.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack1_16,"ax",@progbits
	.globl	__runCodelet_Vertex_pack1_16    # -- Begin function __runCodelet_Vertex_pack1_16
	.p2align	2
	.type	__runCodelet_Vertex_pack1_16,@function
__runCodelet_Vertex_pack1_16:           # @__runCodelet_Vertex_pack1_16
	.worker
.Lpack1_16_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 64
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -64
	get $m0, 1
	ld32 $m1, $m13, $m15, 7
	brz $m1, .Lpack1_16_BB0_12
# %bb.1:                                # %for.body.lr.ph.i
	mov	$m3, $m13
	mov	$m4, $m15
	and $m5, $m0, 7
	sub $m0, 57, $m5
	setzi $m1, 43691
	setzi $m2, 43690
	mul $m1, $m0, $m1
	mul $m0, $m0, $m2
	shr $m1, $m1, 16
	add $m0, $m0, $m1
	ld32step $m6, $m15, $m3+=, 7
	st32 $m3, $m11, $m15, 4                 # 4-byte Folded Spill
	st32 $m5, $m11, $m15, 3                 # 4-byte Folded Spill
	mul $m1, $m5, 15
	shr $m0, $m0, 18
	setzi $m2, 1048064
	ld32 $m3, $m13, $m15, 1
	st32 $m3, $m11, $m15, 15                # 4-byte Folded Spill
	st32 $m6, $m11, $m15, 2                 # 4-byte Folded Spill
	add $m3, $m6, $m1
	add $m0, $m0, 2
	st32 $m0, $m11, $m15, 1                 # 4-byte Folded Spill
	or $m0, $m2, 2146435072
	st32 $m0, $m11, $m15, 7                 # 4-byte Folded Spill
	setzi $m0, 8
	st32 $m0, $m11, $m15, 6                 # 4-byte Folded Spill
.Lpack1_16_BB0_2:                                # %for.body.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
                                        #       Child Loop BB0_4 Depth 3
	ld32 $m5, $m11, $m15, 1                 # 4-byte Folded Reload
	mul $m0, $m4, 765
	add $m5, $m5, -1
	ld32 $m1, $m11, $m15, 2                 # 4-byte Folded Reload
	add $m0, $m1, $m0
	st32 $m0, $m11, $m15, 12                # 4-byte Folded Spill
	shl $m0, $m4, 11
	st32 $m0, $m11, $m15, 8                 # 4-byte Folded Spill
	st32 $m3, $m11, $m15, 5                 # 4-byte Folded Spill
	mov	$m8, $m3
	ld32 $m2, $m11, $m15, 3                 # 4-byte Folded Reload
	st32 $m4, $m11, $m15, 9                 # 4-byte Folded Spill
.Lpack1_16_BB0_3:                                # %for.cond8.preheader.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Loop Header: Depth=2
                                        #       Child Loop BB0_4 Depth 3
	st32 $m5, $m11, $m15, 11                # 4-byte Folded Spill
	mov	$m6, $m15
	mov	$m0, $m15
	shl $m1, $m2, 5
	ld32 $m3, $m11, $m15, 7                 # 4-byte Folded Reload
	and $m3, $m1, $m3
	ld32 $m5, $m11, $m15, 8                 # 4-byte Folded Reload
	add $m3, $m3, $m5
	and $m1, $m1, 480
	or $m7, $m3, $m1
	mul $m3, $m2, 15
	ld32 $m1, $m11, $m15, 6                 # 4-byte Folded Reload
	add $m1, $m1, -1
	st32 $m3, $m11, $m15, 13                # 4-byte Folded Spill
	add $m3, $m3, $m4
	and $m3, $m3, 3
	st32 $m3, $m11, $m15, 14                # 4-byte Folded Spill
	st32 $m8, $m11, $m15, 10                # 4-byte Folded Spill
	mov	$m3, $m8
.Lpack1_16_BB0_4:                                # %for.body11.i
                                        #   Parent Loop BB0_2 Depth=1
                                        #     Parent Loop BB0_3 Depth=2
                                        # =>    This Inner Loop Header: Depth=3
	mov	$m9, $m15
	setzi $m5, 50
	cmpult $m5, $m5, $m2
	brnz $m5, .Lpack1_16_BB0_14
# %bb.5:                                # %for.body11.i
                                        #   in Loop: Header=BB0_4 Depth=3
	setzi $m5, 14
	cmpult $m5, $m5, $m0
	brnz $m5, .Lpack1_16_BB0_14
# %bb.6:                                # %if.end.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m4, $m11, $m15, 14                # 4-byte Folded Reload
	brnz $m4, .Lpack1_16_BB0_8
# %bb.7:                                # %if.end.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m5, $m0, 12
	brz $m5, .Lpack1_16_BB0_8
# %bb.13:                               # %if.then9.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m4, $m11, $m15, 13                # 4-byte Folded Reload
	add $m4, $m0, $m4
	ld32 $m5, $m11, $m15, 12                # 4-byte Folded Reload
	ld32 $m9, $m5, $m4, 0
	bri .Lpack1_16_BB0_14
.Lpack1_16_BB0_8:                                # %for.body.lr.ph.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m10, $m15
	mov	$m9, $m15
	shl $m5, $m6, 2
	sub $m5, 14, $m5
	cmpult $m8, $m5, 3
	setzi $m4, 3
	movnz	$m4, $m8, $m5
	add $m8, $m4, 1
	mov	$m5, $m3
# %bb.9:                                # %for.body.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	{
		rpt $m8, 3
		fnop
	}
	{
		ldz8step $m4, $m15, $m5+=, 1
		fnop
	}
	{
		shl $m4, $m4, $m10
		fnop
	}
	{
		or $m9, $m4, $m9
		fnop
	}
	{
		add $m10, $m10, 8
		fnop
	}
.Lpack1_16_BB0_14:                               # %_ZZN15Vertex_pack1_167computeEjENKUljjE_clEjj.exit.i
                                        #   in Loop: Header=BB0_4 Depth=3
	or $m4, $m0, $m7
	ld32 $m5, $m11, $m15, 15                # 4-byte Folded Reload
	st32 $m9, $m5, $m4, 0
	add $m0, $m0, 4
	add $m3, $m3, 4
	add $m6, $m6, 1
	brnzdec $m1, .Lpack1_16_BB0_4
# %bb.10:                               # %for.cond.cleanup10.i
                                        #   in Loop: Header=BB0_3 Depth=2
	ld32 $m5, $m11, $m15, 11                # 4-byte Folded Reload
	add $m2, $m2, 6
	ld32 $m8, $m11, $m15, 10                # 4-byte Folded Reload
	add $m8, $m8, 90
	ld32 $m4, $m11, $m15, 9                 # 4-byte Folded Reload
	brnzdec $m5, .Lpack1_16_BB0_3
# %bb.11:                               # %for.cond.cleanup6.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m0, $m11, $m15, 4                 # 4-byte Folded Reload
	ld32 $m0, $m0, $m15, 0
	add $m4, $m4, 1
	cmpult $m0, $m4, $m0
	ld32 $m3, $m11, $m15, 5                 # 4-byte Folded Reload
	add $m3, $m3, 765
	brnz $m0, .Lpack1_16_BB0_2
.Lpack1_16_BB0_12:                               # %_ZN15Vertex_pack1_167computeEj.exit
	exitz $m15
.Lpack1_16_func_end0:
	.size	__runCodelet_Vertex_pack1_16, .Lpack1_16_func_end0-__runCodelet_Vertex_pack1_16
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack1_16
	.long	.Lpack1_16_func_begin0
	.byte	64
	.section	.text.__runCodelet_Vertex_pack1_16,"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