move to self host

1 files changed, 513 insertions, 0 deletions

diff --git a/VRCSDK3Worlds/Assets/Editor/x64/Bakery/fixPos3D.ptx b/VRCSDK3Worlds/Assets/Editor/x64/Bakery/fixPos3D.ptx
new file mode 100644
index 00000000..b4ec12de
--- /dev/null
+++ b/VRCSDK3Worlds/Assets/Editor/x64/Bakery/fixPos3D.ptx
@@ -0,0 +1,513 @@
+//
+// Generated by NVIDIA NVVM Compiler
+//
+// Compiler Build ID: CL-23083092
+// Cuda compilation tools, release 9.1, V9.1.85
+// Based on LLVM 3.4svn
+//
+
+.version 6.1
+.target sm_30
+.address_size 64
+
+	// .globl	_Z6oxMainv
+.global .align 8 .b8 pixelID[8];
+.global .align 8 .b8 resolution[8];
+.global .align 4 .b8 normal[12];
+.global .align 4 .b8 camPos[12];
+.global .align 4 .b8 root[4];
+.global .align 4 .u32 imageEnabled;
+.global .texref lightmap;
+.global .align 16 .b8 tileInfo[16];
+.global .align 4 .u32 additive;
+.global .align 1 .b8 image_HDR[1];
+.global .align 1 .b8 image_HDR2[1];
+.global .align 1 .b8 uvnormal[1];
+.global .align 1 .b8 uvpos[1];
+.global .align 4 .b8 voxelSize[12];
+.global .align 4 .b8 _ZN21rti_internal_typeinfo7pixelIDE[8] = {82, 97, 121, 0, 8, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo10resolutionE[8] = {82, 97, 121, 0, 8, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo6normalE[8] = {82, 97, 121, 0, 12, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo6camPosE[8] = {82, 97, 121, 0, 12, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo4rootE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo12imageEnabledE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo8tileInfoE[8] = {82, 97, 121, 0, 16, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo8additiveE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo9voxelSizeE[8] = {82, 97, 121, 0, 12, 0, 0, 0};
+.global .align 8 .u64 _ZN21rti_internal_register20reg_bitness_detectorE;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail0E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail1E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail2E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail3E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail4E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail5E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail6E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail7E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail8E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail9E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail0E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail1E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail2E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail3E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail4E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail5E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail6E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail7E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail8E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail9E;
+.global .align 4 .u32 _ZN21rti_internal_register14reg_rayIndex_xE;
+.global .align 4 .u32 _ZN21rti_internal_register14reg_rayIndex_yE;
+.global .align 4 .u32 _ZN21rti_internal_register14reg_rayIndex_zE;
+.global .align 8 .b8 _ZN21rti_internal_typename7pixelIDE[6] = {117, 105, 110, 116, 50, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename10resolutionE[6] = {117, 105, 110, 116, 50, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename6normalE[7] = {102, 108, 111, 97, 116, 51, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename6camPosE[7] = {102, 108, 111, 97, 116, 51, 0};
+.global .align 16 .b8 _ZN21rti_internal_typename4rootE[9] = {114, 116, 79, 98, 106, 101, 99, 116, 0};
+.global .align 4 .b8 _ZN21rti_internal_typename12imageEnabledE[4] = {105, 110, 116, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename8tileInfoE[6] = {117, 105, 110, 116, 52, 0};
+.global .align 4 .b8 _ZN21rti_internal_typename8additiveE[4] = {105, 110, 116, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename9voxelSizeE[7] = {102, 108, 111, 97, 116, 51, 0};
+.global .align 4 .u32 _ZN21rti_internal_typeenum7pixelIDE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum10resolutionE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum6normalE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum6camPosE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum4rootE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum12imageEnabledE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum8tileInfoE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum8additiveE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum9voxelSizeE = 4919;
+.global .align 16 .b8 _ZN21rti_internal_semantic7pixelIDE[14] = {114, 116, 76, 97, 117, 110, 99, 104, 73, 110, 100, 101, 120, 0};
+.global .align 16 .b8 _ZN21rti_internal_semantic10resolutionE[12] = {114, 116, 76, 97, 117, 110, 99, 104, 68, 105, 109, 0};
+.global .align 16 .b8 _ZN21rti_internal_semantic6normalE[17] = {97, 116, 116, 114, 105, 98, 117, 116, 101, 32, 110, 111, 114, 109, 97, 108, 0};
+.global .align 1 .b8 _ZN21rti_internal_semantic6camPosE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic4rootE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic12imageEnabledE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic8tileInfoE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic8additiveE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic9voxelSizeE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation7pixelIDE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation10resolutionE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation6normalE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation6camPosE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation4rootE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation12imageEnabledE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation8tileInfoE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation8additiveE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation9voxelSizeE[1];
+
+.visible .entry _Z6oxMainv(
+
+)
+{
+	.local .align 4 .b8 	__local_depot0[12];
+	.reg .b64 	%SP;
+	.reg .b64 	%SPL;
+	.reg .pred 	%p<28>;
+	.reg .b16 	%rs<9>;
+	.reg .f32 	%f<277>;
+	.reg .b32 	%r<59>;
+	.reg .b64 	%rd<55>;
+
+
+	mov.u64 	%rd54, __local_depot0;
+	cvta.local.u64 	%SP, %rd54;
+	ld.global.v2.u32 	{%r6, %r7}, [pixelID];
+	cvt.u64.u32	%rd4, %r6;
+	cvt.u64.u32	%rd5, %r7;
+	mov.u64 	%rd8, uvnormal;
+	cvta.global.u64 	%rd3, %rd8;
+	mov.u32 	%r4, 2;
+	mov.u32 	%r5, 4;
+	mov.u64 	%rd7, 0;
+	// inline asm
+	call (%rd2), _rt_buffer_get_64, (%rd3, %r4, %r5, %rd4, %rd5, %rd7, %rd7);
+	// inline asm
+	ld.u32 	%r1, [%rd2];
+	shr.u32 	%r10, %r1, 16;
+	cvt.u16.u32	%rs1, %r10;
+	and.b16  	%rs2, %rs1, 255;
+	cvt.u16.u32	%rs3, %r1;
+	or.b16  	%rs4, %rs3, %rs2;
+	setp.eq.s16	%p10, %rs4, 0;
+	mov.pred 	%p25, -1;
+	mov.pred 	%p26, %p25;
+	mov.pred 	%p27, %p25;
+	@%p10 bra 	BB0_2;
+
+	ld.u8 	%rs5, [%rd2+1];
+	and.b16  	%rs7, %rs3, 255;
+	cvt.rn.f32.u16	%f71, %rs7;
+	div.rn.f32 	%f72, %f71, 0f437F0000;
+	fma.rn.f32 	%f73, %f72, 0f40000000, 0fBF800000;
+	cvt.rn.f32.u16	%f74, %rs5;
+	div.rn.f32 	%f75, %f74, 0f437F0000;
+	fma.rn.f32 	%f76, %f75, 0f40000000, 0fBF800000;
+	cvt.rn.f32.u16	%f77, %rs2;
+	div.rn.f32 	%f78, %f77, 0f437F0000;
+	fma.rn.f32 	%f79, %f78, 0f40000000, 0fBF800000;
+	mul.f32 	%f80, %f76, %f76;
+	fma.rn.f32 	%f81, %f73, %f73, %f80;
+	fma.rn.f32 	%f82, %f79, %f79, %f81;
+	sqrt.rn.f32 	%f83, %f82;
+	rcp.rn.f32 	%f84, %f83;
+	mul.f32 	%f85, %f73, %f84;
+	mul.f32 	%f86, %f76, %f84;
+	mul.f32 	%f87, %f79, %f84;
+	setp.eq.f32	%p25, %f85, 0f00000000;
+	setp.eq.f32	%p26, %f86, 0f00000000;
+	setp.eq.f32	%p27, %f87, 0f00000000;
+
+BB0_2:
+	ld.global.v2.u32 	{%r11, %r12}, [pixelID];
+	ld.global.v2.u32 	{%r14, %r15}, [tileInfo];
+	add.s32 	%r2, %r11, %r14;
+	add.s32 	%r3, %r12, %r15;
+	and.pred  	%p11, %p25, %p26;
+	and.pred  	%p12, %p11, %p27;
+	@%p12 bra 	BB0_23;
+	bra.uni 	BB0_3;
+
+BB0_23:
+	cvt.u64.u32	%rd49, %r2;
+	cvt.u64.u32	%rd50, %r3;
+	mov.u64 	%rd53, image_HDR;
+	cvta.global.u64 	%rd48, %rd53;
+	mov.u32 	%r58, 16;
+	// inline asm
+	call (%rd47), _rt_buffer_get_64, (%rd48, %r4, %r58, %rd49, %rd50, %rd7, %rd7);
+	// inline asm
+	mov.f32 	%f253, 0f00000000;
+	st.v4.f32 	[%rd47], {%f253, %f253, %f253, %f253};
+	bra.uni 	BB0_24;
+
+BB0_3:
+	ld.global.v2.u32 	{%r28, %r29}, [pixelID];
+	cvt.u64.u32	%rd11, %r28;
+	cvt.u64.u32	%rd12, %r29;
+	mov.u64 	%rd28, uvpos;
+	cvta.global.u64 	%rd10, %rd28;
+	mov.u32 	%r27, 12;
+	// inline asm
+	call (%rd9), _rt_buffer_get_64, (%rd10, %r4, %r27, %rd11, %rd12, %rd7, %rd7);
+	// inline asm
+	ld.f32 	%f1, [%rd9];
+	ld.global.v2.u32 	{%r32, %r33}, [pixelID];
+	cvt.u64.u32	%rd17, %r32;
+	cvt.u64.u32	%rd18, %r33;
+	// inline asm
+	call (%rd15), _rt_buffer_get_64, (%rd10, %r4, %r27, %rd17, %rd18, %rd7, %rd7);
+	// inline asm
+	ld.f32 	%f2, [%rd15+4];
+	ld.global.v2.u32 	{%r36, %r37}, [pixelID];
+	cvt.u64.u32	%rd23, %r36;
+	cvt.u64.u32	%rd24, %r37;
+	// inline asm
+	call (%rd21), _rt_buffer_get_64, (%rd10, %r4, %r27, %rd23, %rd24, %rd7, %rd7);
+	// inline asm
+	mul.f32 	%f97, %f1, 0f3456BF95;
+	mul.f32 	%f98, %f2, 0f3456BF95;
+	ld.f32 	%f3, [%rd21+8];
+	mul.f32 	%f99, %f3, 0f3456BF95;
+	abs.f32 	%f100, %f97;
+	abs.f32 	%f101, %f98;
+	abs.f32 	%f102, %f99;
+	max.f32 	%f103, %f100, %f101;
+	max.f32 	%f104, %f103, %f102;
+	mov.f32 	%f105, 0f38D1B717;
+	max.f32 	%f4, %f104, %f105;
+	ld.global.f32 	%f106, [voxelSize];
+	ld.global.f32 	%f107, [voxelSize+4];
+	mul.f32 	%f108, %f107, 0f00000000;
+	sub.f32 	%f109, %f108, %f106;
+	ld.global.f32 	%f110, [voxelSize+8];
+	fma.rn.f32 	%f111, %f110, 0f00000000, %f109;
+	abs.f32 	%f95, %f111;
+	add.u64 	%rd27, %SP, 0;
+	cvta.to.local.u64 	%rd29, %rd27;
+	mov.u32 	%r26, 0;
+	st.local.u32 	[%rd29+8], %r26;
+	st.local.u32 	[%rd29+4], %r26;
+	st.local.u32 	[%rd29], %r26;
+	ld.global.u32 	%r25, [root];
+	mov.f32 	%f91, 0fBF800000;
+	mov.f32 	%f94, 0f00000000;
+	// inline asm
+	call _rt_trace_64, (%r25, %f1, %f2, %f3, %f91, %f94, %f94, %r26, %f94, %f95, %rd27, %r27);
+	// inline asm
+	ld.local.f32 	%f5, [%rd29+4];
+	ld.local.f32 	%f6, [%rd29];
+	add.f32 	%f112, %f6, %f5;
+	ld.local.f32 	%f7, [%rd29+8];
+	add.f32 	%f113, %f112, %f7;
+	mov.f32 	%f261, 0f47C34F80;
+	setp.eq.f32	%p13, %f113, 0f00000000;
+	@%p13 bra 	BB0_4;
+
+	mul.f32 	%f115, %f5, %f5;
+	fma.rn.f32 	%f116, %f6, %f6, %f115;
+	fma.rn.f32 	%f117, %f7, %f7, %f116;
+	sqrt.rn.f32 	%f8, %f117;
+	rcp.rn.f32 	%f118, %f8;
+	mul.f32 	%f119, %f118, %f6;
+	mul.f32 	%f120, %f118, %f5;
+	mul.f32 	%f121, %f118, %f7;
+	fma.rn.f32 	%f122, %f4, %f119, %f1;
+	fma.rn.f32 	%f123, %f4, %f120, %f2;
+	fma.rn.f32 	%f124, %f4, %f121, %f3;
+	sub.f32 	%f9, %f122, %f8;
+	fma.rn.f32 	%f10, %f8, 0f00000000, %f123;
+	fma.rn.f32 	%f11, %f8, 0f00000000, %f124;
+	setp.geu.f32	%p14, %f8, 0f47C34F80;
+	mov.f32 	%f258, %f1;
+	mov.f32 	%f259, %f2;
+	mov.f32 	%f260, %f3;
+	@%p14 bra 	BB0_7;
+
+	mov.f32 	%f258, %f9;
+	mov.f32 	%f259, %f10;
+	mov.f32 	%f260, %f11;
+	mov.f32 	%f261, %f8;
+	bra.uni 	BB0_7;
+
+BB0_4:
+	mov.f32 	%f258, %f1;
+	mov.f32 	%f259, %f2;
+	mov.f32 	%f260, %f3;
+
+BB0_7:
+	ld.global.f32 	%f133, [voxelSize+4];
+	ld.global.f32 	%f134, [voxelSize];
+	fma.rn.f32 	%f135, %f133, 0f00000000, %f134;
+	ld.global.f32 	%f136, [voxelSize+8];
+	fma.rn.f32 	%f137, %f136, 0f00000000, %f135;
+	abs.f32 	%f132, %f137;
+	st.local.u32 	[%rd29+8], %r26;
+	st.local.u32 	[%rd29+4], %r26;
+	st.local.u32 	[%rd29], %r26;
+	ld.global.u32 	%r40, [root];
+	mov.f32 	%f128, 0f3F800000;
+	// inline asm
+	call _rt_trace_64, (%r40, %f1, %f2, %f3, %f128, %f94, %f94, %r26, %f94, %f132, %rd27, %r27);
+	// inline asm
+	ld.local.f32 	%f16, [%rd29+4];
+	ld.local.f32 	%f17, [%rd29];
+	add.f32 	%f138, %f17, %f16;
+	ld.local.f32 	%f18, [%rd29+8];
+	add.f32 	%f139, %f138, %f18;
+	setp.eq.f32	%p15, %f139, 0f00000000;
+	@%p15 bra 	BB0_10;
+
+	mul.f32 	%f140, %f16, %f16;
+	fma.rn.f32 	%f141, %f17, %f17, %f140;
+	fma.rn.f32 	%f142, %f18, %f18, %f141;
+	sqrt.rn.f32 	%f19, %f142;
+	rcp.rn.f32 	%f143, %f19;
+	mul.f32 	%f144, %f143, %f17;
+	mul.f32 	%f145, %f143, %f16;
+	mul.f32 	%f146, %f143, %f18;
+	fma.rn.f32 	%f20, %f4, %f144, %f1;
+	fma.rn.f32 	%f147, %f4, %f145, %f2;
+	fma.rn.f32 	%f148, %f4, %f146, %f3;
+	fma.rn.f32 	%f21, %f19, 0f00000000, %f147;
+	fma.rn.f32 	%f22, %f19, 0f00000000, %f148;
+	setp.geu.f32	%p16, %f19, %f261;
+	@%p16 bra 	BB0_10;
+
+	add.f32 	%f258, %f20, %f19;
+	mov.f32 	%f259, %f21;
+	mov.f32 	%f260, %f22;
+	mov.f32 	%f261, %f19;
+
+BB0_10:
+	ld.global.f32 	%f157, [voxelSize];
+	ld.global.f32 	%f158, [voxelSize+4];
+	neg.f32 	%f159, %f158;
+	fma.rn.f32 	%f160, %f157, 0f00000000, %f159;
+	ld.global.f32 	%f161, [voxelSize+8];
+	fma.rn.f32 	%f162, %f161, 0f00000000, %f160;
+	abs.f32 	%f156, %f162;
+	st.local.u32 	[%rd29+8], %r26;
+	st.local.u32 	[%rd29+4], %r26;
+	st.local.u32 	[%rd29], %r26;
+	ld.global.u32 	%r43, [root];
+	// inline asm
+	call _rt_trace_64, (%r43, %f1, %f2, %f3, %f94, %f91, %f94, %r26, %f94, %f156, %rd27, %r27);
+	// inline asm
+	ld.local.f32 	%f28, [%rd29+4];
+	ld.local.f32 	%f29, [%rd29];
+	add.f32 	%f163, %f29, %f28;
+	ld.local.f32 	%f30, [%rd29+8];
+	add.f32 	%f164, %f163, %f30;
+	setp.eq.f32	%p17, %f164, 0f00000000;
+	@%p17 bra 	BB0_13;
+
+	mul.f32 	%f165, %f28, %f28;
+	fma.rn.f32 	%f166, %f29, %f29, %f165;
+	fma.rn.f32 	%f167, %f30, %f30, %f166;
+	sqrt.rn.f32 	%f31, %f167;
+	rcp.rn.f32 	%f168, %f31;
+	mul.f32 	%f169, %f168, %f29;
+	mul.f32 	%f170, %f168, %f28;
+	mul.f32 	%f171, %f168, %f30;
+	fma.rn.f32 	%f172, %f4, %f169, %f1;
+	fma.rn.f32 	%f173, %f4, %f170, %f2;
+	fma.rn.f32 	%f174, %f4, %f171, %f3;
+	fma.rn.f32 	%f32, %f31, 0f00000000, %f172;
+	sub.f32 	%f33, %f173, %f31;
+	fma.rn.f32 	%f34, %f31, 0f00000000, %f174;
+	setp.geu.f32	%p18, %f31, %f261;
+	@%p18 bra 	BB0_13;
+
+	mov.f32 	%f258, %f32;
+	mov.f32 	%f259, %f33;
+	mov.f32 	%f260, %f34;
+	mov.f32 	%f261, %f31;
+
+BB0_13:
+	ld.global.f32 	%f183, [voxelSize];
+	ld.global.f32 	%f184, [voxelSize+4];
+	fma.rn.f32 	%f185, %f183, 0f00000000, %f184;
+	ld.global.f32 	%f186, [voxelSize+8];
+	fma.rn.f32 	%f187, %f186, 0f00000000, %f185;
+	abs.f32 	%f182, %f187;
+	st.local.u32 	[%rd29+8], %r26;
+	st.local.u32 	[%rd29+4], %r26;
+	st.local.u32 	[%rd29], %r26;
+	ld.global.u32 	%r46, [root];
+	// inline asm
+	call _rt_trace_64, (%r46, %f1, %f2, %f3, %f94, %f128, %f94, %r26, %f94, %f182, %rd27, %r27);
+	// inline asm
+	ld.local.f32 	%f39, [%rd29+4];
+	ld.local.f32 	%f40, [%rd29];
+	add.f32 	%f188, %f40, %f39;
+	ld.local.f32 	%f41, [%rd29+8];
+	add.f32 	%f189, %f188, %f41;
+	setp.eq.f32	%p19, %f189, 0f00000000;
+	@%p19 bra 	BB0_16;
+
+	mul.f32 	%f190, %f39, %f39;
+	fma.rn.f32 	%f191, %f40, %f40, %f190;
+	fma.rn.f32 	%f192, %f41, %f41, %f191;
+	sqrt.rn.f32 	%f42, %f192;
+	rcp.rn.f32 	%f193, %f42;
+	mul.f32 	%f194, %f193, %f40;
+	mul.f32 	%f195, %f193, %f39;
+	mul.f32 	%f196, %f193, %f41;
+	fma.rn.f32 	%f197, %f4, %f194, %f1;
+	fma.rn.f32 	%f43, %f4, %f195, %f2;
+	fma.rn.f32 	%f198, %f4, %f196, %f3;
+	fma.rn.f32 	%f44, %f42, 0f00000000, %f197;
+	fma.rn.f32 	%f45, %f42, 0f00000000, %f198;
+	setp.geu.f32	%p20, %f42, %f261;
+	@%p20 bra 	BB0_16;
+
+	add.f32 	%f259, %f43, %f42;
+	mov.f32 	%f258, %f44;
+	mov.f32 	%f260, %f45;
+	mov.f32 	%f261, %f42;
+
+BB0_16:
+	ld.global.f32 	%f207, [voxelSize];
+	ld.global.f32 	%f208, [voxelSize+4];
+	mul.f32 	%f209, %f208, 0f00000000;
+	fma.rn.f32 	%f210, %f207, 0f00000000, %f209;
+	ld.global.f32 	%f211, [voxelSize+8];
+	sub.f32 	%f212, %f210, %f211;
+	abs.f32 	%f206, %f212;
+	st.local.u32 	[%rd29+8], %r26;
+	st.local.u32 	[%rd29+4], %r26;
+	st.local.u32 	[%rd29], %r26;
+	ld.global.u32 	%r49, [root];
+	// inline asm
+	call _rt_trace_64, (%r49, %f1, %f2, %f3, %f94, %f94, %f91, %r26, %f94, %f206, %rd27, %r27);
+	// inline asm
+	ld.local.f32 	%f51, [%rd29+4];
+	ld.local.f32 	%f52, [%rd29];
+	add.f32 	%f213, %f52, %f51;
+	ld.local.f32 	%f53, [%rd29+8];
+	add.f32 	%f214, %f213, %f53;
+	setp.eq.f32	%p21, %f214, 0f00000000;
+	@%p21 bra 	BB0_19;
+
+	mul.f32 	%f215, %f51, %f51;
+	fma.rn.f32 	%f216, %f52, %f52, %f215;
+	fma.rn.f32 	%f217, %f53, %f53, %f216;
+	sqrt.rn.f32 	%f54, %f217;
+	rcp.rn.f32 	%f218, %f54;
+	mul.f32 	%f219, %f218, %f52;
+	mul.f32 	%f220, %f218, %f51;
+	mul.f32 	%f221, %f218, %f53;
+	fma.rn.f32 	%f222, %f4, %f219, %f1;
+	fma.rn.f32 	%f223, %f4, %f220, %f2;
+	fma.rn.f32 	%f224, %f4, %f221, %f3;
+	fma.rn.f32 	%f55, %f54, 0f00000000, %f222;
+	fma.rn.f32 	%f56, %f54, 0f00000000, %f223;
+	sub.f32 	%f57, %f224, %f54;
+	setp.geu.f32	%p22, %f54, %f261;
+	@%p22 bra 	BB0_19;
+
+	mov.f32 	%f258, %f55;
+	mov.f32 	%f259, %f56;
+	mov.f32 	%f260, %f57;
+	mov.f32 	%f261, %f54;
+
+BB0_19:
+	ld.global.f32 	%f233, [voxelSize];
+	ld.global.f32 	%f234, [voxelSize+4];
+	mul.f32 	%f235, %f234, 0f00000000;
+	fma.rn.f32 	%f236, %f233, 0f00000000, %f235;
+	ld.global.f32 	%f237, [voxelSize+8];
+	add.f32 	%f238, %f236, %f237;
+	abs.f32 	%f232, %f238;
+	st.local.u32 	[%rd29+8], %r26;
+	st.local.u32 	[%rd29+4], %r26;
+	st.local.u32 	[%rd29], %r26;
+	ld.global.u32 	%r52, [root];
+	// inline asm
+	call _rt_trace_64, (%r52, %f1, %f2, %f3, %f94, %f94, %f128, %r26, %f94, %f232, %rd27, %r27);
+	// inline asm
+	ld.local.f32 	%f62, [%rd29+4];
+	ld.local.f32 	%f63, [%rd29];
+	add.f32 	%f239, %f63, %f62;
+	ld.local.f32 	%f64, [%rd29+8];
+	add.f32 	%f240, %f239, %f64;
+	setp.eq.f32	%p23, %f240, 0f00000000;
+	@%p23 bra 	BB0_22;
+
+	mul.f32 	%f241, %f62, %f62;
+	fma.rn.f32 	%f242, %f63, %f63, %f241;
+	fma.rn.f32 	%f243, %f64, %f64, %f242;
+	sqrt.rn.f32 	%f244, %f243;
+	rcp.rn.f32 	%f245, %f244;
+	mul.f32 	%f246, %f245, %f63;
+	mul.f32 	%f247, %f245, %f62;
+	mul.f32 	%f248, %f245, %f64;
+	fma.rn.f32 	%f249, %f4, %f246, %f1;
+	fma.rn.f32 	%f250, %f4, %f247, %f2;
+	fma.rn.f32 	%f251, %f4, %f248, %f3;
+	fma.rn.f32 	%f65, %f244, 0f00000000, %f249;
+	fma.rn.f32 	%f66, %f244, 0f00000000, %f250;
+	add.f32 	%f67, %f251, %f244;
+	setp.geu.f32	%p24, %f244, %f261;
+	@%p24 bra 	BB0_22;
+
+	mov.f32 	%f258, %f65;
+	mov.f32 	%f259, %f66;
+	mov.f32 	%f260, %f67;
+
+BB0_22:
+	cvt.u64.u32	%rd43, %r3;
+	cvt.u64.u32	%rd42, %r2;
+	mov.u64 	%rd46, image_HDR;
+	cvta.global.u64 	%rd41, %rd46;
+	mov.u32 	%r56, 16;
+	// inline asm
+	call (%rd40), _rt_buffer_get_64, (%rd41, %r4, %r56, %rd42, %rd43, %rd7, %rd7);
+	// inline asm
+	st.v4.f32 	[%rd40], {%f258, %f259, %f260, %f128};
+
+BB0_24:
+	ret;
+}
+
+