.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_AddF16,"ax",@progbits
	.globl	__runCodelet_AddF16             # -- Begin function __runCodelet_AddF16
	.p2align	2
	.type	__runCodelet_AddF16,@function
__runCodelet_AddF16:                    # @__runCodelet_AddF16
	.worker
.Lfunc_begin0:
# %bb.0:                                # %entry
	setzi $m6, 8
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -8
	get $m0, 1
	and $m0, $m0, 7
	ld32 $m8, $m13, $m15, 3
	shr $m6, $m8, 1
	brz $m0, .LBB0_2
# %bb.1:                                # %entry
	cmpult $m1, $m0, $m6
	brnz $m1, .LBB0_2
.LBB0_53:                               # %_ZN6AddF167computeEj.exit
	exitz $m15
.LBB0_2:                                # %if.end.i
	ld32 $m1, $m13, $m15, 4
	or $m2, $m8, $m1
	and $m2, $m2, 1
	brnz $m2, .LBB0_31
# %bb.3:                                # %land.lhs.true7.i
	ld32 $m7, $m13, $m15, 5
	and $m2, $m7, 1
	brnz $m2, .LBB0_31
# %bb.4:                                # %if.then10.i
	cmpne $m2, $m1, $m8
	ld32 $m3, $m13, $m15, 0
	ld32 $m5, $m13, $m15, 1
	ld32 $m10, $m13, $m15, 2
	cmpne $m9, $m7, $m8
	brnz $m2, .LBB0_9
# %bb.5:                                # %if.then10.i
	brnz $m9, .LBB0_9
# %bb.6:                                # %for.cond.preheader.i
	cmpult $m1, $m0, $m6
	brz $m1, .LBB0_53
# %bb.7:                                # %for.body.i.preheader
	shl $m6, $m0, 2
	add $m1, $m10, $m6
	add $m2, $m5, $m6
	add $m3, $m3, $m6
.LBB0_8:                                # %for.body.i
                                        # =>This Inner Loop Header: Depth=1
	ld32step $a0, $m15, $m3+=, 6
	ld32step $a1, $m15, $m2+=, 6
	f16v2add $a0, $a0, $a1
	st32step $a0, $m15, $m1+=, 6
	ld32 $m4, $m13, $m15, 3
	add $m0, $m0, 6
	shr $m4, $m4, 1
	cmpult $m4, $m0, $m4
	brnz $m4, .LBB0_8
	bri .LBB0_53
.LBB0_31:                               # %if.end121.i
	shl $m4, $m0, 1
	and $m7, $m8, 1
	add $m5, $m1, $m4
	mov	$m2, $m4
.LBB0_32:                               # %while.cond.i290.i
                                        # =>This Inner Loop Header: Depth=1
	cmpult $m3, $m2, $m1
	sub $m2, $m2, $m1
	sub $m5, $m5, $m1
	brz $m3, .LBB0_32
# %bb.33:                               # %_ZN6AddF164wrapEjj.exit291.i
	ld32 $m3, $m13, $m15, 5
	add $m6, $m3, $m4
	mov	$m2, $m4
.LBB0_34:                               # %while.cond.i295.i
                                        # =>This Inner Loop Header: Depth=1
	cmpult $m9, $m2, $m3
	sub $m2, $m2, $m3
	sub $m6, $m6, $m3
	brz $m9, .LBB0_34
# %bb.35:                               # %for.cond131.preheader.i
	or $m2, $m4, 1
	cmpult $m2, $m2, $m8
	brz $m2, .LBB0_46
.LBB0_36:                               # %for.body136.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_37 Depth 2
                                        #     Child Loop BB0_39 Depth 2
                                        #     Child Loop BB0_41 Depth 2
                                        #     Child Loop BB0_43 Depth 2
	shl $m8, $m5, 1
	shl $m2, $m1, 1
	ld32 $m7, $m13, $m15, 0
	add $m8, $m8, $m2
	ldb16 $a0, $m7, $m15, $m5
	add $m9, $m5, 1
	add $m8, $m8, 2
.LBB0_37:                               # %while.cond.i300.i
                                        #   Parent Loop BB0_36 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	cmpult $m10, $m9, $m1
	sub $m9, $m9, $m1
	sub $m8, $m8, $m2
	brz $m10, .LBB0_37
# %bb.38:                               # %_ZN6AddF164wrapEjj.exit301.i
                                        #   in Loop: Header=BB0_36 Depth=1
	shl $m1, $m6, 1
	shl $m2, $m3, 1
	add $m9, $m1, $m2
	ldb16 $a1, $m7, $m8, 0
	ld32 $m1, $m13, $m15, 1
	ldb16 $a2, $m1, $m15, $m6
	add $m8, $m6, 1
	add $m7, $m9, 2
.LBB0_39:                               # %while.cond.i305.i
                                        #   Parent Loop BB0_36 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	cmpult $m9, $m8, $m3
	sub $m8, $m8, $m3
	sub $m7, $m7, $m2
	brz $m9, .LBB0_39
# %bb.40:                               # %_ZN6AddF164wrapEjj.exit306.i
                                        #   in Loop: Header=BB0_36 Depth=1
	{
		ldb16 $a1, $m1, $m7, 0
		sort4x16lo $a0, $a0, $a1
	}
	{
		ld32 $m1, $m13, $m15, 2
		sort4x16lo $a1, $a2, $a1
	}
	{
		shl $m2, $m4, 1
		f16v2add $a0, $a0, $a1
	}
	st32 $a0, $m1, $m2, 0
	add $m2, $m5, 12
	ld32 $m1, $m13, $m15, 4
	add $m5, $m2, $m1
.LBB0_41:                               # %while.cond.i310.i
                                        #   Parent Loop BB0_36 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	cmpult $m3, $m2, $m1
	sub $m2, $m2, $m1
	sub $m5, $m5, $m1
	brz $m3, .LBB0_41
# %bb.42:                               # %_ZN6AddF164wrapEjj.exit311.i
                                        #   in Loop: Header=BB0_36 Depth=1
	add $m2, $m6, 12
	ld32 $m3, $m13, $m15, 5
	add $m6, $m2, $m3
.LBB0_43:                               # %while.cond.i315.i
                                        #   Parent Loop BB0_36 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	cmpult $m7, $m2, $m3
	sub $m2, $m2, $m3
	sub $m6, $m6, $m3
	brz $m7, .LBB0_43
# %bb.44:                               # %_ZN6AddF164wrapEjj.exit316.i
                                        #   in Loop: Header=BB0_36 Depth=1
	add $m4, $m4, 12
	or $m2, $m4, 1
	ld32 $m8, $m13, $m15, 3
	cmpult $m2, $m2, $m8
	brnz $m2, .LBB0_36
# %bb.45:                               # %for.cond.cleanup135.loopexit.i
	and $m7, $m8, 1
.LBB0_46:                               # %for.cond.cleanup135.i
	brnz $m0, .LBB0_53
# %bb.47:                               # %for.cond.cleanup135.i
	brz $m7, .LBB0_53
# %bb.48:                               # %if.then173.i
	shl $m4, $m8, 1
	shl $m5, $m1, 1
	add $m0, $m8, -1
	add $m2, $m4, $m5
	add $m6, $m2, -2
	mov	$m2, $m0
.LBB0_49:                               # %while.cond.i320.i
                                        # =>This Inner Loop Header: Depth=1
	cmpult $m7, $m2, $m1
	sub $m2, $m2, $m1
	sub $m6, $m6, $m5
	brz $m7, .LBB0_49
# %bb.50:                               # %_ZN6AddF164wrapEjj.exit321.i
	shl $m2, $m3, 1
	add $m1, $m4, $m2
	add $m1, $m1, -2
	ld32 $m4, $m13, $m15, 0
	ldb16 $a0, $m4, $m6, 0
	mov	$m4, $m0
.LBB0_51:                               # %while.cond.i325.i
                                        # =>This Inner Loop Header: Depth=1
	cmpult $m5, $m4, $m3
	sub $m4, $m4, $m3
	sub $m1, $m1, $m2
	brz $m5, .LBB0_51
# %bb.52:                               # %_ZN6AddF164wrapEjj.exit326.i
	ld32 $m2, $m13, $m15, 1
	shl $m0, $m0, 1
	ldb16 $a1, $m2, $m1, 0
	{
		ld32 $m1, $m13, $m15, 2
		f16v2add $a0, $a0, $a1
	}
	{
		andc $m0, $m0, 3
		sort4x16lo $a0, $a0, $azero
	}
	ld32 $m2, $m1, $m0, 0
	setzi $m3, 65535
	andc $m2, $m2, $m3
	mov	$m3, $a0
	or $m2, $m2, $m3
	st32 $m2, $m1, $m0, 0
	exitz $m15
.LBB0_9:                                # %if.else.i
	cmpeq $m2, $m1, $m8
	brnz $m2, .LBB0_11
# %bb.10:                               # %if.else.i
	brnz $m9, .LBB0_21
.LBB0_11:                               # %land.lhs.true33.i
	st32 $m2, $m11, $m15, 1                 # 4-byte Folded Spill
	st32 $m10, $m11, $m15, 0                # 4-byte Folded Spill
	cmpult $m2, $m1, $m7
	mov	$m9, $m7
	movnz	$m9, $m2, $m1
	sub $m10, 0, $m9
	mov	$m2, $m8
.LBB0_12:                               # %while.cond.i.i
                                        # =>This Inner Loop Header: Depth=1
	cmpult $m4, $m2, $m9
	sub $m2, $m2, $m9
	add $m10, $m10, $m9
	brz $m4, .LBB0_12
# %bb.13:                               # %_ZN6AddF164wrapEjj.exit.i
	cmpne $m2, $m8, $m10
	ld32 $m10, $m11, $m15, 0                # 4-byte Folded Reload
	ld32 $m4, $m11, $m15, 1                 # 4-byte Folded Reload
	brnz $m2, .LBB0_21
# %bb.14:                               # %if.then42.i
	cmpult $m2, $m8, 2
	brnz $m2, .LBB0_53
# %bb.15:                               # %for.cond74.preheader.lr.ph.i
	mov	$m6, $m15
	movnz	$m1, $m4, $m7
	shr $m1, $m1, 1
	xnor $m2, $m0, $m15
	add $m2, $m2, $m1
	setzi $m4, 43691
	sort4x16lo $m7, $m2, $m15
	shr $m2, $m2, 16
	mul $m9, $m7, $m4
	mul $m4, $m2, $m4
	shr $m9, $m9, 16
	add $m4, $m4, $m9
	setzi $m9, 43690
	mul $m7, $m7, $m9
	mul $m2, $m2, $m9
	sort4x16lo $m9, $m4, $m15
	shr $m4, $m4, 16
	add $m7, $m7, $m9
	add $m2, $m2, $m4
	shr $m4, $m7, 16
	mov	$m7, $m5
	add $m2, $m2, $m4
	ld32 $m4, $m11, $m15, 1                 # 4-byte Folded Reload
	movnz	$m7, $m4, $m3
	movnz	$m3, $m4, $m5
	shl $m9, $m0, 2
	shr $m2, $m2, 2
	add $m3, $m3, $m9
	st32 $m3, $m11, $m15, 1                 # 4-byte Folded Spill
	add $m4, $m10, $m9
	shl $m5, $m1, 2
	add $m7, $m7, $m9
	add $m2, $m2, 1
	st32 $m2, $m11, $m15, 0                 # 4-byte Folded Spill
	bri .LBB0_16
.LBB0_20:                               # %for.cond.cleanup76.i
                                        #   in Loop: Header=BB0_16 Depth=1
	add $m6, $m6, $m1
	shr $m2, $m8, 1
	cmpult $m2, $m6, $m2
	add $m4, $m4, $m5
	add $m7, $m7, $m5
	brz $m2, .LBB0_53
.LBB0_16:                               # %for.cond74.preheader.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_18 Depth 2
	cmpult $m2, $m0, $m1
	brz $m2, .LBB0_20
# %bb.17:                               # %for.body77.i.preheader
                                        #   in Loop: Header=BB0_16 Depth=1
	ld32 $m2, $m11, $m15, 0                 # 4-byte Folded Reload
	mov	$m9, $m7
	mov	$m10, $m4
	ld32 $m3, $m11, $m15, 1                 # 4-byte Folded Reload
	add $m2, $m2, -1
.LBB0_18:                               # %for.body77.i
                                        #   Parent Loop BB0_16 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	ld32step $a0, $m15, $m9+=, 6
	ld32step $a1, $m15, $m3+=, 6
	f16v2add $a0, $a0, $a1
	st32step $a0, $m15, $m10+=, 6
	brnzdec $m2, .LBB0_18
# %bb.19:                               # %for.cond.cleanup76.loopexit.i
                                        #   in Loop: Header=BB0_16 Depth=1
	ld32 $m8, $m13, $m15, 3
	bri .LBB0_20
.LBB0_21:                               # %if.else90.i
	shr $m2, $m1, 1
	add $m1, $m2, $m0
	mov	$m8, $m0
.LBB0_22:                               # %while.cond.i270.i
                                        # =>This Inner Loop Header: Depth=1
	cmpult $m4, $m8, $m2
	sub $m8, $m8, $m2
	sub $m1, $m1, $m2
	brz $m4, .LBB0_22
# %bb.23:                               # %_ZN6AddF164wrapEjj.exit271.i
	shr $m7, $m7, 1
	add $m2, $m7, $m0
	mov	$m8, $m0
.LBB0_24:                               # %while.cond.i275.i
                                        # =>This Inner Loop Header: Depth=1
	cmpult $m4, $m8, $m7
	sub $m8, $m8, $m7
	sub $m2, $m2, $m7
	brz $m4, .LBB0_24
# %bb.25:                               # %for.cond98.preheader.i
	cmpult $m4, $m0, $m6
	brz $m4, .LBB0_53
.LBB0_26:                               # %for.body103.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_27 Depth 2
                                        #     Child Loop BB0_29 Depth 2
	ld32 $a0, $m3, $m15, $m1
	ld32 $a1, $m5, $m15, $m2
	f16v2add $a0, $a0, $a1
	st32 $a0, $m10, $m15, $m0
	ld32 $m4, $m13, $m15, 4
	add $m7, $m1, 6
	shr $m6, $m4, 1
	add $m1, $m7, $m6
.LBB0_27:                               # %while.cond.i280.i
                                        #   Parent Loop BB0_26 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	cmpult $m4, $m7, $m6
	sub $m7, $m7, $m6
	sub $m1, $m1, $m6
	brz $m4, .LBB0_27
# %bb.28:                               # %_ZN6AddF164wrapEjj.exit281.i
                                        #   in Loop: Header=BB0_26 Depth=1
	ld32 $m4, $m13, $m15, 5
	add $m7, $m2, 6
	shr $m6, $m4, 1
	add $m2, $m7, $m6
.LBB0_29:                               # %while.cond.i285.i
                                        #   Parent Loop BB0_26 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	cmpult $m4, $m7, $m6
	sub $m7, $m7, $m6
	sub $m2, $m2, $m6
	brz $m4, .LBB0_29
# %bb.30:                               # %_ZN6AddF164wrapEjj.exit286.i
                                        #   in Loop: Header=BB0_26 Depth=1
	ld32 $m4, $m13, $m15, 3
	add $m0, $m0, 6
	shr $m4, $m4, 1
	cmpult $m4, $m0, $m4
	brnz $m4, .LBB0_26
	bri .LBB0_53
.Lfunc_end0:
	.size	__runCodelet_AddF16, .Lfunc_end0-__runCodelet_AddF16
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_AddF16
	.long	.Lfunc_begin0
	.byte	8
	.section	.text.__runCodelet_AddF16,"ax",@progbits
                                        # -- End function
	.ident	"clang version 16.0.0 (git@github.com:Software-GCAI/llvm-project.git 6343a843cd5af31429c62a83b6ba249a74d36969)"
	.section	".note.GNU-stack","",@progbits
	.addrsig