//
// Generated by NVIDIA NVVM Compiler
// Compiler built on Fri Jul 25 04:36:16 2014 (1406288176)
// Cuda compilation tools, release 6.5, V6.5.13
//

.version 4.1
.target sm_30
.address_size 64

.global .texref texture0_RECT;
.global .texref texture1_RECT;
// ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local has been demoted

.visible .entry ShaderKernel_fxDay2NiteV(
	.param .u64 ShaderKernel_fxDay2NiteV_param_0,
	.param .u32 ShaderKernel_fxDay2NiteV_param_1,
	.param .u32 ShaderKernel_fxDay2NiteV_param_2,
	.param .u32 ShaderKernel_fxDay2NiteV_param_3,
	.param .u32 ShaderKernel_fxDay2NiteV_param_4,
	.param .u64 ShaderKernel_fxDay2NiteV_param_5,
	.param .u64 ShaderKernel_fxDay2NiteV_param_6,
	.param .u64 ShaderKernel_fxDay2NiteV_param_7
)
{
	.reg .pred 	%p<8>;
	.reg .s16 	%rs<5>;
	.reg .s32 	%r<14>;
	.reg .f32 	%f<195>;
	.reg .s64 	%rd<40>;
	// demoted variable
	.shared .align 16 .b8 ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local[112];

	ld.param.u64 	%rd4, [ShaderKernel_fxDay2NiteV_param_0];
	ld.param.u32 	%r4, [ShaderKernel_fxDay2NiteV_param_1];
	ld.param.u32 	%r5, [ShaderKernel_fxDay2NiteV_param_2];
	ld.param.u32 	%r6, [ShaderKernel_fxDay2NiteV_param_3];
	ld.param.u32 	%r7, [ShaderKernel_fxDay2NiteV_param_4];
	ld.param.u64 	%rd3, [ShaderKernel_fxDay2NiteV_param_5];
	cvta.to.global.u64 	%rd1, %rd4;
	mov.u32 	%r8, %ntid.x;
	mov.u32 	%r9, %ctaid.x;
	mov.u32 	%r1, %tid.x;
	mad.lo.s32 	%r2, %r8, %r9, %r1;
	mov.u32 	%r10, %ntid.y;
	mov.u32 	%r11, %ctaid.y;
	mov.u32 	%r12, %tid.y;
	mad.lo.s32 	%r3, %r10, %r11, %r12;
	setp.lt.s32	%p1, %r2, %r6;
	setp.lt.s32	%p2, %r3, %r7;
	and.pred  	%p3, %p1, %p2;
	@!%p3 bra 	BB0_9;
	bra.uni 	BB0_1;

BB0_1:
	cvt.rn.f32.s32	%f14, %r2;
	add.ftz.f32 	%f1, %f14, 0f3F000000;
	cvt.rn.f32.s32	%f15, %r3;
	add.ftz.f32 	%f2, %f15, 0f3F000000;
	setp.gt.u32	%p4, %r1, 6;
	@%p4 bra 	BB0_3;

	cvta.to.global.u64 	%rd5, %rd3;
	mul.wide.u32 	%rd6, %r1, 16;
	mov.u64 	%rd7, ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local;
	add.s64 	%rd8, %rd7, %rd6;
	add.s64 	%rd9, %rd5, %rd6;
	ld.global.v4.f32 	{%f16, %f17, %f18, %f19}, [%rd9];
	st.shared.v4.f32 	[%rd8], {%f16, %f17, %f18, %f19};

BB0_3:
	bar.sync 	0;
	// inline asm
	tex.2d.v4.f32.f32 {%f24, %f25, %f26, %f27}, [texture0_RECT, {%f1, %f2}];
	// inline asm
	add.ftz.f32 	%f76, %f1, 0f00000000;
	add.ftz.f32 	%f35, %f2, 0fBF800000;
	// inline asm
	tex.2d.v4.f32.f32 {%f30, %f31, %f32, %f33}, [texture0_RECT, {%f76, %f35}];
	// inline asm
	ld.shared.v2.f32 	{%f78, %f79}, [ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local];
	fma.rn.ftz.f32 	%f81, %f32, %f78, %f26;
	fma.rn.ftz.f32 	%f83, %f31, %f79, %f25;
	add.ftz.f32 	%f41, %f2, 0f3F800000;
	mov.f32 	%f84, 0f3F800000;
	// inline asm
	tex.2d.v4.f32.f32 {%f36, %f37, %f38, %f39}, [texture0_RECT, {%f76, %f41}];
	// inline asm
	fma.rn.ftz.f32 	%f85, %f38, %f78, %f81;
	fma.rn.ftz.f32 	%f86, %f37, %f79, %f83;
	add.ftz.f32 	%f47, %f2, 0fC0000000;
	// inline asm
	tex.2d.v4.f32.f32 {%f42, %f43, %f44, %f45}, [texture0_RECT, {%f76, %f47}];
	// inline asm
	ld.shared.v2.f32 	{%f87, %f88}, [ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local+16];
	fma.rn.ftz.f32 	%f90, %f44, %f87, %f85;
	fma.rn.ftz.f32 	%f92, %f43, %f88, %f86;
	add.ftz.f32 	%f53, %f2, 0f40000000;
	// inline asm
	tex.2d.v4.f32.f32 {%f48, %f49, %f50, %f51}, [texture0_RECT, {%f76, %f53}];
	// inline asm
	fma.rn.ftz.f32 	%f93, %f50, %f87, %f90;
	fma.rn.ftz.f32 	%f94, %f49, %f88, %f92;
	add.ftz.f32 	%f59, %f2, 0fC0400000;
	// inline asm
	tex.2d.v4.f32.f32 {%f54, %f55, %f56, %f57}, [texture0_RECT, {%f76, %f59}];
	// inline asm
	ld.shared.v2.f32 	{%f95, %f96}, [ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local+32];
	fma.rn.ftz.f32 	%f98, %f56, %f95, %f93;
	fma.rn.ftz.f32 	%f100, %f55, %f96, %f94;
	add.ftz.f32 	%f65, %f2, 0f40400000;
	// inline asm
	tex.2d.v4.f32.f32 {%f60, %f61, %f62, %f63}, [texture0_RECT, {%f76, %f65}];
	// inline asm
	fma.rn.ftz.f32 	%f101, %f62, %f95, %f98;
	fma.rn.ftz.f32 	%f102, %f61, %f96, %f100;
	add.ftz.f32 	%f71, %f2, 0fC0800000;
	// inline asm
	tex.2d.v4.f32.f32 {%f66, %f67, %f68, %f69}, [texture0_RECT, {%f76, %f71}];
	// inline asm
	ld.shared.v2.f32 	{%f103, %f104}, [ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local+48];
	fma.rn.ftz.f32 	%f106, %f68, %f103, %f101;
	fma.rn.ftz.f32 	%f108, %f67, %f104, %f102;
	add.ftz.f32 	%f77, %f2, 0f40800000;
	// inline asm
	tex.2d.v4.f32.f32 {%f72, %f73, %f74, %f75}, [texture0_RECT, {%f76, %f77}];
	// inline asm
	fma.rn.ftz.f32 	%f109, %f74, %f103, %f106;
	fma.rn.ftz.f32 	%f110, %f73, %f104, %f108;
	ld.shared.v2.f32 	{%f111, %f112}, [ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local+64];
	mul.ftz.f32 	%f4, %f109, %f111;
	mul.ftz.f32 	%f5, %f110, %f112;
	sub.ftz.f32 	%f115, %f4, %f5;
	div.rn.ftz.f32 	%f6, %f84, %f115;
	setp.gt.ftz.f32	%p5, %f115, 0f3A83126F;
	selp.f32	%f7, %f115, 0f3A83126F, %p5;
	setp.gtu.ftz.f32	%p6, %f7, 0f00000000;
	@%p6 bra 	BB0_5;

	mov.f32 	%f194, 0f00000000;
	bra.uni 	BB0_6;

BB0_5:
	lg2.approx.ftz.f32 	%f117, %f7;
	mul.ftz.f32 	%f118, %f117, 0f3F4CCCCD;
	ex2.approx.ftz.f32 	%f194, %f118;

BB0_6:
	// inline asm
	tex.2d.v4.f32.f32 {%f119, %f120, %f121, %f122}, [texture1_RECT, {%f1, %f2}];
	// inline asm
	add.ftz.f32 	%f130, %f2, 0f00000000;
	add.ftz.f32 	%f129, %f1, 0fBF800000;
	// inline asm
	tex.2d.v4.f32.f32 {%f125, %f126, %f127, %f128}, [texture1_RECT, {%f129, %f130}];
	// inline asm
	// inline asm
	tex.2d.v4.f32.f32 {%f131, %f132, %f133, %f134}, [texture1_RECT, {%f76, %f41}];
	// inline asm
	add.ftz.f32 	%f141, %f1, 0f3F800000;
	// inline asm
	tex.2d.v4.f32.f32 {%f137, %f138, %f139, %f140}, [texture1_RECT, {%f141, %f35}];
	// inline asm
	mul.ftz.f32 	%f144, %f6, %f194;
	cvt.ftz.sat.f32.f32	%f145, %f144;
	sub.ftz.f32 	%f146, %f84, %f145;
	mul.ftz.f32 	%f147, %f146, %f5;
	fma.rn.ftz.f32 	%f148, %f145, %f4, %f147;
	add.ftz.f32 	%f149, %f127, %f121;
	add.ftz.f32 	%f150, %f126, %f120;
	add.ftz.f32 	%f151, %f125, %f119;
	add.ftz.f32 	%f152, %f149, %f133;
	add.ftz.f32 	%f153, %f150, %f132;
	add.ftz.f32 	%f154, %f151, %f131;
	add.ftz.f32 	%f155, %f152, %f139;
	add.ftz.f32 	%f156, %f153, %f138;
	add.ftz.f32 	%f157, %f154, %f137;
	ld.shared.v4.f32 	{%f158, %f159, %f160, %f161}, [ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local+80];
	mul.ftz.f32 	%f163, %f148, %f158;
	mul.ftz.f32 	%f165, %f148, %f159;
	mul.ftz.f32 	%f167, %f148, %f160;
	mul.ftz.f32 	%f169, %f148, %f161;
	mul.ftz.f32 	%f170, %f156, 0f3E1645A2;
	fma.rn.ftz.f32 	%f171, %f155, 0f3D991687, %f170;
	fma.rn.ftz.f32 	%f172, %f157, 0f3CE978D5, %f171;
	ld.shared.v4.f32 	{%f173, %f174, %f175, %f176}, [ShaderKernel_fxDay2NiteV$__cuda_local_var_180679_636_non_const_p_local+96];
	add.ftz.f32 	%f178, %f172, %f173;
	cvt.ftz.sat.f32.f32	%f179, %f178;
	add.ftz.f32 	%f181, %f172, %f174;
	cvt.ftz.sat.f32.f32	%f182, %f181;
	add.ftz.f32 	%f184, %f172, %f175;
	cvt.ftz.sat.f32.f32	%f185, %f184;
	sub.ftz.f32 	%f186, %f84, %f179;
	mul.ftz.f32 	%f187, %f186, %f163;
	fma.rn.ftz.f32 	%f10, %f179, %f121, %f187;
	sub.ftz.f32 	%f188, %f84, %f182;
	mul.ftz.f32 	%f189, %f188, %f165;
	fma.rn.ftz.f32 	%f11, %f182, %f120, %f189;
	sub.ftz.f32 	%f190, %f84, %f185;
	mul.ftz.f32 	%f191, %f190, %f167;
	fma.rn.ftz.f32 	%f12, %f185, %f119, %f191;
	sub.ftz.f32 	%f192, %f84, 0f3F800000;
	mul.ftz.f32 	%f193, %f192, %f169;
	fma.rn.ftz.f32 	%f13, %f122, 0f3F800000, %f193;
	mad.lo.s32 	%r13, %r3, %r4, %r2;
	cvt.s64.s32	%rd2, %r13;
	setp.eq.s32	%p7, %r5, 0;
	@%p7 bra 	BB0_8;

	shl.b64 	%rd36, %rd2, 4;
	add.s64 	%rd37, %rd1, %rd36;
	st.global.v4.f32 	[%rd37], {%f12, %f11, %f10, %f13};
	bra.uni 	BB0_9;

BB0_8:
	shl.b64 	%rd38, %rd2, 3;
	add.s64 	%rd39, %rd1, %rd38;
	{
	.reg .b16 %temp;
	cvt.rn.ftz.f16.f32 	%temp, %f13;
	mov.b16 	%rs1, %temp;
}
	{
	.reg .b16 %temp;
	cvt.rn.ftz.f16.f32 	%temp, %f10;
	mov.b16 	%rs2, %temp;
}
	{
	.reg .b16 %temp;
	cvt.rn.ftz.f16.f32 	%temp, %f11;
	mov.b16 	%rs3, %temp;
}
	{
	.reg .b16 %temp;
	cvt.rn.ftz.f16.f32 	%temp, %f12;
	mov.b16 	%rs4, %temp;
}
	st.global.v4.u16 	[%rd39], {%rs4, %rs3, %rs2, %rs1};

BB0_9:
	ret;
}


