result code = 0
standard error = {

ir_global_var %1	: Ptr<@ThreadGroup vector<float,4>[64]>;

ir_global_var %2	: Ptr<StructuredBuffer<vector<float,4>>>;

ir_global_var %3	: Ptr<RWStructuredBuffer<vector<float,4>>>;

ir_func @_S04mainp3uuuV	: (uint, uint, uint) -> void
{
block %4(
		param %5	: uint,
		param %6	: uint,
		param %7	: uint):
	let  %8	: Ptr<uint>	= var()
	store(%8, %5)
	let  %9	: Ptr<uint>	= var()
	store(%9, %6)
	let  %10	: Ptr<uint>	= var()
	store(%10, %7)
	let  %11	: uint	= load(%9)
	let  %12	: Ptr<vector<float,4>>	= getElementPtr(%1, %11)
	let  %13	: StructuredBuffer<vector<float,4>>	= load(%2)
	let  %14	: uint	= load(%8)
	let  %15	: vector<float,4>	= bufferLoad(%13, %14)
	store(%12, %15)
	let  %16	: Ptr<uint>	= var()
	let  %17	: uint	= construct(1)
	store(%16, %17)
	loop(%18, %19, %20)

block %18:
	let  %21	: uint	= load(%16)
	let  %22	: uint	= construct(64)
	let  %23	: bool	= cmpLT(%21, %22)
	loopTest(%23, %24, %19)

block %24:
	GroupMemoryBarrierWithGroupSync()
	let  %25	: uint	= load(%9)
	let  %26	: Ptr<vector<float,4>>	= getElementPtr(%1, %25)
	let  %27	: Ptr<vector<float,4>>	= var()
	let  %28	: vector<float,4>	= load(%26)
	store(%27, %28)
	let  %29	: uint	= load(%9)
	let  %30	: uint	= load(%16)
	let  %31	: uint	= sub(%29, %30)
	let  %32	: Ptr<vector<float,4>>	= getElementPtr(%1, %31)
	let  %33	: vector<float,4>	= load(%32)
	let  %34	: vector<float,4>	= load(%27)
	let  %35	: vector<float,4>	= add(%34, %33)
	store(%27, %35)
	let  %36	: vector<float,4>	= load(%27)
	store(%26, %36)
	unconditionalBranch(%20)

block %20:
	let  %37	: Ptr<uint>	= var()
	let  %38	: uint	= load(%16)
	store(%37, %38)
	let  %39	: uint	= construct(1)
	let  %40	: uint	= load(%37)
	let  %41	: uint	= shl(%40, %39)
	store(%37, %41)
	let  %42	: uint	= load(%37)
	store(%16, %42)
	unconditionalBranch(%18)

block %19:
	GroupMemoryBarrierWithGroupSync()
	let  %43	: RWStructuredBuffer<vector<float,4>>	= load(%3)
	let  %44	: uint	= load(%8)
	let  %45	: Ptr<vector<float,4>>	= getElementPtr(%1, 0)
	let  %46	: vector<float,4>	= load(%45)
	bufferStore(%43, %44, %46)
	return_void()
}

}
standard output = {
}