.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack1_5,"ax",@progbits
	.globl	__runCodelet_Vertex_pack1_5     # -- Begin function __runCodelet_Vertex_pack1_5
	.p2align	2
	.type	__runCodelet_Vertex_pack1_5,@function
__runCodelet_Vertex_pack1_5:            # @__runCodelet_Vertex_pack1_5
	.worker
.Lpack1_5_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 16
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -16
	get $m1, 1
	ld32 $m0, $m13, $m15, 7
	brz $m0, .Lpack1_5_BB0_9
# %bb.1:                                # %for.cond3.preheader.i.preheader
	mov	$m0, $m15
	and $m1, $m1, 7
	ld32 $m2, $m13, $m15, 0
	ld32 $m3, $m13, $m15, 1
	st32 $m1, $m11, $m15, 2                 # 4-byte Folded Spill
	mul $m1, $m1, 288
	st32 $m1, $m11, $m15, 1                 # 4-byte Folded Spill
	add $m1, $m13, 28
	st32 $m1, $m11, $m15, 0                 # 4-byte Folded Spill
	bri .Lpack1_5_BB0_2
.Lpack1_5_BB0_8:                                # %for.cond.cleanup5.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m0, $m11, $m15, 0                 # 4-byte Folded Reload
	ld32 $m1, $m0, $m15, 0
	ld32 $m0, $m11, $m15, 3                 # 4-byte Folded Reload
	add $m0, $m0, 1
	setzi $m4, 70272
	cmpult $m1, $m0, $m1
	add $m2, $m2, $m4
	setzi $m4, 73728
	add $m3, $m3, $m4
	brz $m1, .Lpack1_5_BB0_9
.Lpack1_5_BB0_2:                                # %for.cond3.preheader.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
                                        #       Child Loop BB0_4 Depth 3
	st32 $m0, $m11, $m15, 3                 # 4-byte Folded Spill
	ld32 $m6, $m11, $m15, 1                 # 4-byte Folded Reload
	ld32 $m7, $m11, $m15, 2                 # 4-byte Folded Reload
.Lpack1_5_BB0_3:                                # %for.body6.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Loop Header: Depth=2
                                        #       Child Loop BB0_4 Depth 3
	mov	$m8, $m15
	shr $m1, $m7, 4
	shl $m4, $m7, 4
	mul $m9, $m1, 4608
	and $m10, $m4, 240
	bri .Lpack1_5_BB0_4
.Lpack1_5_BB0_5:                                # %cond.end.7.i
                                        #   in Loop: Header=BB0_4 Depth=3
	add $m4, $m6, $m8
	shl $m5, $m4, 1
	ld32 $m0, $m2, $m5, 0
	shl $m4, $m1, 2
	stm32 $m0, $m3, $m1
	or $m0, $m5, 4
	ld32 $m0, $m2, $m0, 0
	or $m1, $m4, 4
	st32 $m0, $m3, $m1, 0
	or $m0, $m5, 8
	ld32 $m0, $m2, $m0, 0
	or $m1, $m4, 8
	st32 $m0, $m3, $m1, 0
	or $m0, $m5, 12
	ld32 $m0, $m2, $m0, 0
	or $m1, $m4, 12
	st32 $m0, $m3, $m1, 0
	or $m0, $m5, 16
	ld32 $m0, $m2, $m0, 0
	or $m1, $m4, 16
	st32 $m0, $m3, $m1, 0
	or $m0, $m5, 20
	ld32 $m0, $m2, $m0, 0
	or $m1, $m4, 20
	st32 $m0, $m3, $m1, 0
	or $m0, $m5, 24
	ld32 $m0, $m2, $m0, 0
	or $m1, $m4, 24
	st32 $m0, $m3, $m1, 0
	or $m0, $m5, 28
	setzi $m1, 271
	ld32 $m0, $m2, $m0, 0
	or $m4, $m4, 28
	cmpult $m1, $m1, $m8
	st32 $m0, $m3, $m4, 0
	brnz $m1, .Lpack1_5_BB0_10
.Lpack1_5_BB0_6:                                # %for.body10.i.backedge
                                        #   in Loop: Header=BB0_4 Depth=3
	add $m8, $m8, 16
	add $m9, $m9, 256
.Lpack1_5_BB0_4:                                # %for.body10.i
                                        #   Parent Loop BB0_2 Depth=1
                                        #     Parent Loop BB0_3 Depth=2
                                        # =>    This Inner Loop Header: Depth=3
	setzi $m1, 121
	cmpult $m4, $m1, $m7
	or $m1, $m9, $m10
	shr $m1, $m1, 1
	brz $m4, .Lpack1_5_BB0_5
# %bb.7:                                # %cond.end.7.i.thread
                                        #   in Loop: Header=BB0_4 Depth=3
	shl $m0, $m1, 2
	st32 $azero, $m3, $m15, $m1
	or $m1, $m0, 4
	st32 $azero, $m3, $m1, 0
	or $m1, $m0, 8
	st32 $azero, $m3, $m1, 0
	or $m1, $m0, 12
	st32 $azero, $m3, $m1, 0
	or $m1, $m0, 16
	st32 $azero, $m3, $m1, 0
	or $m1, $m0, 20
	st32 $azero, $m3, $m1, 0
	or $m1, $m0, 24
	or $m0, $m0, 28
	st32 $azero, $m3, $m1, 0
	cmpult $m1, $m8, 272
	st32 $azero, $m3, $m0, 0
	brnz $m1, .Lpack1_5_BB0_6
	bri .Lpack1_5_BB0_8
.Lpack1_5_BB0_10:                               # %for.cond.cleanup9.i
                                        #   in Loop: Header=BB0_3 Depth=2
	add $m7, $m7, 6
	add $m6, $m6, 1728
	bri .Lpack1_5_BB0_3
.Lpack1_5_BB0_9:                                # %_ZN14Vertex_pack1_57computeEj.exit
	exitz $m15
.Lpack1_5_func_end0:
	.size	__runCodelet_Vertex_pack1_5, .Lpack1_5_func_end0-__runCodelet_Vertex_pack1_5
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack1_5
	.long	.Lpack1_5_func_begin0
	.byte	16
	.section	.text.__runCodelet_Vertex_pack1_5,"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