.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack2_10,"ax",@progbits
	.globl	__runCodelet_Vertex_pack2_10    # -- Begin function __runCodelet_Vertex_pack2_10
	.p2align	2
	.type	__runCodelet_Vertex_pack2_10,@function
__runCodelet_Vertex_pack2_10:           # @__runCodelet_Vertex_pack2_10
	.worker
.Lpack2_10_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 88
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -88
	get $m0, 1
	ld32 $m1, $m13, $m15, 7
	brz $m1, .Lpack2_10_BB0_8
# %bb.1:                                # %for.body.lr.ph.i
	mov	$m5, $m13
	mov	$m6, $m15
	shl $m1, $m0, 2
	and $m2, $m1, 28
	sub $m1, 72, $m2
	min $m1, $m1, 1
	st32 $m2, $m11, $m15, 2                 # 4-byte Folded Spill
	or $m2, $m1, $m2
	sub $m2, 72, $m2
	setzi $m3, 43691
	mul $m3, $m2, $m3
	setzi $m4, 43690
	shr $m3, $m3, 16
	mul $m2, $m2, $m4
	sort4x16lo $m3, $m3, $m15
	add $m2, $m2, $m3
	and $m0, $m0, 7
	shr $m2, $m2, 20
	setzi $m3, 983040
	ld32step $m4, $m15, $m5+=, 7
	st32 $m5, $m11, $m15, 3                 # 4-byte Folded Spill
	mul $m0, $m0, 288
	add $m1, $m1, $m2
	or $m2, $m15, 4278190080
	st32 $m2, $m11, $m15, 11                # 4-byte Folded Spill
	or $m2, $m3, 15728640
	st32 $m2, $m11, $m15, 10                # 4-byte Folded Spill
	setzi $m2, 65280
	st32 $m2, $m11, $m15, 9                 # 4-byte Folded Spill
	ld32 $m2, $m13, $m15, 1
	st32 $m2, $m11, $m15, 8                 # 4-byte Folded Spill
	add $m2, $m4, $m0
	add $m0, $m1, 1
	st32 $m0, $m11, $m15, 1                 # 4-byte Folded Spill
.Lpack2_10_BB0_2:                                # %for.body.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
                                        #       Child Loop BB0_4 Depth 3
	ld32 $m0, $m11, $m15, 1                 # 4-byte Folded Reload
	st32 $m6, $m11, $m15, 5                 # 4-byte Folded Spill
	mul $m1, $m6, 7680
	st32 $m1, $m11, $m15, 6                 # 4-byte Folded Spill
	add $m0, $m0, -1
	st32 $m2, $m11, $m15, 4                 # 4-byte Folded Spill
	mov	$m6, $m2
	ld32 $m4, $m11, $m15, 2                 # 4-byte Folded Reload
.Lpack2_10_BB0_3:                                # %for.cond9.preheader.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Loop Header: Depth=2
                                        #       Child Loop BB0_4 Depth 3
	st32 $m0, $m11, $m15, 7                 # 4-byte Folded Spill
	st32 $m15, $m11, $m15, 21               # 4-byte Folded Spill
	st32 $m15, $m11, $m15, 20               # 4-byte Folded Spill
	setzi $m0, 20
	shr $m2, $m4, 5
	and $m3, $m4, 28
	or $m1, $m4, 1
	st32 $m1, $m11, $m15, 16                # 4-byte Folded Spill
	or $m1, $m4, 2
	st32 $m1, $m11, $m15, 15                # 4-byte Folded Spill
	or $m1, $m4, 3
	st32 $m1, $m11, $m15, 14                # 4-byte Folded Spill
	mul $m1, $m2, 5
	st32 $m1, $m11, $m15, 13                # 4-byte Folded Spill
	ld32 $m1, $m11, $m15, 6                 # 4-byte Folded Reload
	or $m1, $m3, $m1
	st32 $m1, $m11, $m15, 12                # 4-byte Folded Spill
	st32 $m4, $m11, $m15, 17                # 4-byte Folded Spill
	st32 $m6, $m11, $m15, 18                # 4-byte Folded Spill
.Lpack2_10_BB0_4:                                # %for.body12.i
                                        #   Parent Loop BB0_2 Depth=1
                                        #     Parent Loop BB0_3 Depth=2
                                        # =>    This Inner Loop Header: Depth=3
	mov	$m9, $m15
	setzi $m2, 72
	cmpult $m3, $m2, $m4
	setzi $m10, 71
	brnz $m3, .Lpack2_10_BB0_5
# %bb.9:                                # %for.body12.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m1, $m11, $m15, 20                # 4-byte Folded Reload
	cmpult $m3, $m10, $m1
	brnz $m3, .Lpack2_10_BB0_13
# %bb.10:                               # %if.end.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m3, $m1, 69
	brz $m3, .Lpack2_10_BB0_11
# %bb.12:                               # %if.then9.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m9, $m6, $m1, 0
	bri .Lpack2_10_BB0_13
.Lpack2_10_BB0_5:                                #   in Loop: Header=BB0_4 Depth=3
	ld32 $m1, $m11, $m15, 20                # 4-byte Folded Reload
	bri .Lpack2_10_BB0_13
.Lpack2_10_BB0_11:                               # %for.body.i.preheader.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ldz8 $m3, $m6, $m1, 1
	ldz8 $m4, $m6, $m15, $m1
	shl $m3, $m3, 8
	or $m3, $m3, $m4
	ldz8 $m4, $m6, $m1, 2
	shl $m4, $m4, 16
	or $m3, $m3, $m4
	ldz8 $m4, $m6, $m1, 3
	shl $m4, $m4, 24
	or $m9, $m3, $m4
.Lpack2_10_BB0_13:                               # %_ZZN15Vertex_pack2_107computeEjENKUljjE_clEjj.exit.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m3, $m15
	ld32 $m4, $m11, $m15, 16                # 4-byte Folded Reload
	cmpult $m4, $m2, $m4
	brnz $m4, .Lpack2_10_BB0_18
# %bb.14:                               # %_ZZN15Vertex_pack2_107computeEjENKUljjE_clEjj.exit.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m4, $m10, $m1
	brnz $m4, .Lpack2_10_BB0_18
# %bb.15:                               # %if.end.i95.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m4, $m1, 69
	add $m3, $m6, $m1
	brz $m4, .Lpack2_10_BB0_16
# %bb.17:                               # %if.then9.i99.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m3, $m3, $m15, 18
	bri .Lpack2_10_BB0_18
.Lpack2_10_BB0_16:                               # %for.body.i110.preheader.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ldz8 $m4, $m6, $m1, 73
	ldz8 $m3, $m3, $m15, 72
	shl $m4, $m4, 8
	or $m3, $m4, $m3
	ldz8 $m4, $m6, $m1, 74
	shl $m4, $m4, 16
	or $m3, $m3, $m4
	ldz8 $m4, $m6, $m1, 75
	shl $m4, $m4, 24
	or $m3, $m3, $m4
.Lpack2_10_BB0_18:                               # %_ZZN15Vertex_pack2_107computeEjENKUljjE_clEjj.exit112.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m4, $m15
	ld32 $m5, $m11, $m15, 15                # 4-byte Folded Reload
	cmpult $m5, $m2, $m5
	brnz $m5, .Lpack2_10_BB0_23
# %bb.19:                               # %_ZZN15Vertex_pack2_107computeEjENKUljjE_clEjj.exit112.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m5, $m10, $m1
	brnz $m5, .Lpack2_10_BB0_23
# %bb.20:                               # %if.end.i122.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m5, $m1, 69
	add $m4, $m6, $m1
	brz $m5, .Lpack2_10_BB0_21
# %bb.22:                               # %if.then9.i126.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m4, $m4, $m15, 36
	bri .Lpack2_10_BB0_23
.Lpack2_10_BB0_21:                               # %for.body.i137.preheader.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ldz8 $m5, $m6, $m1, 145
	ldz8 $m4, $m4, $m15, 144
	shl $m5, $m5, 8
	or $m4, $m5, $m4
	ldz8 $m5, $m6, $m1, 146
	shl $m5, $m5, 16
	or $m4, $m4, $m5
	ldz8 $m5, $m6, $m1, 147
	shl $m5, $m5, 24
	or $m4, $m4, $m5
.Lpack2_10_BB0_23:                               # %_ZZN15Vertex_pack2_107computeEjENKUljjE_clEjj.exit139.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m5, $m15
	ld32 $m7, $m11, $m15, 14                # 4-byte Folded Reload
	cmpult $m2, $m2, $m7
	brnz $m2, .Lpack2_10_BB0_28
# %bb.24:                               # %_ZZN15Vertex_pack2_107computeEjENKUljjE_clEjj.exit139.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m2, $m10, $m1
	brnz $m2, .Lpack2_10_BB0_28
# %bb.25:                               # %if.end.i149.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m5, $m1, 69
	add $m2, $m6, $m1
	brz $m5, .Lpack2_10_BB0_26
# %bb.27:                               # %if.then9.i153.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m5, $m2, $m15, 54
	bri .Lpack2_10_BB0_28
.Lpack2_10_BB0_26:                               # %for.body.i164.preheader.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ldz8 $m5, $m6, $m1, 217
	ldz8 $m2, $m2, $m15, 216
	shl $m5, $m5, 8
	or $m2, $m5, $m2
	ldz8 $m5, $m6, $m1, 218
	shl $m5, $m5, 16
	or $m2, $m2, $m5
	ldz8 $m5, $m6, $m1, 219
	shl $m5, $m5, 24
	or $m5, $m2, $m5
.Lpack2_10_BB0_28:                               # %_ZZN15Vertex_pack2_107computeEjENKUljjE_clEjj.exit166.i
                                        #   in Loop: Header=BB0_4 Depth=3
	add $m0, $m0, -1
	st32 $m0, $m11, $m15, 19                # 4-byte Folded Spill
	shr $m2, $m1, 4
	ld32 $m0, $m11, $m15, 13                # 4-byte Folded Reload
	add $m2, $m2, $m0
	shl $m2, $m2, 9
	ld32 $m0, $m11, $m15, 12                # 4-byte Folded Reload
	add $m2, $m0, $m2
	add $m1, $m1, 4
	st32 $m1, $m11, $m15, 20                # 4-byte Folded Spill
	shr $m10, $m9, 8
	and $m10, $m10, 255
	shr $m6, $m9, 16
	and $m6, $m6, 255
	shr $m7, $m3, 8
	ld32 $m1, $m11, $m15, 9                 # 4-byte Folded Reload
	and $m7, $m7, $m1
	or $m6, $m7, $m6
	shr $m7, $m3, 16
	and $m7, $m7, $m1
	and $m8, $m9, 255
	shr $m9, $m9, 24
	or $m7, $m7, $m9
	shl $m9, $m3, 8
	and $m3, $m3, $m1
	and $m9, $m9, $m1
	or $m3, $m3, $m10
	shl $m10, $m5, 24
	or $m8, $m10, $m8
	shl $m10, $m4, 8
	ld32 $m1, $m11, $m15, 10                # 4-byte Folded Reload
	and $m10, $m10, $m1
	or $m8, $m8, $m9
	shr $m9, $m4, 8
	and $m9, $m9, $m1
	or $m3, $m3, $m10
	shl $m10, $m4, 16
	and $m4, $m4, $m1
	and $m10, $m10, $m1
	or $m4, $m6, $m4
	ld32 $m0, $m11, $m15, 21                # 4-byte Folded Reload
	and $m6, $m0, 384
	or $m6, $m2, $m6
	shl $m2, $m5, 16
	ld32 $m1, $m11, $m15, 11                # 4-byte Folded Reload
	and $m2, $m2, $m1
	or $m7, $m7, $m9
	shl $m9, $m5, 8
	and $m9, $m9, $m1
	and $m5, $m5, $m1
	or $m8, $m8, $m10
	or $m10, $m3, $m2
	or $m1, $m6, 32
	or $m4, $m4, $m9
	or $m9, $m6, 64
	or $m2, $m7, $m5
	or $m3, $m6, 96
	ld32 $m5, $m11, $m15, 8                 # 4-byte Folded Reload
	st32 $m8, $m5, $m6, 0
	ld32 $m6, $m11, $m15, 18                # 4-byte Folded Reload
	st32 $m10, $m5, $m1, 0
	st32 $m4, $m5, $m9, 0
	st32 $m2, $m5, $m3, 0
	add $m0, $m0, 128
	st32 $m0, $m11, $m15, 21                # 4-byte Folded Spill
	ld32 $m0, $m11, $m15, 19                # 4-byte Folded Reload
	ld32 $m4, $m11, $m15, 17                # 4-byte Folded Reload
	brnz $m0, .Lpack2_10_BB0_4
# %bb.6:                                # %for.cond.cleanup11.i
                                        #   in Loop: Header=BB0_3 Depth=2
	ld32 $m0, $m11, $m15, 7                 # 4-byte Folded Reload
	add $m4, $m4, 24
	add $m6, $m6, 1728
	brnzdec $m0, .Lpack2_10_BB0_3
# %bb.7:                                # %for.cond.cleanup7.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m0, $m11, $m15, 3                 # 4-byte Folded Reload
	ld32 $m0, $m0, $m15, 0
	ld32 $m6, $m11, $m15, 5                 # 4-byte Folded Reload
	add $m6, $m6, 1
	cmpult $m0, $m6, $m0
	ld32 $m2, $m11, $m15, 4                 # 4-byte Folded Reload
	add $m2, $m2, 5256
	brnz $m0, .Lpack2_10_BB0_2
.Lpack2_10_BB0_8:                                # %_ZN15Vertex_pack2_107computeEj.exit
	exitz $m15
.Lpack2_10_func_end0:
	.size	__runCodelet_Vertex_pack2_10, .Lpack2_10_func_end0-__runCodelet_Vertex_pack2_10
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack2_10
	.long	.Lpack2_10_func_begin0
	.byte	88
	.section	.text.__runCodelet_Vertex_pack2_10,"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