.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack2_1,"ax",@progbits
	.globl	__runCodelet_Vertex_pack2_1     # -- Begin function __runCodelet_Vertex_pack2_1
	.p2align	2
	.type	__runCodelet_Vertex_pack2_1,@function
__runCodelet_Vertex_pack2_1:            # @__runCodelet_Vertex_pack2_1
	.worker
.Lpack2_1_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 56
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -56
	get $m0, 1
	ld32 $m1, $m13, $m15, 7
	brz $m1, .Lpack2_1_BB0_8
# %bb.1:                                # %for.cond3.preheader.i.preheader
	mov	$m4, $m15
	and $m3, $m0, 7
	sub $m0, 41, $m3
	setzi $m1, 43691
	setzi $m2, 43690
	mul $m1, $m0, $m1
	mul $m0, $m0, $m2
	shr $m1, $m1, 16
	ld32 $m2, $m13, $m15, 0
	st32 $m3, $m11, $m15, 3                 # 4-byte Folded Spill
	shl $m3, $m3, 7
	add $m0, $m0, $m1
	setzi $m1, 1048572
	add $m3, $m3, $m2
	shr $m0, $m0, 18
	ld32 $m2, $m13, $m15, 1
	or $m1, $m1, 15728640
	st32 $m1, $m11, $m15, 13                # 4-byte Folded Spill
	add $m8, $m3, 64
	add $m0, $m0, 2
	st32 $m0, $m11, $m15, 2                 # 4-byte Folded Spill
	add $m0, $m13, 28
	st32 $m0, $m11, $m15, 1                 # 4-byte Folded Spill
	setzi $m0, 16
	st32 $m0, $m11, $m15, 6                 # 4-byte Folded Spill
.Lpack2_1_BB0_2:                                # %for.cond3.preheader.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
                                        #       Child Loop BB0_4 Depth 3
	st32 $m4, $m11, $m15, 5                 # 4-byte Folded Spill
	ld32 $m0, $m11, $m15, 2                 # 4-byte Folded Reload
	st32 $m8, $m11, $m15, 4                 # 4-byte Folded Spill
	ld32 $m10, $m11, $m15, 3                # 4-byte Folded Reload
	add $m0, $m0, -1
.Lpack2_1_BB0_3:                                # %for.body6.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Loop Header: Depth=2
                                        #       Child Loop BB0_4 Depth 3
	st32 $m0, $m11, $m15, 8                 # 4-byte Folded Spill
	mov	$m1, $m15
	mov	$m6, $m15
	ld32 $m7, $m11, $m15, 6                 # 4-byte Folded Reload
	add $m7, $m7, -1
	shl $m3, $m10, 1
	shr $m0, $m10, 2
	ld32 $m4, $m11, $m15, 13                # 4-byte Folded Reload
	and $m0, $m0, $m4
	st32 $m0, $m11, $m15, 12                # 4-byte Folded Spill
	shl $m4, $m10, 5
	and $m0, $m4, 256
	st32 $m0, $m11, $m15, 11                # 4-byte Folded Spill
	and $m0, $m3, 14
	st32 $m0, $m11, $m15, 10                # 4-byte Folded Spill
	or $m0, $m3, 1
	st32 $m0, $m11, $m15, 9                 # 4-byte Folded Spill
	st32 $m8, $m11, $m15, 7                 # 4-byte Folded Spill
.Lpack2_1_BB0_4:                                # %for.body10.i
                                        #   Parent Loop BB0_2 Depth=1
                                        #     Parent Loop BB0_3 Depth=2
                                        # =>    This Inner Loop Header: Depth=3
	setzi $m3, 36
	cmpult $m3, $m3, $m10
	brnz $m3, .Lpack2_1_BB0_5
# %bb.9:                                # %if.then.i
                                        #   in Loop: Header=BB0_4 Depth=3
	mov	$m3, $m15
	setzi $m9, 72
	ld32 $m0, $m11, $m15, 9                 # 4-byte Folded Reload
	cmpult $m0, $m9, $m0
	add $m9, $m15, -64
	ld32 $m9, $m8, $m9, 0
	brnz $m0, .Lpack2_1_BB0_11
# %bb.10:                               # %if.then16.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m3, $m8, $m15, 0
	bri .Lpack2_1_BB0_11
.Lpack2_1_BB0_5:                                #   in Loop: Header=BB0_4 Depth=3
	mov	$m9, $m15
	mov	$m3, $m15
.Lpack2_1_BB0_11:                               # %if.end19.i
                                        #   in Loop: Header=BB0_4 Depth=3
	add $m8, $m8, 4
	shr $m0, $m6, 3
	add $m6, $m6, 2
	ld32 $m4, $m11, $m15, 13                # 4-byte Folded Reload
	add $m4, $m4, 2
	and $m0, $m0, $m4
	ld32 $m4, $m11, $m15, 12                # 4-byte Folded Reload
	add $m0, $m0, $m4
	shl $m0, $m0, 8
	ld32 $m4, $m11, $m15, 11                # 4-byte Folded Reload
	or $m0, $m0, $m4
	ld32 $m4, $m11, $m15, 10                # 4-byte Folded Reload
	or $m0, $m0, $m4
	and $m4, $m1, 224
	or $m0, $m0, $m4
	setzi $m4, 65535
	andc $m4, $m3, $m4
	shl $m3, $m3, 16
	shl $m0, $m0, 1
	add $m1, $m1, 32
	sort4x16lo $m5, $m9, $m15
	shr $m9, $m9, 16
	or $m3, $m3, $m5
	or $m4, $m4, $m9
	or $m5, $m0, 32
	st32 $m3, $m2, $m0, 0
	st32 $m4, $m2, $m5, 0
	brnzdec $m7, .Lpack2_1_BB0_4
# %bb.6:                                # %for.cond.cleanup9.i
                                        #   in Loop: Header=BB0_3 Depth=2
	ld32 $m0, $m11, $m15, 8                 # 4-byte Folded Reload
	add $m10, $m10, 6
	ld32 $m8, $m11, $m15, 7                 # 4-byte Folded Reload
	add $m8, $m8, 768
	brnzdec $m0, .Lpack2_1_BB0_3
# %bb.7:                                # %for.cond.cleanup5.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m0, $m11, $m15, 1                 # 4-byte Folded Reload
	ld32 $m0, $m0, $m15, 0
	ld32 $m4, $m11, $m15, 5                 # 4-byte Folded Reload
	add $m4, $m4, 1
	cmpult $m0, $m4, $m0
	add $m2, $m2, 6144
	ld32 $m8, $m11, $m15, 4                 # 4-byte Folded Reload
	add $m8, $m8, 4672
	brnz $m0, .Lpack2_1_BB0_2
.Lpack2_1_BB0_8:                                # %_ZN14Vertex_pack2_17computeEj.exit
	exitz $m15
.Lpack2_1_func_end0:
	.size	__runCodelet_Vertex_pack2_1, .Lpack2_1_func_end0-__runCodelet_Vertex_pack2_1
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack2_1
	.long	.Lpack2_1_func_begin0
	.byte	56
	.section	.text.__runCodelet_Vertex_pack2_1,"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