.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack2_8,"ax",@progbits
	.globl	__runCodelet_Vertex_pack2_8     # -- Begin function __runCodelet_Vertex_pack2_8
	.p2align	2
	.type	__runCodelet_Vertex_pack2_8,@function
__runCodelet_Vertex_pack2_8:            # @__runCodelet_Vertex_pack2_8
	.worker
.Lpack2_8_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 168
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -168
	get $m0, 1
	ld32 $m1, $m13, $m15, 7
	brz $m1, .Lpack2_8_BB0_26
# %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 $m1, $m1, 28
	and $m0, $m0, 7
	mul $m0, $m0, 36
	st32 $m2, $m11, $m15, 2                 # 4-byte Folded Spill
	add $m4, $m2, $m0
	sub $m0, 72, $m1
	min $m0, $m0, 1
	st32 $m1, $m11, $m15, 1                 # 4-byte Folded Spill
	or $m1, $m0, $m1
	sub $m1, 72, $m1
	setzi $m2, 43691
	mul $m2, $m1, $m2
	shr $m2, $m2, 16
	sort4x16lo $m2, $m2, $m15
	setzi $m3, 43690
	mul $m1, $m1, $m3
	add $m1, $m1, $m2
	shr $m1, $m1, 20
	setzi $m2, 983040
	add $m0, $m0, $m1
	or $m1, $m15, 4278190080
	st32 $m1, $m11, $m15, 26                # 4-byte Folded Spill
	or $m1, $m2, 15728640
	st32 $m1, $m11, $m15, 25                # 4-byte Folded Spill
	setzi $m1, 65280
	st32 $m1, $m11, $m15, 24                # 4-byte Folded Spill
	add $m0, $m0, 1
	st32 $m0, $m11, $m15, 0                 # 4-byte Folded Spill
	ld32 $m0, $m13, $m15, 1
	st32 $m0, $m11, $m15, 23                # 4-byte Folded Spill
	add $m3, $m4, 9
	add $m6, $m4, 18
	add $m7, $m4, 27
.Lpack2_8_BB0_2:                                # %for.body.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
                                        #       Child Loop BB0_4 Depth 3
	mov	$m0, $m5
	ld32 $m5, $m11, $m15, 0                 # 4-byte Folded Reload
	add $m5, $m5, -1
	mul $m1, $m0, 585
	ld32 $m2, $m11, $m15, 2                 # 4-byte Folded Reload
	add $m1, $m2, $m1
	st32 $m1, $m11, $m15, 27                # 4-byte Folded Spill
	mul $m1, $m0, 1536
	st32 $m1, $m11, $m15, 9                 # 4-byte Folded Spill
	and $m1, $m0, 3
	st32 $m1, $m11, $m15, 22                # 4-byte Folded Spill
	add $m1, $m0, 2
	and $m1, $m1, 3
	st32 $m1, $m11, $m15, 21                # 4-byte Folded Spill
	add $m1, $m0, -1
	add $m0, $m0, 1
	and $m1, $m1, 3
	st32 $m1, $m11, $m15, 20                # 4-byte Folded Spill
	st32 $m0, $m11, $m15, 7                 # 4-byte Folded Spill
	and $m0, $m0, 3
	st32 $m0, $m11, $m15, 19                # 4-byte Folded Spill
	st32 $m7, $m11, $m15, 4                 # 4-byte Folded Spill
	st32 $m6, $m11, $m15, 5                 # 4-byte Folded Spill
	st32 $m3, $m11, $m15, 6                 # 4-byte Folded Spill
	mov	$m8, $m3
	st32 $m4, $m11, $m15, 8                 # 4-byte Folded Spill
	ld32 $m3, $m11, $m15, 1                 # 4-byte Folded Reload
.Lpack2_8_BB0_3:                                # %for.cond9.preheader.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Loop Header: Depth=2
                                        #       Child Loop BB0_4 Depth 3
	st32 $m5, $m11, $m15, 14                # 4-byte Folded Spill
	mov	$m5, $m15
	mov	$m10, $m15
	setzi $m0, 1048064
	or $m0, $m0, 2146435072
	and $m1, $m3, 28
	ld32 $m2, $m11, $m15, 9                 # 4-byte Folded Reload
	or $m1, $m1, $m2
	shl $m2, $m3, 4
	and $m0, $m2, $m0
	setzi $m2, 4
	add $m0, $m1, $m0
	or $m1, $m3, 1
	or $m9, $m3, 2
	st32 $m9, $m11, $m15, 35                # 4-byte Folded Spill
	or $m9, $m3, 3
	st32 $m9, $m11, $m15, 34                # 4-byte Folded Spill
	mul $m9, $m3, 9
	st32 $m9, $m11, $m15, 18                # 4-byte Folded Spill
	st32 $m1, $m11, $m15, 31                # 4-byte Folded Spill
	mul $m1, $m1, 9
	st32 $m1, $m11, $m15, 17                # 4-byte Folded Spill
	ld32 $m1, $m11, $m15, 35                # 4-byte Folded Reload
	mul $m1, $m1, 9
	st32 $m1, $m11, $m15, 16                # 4-byte Folded Spill
	ld32 $m1, $m11, $m15, 34                # 4-byte Folded Reload
	mul $m1, $m1, 9
	st32 $m1, $m11, $m15, 15                # 4-byte Folded Spill
	or $m1, $m0, 32
	st32 $m1, $m11, $m15, 30                # 4-byte Folded Spill
	or $m1, $m0, 64
	st32 $m1, $m11, $m15, 29                # 4-byte Folded Spill
	st32 $m0, $m11, $m15, 32                # 4-byte Folded Spill
	or $m0, $m0, 96
	st32 $m0, $m11, $m15, 28                # 4-byte Folded Spill
	st32 $m7, $m11, $m15, 13                # 4-byte Folded Spill
	st32 $m7, $m11, $m15, 37                # 4-byte Folded Spill
	st32 $m6, $m11, $m15, 12                # 4-byte Folded Spill
	st32 $m6, $m11, $m15, 40                # 4-byte Folded Spill
	st32 $m8, $m11, $m15, 11                # 4-byte Folded Spill
	st32 $m8, $m11, $m15, 39                # 4-byte Folded Spill
	st32 $m4, $m11, $m15, 10                # 4-byte Folded Spill
	st32 $m4, $m11, $m15, 38                # 4-byte Folded Spill
	st32 $m3, $m11, $m15, 33                # 4-byte Folded Spill
	st32 $m2, $m11, $m15, 41                # 4-byte Folded Spill
.Lpack2_8_BB0_4:                                # %for.body12.i
                                        #   Parent Loop BB0_2 Depth=1
                                        #     Parent Loop BB0_3 Depth=2
                                        # =>    This Inner Loop Header: Depth=3
	mov	$m4, $m15
	shl $m0, $m5, 2
	sub $m0, 8, $m0
	setzi $m6, 64
	cmpult $m1, $m0, 3
	setzi $m2, 3
	movnz	$m2, $m1, $m0
	cmpult $m0, $m6, $m3
	add $m7, $m2, 1
	setzi $m9, 8
	st32 $m5, $m11, $m15, 36                # 4-byte Folded Spill
	mov	$m3, $m10
	brnz $m0, .Lpack2_8_BB0_10
# %bb.5:                                # %for.body12.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m9, $m3
	brnz $m0, .Lpack2_8_BB0_10
# %bb.6:                                # %if.end.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 22                # 4-byte Folded Reload
	brnz $m0, .Lpack2_8_BB0_8
# %bb.7:                                # %if.end.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m3, 6
	brz $m0, .Lpack2_8_BB0_8
# %bb.33:                               # %if.then9.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 18                # 4-byte Folded Reload
	add $m0, $m3, $m0
	ld32 $m1, $m11, $m15, 27                # 4-byte Folded Reload
	ld32 $m4, $m1, $m0, 0
	bri .Lpack2_8_BB0_10
.Lpack2_8_BB0_8:                                # %for.body.lr.ph.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m1, $m15
	mov	$m4, $m15
	mov	$m2, $m7
	ld32 $m5, $m11, $m15, 38                # 4-byte Folded Reload
# %bb.9:                                # %for.body.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	{
		rpt $m2, 3
		fnop
	}
	{
		ldz8step $m0, $m15, $m5+=, 1
		fnop
	}
	{
		shl $m0, $m0, $m1
		fnop
	}
	{
		or $m4, $m0, $m4
		fnop
	}
	{
		add $m1, $m1, 8
		fnop
	}
.Lpack2_8_BB0_10:                               # %_ZZN14Vertex_pack2_87computeEjENKUljjE_clEjj.exit.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m8, $m15
	ld32 $m0, $m11, $m15, 31                # 4-byte Folded Reload
	cmpult $m0, $m6, $m0
	brnz $m0, .Lpack2_8_BB0_16
# %bb.11:                               # %_ZZN14Vertex_pack2_87computeEjENKUljjE_clEjj.exit.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m9, $m3
	brnz $m0, .Lpack2_8_BB0_16
# %bb.12:                               # %if.end.i95.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 19                # 4-byte Folded Reload
	brnz $m0, .Lpack2_8_BB0_14
# %bb.13:                               # %if.end.i95.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m3, 6
	brz $m0, .Lpack2_8_BB0_14
# %bb.34:                               # %if.then9.i99.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 17                # 4-byte Folded Reload
	add $m0, $m3, $m0
	ld32 $m1, $m11, $m15, 27                # 4-byte Folded Reload
	ld32 $m8, $m1, $m0, 0
	bri .Lpack2_8_BB0_16
.Lpack2_8_BB0_14:                               # %for.body.lr.ph.i97.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m1, $m15
	mov	$m8, $m15
	mov	$m2, $m7
	ld32 $m5, $m11, $m15, 39                # 4-byte Folded Reload
# %bb.15:                               # %for.body.i110.i
                                        #   in Loop: Header=BB0_4 Depth=3
	{
		rpt $m2, 3
		fnop
	}
	{
		ldz8step $m0, $m15, $m5+=, 1
		fnop
	}
	{
		shl $m0, $m0, $m1
		fnop
	}
	{
		or $m8, $m0, $m8
		fnop
	}
	{
		add $m1, $m1, 8
		fnop
	}
.Lpack2_8_BB0_16:                               # %_ZZN14Vertex_pack2_87computeEjENKUljjE_clEjj.exit112.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m2, $m15
	ld32 $m0, $m11, $m15, 35                # 4-byte Folded Reload
	cmpult $m0, $m6, $m0
	brnz $m0, .Lpack2_8_BB0_22
# %bb.17:                               # %_ZZN14Vertex_pack2_87computeEjENKUljjE_clEjj.exit112.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m9, $m3
	brnz $m0, .Lpack2_8_BB0_22
# %bb.18:                               # %if.end.i123.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 21                # 4-byte Folded Reload
	brnz $m0, .Lpack2_8_BB0_20
# %bb.19:                               # %if.end.i123.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m3, 6
	brz $m0, .Lpack2_8_BB0_20
# %bb.35:                               # %if.then9.i127.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 16                # 4-byte Folded Reload
	add $m0, $m3, $m0
	ld32 $m1, $m11, $m15, 27                # 4-byte Folded Reload
	ld32 $m2, $m1, $m0, 0
	bri .Lpack2_8_BB0_22
.Lpack2_8_BB0_20:                               # %for.body.lr.ph.i125.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m1, $m15
	mov	$m2, $m15
	mov	$m5, $m7
	ld32 $m0, $m11, $m15, 40                # 4-byte Folded Reload
# %bb.21:                               # %for.body.i138.i
                                        #   in Loop: Header=BB0_4 Depth=3
	{
		rpt $m5, 3
		fnop
	}
	{
		ldz8step $m10, $m15, $m0+=, 1
		fnop
	}
	{
		shl $m10, $m10, $m1
		fnop
	}
	{
		or $m2, $m10, $m2
		fnop
	}
	{
		add $m1, $m1, 8
		fnop
	}
.Lpack2_8_BB0_22:                               # %_ZZN14Vertex_pack2_87computeEjENKUljjE_clEjj.exit140.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m1, $m15
	ld32 $m0, $m11, $m15, 34                # 4-byte Folded Reload
	cmpult $m0, $m6, $m0
	brnz $m0, .Lpack2_8_BB0_23
# %bb.27:                               # %_ZZN14Vertex_pack2_87computeEjENKUljjE_clEjj.exit140.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m9, $m3
	ld32 $m9, $m11, $m15, 37                # 4-byte Folded Reload
	brnz $m0, .Lpack2_8_BB0_32
# %bb.28:                               # %if.end.i151.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 20                # 4-byte Folded Reload
	brnz $m0, .Lpack2_8_BB0_30
# %bb.29:                               # %if.end.i151.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m0, $m3, 6
	brz $m0, .Lpack2_8_BB0_30
# %bb.36:                               # %if.then9.i155.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 15                # 4-byte Folded Reload
	add $m0, $m3, $m0
	ld32 $m1, $m11, $m15, 27                # 4-byte Folded Reload
	ld32 $m1, $m1, $m0, 0
	bri .Lpack2_8_BB0_32
.Lpack2_8_BB0_23:                               #   in Loop: Header=BB0_4 Depth=3
	ld32 $m9, $m11, $m15, 37                # 4-byte Folded Reload
	bri .Lpack2_8_BB0_32
.Lpack2_8_BB0_30:                               # %for.body.lr.ph.i153.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m6, $m15
	mov	$m1, $m15
	mov	$m0, $m9
# %bb.31:                               # %for.body.i166.i
                                        #   in Loop: Header=BB0_4 Depth=3
	{
		rpt $m7, 3
		fnop
	}
	{
		ldz8step $m5, $m15, $m0+=, 1
		fnop
	}
	{
		shl $m5, $m5, $m6
		fnop
	}
	{
		or $m1, $m5, $m1
		fnop
	}
	{
		add $m6, $m6, 8
		fnop
	}
.Lpack2_8_BB0_32:                               # %_ZZN14Vertex_pack2_87computeEjENKUljjE_clEjj.exit168.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m0, $m11, $m15, 41                # 4-byte Folded Reload
	add $m0, $m0, -1
	st32 $m0, $m11, $m15, 41                # 4-byte Folded Spill
	ld32 $m0, $m11, $m15, 38                # 4-byte Folded Reload
	add $m0, $m0, 4
	st32 $m0, $m11, $m15, 38                # 4-byte Folded Spill
	ld32 $m0, $m11, $m15, 39                # 4-byte Folded Reload
	add $m0, $m0, 4
	st32 $m0, $m11, $m15, 39                # 4-byte Folded Spill
	ld32 $m0, $m11, $m15, 40                # 4-byte Folded Reload
	add $m0, $m0, 4
	st32 $m0, $m11, $m15, 40                # 4-byte Folded Spill
	add $m9, $m9, 4
	st32 $m9, $m11, $m15, 37                # 4-byte Folded Spill
	ld32 $m10, $m11, $m15, 36               # 4-byte Folded Reload
	add $m10, $m10, 1
	shr $m0, $m4, 8
	and $m0, $m0, 255
	shr $m5, $m4, 16
	and $m5, $m5, 255
	shr $m6, $m8, 8
	ld32 $m9, $m11, $m15, 24                # 4-byte Folded Reload
	and $m6, $m6, $m9
	or $m5, $m6, $m5
	shr $m6, $m8, 16
	and $m6, $m6, $m9
	and $m7, $m4, 255
	shr $m4, $m4, 24
	or $m4, $m6, $m4
	shl $m6, $m8, 8
	and $m8, $m8, $m9
	and $m6, $m6, $m9
	or $m0, $m8, $m0
	shl $m8, $m1, 24
	or $m7, $m8, $m7
	shl $m8, $m2, 8
	ld32 $m9, $m11, $m15, 25                # 4-byte Folded Reload
	and $m8, $m8, $m9
	or $m6, $m7, $m6
	shr $m7, $m2, 8
	and $m7, $m7, $m9
	or $m0, $m0, $m8
	shl $m8, $m2, 16
	and $m2, $m2, $m9
	and $m8, $m8, $m9
	or $m2, $m5, $m2
	shl $m5, $m1, 16
	ld32 $m9, $m11, $m15, 26                # 4-byte Folded Reload
	and $m5, $m5, $m9
	or $m4, $m4, $m7
	shl $m7, $m1, 8
	and $m7, $m7, $m9
	and $m1, $m1, $m9
	or $m6, $m6, $m8
	shl $m8, $m3, 5
	or $m0, $m0, $m5
	ld32 $m5, $m11, $m15, 32                # 4-byte Folded Reload
	add $m5, $m8, $m5
	or $m7, $m2, $m7
	ld32 $m2, $m11, $m15, 30                # 4-byte Folded Reload
	add $m9, $m2, $m8
	or $m1, $m4, $m1
	ld32 $m2, $m11, $m15, 29                # 4-byte Folded Reload
	add $m4, $m2, $m8
	ld32 $m2, $m11, $m15, 28                # 4-byte Folded Reload
	add $m2, $m2, $m8
	ld32 $m8, $m11, $m15, 23                # 4-byte Folded Reload
	st32 $m6, $m8, $m5, 0
	mov	$m5, $m10
	st32 $m0, $m8, $m9, 0
	st32 $m7, $m8, $m4, 0
	st32 $m1, $m8, $m2, 0
	add $m3, $m3, 4
	mov	$m10, $m3
	ld32 $m0, $m11, $m15, 41                # 4-byte Folded Reload
	ld32 $m3, $m11, $m15, 33                # 4-byte Folded Reload
	brnz $m0, .Lpack2_8_BB0_4
# %bb.24:                               # %for.cond.cleanup11.i
                                        #   in Loop: Header=BB0_3 Depth=2
	ld32 $m5, $m11, $m15, 14                # 4-byte Folded Reload
	add $m3, $m3, 24
	ld32 $m4, $m11, $m15, 10                # 4-byte Folded Reload
	add $m4, $m4, 216
	ld32 $m8, $m11, $m15, 11                # 4-byte Folded Reload
	add $m8, $m8, 216
	ld32 $m6, $m11, $m15, 12                # 4-byte Folded Reload
	add $m6, $m6, 216
	ld32 $m7, $m11, $m15, 13                # 4-byte Folded Reload
	add $m7, $m7, 216
	brnzdec $m5, .Lpack2_8_BB0_3
# %bb.25:                               # %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, 7                 # 4-byte Folded Reload
	cmpult $m0, $m5, $m0
	ld32 $m4, $m11, $m15, 8                 # 4-byte Folded Reload
	add $m4, $m4, 585
	ld32 $m3, $m11, $m15, 6                 # 4-byte Folded Reload
	add $m3, $m3, 585
	ld32 $m6, $m11, $m15, 5                 # 4-byte Folded Reload
	add $m6, $m6, 585
	ld32 $m7, $m11, $m15, 4                 # 4-byte Folded Reload
	add $m7, $m7, 585
	brnz $m0, .Lpack2_8_BB0_2
.Lpack2_8_BB0_26:                               # %_ZN14Vertex_pack2_87computeEj.exit
	exitz $m15
.Lpack2_8_func_end0:
	.size	__runCodelet_Vertex_pack2_8, .Lpack2_8_func_end0-__runCodelet_Vertex_pack2_8
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack2_8
	.long	.Lpack2_8_func_begin0
	.ascii	"\250\001"
	.section	.text.__runCodelet_Vertex_pack2_8,"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