMipSize.x / 8f), Mathf.CeilToInt(outputMipSize.y / 8f), 1);
                     mipCnt = mipCnt - 4;
+                    break;
                 }
+                cmd.EndSample("Depth-Downsample");
+
                 cmd.SetGlobalTexture(HizShaderIds.DepthPyramidTexId, hizBuffer);
             }
 
@@ -441,7 +446,7 @@ namespace X.Rendering.Feature
                 var dispatchX = Mathf.CeilToInt(mip0SizeNOP.x / 64f);
                 var dispatchY = Mathf.CeilToInt(mip0SizeNOP.y / 64f);
                 cmd.SetComputeIntParam(settings.Spd, "mips", mipLevelCount);
-                cmd.SetComputeIntParam(settings.Spd, "numWorkGroups", dispatchX);
+                cmd.SetComputeIntParam(settings.Spd, "numWorkGroups", dispatchX * dispatchY);
 
 
                 cmd.SetComputeVectorArrayParam(settings.Spd, "_MipOffsetAndSizeArray", mipOffsetAndSizes);
@@ -469,6 +474,7 @@ namespace X.Rendering.Feature
                 else
                 {
                     cmd.SetGlobalMatrix(HizShaderIds.GPUCullingVPId, world2Project);
+                    cmd.SetViewProjectionMatrices(Matrix4x4.identity, Matrix4x4.identity);
 
                     cmd.SetRenderTarget(cullResult.ResultTex, RenderBufferLoadAction.DontCare, RenderBufferStoreAction.Store);
                     cmd.DrawMesh(RenderingUtils.fullscreenMesh, Matrix4x4.identity, settings.CullMat, 0, 0);

Packages/com.unity.render-pipelines.universal@14.0.11/Runtime/OcclusionCulling/HizObjectsManager.cs

@@ -163,7 +163,7 @@ namespace X.Rendering.Feature
                 for (var i = 0; i < renderers.Count; i++)
                 {
                     var rdr = renderers[i];
-                    if (rdr)
+                    if (rdr && cullResult.ResultArray.IsCreated)
                     {
                         bool needCull = cullResult.ResultArray[i] > 0;
 #if UNITY_EDITOR

Packages/com.unity.render-pipelines.universal@14.0.11/Runtime/OcclusionCulling/Shaders/CopyDepth.shader

@@ -10,7 +10,7 @@ Shader "Hidden/CopyDepth"
             HLSLPROGRAM
             #pragma vertex Vertex
             #pragma fragment DownsampleDepthFrag
-
+#pragma enable_d3d11_debug_symbols
             #include "Packages/com.unity.render-pipelines.universal/ShaderLibrary/Core.hlsl"
 
             struct Attributes

Packages/com.unity.render-pipelines.universal@14.0.11/Runtime/OcclusionCulling/Shaders/DepthPyramid.compute

@@ -2,10 +2,13 @@
 #pragma kernel CSMainMipmapGroup0
 #pragma kernel CSMainMipmapGroup0 _INPUTE_DEPTH_TEXTURE
 #pragma kernel CSMainMipmapGroup0 _INPUTE_DEPTH_TEXTURE _SKIP_3_MIP
+#pragma enable_d3d11_debug_symbols
+#pragma target 5.0
 
 Texture2D<float> _InputDepth;
 
 RWTexture2D<float> _DepthMipChain;
+#include "Packages/com.unity.render-pipelines.core/ShaderLibrary/Common.hlsl"
 
 #if UNITY_REVERSED_Z
 # define MIN_DEPTH(l, r) min(l, r)
@@ -23,27 +26,27 @@ groupshared float _LDSDepths[GROUP_TILE_SIZE * GROUP_TILE_SIZE];
 void CSMainMipmapGroup0(uint3 dispatchThreadId : SV_DispatchThreadID, uint groupThreadIndex : SV_GroupIndex, uint2 groupId : SV_GroupID, uint3 groupThreadID : SV_GroupThreadID)
 {
     uint2 curMipSize = _MipOffsetAndSizeArray[0].zw;
+    if (all(dispatchThreadId.xy < curMipSize.xy))
+    {
         //Mip0从InputeTexture贴图下采样
         float2 uv = dispatchThreadId.xy / float2(curMipSize);
         uv = clamp(uv, 0, 1);
-    int2 texCrood = _InputMipOffsetAndSize.xy + uv * (_InputMipOffsetAndSize.zw);
+        int3 texCrood = int3(_InputMipOffsetAndSize.xy + uv * (_InputMipOffsetAndSize.zw), 0);
-    uint2 maxIndex = _InputMipOffsetAndSize.xy + _InputMipOffsetAndSize.zw - 1;
+        uint2 maxIndex =  int3(_InputMipOffsetAndSize.xy + _InputMipOffsetAndSize.zw - 1,0);
     #ifdef _INPUTE_DEPTH_TEXTURE //第一次Dispath使用Depth Texture
-    float p00 = _InputDepth[min(texCrood + uint2(0, 0), maxIndex)];
+        float p00 = _InputDepth[min(texCrood + uint3(0, 0, 0), maxIndex)];
-    float p01 = _InputDepth[min(texCrood + uint2(1, 0), maxIndex)];
+        float p01 = _InputDepth[min(texCrood + uint3(1, 0, 0), maxIndex)];
-    float p10 = _InputDepth[min(texCrood + uint2(0, 1), maxIndex)];
+        float p10 = _InputDepth[min(texCrood + uint3(0, 1, 0), maxIndex)];
-    float p11 = _InputDepth[min(texCrood + uint2(1, 1), maxIndex)];
+        float p11 = _InputDepth[min(texCrood + uint3(1, 1, 0), maxIndex)];
     #else
-    float p00 = _DepthMipChain[min(texCrood + uint2(0, 0), maxIndex)];
+        float p00 = _DepthMipChain[min(texCrood + uint3(0, 0, 0), maxIndex)];
-    float p01 = _DepthMipChain[min(texCrood + uint2(1, 0), maxIndex)];
+        float p01 = _DepthMipChain[min(texCrood + uint3(1, 0, 0), maxIndex)];
-    float p10 = _DepthMipChain[min(texCrood + uint2(0, 1), maxIndex)];
+        float p10 = _DepthMipChain[min(texCrood + uint3(0, 1, 0), maxIndex)];
-    float p11 = _DepthMipChain[min(texCrood + uint2(1, 1), maxIndex)];
+        float p11 = _DepthMipChain[min(texCrood + uint3(1, 1, 0), maxIndex)];
     #endif
         float4 depths = float4(p00, p10, p01, p11);
         float minDepth = MIN_DEPTH(MIN_DEPTH(depths.x, depths.y), MIN_DEPTH(depths.z, depths.w));
 
-    if (all(dispatchThreadId.xy < curMipSize.xy))
-    {
 #ifndef _SKIP_3_MIP //跳过前3级,不输出到RT
         _DepthMipChain[_MipOffsetAndSizeArray[0].xy + dispatchThreadId.xy] = minDepth;
 #endif
@@ -80,6 +83,11 @@ void CSMainMipmapGroup0(uint3 dispatchThreadId : SV_DispatchThreadID, uint group
         int threadIndex = xy.x + xy.y * TileSize;
         _LDSDepths[threadIndex] = furthestDeviceZ;
     }
+    else
+    {
+        int threadIndex = xy.x + xy.y * TileSize;
+        _LDSDepths[threadIndex] = 0;
+    }
 
     //Mip2
     GroupMemoryBarrierWithGroupSync();
@@ -113,7 +121,11 @@ void CSMainMipmapGroup0(uint3 dispatchThreadId : SV_DispatchThreadID, uint group
         int threadIndex = xy.x + xy.y * TileSize;
         _LDSDepths[threadIndex] = furthestDeviceZ;
     }
-
+    else
+    {
+        int threadIndex = xy.x + xy.y * TileSize;
+        _LDSDepths[threadIndex] = 0;
+    }
     //Mip3
     GroupMemoryBarrierWithGroupSync();
 
@@ -132,7 +144,7 @@ void CSMainMipmapGroup0(uint3 dispatchThreadId : SV_DispatchThreadID, uint group
     parentFurthestDeviceZ.z = _LDSDepths[index2];
     parentFurthestDeviceZ.w = _LDSDepths[index3];
 
-    GroupMemoryBarrierWithGroupSync();
+    // GroupMemoryBarrierWithGroupSync();
     furthestDeviceZ = MIN_DEPTH(MIN_DEPTH(parentFurthestDeviceZ.x, parentFurthestDeviceZ.y), MIN_DEPTH(parentFurthestDeviceZ.z, parentFurthestDeviceZ.w));
     localIndex = dispatchThreadId.xy - (groupId.xy * (GROUP_TILE_SIZE - TileSize)); //因为过滤了3/4的线程组,所以线程索引需要往前补上 
 

Packages/com.unity.render-pipelines.universal@14.0.11/Runtime/OcclusionCulling/Shaders/HizCull.shader

@@ -11,6 +11,7 @@
             #pragma vertex Vertex
             #pragma fragment CullFrag
             #pragma enable_d3d11_debug_symbols
+            #pragma target 5.0
 
             #include "Packages/com.unity.render-pipelines.universal/ShaderLibrary/Core.hlsl"
 
@@ -131,7 +132,6 @@
 
                 float4 offsetAndSize = _MipOffsetAndSize[mip];
                 int4 pxMinMax = boxUVs * offsetAndSize.zwzw + offsetAndSize.xyxy;
-                
                 float4 depth = float4(LOAD_TEXTURE2D_LOD(_DepthPyramidTexture, pxMinMax.xy, 0).r,
                       LOAD_TEXTURE2D_LOD(_DepthPyramidTexture, pxMinMax.zy, 0).r,
                       LOAD_TEXTURE2D_LOD(_DepthPyramidTexture, pxMinMax.xw, 0).r,

Packages/com.unity.render-pipelines.universal@14.0.11/Runtime/OcclusionCulling/Shaders/SPD.compute

@@ -2,6 +2,7 @@
 #pragma kernel CSMain
 #define FFX_SPD_NO_WAVE_OPERATIONS 1
 // #pragma multi_compile FFX_SPD_NO_WAVE_OPERATIONS _ 
+#pragma enable_d3d11_debug_symbols
 
 #define FFX_GPU 1
 #define FFX_HLSL 1
@@ -13,6 +14,8 @@
 
 #include "ffx/ffx_core.h"
 #include "ffx/ffx_common_types.h"
+#include "Packages/com.unity.render-pipelines.core/ShaderLibrary/Common.hlsl"
+
 
 FFX_GROUPSHARED FfxFloat32 spdIntermediate[16][16];
 void SpdStoreIntermediate(FfxUInt32 x, FfxUInt32 y, FfxFloat32x4 value) {
@@ -35,18 +38,18 @@ FfxFloat32x4 SpdLoadIntermediateH(FfxUInt32 x, FfxUInt32 y) {
 }
 
 FfxFloat32x4 SpdReduce4(FfxFloat32x4 v0, FfxFloat32x4 v1, FfxFloat32x4 v2, FfxFloat32x4 v3) {
-    #if FFX_SSSR_OPTION_INVERTED_DEPTH
+    #if UNITY_REVERSED_Z
-    return max(max(v0, v1), max(v2, v3));
-    #else
     return min(min(v0, v1), min(v2, v3));
+    #else
+    return max(max(v0, v1), max(v2, v3));
     #endif
 }
 
 FfxFloat16x4 SpdReduce4H(FfxFloat16x4 v0, FfxFloat16x4 v1, FfxFloat16x4 v2, FfxFloat16x4 v3) {
-    #if FFX_SSSR_OPTION_INVERTED_DEPTH
+    #if UNITY_REVERSED_Z
-    return max(max(v0, v1), max(v2, v3));
-    #else
     return min(min(v0, v1), min(v2, v3));
+    #else
+    return max(max(v0, v1), max(v2, v3));
     #endif
 }
 Texture2D<FfxFloat32>  _InputDepth;
@@ -55,7 +58,8 @@ float4 _MipOffsetAndSizeArray[16];
 
 FfxFloat32x4 SpdLoad(FfxInt32x2 coordinate, FfxUInt32 slice)
 {
-    return _InputDepth[coordinate].xxxx;   // 5 -> 6 as we store a copy of the depth buffer at index 0
+    uint4 cur = _MipOffsetAndSizeArray[6];
+    return _OutDepth[coordinate + cur.xy].xxxx;   // 5 -> 6 as we store a copy of the depth buffer at index 0
 }
 
 void SpdStore(FfxInt32x2 pix, FfxFloat32x4 outValue, FfxUInt32 coordinate, FfxUInt32 slice)
@@ -66,7 +70,8 @@ void SpdStore(FfxInt32x2 pix, FfxFloat32x4 outValue, FfxUInt32 coordinate, FfxUI
 
 FfxFloat32x4 SpdLoadH(FfxInt32x2 coordinate, FfxUInt32 slice)
 {
-    return _InputDepth[coordinate].xxxx;   // 5 -> 6 as we store a copy of the depth buffer at index 0
+    uint4 cur = _MipOffsetAndSizeArray[6];
+    return _OutDepth[coordinate + cur.xy].xxxx;   // 5 -> 6 as we store a copy of the depth buffer at index 0
 }
 
 void SpdStoreH(FfxInt32x2 pix, FfxFloat32x4 outValue, FfxUInt32 coordinate, FfxUInt32 slice)

Packages/com.unity.render-pipelines.universal@14.0.11/Runtime/OcclusionCulling/Shaders/ffx/ffx_spd.h

@@ -971,9 +971,9 @@ void SpdDownsampleH(FfxUInt32x2 workGroupID, FfxUInt32 localInvocationIndex, Ffx
     // compute MIP level 0 and 1
     SpdDownsampleMips_0_1H(x, y, workGroupID, localInvocationIndex, mips, slice);
 
-    // compute MIP level 2, 3, 4, 5
+    // // compute MIP level 2, 3, 4, 5
     SpdDownsampleNextFourH(x, y, workGroupID, localInvocationIndex, 2, mips, slice);
-
+    //
     if (mips < 7)
         return;