.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack1_8,"ax",@progbits
	.globl	__runCodelet_Vertex_pack1_8     # -- Begin function __runCodelet_Vertex_pack1_8
	.p2align	2
	.type	__runCodelet_Vertex_pack1_8,@function
__runCodelet_Vertex_pack1_8:            # @__runCodelet_Vertex_pack1_8
	.worker
.Lpack1_8_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_8_BB0_8
# %bb.1:                                # %for.cond3.preheader.i.preheader
	mov	$m0, $m15
	and $m1, $m1, 7
	sub $m2, 9, $m1
	setzi $m3, 43691
	setzi $m4, 43690
	mul $m3, $m2, $m3
	mul $m2, $m2, $m4
	shr $m3, $m3, 16
	ld32 $m4, $m13, $m15, 0
	mul $m5, $m1, 208
	add $m2, $m2, $m3
	add $m3, $m5, $m4
	shr $m5, $m2, 18
	ld32 $m2, $m13, $m15, 1
	shl $m4, $m1, 3
	st32 $m4, $m11, $m15, 3                 # 4-byte Folded Spill
	add $m4, $m3, 104
	add $m3, $m5, 2
	st32 $m3, $m11, $m15, 2                 # 4-byte Folded Spill
	add $m3, $m13, 28
	st32 $m3, $m11, $m15, 1                 # 4-byte Folded Spill
.Lpack1_8_BB0_2:                                # %for.cond3.preheader.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
	ld32 $m7, $m11, $m15, 2                 # 4-byte Folded Reload
	mov	$m8, $m4
	ld32 $m9, $m11, $m15, 3                 # 4-byte Folded Reload
	mov	$m10, $m1
	add $m7, $m7, -1
.Lpack1_8_BB0_3:                                # %for.cond7.preheader.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	cmpult $m6, $m10, 2
	and $m5, $m9, 120
	shl $m3, $m5, 2
	brz $m6, .Lpack1_8_BB0_4
# %bb.5:                                # %land.lhs.true.7.6.i
                                        #   in Loop: Header=BB0_3 Depth=2
	add $m6, $m15, -104
	ld32 $m6, $m8, $m6, 0
	stm32 $m6, $m2, $m5
	add $m5, $m15, -100
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 4
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -96
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 8
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -92
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 12
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -88
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 16
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -84
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 20
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -80
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 24
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -76
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 28
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -72
	ld32 $m5, $m8, $m5, 0
	st32 $m5, $m2, $m3, 128
	add $m5, $m15, -68
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 516
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -64
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 520
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -60
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 524
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -56
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 528
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -52
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 532
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -48
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 536
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -44
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 540
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -40
	ld32 $m5, $m8, $m5, 0
	st32 $m5, $m2, $m3, 256
	add $m5, $m15, -36
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 1028
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -32
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 1032
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -28
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 1036
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -24
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 1040
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -20
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 1044
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -16
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 1048
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -12
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 1052
	st32 $m5, $m2, $m6, 0
	add $m5, $m15, -8
	ld32 $m5, $m8, $m5, 0
	st32 $m5, $m2, $m3, 384
	add $m5, $m15, -4
	ld32 $m5, $m8, $m5, 0
	or $m6, $m3, 1540
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 0
	or $m6, $m3, 1544
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 1
	or $m6, $m3, 1548
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 2
	or $m6, $m3, 1552
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 3
	or $m6, $m3, 1556
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 4
	or $m6, $m3, 1560
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 5
	or $m6, $m3, 1564
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 6
	st32 $m5, $m2, $m3, 512
	ld32 $m5, $m8, $m15, 7
	or $m6, $m3, 2052
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 8
	or $m6, $m3, 2056
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 9
	or $m6, $m3, 2060
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 10
	or $m6, $m3, 2064
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 11
	or $m6, $m3, 2068
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 12
	or $m6, $m3, 2072
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 13
	or $m6, $m3, 2076
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 14
	st32 $m5, $m2, $m3, 640
	ld32 $m5, $m8, $m15, 15
	or $m6, $m3, 2564
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 16
	or $m6, $m3, 2568
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 17
	or $m6, $m3, 2572
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 18
	or $m6, $m3, 2576
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 19
	or $m6, $m3, 2580
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 20
	or $m6, $m3, 2584
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 21
	or $m6, $m3, 2588
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 22
	st32 $m5, $m2, $m3, 768
	ld32 $m5, $m8, $m15, 23
	or $m6, $m3, 3076
	st32 $m5, $m2, $m6, 0
	ld32 $m5, $m8, $m15, 24
	or $m6, $m3, 3080
	st32 $m5, $m2, $m6, 0
	ld32 $m6, $m8, $m15, 25
	bri .Lpack1_8_BB0_6
.Lpack1_8_BB0_4:                                # %cond.end.6.6.i
                                        #   in Loop: Header=BB0_3 Depth=2
	mov	$m6, $m15
	st32 $azero, $m2, $m15, $m5
	or $m5, $m3, 8
	st32 $azero, $m2, $m3, 1
	st32 $azero, $m2, $m5, 1
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 16
	st32 $azero, $m2, $m5, 1
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 24
	st32 $azero, $m2, $m5, 1
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 516
	st32 $azero, $m2, $m3, 128
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 520
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 524
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 528
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 532
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 536
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 540
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1028
	st32 $azero, $m2, $m3, 256
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1032
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1036
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1040
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1044
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1048
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1052
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1540
	st32 $azero, $m2, $m3, 384
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1544
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1548
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1552
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1556
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1560
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 1564
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2052
	st32 $azero, $m2, $m3, 512
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2056
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2060
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2064
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2068
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2072
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2076
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2564
	st32 $azero, $m2, $m3, 640
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2568
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2572
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2576
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2580
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2584
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 2588
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 3076
	st32 $azero, $m2, $m3, 768
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 3080
	st32 $azero, $m2, $m5, 0
.Lpack1_8_BB0_6:                                # %cond.end.7.6.i
                                        #   in Loop: Header=BB0_3 Depth=2
	or $m5, $m3, 3084
	st32 $m6, $m2, $m5, 0
	or $m5, $m3, 3088
	or $m6, $m3, 3092
	st32 $azero, $m2, $m5, 0
	or $m5, $m3, 3096
	or $m3, $m3, 3100
	st32 $azero, $m2, $m6, 0
	st32 $azero, $m2, $m5, 0
	st32 $azero, $m2, $m3, 0
	add $m10, $m10, 6
	add $m9, $m9, 48
	add $m8, $m8, 1248
	brnzdec $m7, .Lpack1_8_BB0_3
# %bb.7:                                # %for.cond.cleanup5.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m3, $m11, $m15, 1                 # 4-byte Folded Reload
	ld32 $m3, $m3, $m15, 0
	add $m0, $m0, 1
	cmpult $m3, $m0, $m3
	add $m2, $m2, 3584
	add $m4, $m4, 416
	brnz $m3, .Lpack1_8_BB0_2
.Lpack1_8_BB0_8:                                # %_ZN14Vertex_pack1_87computeEj.exit
	exitz $m15
.Lpack1_8_func_end0:
	.size	__runCodelet_Vertex_pack1_8, .Lpack1_8_func_end0-__runCodelet_Vertex_pack1_8
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack1_8
	.long	.Lpack1_8_func_begin0
	.byte	16
	.section	.text.__runCodelet_Vertex_pack1_8,"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