标签:iat 技术 volume tor box sample ptr else order
【目标】
编译UNREALPORJECT2工程
【思路】
1
2
3
一件衣服23932个面
vs:
//
// Generated by Microsoft (R) HLSL Shader Compiler 6.3.9600.17672
//
//
// Buffer Definitions:
//
// cbuffer WorldBuffer
// {
//
// struct WorldStruct
// {
//
// row_major float4x4 ViewProject;// Offset: 0
//
// struct WorldStruct_PerInstanceData
// {
//
// row_major float4x4 World; // Offset: 64
// row_major float4x4 WorldViewProject;// Offset: 128
//
// } PerInstance[256]; // Offset: 64
//
// } WorldParameters; // Offset: 0 Size: 32832
//
// }
//
// cbuffer SkinningBuffer
// {
//
// struct SkinningStruct
// {
//
// float NumSkinMatricesPerInstance;// Offset: 0
// row_major float4x4 SkinMatrices[1023];// Offset: 16
//
// } SkinningParameters; // Offset: 0 Size: 65488
//
// }
//
// cbuffer SceneBuffer
// {
//
// row_major float4x4 View; // Offset: 0 Size: 64 [unused]
// row_major float4x4 ScreenMatrix; // Offset: 64 Size: 64 [unused]
// float2 DepthExportScale; // Offset: 128 Size: 8 [unused]
// float2 __padding0; // Offset: 136 Size: 8 [unused]
// float4 FogParams; // Offset: 144 Size: 16 [unused]
// float3 __CameraPosition; // Offset: 160 Size: 12 [unused]
// float __padding12; // Offset: 172 Size: 4 [unused]
// float3 CameraDirection; // Offset: 176 Size: 12 [unused]
// float __padding9; // Offset: 188 Size: 4 [unused]
// float3 DepthFactors; // Offset: 192 Size: 12 [unused]
// float __padding10; // Offset: 204 Size: 4 [unused]
// float3 ShadowDepthBiasAndLightType;// Offset: 208 Size: 12 [unused]
// float __padding11; // Offset: 220 Size: 4 [unused]
// float4 SubframeViewport; // Offset: 224 Size: 16 [unused]
// row_major float3x4 DepthToWorld; // Offset: 240 Size: 48 [unused]
// float4 DepthToView; // Offset: 288 Size: 16 [unused]
// float4 OneOverDepthToView; // Offset: 304 Size: 16 [unused]
// float4 DepthToW; // Offset: 320 Size: 16 [unused]
// float4 ClipPlane; // Offset: 336 Size: 16 [unused]
// float2 ViewportDepthScaleOffset; // Offset: 352 Size: 8 [unused]
// float2 __padding1; // Offset: 360 Size: 8 [unused]
// float2 ColorDOFDepthScaleOffset; // Offset: 368 Size: 8 [unused]
// float2 __padding2; // Offset: 376 Size: 8 [unused]
// float4 TimeVector; // Offset: 384 Size: 16
// float4 FogParams2; // Offset: 400 Size: 16 [unused]
// float4 FogParams3; // Offset: 416 Size: 16 [unused]
// float3 GlobalAmbient; // Offset: 432 Size: 12 [unused]
// float __padding8; // Offset: 444 Size: 4 [unused]
// float4 GlobalParams[16]; // Offset: 448 Size: 256 [unused]
// float4 ViewToFogH; // Offset: 704 Size: 16 [unused]
// float4 ScreenExtents; // Offset: 720 Size: 16 [unused]
// float2 ScreenResolution; // Offset: 736 Size: 8 [unused]
// float2 __padding3; // Offset: 744 Size: 8 [unused]
// float4 PSSMToMap1Lin; // Offset: 752 Size: 16 [unused]
// float4 PSSMToMap1Const; // Offset: 768 Size: 16 [unused]
// float4 PSSMToMap2Lin; // Offset: 784 Size: 16 [unused]
// float4 PSSMToMap2Const; // Offset: 800 Size: 16 [unused]
// float4 PSSMToMap3Lin; // Offset: 816 Size: 16 [unused]
// float4 PSSMToMap3Const; // Offset: 832 Size: 16 [unused]
// float4 PSSMDistances; // Offset: 848 Size: 16 [unused]
// row_major float4x4 WorldToPSSM0; // Offset: 864 Size: 64 [unused]
// row_major float4x4 PrevViewProject;// Offset: 928 Size: 64 [unused]
// row_major float4x4 PrevWorld; // Offset: 992 Size: 64 [unused]
// row_major float4x4 ViewT; // Offset: 1056 Size: 64 [unused]
// float4 PSSMExtents; // Offset: 1120 Size: 16 [unused]
// float4 ShadowAtlasResolution; // Offset: 1136 Size: 16 [unused]
// float4 UnitRimData[3]; // Offset: 1152 Size: 48 [unused]
// float3 __CameraPositionForCorrection;// Offset: 1200 Size: 12
// float __padding7; // Offset: 1212 Size: 4 [unused]
// row_major float4x4 CameraViewProject;// Offset: 1216 Size: 64 [unused]
// float4 BackBufferResolution; // Offset: 1280 Size: 16 [unused]
// row_major float4x4 InverseProjection;// Offset: 1296 Size: 64 [unused]
// float4 StereoOffset; // Offset: 1360 Size: 16 [unused]
// row_major float4x4 Projection; // Offset: 1376 Size: 64 [unused]
// row_major float4x4 ViewInv; // Offset: 1440 Size: 64 [unused]
// float4 ColorSSAO; // Offset: 1504 Size: 16 [unused]
// float4 GlobalFogColor; // Offset: 1520 Size: 16 [unused]
// float4 VolumetricLightGlobalParams;// Offset: 1536 Size: 16 [unused]
// float4 SnowParams01; // Offset: 1552 Size: 16 [unused]
// float4 SnowParams02; // Offset: 1568 Size: 16 [unused]
// float4 SnowParams03; // Offset: 1584 Size: 16 [unused]
// int SSREnabled; // Offset: 1600 Size: 4 [unused]
// int __padding4; // Offset: 1604 Size: 4 [unused]
// int __padding5; // Offset: 1608 Size: 4 [unused]
// int __padding6; // Offset: 1612 Size: 4 [unused]
//
// }
//
// cbuffer StreamDeclBuffer
// {
//
// float4 NormalScaleOffset; // Offset: 0 Size: 16
// float4 TexcoordScales; // Offset: 16 Size: 16
//
// }
//
// cbuffer MaterialBuffer
// {
//
// float4 MaterialParams[512]; // Offset: 0 Size: 8192
//
// }
//
// cbuffer InstanceBuffer
// {
//
// struct InstanceStruct
// {
//
// float4 InstanceParams[8]; // Offset: 0
//
// } InstanceParameters[256]; // Offset: 0 Size: 32768
//
// }
//
//
// Resource Bindings:
//
// Name Type Format Dim Slot Elements
// ------------------------------ ---------- ------- ----------- ---- --------
// WorldBuffer cbuffer NA NA 0 1
// SkinningBuffer cbuffer NA NA 1 1
// SceneBuffer cbuffer NA NA 2 1
// StreamDeclBuffer cbuffer NA NA 3 1
// MaterialBuffer cbuffer NA NA 4 1
// InstanceBuffer cbuffer NA NA 5 1
//
//
//
// Input signature:
//
// Name Index Mask Register SysValue Format Used
// -------------------- ----- ------ -------- -------- ------- ------
// NORMAL 0 xyz 0 NONE float xyz
// BLENDWEIGHT 0 xyzw 1 NONE float xyzw
// BLENDINDICES 0 xyzw 2 NONE float xyzw
// COLOR 0 xyzw 3 NONE float x
// TEXCOORD 0 xyzw 4 NONE float xy
// POSITION 0 xyz 5 NONE float xyz
// SV_InstanceID 0 x 6 INSTID uint x
// SV_VertexID 0 x 7 VERTID uint
//
//
// Output signature:
//
// Name Index Mask Register SysValue Format Used
// -------------------- ----- ------ -------- -------- ------- ------
// SV_POSITION 0 xyzw 0 POS float xyzw
// COLOR 1 xyzw 1 NONE float xyzw
// TEXCOORD 0 xyzw 2 NONE float xyzw
// TEXCOORD 2 xyz 3 NONE float xyz
// PSIZE 0 x 4 NONE uint x
//
vs_5_0
dcl_globalFlags refactoringAllowed
dcl_constantbuffer cb0[4], immediateIndexed
dcl_constantbuffer cb1[4093], dynamicIndexed
dcl_constantbuffer cb2[76], immediateIndexed
dcl_constantbuffer cb3[2], immediateIndexed
dcl_constantbuffer cb4[1], immediateIndexed
dcl_constantbuffer cb5[2046], dynamicIndexed
dcl_input v0.xyz
dcl_input v1.xyzw
dcl_input v2.xyzw
dcl_input v3.x
dcl_input v4.xy
dcl_input v5.xyz
dcl_input_sgv v6.x, instance_id
dcl_output_siv o0.xyzw, position
dcl_output o1.xyzw
dcl_output o2.xyzw
dcl_output o3.xyz
dcl_output o4.x
dcl_temps 7
ishl r0.x, v6.x, l(3)
mul r0.xyz, cb2[24].xxxx, cb5[r0.x + 5].xyzx
mul r0.xyz, r0.xyzx, cb4[0].yyyy
mul r0.xyz, r0.xyzx, v5.xyzx
mul r0.xyz, r0.xyzx, l(0.005000, 0.005000, 0.005000, 0.000000)
sincos r0.xyz, null, r0.xyzx
mul r0.xyz, r0.xyzx, cb4[0].xxxx
utof r0.w, v6.x
mul r0.w, r0.w, cb1[0].x
round_z r0.w, r0.w
mul r1.xyzw, v2.xyzw, l(255.000000, 255.000000, 255.000000, 255.000000)
round_ne r1.xyzw, r1.xyzw
add r1.xyzw, r0.wwww, r1.xyzw
ftou r1.xyzw, r1.xyzw
ishl r1.xyzw, r1.xyzw, l(2, 2, 2, 2)
mul r2.xyzw, v1.yyyy, cb1[r1.y + 1].xyzw
mad r2.xyzw, cb1[r1.x + 1].xyzw, v1.xxxx, r2.xyzw
mad r2.xyzw, cb1[r1.z + 1].xyzw, v1.zzzz, r2.xyzw
mad r2.xyzw, cb1[r1.w + 1].xyzw, v1.wwww, r2.xyzw
mov r3.xyz, v5.xyzx
mov r3.w, l(1.000000)
dp4 r4.x, r2.xyzw, r3.xyzw
mul r5.xyzw, v1.yyyy, cb1[r1.y + 2].xyzw
mad r5.xyzw, cb1[r1.x + 2].xyzw, v1.xxxx, r5.xyzw
mad r5.xyzw, cb1[r1.z + 2].xyzw, v1.zzzz, r5.xyzw
mad r5.xyzw, cb1[r1.w + 2].xyzw, v1.wwww, r5.xyzw
dp4 r4.y, r5.xyzw, r3.xyzw
mul r6.xyzw, v1.yyyy, cb1[r1.y + 3].xyzw
mad r6.xyzw, cb1[r1.x + 3].xyzw, v1.xxxx, r6.xyzw
mad r6.xyzw, cb1[r1.z + 3].xyzw, v1.zzzz, r6.xyzw
mad r6.xyzw, cb1[r1.w + 3].xyzw, v1.wwww, r6.xyzw
dp4 r4.z, r6.xyzw, r3.xyzw
mad r0.xyz, r0.xyzx, v3.xxxx, r4.xyzx
add r0.xyz, r0.xyzx, -cb2[75].xyzx
mul r3.xyzw, r0.yyyy, cb0[1].xyzw
mad r3.xyzw, r0.xxxx, cb0[0].xyzw, r3.xyzw
mad r0.xyzw, r0.zzzz, cb0[2].xyzw, r3.xyzw
add o0.xyzw, r0.xyzw, cb0[3].xyzw
mul r0.xyzw, v1.yyyy, cb1[r1.y + 4].xyzw
mad r0.xyzw, cb1[r1.x + 4].xyzw, v1.xxxx, r0.xyzw
mad r0.xyzw, cb1[r1.z + 4].xyzw, v1.zzzz, r0.xyzw
mad r0.xyzw, cb1[r1.w + 4].xyzw, v1.wwww, r0.xyzw
and r1.xyzw, r0.xyzw, l(0x7f800000, 0x7f800000, 0x7f800000, 0x7f800000)
ine r1.xyzw, r1.xyzw, l(0x7f800000, 0x7f800000, 0x7f800000, 0x7f800000)
and o1.xyzw, r0.xyzw, r1.xyzw
mul o2.xy, v4.xyxx, cb3[1].xxxx
mov o2.zw, l(0,0,0,0)
mad r0.xyz, cb3[0].xxxx, v0.xyzx, cb3[0].yyyy
dp3 o3.x, r2.xyzx, r0.xyzx
dp3 o3.y, r5.xyzx, r0.xyzx
dp3 o3.z, r6.xyzx, r0.xyzx
mov o4.x, v6.x
ret
// Approximately 53 instruction slots used
PS:
//
// Generated by Microsoft (R) HLSL Shader Compiler 10.0.10011.16384
//
//
// Buffer Definitions:
//
// cbuffer VoxelizationCB
// {
//
// struct VxgiVoxelizationConstants
// {
//
// float4 GridCenter; // Offset: 0
// float4 GridCenterPrevious; // Offset: 16
// int4 ToroidalOffset; // Offset: 32
//
// struct VxgiBox4f
// {
//
// float4 lower; // Offset: 48
// float4 upper; // Offset: 64
//
// } ScissorRegionsClipSpace[5]; // Offset: 48
// int4 TextureToAmapTranslation[5];// Offset: 208
// float IrradianceMapSize; // Offset: 288
// uint ClipLevelSize; // Offset: 292
// uint PackingStride; // Offset: 296
// uint AllocationMapSize; // Offset: 300
// uint ClipLevelMask; // Offset: 304
// uint MaxClipLevel; // Offset: 308
// int FirstLevelToDiscard; // Offset: 312
// float DiscardLower; // Offset: 316
// float DiscardUpper; // Offset: 320
// float DiscardClipSpace; // Offset: 324
// uint UseCullFunction; // Offset: 328
// float EmittanceStorageScale; // Offset: 332
// uint UseIrradianceMap; // Offset: 336
// uint Use6DOpacity; // Offset: 340
// uint UseFP32Emittance; // Offset: 344
// uint PersistentVoxelData; // Offset: 348
// uint UseInvalidateBitmap; // Offset: 352
//
// } g_VxgiVoxelizationCB; // Offset: 0 Size: 356
//
// }
//
// cbuffer VoxelizationMaterialCB
// {
//
// struct VxgiVoxelizationMaterialConstants
// {
//
// float4 ResolutionFactors[5]; // Offset: 0
// float NoiseScale; // Offset: 80
// float NoiseBias; // Offset: 84
// int TwoSided; // Offset: 88
// int ProportionalEmittance; // Offset: 92
// int DepthSamples; // Offset: 96
// int FrontCCW; // Offset: 100
// int OmnidirectionalLight; // Offset: 104
//
// } g_VxgiVoxelizationMaterialCB; // Offset: 0 Size: 108
//
// }
//
// Resource bind info for t_VoxelizationCoverageMasks
// {
//
// uint4 $Element; // Offset: 0 Size: 16
//
// }
//
//
// Resource Bindings:
//
// Name Type Format Dim Slot Elements
// ------------------------------ ---------- ------- ----------- ---- --------
// t_VoxelizationCoverageMasks texture struct r/o 1 1
// u_AllocationMap UAV uint 3d 1 1
// u_CoverageTextureXYZ_Pos UAV uint 3d 2 1
// u_CoverageTextureXYZ_Neg UAV uint 3d 3 1
// VoxelizationCB cbuffer NA NA 1 1
// VoxelizationMaterialCB cbuffer NA NA 2 1
//
//
//
// Input signature:
//
// Name Index Mask Register SysValue Format Used
// -------------------- ----- ------ -------- -------- ------- ------
// SV_Position 0 xyzw 0 POS float xyz
// SV_ViewportArrayIndex 0 x 1 VPINDEX uint x
// SV_IsFrontFace 0 x 2 FFACE uint x
//
//
// Output signature:
//
// Name Index Mask Register SysValue Format Used
// -------------------- ----- ------ -------- -------- ------- ------
// no Output
ps_5_0
dcl_globalFlags refactoringAllowed
dcl_constantbuffer cb1[23], dynamicIndexed
dcl_constantbuffer cb2[7], immediateIndexed
dcl_resource_structured t1, 16
dcl_uav_typed_texture3d (uint,uint,uint,uint) u1
dcl_uav_typed_texture3d (uint,uint,uint,uint) u2
dcl_uav_typed_texture3d (uint,uint,uint,uint) u3
dcl_input_ps_siv linear noperspective v0.xyz, position
dcl_input_ps_siv constant v1.x, viewport_array_index
dcl_input_ps_sgv v2.x, is_front_face
dcl_input vCoverage
dcl_temps 12
utof r0.x, v1.x
mul r0.x, r0.x, l(0.334000)
frc r0.y, r0.x
mul r0.y, r0.y, l(3.000000)
round_ni r0.xy, r0.xyxx
ftoi r0.xy, r0.xyxx
iadd r0.z, -r0.x, cb1[19].y
ishl r0.z, l(1), r0.z
itof r0.z, r0.z
mul r0.z, r0.z, v0.z
mad r0.z, r0.z, l(0.500000), l(0.500000)
utof r0.w, cb1[18].y
mul r1.x, r0.w, r0.z
round_ne r1.y, r1.x
mad r1.y, r0.z, r0.w, -r1.y
lt r1.y, |r1.y|, l(0.007813)
mad r0.z, r0.z, r0.w, l(0.015625)
movc r1.y, r1.y, r0.z, r1.x
add r1.x, r0.w, -v0.y
if_z r0.y
ishl r0.z, r0.x, l(1)
lt r0.w, v0.z, cb1[r0.z + 3].z
lt r0.z, cb1[r0.z + 4].z, v0.z
or r0.z, r0.z, r0.w
mov r2.x, v0.x
mov r2.yz, r1.xxyx
mov r3.xyz, l(0,0,1,0)
else
ieq r0.w, r0.y, l(1)
if_nz r0.w
ishl r0.w, r0.x, l(1)
lt r2.w, v0.z, cb1[r0.w + 3].y
lt r0.w, cb1[r0.w + 4].y, v0.z
or r0.z, r0.w, r2.w
mov r1.z, v0.x
mov r2.xyz, r1.xyzx
mov r3.xy, l(0,1,0,0)
else
ishl r0.w, r0.x, l(1)
lt r1.z, v0.z, cb1[r0.w + 3].x
lt r0.w, cb1[r0.w + 4].x, v0.z
or r0.z, r0.w, r1.z
mov r1.w, v0.x
mov r2.xyz, r1.ywxy
mov r3.xy, l(1,0,0,0)
endif
mov r3.z, l(0)
endif
discard_nz r0.z
if_z r0.z
not r0.z, v2.x
movc r0.z, cb2[6].y, r0.z, v2.x
round_ni r1.xzw, r2.xxyz
ftoi r1.xzw, r1.xxzw
movc r0.w, r0.z, l(0.334000), l(-0.334000)
iadd r4.xyz, -r3.xyzx, r1.xzwx
movc r1.xzw, r0.zzzz, r1.xxzw, r4.xxyz
deriv_rtx_coarse r4.x, r1.y
deriv_rty_coarse r4.y, r1.y
frc r1.y, r1.y
itof r2.w, cb2[6].x
mad r0.w, r0.w, r2.w, l(2.000000)
add r0.w, r0.w, -cb2[5].x
add r0.w, r0.w, -cb2[5].y
add r0.w, r0.w, r1.y
add r1.y, r1.y, cb2[5].y
add r1.y, r1.y, l(1.000000)
movc r0.w, r0.z, r1.y, r0.w
imad r0.y, cb2[6].x, l(3), r0.y
imul null, r0.y, r0.y, l(9)
ishl r0.y, r0.y, l(3)
and r5.xyzw, vCoverage.xxxx, l(1, 2, 4, 8)
dp2 r1.y, r4.xyxx, l(0.062500, -0.187500, 0.000000, 0.000000)
add r1.y, r0.w, r1.y
mad r1.y, cb2[5].x, l(0.900000), r1.y
mul r1.y, r1.y, l(3.000000)
ftoi r1.y, r1.y
imin r1.y, r1.y, l(8)
imax r1.y, r1.y, l(0)
ishl r1.y, r1.y, l(3)
iadd r1.y, r0.y, r1.y
ld_structured_indexable(structured_buffer, stride=16)(mixed,mixed,mixed,mixed) r6.xyzw, r1.y, l(0), t1.xyzw
movc r6.xyzw, r5.xxxx, r6.xyzw, l(0,0,0,0)
dp2 r1.y, r4.xyxx, l(-0.062500, 0.187500, 0.000000, 0.000000)
add r1.y, r0.w, r1.y
mad r1.y, cb2[5].x, l(0.400000), r1.y
mul r1.y, r1.y, l(3.000000)
ftoi r1.y, r1.y
imin r1.y, r1.y, l(8)
imax r1.y, r1.y, l(0)
ishl r1.y, r1.y, l(3)
iadd r1.y, r0.y, r1.y
iadd r1.y, r1.y, l(1)
ld_structured_indexable(structured_buffer, stride=16)(mixed,mixed,mixed,mixed) r7.xyzw, r1.y, l(0), t1.xyzw
or r7.xyzw, r6.xyzw, r7.xyzw
movc r6.xyzw, r5.yyyy, r7.xyzw, r6.xyzw
dp2 r1.y, r4.xyxx, l(0.312500, 0.062500, 0.000000, 0.000000)
add r1.y, r0.w, r1.y
mad r1.y, cb2[5].x, l(0.500000), r1.y
mul r1.y, r1.y, l(3.000000)
ftoi r1.y, r1.y
imin r1.y, r1.y, l(8)
imax r1.y, r1.y, l(0)
ishl r1.y, r1.y, l(3)
iadd r1.y, r0.y, r1.y
iadd r1.y, r1.y, l(2)
ld_structured_indexable(structured_buffer, stride=16)(mixed,mixed,mixed,mixed) r7.xyzw, r1.y, l(0), t1.xyzw
or r7.xyzw, r6.xyzw, r7.xyzw
movc r6.xyzw, r5.zzzz, r7.xyzw, r6.xyzw
dp2 r1.y, r4.xyxx, l(-0.187500, -0.312500, 0.000000, 0.000000)
add r1.y, r0.w, r1.y
mad r1.y, cb2[5].x, l(0.600000), r1.y
mul r1.y, r1.y, l(3.000000)
ftoi r1.y, r1.y
imin r1.y, r1.y, l(8)
imax r1.y, r1.y, l(0)
ishl r1.y, r1.y, l(3)
iadd r1.y, r0.y, r1.y
iadd r1.y, r1.y, l(3)
ld_structured_indexable(structured_buffer, stride=16)(mixed,mixed,mixed,mixed) r7.xyzw, r1.y, l(0), t1.xyzw
or r7.xyzw, r6.xyzw, r7.xyzw
movc r5.xyzw, r5.wwww, r7.xyzw, r6.xyzw
and r6.xyzw, vCoverage.xxxx, l(16, 32, 64, 128)
dp2 r1.y, r4.xyxx, l(-0.312500, 0.312500, 0.000000, 0.000000)
add r1.y, r0.w, r1.y
mad r1.y, cb2[5].x, l(0.100000), r1.y
mul r1.y, r1.y, l(3.000000)
ftoi r1.y, r1.y
imin r1.y, r1.y, l(8)
imax r1.y, r1.y, l(0)
ishl r1.y, r1.y, l(3)
iadd r1.y, r0.y, r1.y
iadd r1.y, r1.y, l(4)
ld_structured_indexable(structured_buffer, stride=16)(mixed,mixed,mixed,mixed) r7.xyzw, r1.y, l(0), t1.xyzw
or r7.xyzw, r5.xyzw, r7.xyzw
movc r5.xyzw, r6.xxxx, r7.xyzw, r5.xyzw
dp2 r1.y, r4.xyxx, l(-0.437500, 0.062500, 0.000000, 0.000000)
add r1.y, r0.w, r1.y
mad r1.y, cb2[5].x, l(0.800000), r1.y
mul r1.y, r1.y, l(3.000000)
ftoi r1.y, r1.y
imin r1.y, r1.y, l(8)
imax r1.y, r1.y, l(0)
ishl r1.y, r1.y, l(3)
iadd r1.y, r0.y, r1.y
iadd r1.y, r1.y, l(5)
ld_structured_indexable(structured_buffer, stride=16)(mixed,mixed,mixed,mixed) r7.xyzw, r1.y, l(0), t1.xyzw
or r7.xyzw, r5.xyzw, r7.xyzw
movc r5.xyzw, r6.yyyy, r7.xyzw, r5.xyzw
dp2 r1.y, r4.xyxx, l(0.187500, 0.437500, 0.000000, 0.000000)
add r1.y, r0.w, r1.y
mad r1.y, cb2[5].x, l(0.700000), r1.y
mul r1.y, r1.y, l(3.000000)
ftoi r1.y, r1.y
imin r1.y, r1.y, l(8)
imax r1.y, r1.y, l(0)
ishl r1.y, r1.y, l(3)
iadd r1.y, r0.y, r1.y
iadd r1.y, r1.y, l(6)
ld_structured_indexable(structured_buffer, stride=16)(mixed,mixed,mixed,mixed) r7.xyzw, r1.y, l(0), t1.xyzw
or r7.xyzw, r5.xyzw, r7.xyzw
movc r5.xyzw, r6.zzzz, r7.xyzw, r5.xyzw
dp2 r1.y, r4.xyxx, l(0.437500, -0.437500, 0.000000, 0.000000)
add r0.w, r0.w, r1.y
mad r0.w, cb2[5].x, l(0.300000), r0.w
mul r0.w, r0.w, l(3.000000)
ftoi r0.w, r0.w
imin r0.w, r0.w, l(8)
imax r0.w, r0.w, l(0)
ishl r0.w, r0.w, l(3)
iadd r0.y, r0.w, r0.y
iadd r0.y, r0.y, l(7)
ld_structured_indexable(structured_buffer, stride=16)(mixed,mixed,mixed,mixed) r4.xyzw, r0.y, l(0), t1.xyzw
or r4.xyzw, r4.xyzw, r5.xyzw
movc r4.xyzw, r6.wwww, r4.xyzw, r5.xyzw
ine r0.y, cb2[5].z, l(0)
ine r0.w, l(0), cb1[21].y
not r1.y, r0.w
or r0.y, r0.y, r1.y
deriv_rtx_coarse r5.xyz, r2.zxyz
deriv_rty_coarse r2.xyz, r2.yzxy
mul r6.xyz, r2.xyzx, r5.xyzx
mad r2.xyz, r5.zxyz, r2.yzxy, -r6.xyzx
dp3 r1.y, r2.xyzx, r2.xyzx
rsq r1.y, r1.y
mul r2.xyz, r1.yyyy, r2.xyzx
movc r2.xyz, r0.zzzz, r2.xyzx, -r2.xyzx
lt r5.xyz, l(-0.010000, -0.010000, -0.010000, 0.000000), r2.xyzx
and r5.yz, r5.yyzy, l(0, 0x000ffc00, 0x3ff00000, 0)
bfi r0.z, l(10), l(0), r5.x, r5.y
iadd r5.x, r5.z, r0.z
lt r2.xyz, r2.xyzx, l(0.010000, 0.010000, 0.010000, 0.000000)
and r2.yz, r2.yyzy, l(0, 0x000ffc00, 0x3ff00000, 0)
bfi r0.z, l(10), l(0), r2.x, r2.y
iadd r5.y, r2.z, r0.z
movc r0.yz, r0.yyyy, l(0,2.000000,2.000000,0), r5.xxyx
iadd r1.xyz, -r3.xyzx, r1.xzwx
or r1.w, r0.z, r0.y
iadd r2.xy, l(-1, -1, 0, 0), cb1[18].ywyy
not r2.z, r2.x
ishr r5.xyz, cb1[2].xyzx, r0.xxxx
imad r6.z, cb1[18].z, r0.x, l(1)
mov r6.xy, l(0,0,0,0)
mov r7.xyz, r1.xyzx
mov r8.xy, r4.yzyy
mov r8.zw, l(0,0,-1,0)
mov r2.w, r4.x
mov r3.w, l(0)
loop
uge r5.w, r3.w, l(4)
breakc_nz r5.w
and r5.w, r1.w, r2.w
if_nz r5.w
or r5.w, r7.y, r7.x
or r5.w, r7.z, r5.w
and r5.w, r2.z, r5.w
if_z r5.w
ishr r9.xyzw, r7.xyzz, cb1[r0.x + 13].wwww
iadd r9.xyzw, r9.xyzw, cb1[r0.x + 13].xyzz
and r9.xyzw, r2.yyyy, r9.xyzw
iadd r5.w, r9.y, r9.x
iadd r10.x, r9.w, r5.w
ine r5.w, r8.z, r10.x
ld_uav_typed_indexable(texture3d)(uint,uint,uint,uint) r6.w, r9.xyww, u1.yzwx
movc r10.y, r5.w, r6.w, r8.w
and r5.w, r10.y, l(4)
if_nz r5.w
and r5.w, r10.y, l(1)
if_z r5.w
or r10.y, r10.y, l(1)
store_uav_typed u1.xyzw, r9.xyzw, r10.yyyy
endif
and r9.xy, r0.yzyy, r2.wwww
iadd r11.xyz, r5.xyzx, r7.xyzx
and r11.xyz, r2.xxxx, r11.xyzx
iadd r11.xyz, r6.xyzx, r11.xyzx
if_nz r9.x
atomic_or u2, r11.xyzx, r9.x
endif
ine r5.w, r9.y, l(0)
and r5.w, r0.w, r5.w
if_nz r5.w
atomic_or u3, r11.xyzx, r9.y
endif
endif
mov r8.zw, r10.xxxy
endif
endif
iadd r7.xyz, r3.xyzx, r7.xyzx
iadd r3.w, r3.w, l(1)
mov r9.x, r8.y
mov r9.y, r4.w
mov r2.w, r8.x
mov r8.xy, r9.xyxx
endloop
discard_nz l(-1)
endif
ret
// Approximately 258 instruction slots used
4
头部:21006
【步骤】
1 先编译【!BuildAll】
【注】先把SYSTEM文件夹该为非只读属性,编译生成的dll等文件要覆盖,
标签:iat 技术 volume tor box sample ptr else order
原文地址:http://www.cnblogs.com/username/p/6022475.html