.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack0_18,"ax",@progbits
	.globl	__runCodelet_Vertex_pack0_18    # -- Begin function __runCodelet_Vertex_pack0_18
	.p2align	2
	.type	__runCodelet_Vertex_pack0_18,@function
__runCodelet_Vertex_pack0_18:           # @__runCodelet_Vertex_pack0_18
	.worker
.Lpack0_18_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 40
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -40
	get $m2, 1
	ld32 $m1, $m13, $m15, 7
	brz $m1, .Lpack0_18_BB0_8
# %bb.1:                                # %for.body.lr.ph.i
	mov	$m0, $m15
	and $m2, $m2, 7
	ld32 $m4, $m13, $m15, 0
	mul $m5, $m2, 59
	setzi $m3, 2
	ld32 $m6, $m13, $m15, 1
	st32 $m6, $m11, $m15, 9                 # 4-byte Folded Spill
	shl $m6, $m2, 5
	st32 $m6, $m11, $m15, 8                 # 4-byte Folded Spill
	st32 $m4, $m11, $m15, 3                 # 4-byte Folded Spill
	st32 $m5, $m11, $m15, 6                 # 4-byte Folded Spill
	add $m4, $m4, $m5
	cmpult $m3, $m3, $m2
	setzi $m2, 16
	st32 $m2, $m11, $m15, 1                 # 4-byte Folded Spill
	st32 $m3, $m11, $m15, 2                 # 4-byte Folded Spill
	bri .Lpack0_18_BB0_2
.Lpack0_18_BB0_7:                                # %for.cond.cleanup6.i
                                        #   in Loop: Header=BB0_2 Depth=1
	add $m0, $m0, 1
	cmpult $m2, $m0, $m1
	add $m4, $m4, 177
	brz $m2, .Lpack0_18_BB0_8
.Lpack0_18_BB0_2:                                # %for.body.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_4 Depth 2
	brnz $m3, .Lpack0_18_BB0_7
# %bb.3:                                # %for.cond8.preheader.preheader.i
                                        #   in Loop: Header=BB0_2 Depth=1
	mov	$m8, $m15
	mov	$m9, $m15
	ld32 $m10, $m11, $m15, 1                # 4-byte Folded Reload
	mul $m1, $m0, 177
	add $m10, $m10, -1
	ld32 $m2, $m11, $m15, 6                 # 4-byte Folded Reload
	add $m2, $m0, $m2
	ld32 $m3, $m11, $m15, 3                 # 4-byte Folded Reload
	add $m1, $m3, $m1
	st32 $m1, $m11, $m15, 5                 # 4-byte Folded Spill
	and $m1, $m2, 3
	st32 $m1, $m11, $m15, 7                 # 4-byte Folded Spill
	st32 $m4, $m11, $m15, 4                 # 4-byte Folded Spill
	mov	$m3, $m4
.Lpack0_18_BB0_4:                                # %for.body11.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	setzi $m1, 58
	cmpult $m1, $m1, $m9
	ld32 $m2, $m13, $m15, 7
	brz $m1, .Lpack0_18_BB0_9
# %bb.5:                                #   in Loop: Header=BB0_4 Depth=2
	mov	$m1, $m15
	bri .Lpack0_18_BB0_13
.Lpack0_18_BB0_9:                                # %if.end.i.i
                                        #   in Loop: Header=BB0_4 Depth=2
	ld32 $m1, $m11, $m15, 7                 # 4-byte Folded Reload
	brnz $m1, .Lpack0_18_BB0_11
# %bb.10:                               # %if.end.i.i
                                        #   in Loop: Header=BB0_4 Depth=2
	cmpult $m1, $m9, 56
	brz $m1, .Lpack0_18_BB0_11
# %bb.14:                               # %if.then9.i.i
                                        #   in Loop: Header=BB0_4 Depth=2
	ld32 $m1, $m11, $m15, 6                 # 4-byte Folded Reload
	add $m1, $m9, $m1
	ld32 $m4, $m11, $m15, 5                 # 4-byte Folded Reload
	ld32 $m1, $m4, $m1, 0
	bri .Lpack0_18_BB0_13
.Lpack0_18_BB0_11:                               # %for.body.lr.ph.i.i
                                        #   in Loop: Header=BB0_4 Depth=2
	mov	$m6, $m15
	mov	$m1, $m15
	shl $m5, $m8, 2
	sub $m5, 58, $m5
	cmpult $m7, $m5, 3
	setzi $m4, 3
	movnz	$m4, $m7, $m5
	add $m7, $m4, 1
	mov	$m5, $m3
# %bb.12:                               # %for.body.i.i
                                        #   in Loop: Header=BB0_4 Depth=2
	{
		rpt $m7, 3
		fnop
	}
	{
		ldz8step $m4, $m15, $m5+=, 1
		fnop
	}
	{
		shl $m4, $m4, $m6
		fnop
	}
	{
		or $m1, $m4, $m1
		fnop
	}
	{
		add $m6, $m6, 8
		fnop
	}
.Lpack0_18_BB0_13:                               # %_ZZN15Vertex_pack0_187computeEjENKUljjE_clEjj.exit.i
                                        #   in Loop: Header=BB0_4 Depth=2
	shr $m4, $m9, 5
	mul $m2, $m2, $m4
	add $m2, $m2, $m0
	and $m4, $m9, 28
	mul $m2, $m2, 96
	ld32 $m5, $m11, $m15, 8                 # 4-byte Folded Reload
	or $m4, $m4, $m5
	add $m2, $m4, $m2
	ld32 $m4, $m11, $m15, 9                 # 4-byte Folded Reload
	st32 $m1, $m4, $m2, 0
	add $m9, $m9, 4
	add $m3, $m3, 4
	add $m8, $m8, 1
	brnzdec $m10, .Lpack0_18_BB0_4
# %bb.6:                                # %for.cond.cleanup10.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m1, $m13, $m15, 7
	ld32 $m4, $m11, $m15, 4                 # 4-byte Folded Reload
	ld32 $m3, $m11, $m15, 2                 # 4-byte Folded Reload
	bri .Lpack0_18_BB0_7
.Lpack0_18_BB0_8:                                # %_ZN15Vertex_pack0_187computeEj.exit
	exitz $m15
.Lpack0_18_func_end0:
	.size	__runCodelet_Vertex_pack0_18, .Lpack0_18_func_end0-__runCodelet_Vertex_pack0_18
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack0_18
	.long	.Lpack0_18_func_begin0
	.byte	40
	.section	.text.__runCodelet_Vertex_pack0_18,"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