//
// Generated by NVIDIA NVVM Compiler
//
// Compiler Build ID: CL-26907403
// Cuda compilation tools, release 10.1, V10.1.243
// Based on LLVM 3.4svn
//

.version 6.4
.target sm_30
.address_size 64

	// .globl	VecAdd_kernel

.visible .entry VecAdd_kernel(
	.param .u64 VecAdd_kernel_param_0,
	.param .u64 VecAdd_kernel_param_1,
	.param .u64 VecAdd_kernel_param_2,
	.param .u32 VecAdd_kernel_param_3
)
{
	.reg .pred 	%p<2>;
	.reg .f32 	%f<4>;
	.reg .b32 	%r<6>;
	.reg .b64 	%rd<11>;


	ld.param.u64 	%rd1, [VecAdd_kernel_param_0];
	ld.param.u64 	%rd2, [VecAdd_kernel_param_1];
	ld.param.u64 	%rd3, [VecAdd_kernel_param_2];
	ld.param.u32 	%r2, [VecAdd_kernel_param_3];
	mov.u32 	%r3, %ntid.x;
	mov.u32 	%r4, %ctaid.x;
	mov.u32 	%r5, %tid.x;
	mad.lo.s32 	%r1, %r4, %r3, %r5;
	setp.ge.s32	%p1, %r1, %r2;
	@%p1 bra 	BB0_2;

	cvta.to.global.u64 	%rd4, %rd1;
	mul.wide.s32 	%rd5, %r1, 4;
	add.s64 	%rd6, %rd4, %rd5;
	cvta.to.global.u64 	%rd7, %rd2;
	add.s64 	%rd8, %rd7, %rd5;
	ld.global.f32 	%f1, [%rd8];
	ld.global.f32 	%f2, [%rd6];
	add.f32 	%f3, %f2, %f1;
	cvta.to.global.u64 	%rd9, %rd3;
	add.s64 	%rd10, %rd9, %rd5;
	st.global.f32 	[%rd10], %f3;

BB0_2:
	ret;
}


