.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack2_14,"ax",@progbits
	.globl	__runCodelet_Vertex_pack2_14    # -- Begin function __runCodelet_Vertex_pack2_14
	.p2align	2
	.type	__runCodelet_Vertex_pack2_14,@function
__runCodelet_Vertex_pack2_14:           # @__runCodelet_Vertex_pack2_14
	.worker
.Lpack2_14_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 152
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -152
	get $m0, 1
	ld32 $m1, $m13, $m15, 7
	brz $m1, .Lpack2_14_BB0_23
# %bb.1:                                # %for.body.lr.ph.i
	mov	$m1, $m13
	mov	$m5, $m15
	ld32step $m2, $m15, $m1+=, 7
	st32 $m1, $m11, $m15, 3                 # 4-byte Folded Spill
	shl $m1, $m0, 2
	and $m4, $m1, 28
	and $m0, $m0, 7
	mul $m0, $m0, 28
	st32 $m2, $m11, $m15, 2                 # 4-byte Folded Spill
	add $m6, $m2, $m0
	max $m0, $m4, 8
	sub $m1, $m0, $m4
	cmpeq $m2, $m1, 0
	setzi $m3, 1
	movnz	$m3, $m2, $m1
	sub $m0, $m0, $m3
	st32 $m4, $m11, $m15, 1                 # 4-byte Folded Spill
	sub $m0, $m0, $m4
	setzi $m1, 43691
	sort4x16lo $m2, $m0, $m15
	shr $m0, $m0, 16
	mul $m4, $m2, $m1
	mul $m1, $m0, $m1
	shr $m4, $m4, 16
	add $m1, $m1, $m4
	setzi $m4, 43690
	mul $m2, $m2, $m4
	mul $m0, $m0, $m4
	sort4x16lo $m4, $m1, $m15
	shr $m1, $m1, 16
	add $m2, $m2, $m4
	add $m0, $m0, $m1
	shr $m1, $m2, 16
	add $m0, $m0, $m1
	shr $m0, $m0, 4
	setzi $m1, 983040
	add $m0, $m3, $m0
	or $m2, $m15, 4278190080
	st32 $m2, $m11, $m15, 21                # 4-byte Folded Spill
	or $m1, $m1, 15728640
	st32 $m1, $m11, $m15, 20                # 4-byte Folded Spill
	setzi $m1, 65280
	st32 $m1, $m11, $m15, 19                # 4-byte Folded Spill
	ld32 $m1, $m13, $m15, 1
	st32 $m1, $m11, $m15, 18                # 4-byte Folded Spill
	add $m0, $m0, 1
	st32 $m0, $m11, $m15, 0                 # 4-byte Folded Spill
	add $m2, $m6, 7
	add $m3, $m6, 14
	add $m4, $m6, 21
.Lpack2_14_BB0_2:                                # %for.body.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
                                        #       Child Loop BB0_4 Depth 3
	ld32 $m7, $m11, $m15, 0                 # 4-byte Folded Reload
	add $m7, $m7, -1
	mul $m0, $m5, 70
	ld32 $m1, $m11, $m15, 2                 # 4-byte Folded Reload
	add $m0, $m1, $m0
	st32 $m0, $m11, $m15, 17                # 4-byte Folded Spill
	shl $m0, $m5, 9
	st32 $m0, $m11, $m15, 9                 # 4-byte Folded Spill
	st32 $m5, $m11, $m15, 8                 # 4-byte Folded Spill
	and $m0, $m5, 1
	st32 $m0, $m11, $m15, 22                # 4-byte Folded Spill
	st32 $m4, $m11, $m15, 4                 # 4-byte Folded Spill
	st32 $m3, $m11, $m15, 5                 # 4-byte Folded Spill
	st32 $m2, $m11, $m15, 6                 # 4-byte Folded Spill
	mov	$m5, $m2
	st32 $m6, $m11, $m15, 7                 # 4-byte Folded Spill
	ld32 $m8, $m11, $m15, 1                 # 4-byte Folded Reload
.Lpack2_14_BB0_3:                                # %for.cond9.preheader.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Loop Header: Depth=2
                                        #       Child Loop BB0_4 Depth 3
	st32 $m7, $m11, $m15, 14                # 4-byte Folded Spill
	mov	$m9, $m15
	mov	$m2, $m15
	and $m0, $m8, 28
	ld32 $m1, $m11, $m15, 9                 # 4-byte Folded Reload
	or $m0, $m0, $m1
	setzi $m1, 4
	or $m7, $m8, 2
	or $m10, $m8, 1
	st32 $m10, $m11, $m15, 27               # 4-byte Folded Spill
	or $m10, $m8, 3
	st32 $m10, $m11, $m15, 26               # 4-byte Folded Spill
	mul $m10, $m8, 7
	st32 $m10, $m11, $m15, 15               # 4-byte Folded Spill
	st32 $m7, $m11, $m15, 28                # 4-byte Folded Spill
	mul $m7, $m7, 7
	st32 $m7, $m11, $m15, 16                # 4-byte Folded Spill
	or $m7, $m0, 32
	st32 $m7, $m11, $m15, 25                # 4-byte Folded Spill
	or $m7, $m0, 64
	st32 $m7, $m11, $m15, 24                # 4-byte Folded Spill
	st32 $m0, $m11, $m15, 29                # 4-byte Folded Spill
	or $m0, $m0, 96
	st32 $m0, $m11, $m15, 23                # 4-byte Folded Spill
	st32 $m4, $m11, $m15, 13                # 4-byte Folded Spill
	st32 $m4, $m11, $m15, 32                # 4-byte Folded Spill
	st32 $m3, $m11, $m15, 12                # 4-byte Folded Spill
	st32 $m3, $m11, $m15, 33                # 4-byte Folded Spill
	st32 $m5, $m11, $m15, 11                # 4-byte Folded Spill
	st32 $m5, $m11, $m15, 35                # 4-byte Folded Spill
	st32 $m6, $m11, $m15, 10                # 4-byte Folded Spill
	st32 $m6, $m11, $m15, 34                # 4-byte Folded Spill
	st32 $m8, $m11, $m15, 30                # 4-byte Folded Spill
	st32 $m1, $m11, $m15, 36                # 4-byte Folded Spill
.Lpack2_14_BB0_4:                                # %for.body12.i
                                        #   Parent Loop BB0_2 Depth=1
                                        #     Parent Loop BB0_3 Depth=2
                                        # =>    This Inner Loop Header: Depth=3
	mov	$m5, $m15
	shl $m0, $m9, 2
	sub $m0, 6, $m0
	setzi $m7, 9
	cmpult $m1, $m0, 3
	setzi $m3, 3
	movnz	$m3, $m1, $m0
	cmpult $m0, $m7, $m8
	add $m3, $m3, 1
	setzi $m8, 6
	st32 $m9, $m11, $m15, 37                # 4-byte Folded Spill
	brnz $m0, .Lpack2_14_BB0_9
# %bb.5:                                # %for.body12.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m8, $m2
	brnz $m0, .Lpack2_14_BB0_9
# %bb.6:                                # %if.end.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 22                # 4-byte Folded Reload
	or $m0, $m2, $m0
	brz $m0, .Lpack2_14_BB0_28
# %bb.7:                                # %for.body.lr.ph.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m0, $m15
	mov	$m5, $m15
	mov	$m9, $m3
	ld32 $m6, $m11, $m15, 34                # 4-byte Folded Reload
# %bb.8:                                # %for.body.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	{
		rpt $m9, 3
		fnop
	}
	{
		ldz8step $m1, $m15, $m6+=, 1
		fnop
	}
	{
		shl $m1, $m1, $m0
		fnop
	}
	{
		or $m5, $m1, $m5
		fnop
	}
	{
		add $m0, $m0, 8
		fnop
	}
	bri .Lpack2_14_BB0_9
.Lpack2_14_BB0_28:                               # %if.then9.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 15                # 4-byte Folded Reload
	add $m0, $m2, $m0
	ld32 $m1, $m11, $m15, 17                # 4-byte Folded Reload
	ld32 $m5, $m1, $m0, 0
.Lpack2_14_BB0_9:                                # %_ZZN15Vertex_pack2_147computeEjENKUljjE_clEjj.exit.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m10, $m15
	ld32 $m0, $m11, $m15, 27                # 4-byte Folded Reload
	cmpult $m0, $m7, $m0
	brnz $m0, .Lpack2_14_BB0_13
# %bb.10:                               # %_ZZN15Vertex_pack2_147computeEjENKUljjE_clEjj.exit.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m8, $m2
	brnz $m0, .Lpack2_14_BB0_13
# %bb.11:                               # %if.end.i93.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m0, $m15
	mov	$m10, $m15
	mov	$m1, $m3
	ld32 $m6, $m11, $m15, 35                # 4-byte Folded Reload
# %bb.12:                               # %for.body.i106.i
                                        #   in Loop: Header=BB0_4 Depth=3
	{
		rpt $m1, 3
		fnop
	}
	{
		ldz8step $m9, $m15, $m6+=, 1
		fnop
	}
	{
		shl $m9, $m9, $m0
		fnop
	}
	{
		or $m10, $m9, $m10
		fnop
	}
	{
		add $m0, $m0, 8
		fnop
	}
.Lpack2_14_BB0_13:                               # %_ZZN15Vertex_pack2_147computeEjENKUljjE_clEjj.exit108.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m0, $m15
	ld32 $m1, $m11, $m15, 28                # 4-byte Folded Reload
	cmpult $m1, $m7, $m1
	brnz $m1, .Lpack2_14_BB0_19
# %bb.14:                               # %_ZZN15Vertex_pack2_147computeEjENKUljjE_clEjj.exit108.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m1, $m8, $m2
	brnz $m1, .Lpack2_14_BB0_19
# %bb.15:                               # %if.end.i120.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 22                # 4-byte Folded Reload
	brz $m0, .Lpack2_14_BB0_17
# %bb.16:                               # %if.end.i120.i
                                        #   in Loop: Header=BB0_4 Depth=3
	brnz $m2, .Lpack2_14_BB0_17
# %bb.29:                               # %if.then9.i124.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 16                # 4-byte Folded Reload
	add $m0, $m2, $m0
	ld32 $m1, $m11, $m15, 17                # 4-byte Folded Reload
	ld32 $m0, $m1, $m0, 0
	bri .Lpack2_14_BB0_19
.Lpack2_14_BB0_17:                               # %for.body.lr.ph.i122.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m9, $m15
	mov	$m0, $m15
	mov	$m6, $m3
	ld32 $m1, $m11, $m15, 33                # 4-byte Folded Reload
# %bb.18:                               # %for.body.i135.i
                                        #   in Loop: Header=BB0_4 Depth=3
	{
		rpt $m6, 3
		fnop
	}
	{
		ldz8step $m4, $m15, $m1+=, 1
		fnop
	}
	{
		shl $m4, $m4, $m9
		fnop
	}
	{
		or $m0, $m4, $m0
		fnop
	}
	{
		add $m9, $m9, 8
		fnop
	}
.Lpack2_14_BB0_19:                               # %_ZZN15Vertex_pack2_147computeEjENKUljjE_clEjj.exit137.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m9, $m15
	ld32 $m1, $m11, $m15, 26                # 4-byte Folded Reload
	cmpult $m1, $m7, $m1
	st32 $m2, $m11, $m15, 31                # 4-byte Folded Spill
	brnz $m1, .Lpack2_14_BB0_20
# %bb.24:                               # %_ZZN15Vertex_pack2_147computeEjENKUljjE_clEjj.exit137.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m1, $m8, $m2
	ld32 $m2, $m11, $m15, 32                # 4-byte Folded Reload
	brnz $m1, .Lpack2_14_BB0_27
# %bb.25:                               # %if.end.i147.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m7, $m15
	mov	$m9, $m15
	mov	$m1, $m2
# %bb.26:                               # %for.body.i160.i
                                        #   in Loop: Header=BB0_4 Depth=3
	{
		rpt $m3, 3
		fnop
	}
	{
		ldz8step $m4, $m15, $m1+=, 1
		fnop
	}
	{
		shl $m4, $m4, $m7
		fnop
	}
	{
		or $m9, $m4, $m9
		fnop
	}
	{
		add $m7, $m7, 8
		fnop
	}
	bri .Lpack2_14_BB0_27
.Lpack2_14_BB0_20:                               #   in Loop: Header=BB0_4 Depth=3
	ld32 $m2, $m11, $m15, 32                # 4-byte Folded Reload
.Lpack2_14_BB0_27:                               # %_ZZN15Vertex_pack2_147computeEjENKUljjE_clEjj.exit162.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m1, $m11, $m15, 36                # 4-byte Folded Reload
	add $m1, $m1, -1
	st32 $m1, $m11, $m15, 36                # 4-byte Folded Spill
	ld32 $m1, $m11, $m15, 34                # 4-byte Folded Reload
	add $m1, $m1, 4
	st32 $m1, $m11, $m15, 34                # 4-byte Folded Spill
	ld32 $m1, $m11, $m15, 35                # 4-byte Folded Reload
	add $m1, $m1, 4
	st32 $m1, $m11, $m15, 35                # 4-byte Folded Spill
	ld32 $m1, $m11, $m15, 33                # 4-byte Folded Reload
	add $m1, $m1, 4
	st32 $m1, $m11, $m15, 33                # 4-byte Folded Spill
	add $m2, $m2, 4
	st32 $m2, $m11, $m15, 32                # 4-byte Folded Spill
	ld32 $m1, $m11, $m15, 37                # 4-byte Folded Reload
	add $m1, $m1, 1
	st32 $m1, $m11, $m15, 37                # 4-byte Folded Spill
	shr $m1, $m5, 8
	and $m1, $m1, 255
	shr $m3, $m5, 16
	and $m3, $m3, 255
	shr $m4, $m10, 8
	ld32 $m8, $m11, $m15, 19                # 4-byte Folded Reload
	and $m4, $m4, $m8
	or $m3, $m4, $m3
	shr $m4, $m10, 16
	and $m4, $m4, $m8
	and $m6, $m5, 255
	shr $m5, $m5, 24
	or $m4, $m4, $m5
	shl $m5, $m10, 8
	and $m7, $m10, $m8
	and $m5, $m5, $m8
	or $m1, $m7, $m1
	shl $m7, $m9, 24
	or $m6, $m7, $m6
	shl $m7, $m0, 8
	ld32 $m8, $m11, $m15, 20                # 4-byte Folded Reload
	and $m7, $m7, $m8
	or $m5, $m6, $m5
	shr $m6, $m0, 8
	and $m6, $m6, $m8
	or $m1, $m1, $m7
	shl $m7, $m0, 16
	and $m0, $m0, $m8
	and $m7, $m7, $m8
	or $m0, $m3, $m0
	shl $m3, $m9, 16
	ld32 $m8, $m11, $m15, 21                # 4-byte Folded Reload
	and $m3, $m3, $m8
	or $m4, $m4, $m6
	shl $m6, $m9, 8
	and $m6, $m6, $m8
	and $m8, $m9, $m8
	or $m5, $m5, $m7
	ld32 $m2, $m11, $m15, 31                # 4-byte Folded Reload
	shl $m7, $m2, 5
	or $m1, $m1, $m3
	ld32 $m3, $m11, $m15, 29                # 4-byte Folded Reload
	add $m9, $m7, $m3
	or $m6, $m0, $m6
	ld32 $m0, $m11, $m15, 25                # 4-byte Folded Reload
	add $m10, $m0, $m7
	or $m0, $m4, $m8
	ld32 $m3, $m11, $m15, 24                # 4-byte Folded Reload
	add $m4, $m3, $m7
	ld32 $m3, $m11, $m15, 23                # 4-byte Folded Reload
	add $m3, $m3, $m7
	ld32 $m7, $m11, $m15, 18                # 4-byte Folded Reload
	st32 $m5, $m7, $m9, 0
	ld32 $m9, $m11, $m15, 37                # 4-byte Folded Reload
	st32 $m1, $m7, $m10, 0
	st32 $m6, $m7, $m4, 0
	st32 $m0, $m7, $m3, 0
	add $m2, $m2, 4
	ld32 $m8, $m11, $m15, 30                # 4-byte Folded Reload
	ld32 $m0, $m11, $m15, 36                # 4-byte Folded Reload
	brnz $m0, .Lpack2_14_BB0_4
# %bb.21:                               # %for.cond.cleanup11.i
                                        #   in Loop: Header=BB0_3 Depth=2
	ld32 $m7, $m11, $m15, 14                # 4-byte Folded Reload
	add $m8, $m8, 24
	ld32 $m6, $m11, $m15, 10                # 4-byte Folded Reload
	add $m6, $m6, 168
	ld32 $m5, $m11, $m15, 11                # 4-byte Folded Reload
	add $m5, $m5, 168
	ld32 $m3, $m11, $m15, 12                # 4-byte Folded Reload
	add $m3, $m3, 168
	ld32 $m4, $m11, $m15, 13                # 4-byte Folded Reload
	add $m4, $m4, 168
	brnzdec $m7, .Lpack2_14_BB0_3
# %bb.22:                               # %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 $m5, $m11, $m15, 8                 # 4-byte Folded Reload
	add $m5, $m5, 1
	cmpult $m0, $m5, $m0
	ld32 $m6, $m11, $m15, 7                 # 4-byte Folded Reload
	add $m6, $m6, 70
	ld32 $m2, $m11, $m15, 6                 # 4-byte Folded Reload
	add $m2, $m2, 70
	ld32 $m3, $m11, $m15, 5                 # 4-byte Folded Reload
	add $m3, $m3, 70
	ld32 $m4, $m11, $m15, 4                 # 4-byte Folded Reload
	add $m4, $m4, 70
	brnz $m0, .Lpack2_14_BB0_2
.Lpack2_14_BB0_23:                               # %_ZN15Vertex_pack2_147computeEj.exit
	exitz $m15
.Lpack2_14_func_end0:
	.size	__runCodelet_Vertex_pack2_14, .Lpack2_14_func_end0-__runCodelet_Vertex_pack2_14
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack2_14
	.long	.Lpack2_14_func_begin0
	.ascii	"\230\001"
	.section	.text.__runCodelet_Vertex_pack2_14,"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