.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack0_14,"ax",@progbits
	.globl	__runCodelet_Vertex_pack0_14    # -- Begin function __runCodelet_Vertex_pack0_14
	.p2align	2
	.type	__runCodelet_Vertex_pack0_14,@function
__runCodelet_Vertex_pack0_14:           # @__runCodelet_Vertex_pack0_14
	.worker
.Lpack0_14_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 24
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -24
	get $m2, 1
	ld32 $m0, $m13, $m15, 7
	brz $m0, .Lpack0_14_BB0_5
# %bb.1:                                # %for.body.lr.ph.i
	mov	$m0, $m13
	mov	$m1, $m15
	and $m4, $m2, 7
	sub $m2, 80, $m4
	setzi $m3, 43691
	setzi $m5, 43690
	mul $m3, $m2, $m3
	mul $m2, $m2, $m5
	shr $m3, $m3, 16
	add $m2, $m2, $m3
	ld32step $m5, $m15, $m0+=, 7
	st32 $m0, $m11, $m15, 2                 # 4-byte Folded Spill
	shr $m6, $m2, 18
	ld32 $m2, $m13, $m15, 1
	shl $m9, $m4, 5
	add $m7, $m5, $m4
	add $m0, $m6, 2
	st32 $m0, $m11, $m15, 1                 # 4-byte Folded Spill
.Lpack0_14_BB0_2:                                # %for.body.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
	st32 $m1, $m11, $m15, 5                 # 4-byte Folded Spill
	ld32 $m6, $m11, $m15, 1                 # 4-byte Folded Reload
	st32 $m7, $m11, $m15, 3                 # 4-byte Folded Spill
	st32 $m9, $m11, $m15, 4                 # 4-byte Folded Spill
	mov	$m8, $m9
	add $m6, $m6, -1
.Lpack0_14_BB0_3:                                # %_ZZN15Vertex_pack0_147computeEjENKUljjE_clEjj.exit.7.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	ldz8step $m10, $m15, $m7+=, 6
	st32step $m10, $m2, $m8+=, 48
	or $m10, $m9, 4
	or $m0, $m9, 8
	or $m5, $m9, 12
	or $m1, $m9, 16
	or $m3, $m9, 20
	or $m4, $m9, 24
	or $m9, $m9, 28
	st32 $azero, $m2, $m10, 0
	st32 $azero, $m2, $m0, 0
	st32 $azero, $m2, $m5, 0
	st32 $azero, $m2, $m1, 0
	st32 $azero, $m2, $m3, 0
	st32 $azero, $m2, $m4, 0
	st32 $azero, $m2, $m9, 0
	mov	$m9, $m8
	brnzdec $m6, .Lpack0_14_BB0_3
# %bb.4:                                # %for.cond.cleanup6.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m0, $m11, $m15, 2                 # 4-byte Folded Reload
	ld32 $m6, $m0, $m15, 0
	ld32 $m1, $m11, $m15, 5                 # 4-byte Folded Reload
	add $m1, $m1, 1
	cmpult $m6, $m1, $m6
	ld32 $m9, $m11, $m15, 4                 # 4-byte Folded Reload
	add $m9, $m9, 2784
	ld32 $m7, $m11, $m15, 3                 # 4-byte Folded Reload
	add $m7, $m7, 87
	brnz $m6, .Lpack0_14_BB0_2
.Lpack0_14_BB0_5:                                # %_ZN15Vertex_pack0_147computeEj.exit
	exitz $m15
.Lpack0_14_func_end0:
	.size	__runCodelet_Vertex_pack0_14, .Lpack0_14_func_end0-__runCodelet_Vertex_pack0_14
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack0_14
	.long	.Lpack0_14_func_begin0
	.byte	24
	.section	.text.__runCodelet_Vertex_pack0_14,"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