.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack1_15,"ax",@progbits
	.globl	__runCodelet_Vertex_pack1_15    # -- Begin function __runCodelet_Vertex_pack1_15
	.p2align	2
	.type	__runCodelet_Vertex_pack1_15,@function
__runCodelet_Vertex_pack1_15:           # @__runCodelet_Vertex_pack1_15
	.worker
.Lpack1_15_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_15_BB0_8
# %bb.1:                                # %for.cond3.preheader.i.preheader
	mov	$m0, $m15
	and $m5, $m1, 7
	sub $m1, 73, $m5
	setzi $m2, 43691
	setzi $m3, 43690
	mul $m2, $m1, $m2
	mul $m1, $m1, $m3
	shr $m2, $m2, 16
	add $m1, $m1, $m2
	shl $m4, $m5, 3
	shr $m1, $m1, 18
	ld32 $m2, $m13, $m15, 0
	ld32 $m3, $m13, $m15, 1
	or $m4, $m4, 7
	st32 $m4, $m11, $m15, 2                 # 4-byte Folded Spill
	st32 $m5, $m11, $m15, 3                 # 4-byte Folded Spill
	shl $m4, $m5, 5
	st32 $m4, $m11, $m15, 1                 # 4-byte Folded Spill
	add $m6, $m1, 2
	add $m7, $m13, 28
.Lpack1_15_BB0_2:                                # %for.cond3.preheader.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
	mov	$m8, $m6
	ld32 $m9, $m11, $m15, 1                 # 4-byte Folded Reload
	ld32 $m10, $m11, $m15, 2                # 4-byte Folded Reload
	ld32 $m1, $m11, $m15, 3                 # 4-byte Folded Reload
	add $m8, $m8, -1
.Lpack1_15_BB0_3:                                # %for.cond7.preheader.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	cmpult $m4, $m1, 70
	brz $m4, .Lpack1_15_BB0_4
# %bb.5:                                # %cond.true.7.i
                                        #   in Loop: Header=BB0_3 Depth=2
	ld32 $m4, $m2, $m9, 0
	st32 $m4, $m3, $m9, 0
	ld32 $m4, $m2, $m9, 1
	st32 $m4, $m3, $m9, 1
	ld32 $m4, $m2, $m9, 2
	st32 $m4, $m3, $m9, 2
	ld32 $m4, $m2, $m9, 3
	st32 $m4, $m3, $m9, 3
	ld32 $m4, $m2, $m9, 4
	st32 $m4, $m3, $m9, 4
	ld32 $m4, $m2, $m9, 5
	st32 $m4, $m3, $m9, 5
	ld32 $m4, $m2, $m9, 6
	shl $m5, $m1, 3
	st32 $m4, $m3, $m9, 6
	or $m4, $m5, 7
	ld32 $m5, $m2, $m9, 7
	bri .Lpack1_15_BB0_6
.Lpack1_15_BB0_4:                                # %cond.end.6.i
                                        #   in Loop: Header=BB0_3 Depth=2
	mov	$m5, $m15
	st32 $azero, $m3, $m9, 1
	st32 $azero, $m3, $m9, 0
	st32 $azero, $m3, $m9, 3
	st32 $azero, $m3, $m9, 2
	st32 $azero, $m3, $m9, 5
	st32 $azero, $m3, $m9, 4
	st32 $azero, $m3, $m9, 6
	mov	$m4, $m10
.Lpack1_15_BB0_6:                                # %cond.end.7.i
                                        #   in Loop: Header=BB0_3 Depth=2
	stm32 $m5, $m3, $m4
	add $m1, $m1, 6
	add $m10, $m10, 48
	add $m9, $m9, 192
	brnzdec $m8, .Lpack1_15_BB0_3
# %bb.7:                                # %for.cond.cleanup5.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m1, $m7, $m15, 0
	add $m0, $m0, 1
	cmpult $m1, $m0, $m1
	add $m2, $m2, 2240
	add $m3, $m3, 2560
	brnz $m1, .Lpack1_15_BB0_2
.Lpack1_15_BB0_8:                                # %_ZN15Vertex_pack1_157computeEj.exit
	exitz $m15
.Lpack1_15_func_end0:
	.size	__runCodelet_Vertex_pack1_15, .Lpack1_15_func_end0-__runCodelet_Vertex_pack1_15
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack1_15
	.long	.Lpack1_15_func_begin0
	.byte	16
	.section	.text.__runCodelet_Vertex_pack1_15,"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