.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack1_16,"ax",@progbits
	.globl	__runCodelet_Vertex_pack1_16    # -- Begin function __runCodelet_Vertex_pack1_16
	.p2align	2
	.type	__runCodelet_Vertex_pack1_16,@function
__runCodelet_Vertex_pack1_16:           # @__runCodelet_Vertex_pack1_16
	.worker
.Lpack1_16_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 8
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -8
	get $m1, 1
	ld32 $m0, $m13, $m15, 7
	brz $m0, .Lpack1_16_BB0_5
# %bb.1:                                # %for.cond3.preheader.i.preheader
	mov	$m0, $m15
	and $m2, $m1, 7
	sub $m1, 9, $m2
	setzi $m3, 43691
	setzi $m4, 43690
	mul $m3, $m1, $m3
	mul $m1, $m1, $m4
	shr $m3, $m3, 16
	ld32 $m4, $m13, $m15, 0
	mul $m5, $m2, 52
	add $m1, $m1, $m3
	add $m3, $m5, $m4
	shr $m4, $m1, 18
	ld32 $m1, $m13, $m15, 1
	shl $m2, $m2, 3
	st32 $m2, $m11, $m15, 1                 # 4-byte Folded Spill
	add $m3, $m3, 24
	add $m4, $m4, 2
	add $m2, $m13, 28
	st32 $m2, $m11, $m15, 0                 # 4-byte Folded Spill
	add $m5, $m15, -20
.Lpack1_16_BB0_2:                                # %for.cond3.preheader.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
	mov	$m6, $m4
	mov	$m9, $m3
	ld32 $m7, $m11, $m15, 1                 # 4-byte Folded Reload
	mov	$m8, $m9
	add $m6, $m6, -1
.Lpack1_16_BB0_3:                                # %cond.end.7.1.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	add $m10, $m15, -24
	and $m2, $m7, 120
	ld32 $m10, $m9, $m10, 0
	stm32 $m10, $m1, $m2
	shl $m10, $m2, 2
	ld32 $m2, $m9, $m5, 0
	st32 $m2, $m1, $m10, 1
	add $m2, $m15, -16
	ld32 $m2, $m9, $m2, 0
	st32 $m2, $m1, $m10, 2
	add $m2, $m15, -12
	ld32 $m2, $m9, $m2, 0
	st32 $m2, $m1, $m10, 3
	add $m2, $m15, -8
	ld32 $m2, $m9, $m2, 0
	st32 $m2, $m1, $m10, 4
	add $m2, $m15, -4
	ld32 $m2, $m9, $m2, 0
	st32 $m2, $m1, $m10, 5
	ld32step $m2, $m15, $m8+=, 78
	st32 $m2, $m1, $m10, 6
	ld32 $m2, $m9, $m15, 1
	st32 $m2, $m1, $m10, 7
	ld32 $m2, $m9, $m15, 2
	st32 $m2, $m1, $m10, 128
	ld32 $m2, $m9, $m15, 3
	st32 $m2, $m1, $m10, 129
	ld32 $m2, $m9, $m15, 4
	st32 $m2, $m1, $m10, 130
	ld32 $m2, $m9, $m15, 5
	st32 $m2, $m1, $m10, 131
	ld32 $m2, $m9, $m15, 6
	st32 $m2, $m1, $m10, 132
	st32 $azero, $m1, $m10, 133
	st32 $azero, $m1, $m10, 134
	st32 $azero, $m1, $m10, 135
	add $m7, $m7, 48
	mov	$m9, $m8
	brnzdec $m6, .Lpack1_16_BB0_3
# %bb.4:                                # %for.cond.cleanup5.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m2, $m11, $m15, 0                 # 4-byte Folded Reload
	ld32 $m6, $m2, $m15, 0
	add $m0, $m0, 1
	cmpult $m6, $m0, $m6
	add $m1, $m1, 1024
	add $m3, $m3, 832
	brnz $m6, .Lpack1_16_BB0_2
.Lpack1_16_BB0_5:                                # %_ZN15Vertex_pack1_167computeEj.exit
	exitz $m15
.Lpack1_16_func_end0:
	.size	__runCodelet_Vertex_pack1_16, .Lpack1_16_func_end0-__runCodelet_Vertex_pack1_16
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack1_16
	.long	.Lpack1_16_func_begin0
	.byte	8
	.section	.text.__runCodelet_Vertex_pack1_16,"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