//
// 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;
// ShaderKernel_Gain$__cuda_local_var_180673_464_non_const_p_local has been demoted

.visible .entry ShaderKernel_Gain(
	.param .u64 ShaderKernel_Gain_param_0,
	.param .u32 ShaderKernel_Gain_param_1,
	.param .u32 ShaderKernel_Gain_param_2,
	.param .u32 ShaderKernel_Gain_param_3,
	.param .u32 ShaderKernel_Gain_param_4,
	.param .u64 ShaderKernel_Gain_param_5,
	.param .u64 ShaderKernel_Gain_param_6
)
{
	.reg .pred 	%p<6>;
	.reg .s16 	%rs<5>;
	.reg .s32 	%r<14>;
	.reg .f32 	%f<31>;
	.reg .s64 	%rd<11>;
	// demoted variable
	.shared .align 16 .b8 ShaderKernel_Gain$__cuda_local_var_180673_464_non_const_p_local[16];

	ld.param.u64 	%rd4, [ShaderKernel_Gain_param_0];
	ld.param.u32 	%r4, [ShaderKernel_Gain_param_1];
	ld.param.u32 	%r5, [ShaderKernel_Gain_param_2];
	ld.param.u32 	%r6, [ShaderKernel_Gain_param_3];
	ld.param.u32 	%r7, [ShaderKernel_Gain_param_4];
	ld.param.u64 	%rd3, [ShaderKernel_Gain_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_6;
	bra.uni 	BB0_1;

BB0_1:
	setp.ne.s32	%p4, %r1, 0;
	@%p4 bra 	BB0_3;

	cvta.to.global.u64 	%rd5, %rd3;
	ld.global.v4.f32 	{%f7, %f8, %f9, %f10}, [%rd5];
	st.shared.v4.f32 	[ShaderKernel_Gain$__cuda_local_var_180673_464_non_const_p_local], {%f7, %f8, %f9, %f10};

BB0_3:
	cvt.rn.f32.s32	%f15, %r2;
	add.ftz.f32 	%f1, %f15, 0f3F000000;
	cvt.rn.f32.s32	%f16, %r3;
	add.ftz.f32 	%f2, %f16, 0f3F000000;
	bar.sync 	0;
	// inline asm
	tex.2d.v4.f32.f32 {%f17, %f18, %f19, %f20}, [texture0_RECT, {%f1, %f2}];
	// inline asm
	ld.shared.v4.f32 	{%f23, %f24, %f25, %f26}, [ShaderKernel_Gain$__cuda_local_var_180673_464_non_const_p_local];
	mul.ftz.f32 	%f3, %f19, %f23;
	mul.ftz.f32 	%f4, %f18, %f24;
	mul.ftz.f32 	%f5, %f17, %f25;
	mul.ftz.f32 	%f6, %f20, %f26;
	mad.lo.s32 	%r13, %r3, %r4, %r2;
	cvt.s64.s32	%rd2, %r13;
	setp.eq.s32	%p5, %r5, 0;
	@%p5 bra 	BB0_5;

	shl.b64 	%rd7, %rd2, 4;
	add.s64 	%rd8, %rd1, %rd7;
	st.global.v4.f32 	[%rd8], {%f5, %f4, %f3, %f6};
	bra.uni 	BB0_6;

BB0_5:
	shl.b64 	%rd9, %rd2, 3;
	add.s64 	%rd10, %rd1, %rd9;
	{
	.reg .b16 %temp;
	cvt.rn.ftz.f16.f32 	%temp, %f6;
	mov.b16 	%rs1, %temp;
}
	{
	.reg .b16 %temp;
	cvt.rn.ftz.f16.f32 	%temp, %f3;
	mov.b16 	%rs2, %temp;
}
	{
	.reg .b16 %temp;
	cvt.rn.ftz.f16.f32 	%temp, %f4;
	mov.b16 	%rs3, %temp;
}
	{
	.reg .b16 %temp;
	cvt.rn.ftz.f16.f32 	%temp, %f5;
	mov.b16 	%rs4, %temp;
}
	st.global.v4.u16 	[%rd10], {%rs4, %rs3, %rs2, %rs1};

BB0_6:
	ret;
}


