.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack1_7,"ax",@progbits
	.globl	__runCodelet_Vertex_pack1_7     # -- Begin function __runCodelet_Vertex_pack1_7
	.p2align	2
	.type	__runCodelet_Vertex_pack1_7,@function
__runCodelet_Vertex_pack1_7:            # @__runCodelet_Vertex_pack1_7
	.worker
.Lpack1_7_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 $m1, 1
	ld32 $m0, $m13, $m15, 7
	brz $m0, .Lpack1_7_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
	ld32 $m3, $m13, $m15, 0
	mul $m4, $m5, 36
	add $m1, $m1, $m2
	add $m3, $m4, $m3
	shr $m1, $m1, 18
	ld32 $m2, $m13, $m15, 1
	shl $m4, $m5, 5
	st32 $m4, $m11, $m15, 4                 # 4-byte Folded Spill
	st32 $m5, $m11, $m15, 5                 # 4-byte Folded Spill
	shl $m4, $m5, 4
	st32 $m4, $m11, $m15, 3                 # 4-byte Folded Spill
	add $m5, $m3, 16
	add $m1, $m1, 2
	st32 $m1, $m11, $m15, 2                 # 4-byte Folded Spill
	add $m1, $m13, 28
	st32 $m1, $m11, $m15, 1                 # 4-byte Folded Spill
.Lpack1_7_BB0_2:                                # %for.cond3.preheader.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
	ld32 $m8, $m11, $m15, 2                 # 4-byte Folded Reload
	mov	$m9, $m5
	ld32 $m10, $m11, $m15, 3                # 4-byte Folded Reload
	ld32 $m3, $m11, $m15, 4                 # 4-byte Folded Reload
	ld32 $m1, $m11, $m15, 5                 # 4-byte Folded Reload
	add $m8, $m8, -1
.Lpack1_7_BB0_3:                                # %for.cond7.preheader.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Inner Loop Header: Depth=2
	andc $m4, $m3, 511
	and $m6, $m10, 240
	or $m4, $m4, $m6
	cmpult $m6, $m1, 73
	shr $m4, $m4, 1
	shl $m7, $m4, 2
	brz $m6, .Lpack1_7_BB0_4
# %bb.5:                                # %land.lhs.true.7.1.i
                                        #   in Loop: Header=BB0_3 Depth=2
	add $m6, $m15, -16
	ld32 $m6, $m9, $m6, 0
	stm32 $m6, $m2, $m4
	add $m4, $m15, -12
	ld32 $m4, $m9, $m4, 0
	or $m6, $m7, 4
	st32 $m4, $m2, $m6, 0
	add $m4, $m15, -8
	ld32 $m4, $m9, $m4, 0
	or $m6, $m7, 8
	st32 $m4, $m2, $m6, 0
	add $m4, $m15, -4
	ld32 $m4, $m9, $m4, 0
	or $m6, $m7, 12
	st32 $m4, $m2, $m6, 0
	ld32 $m4, $m9, $m15, 0
	or $m6, $m7, 16
	st32 $m4, $m2, $m6, 0
	ld32 $m4, $m9, $m15, 1
	or $m6, $m7, 20
	st32 $m4, $m2, $m6, 0
	ld32 $m4, $m9, $m15, 2
	or $m6, $m7, 24
	st32 $m4, $m2, $m6, 0
	ld32 $m4, $m9, $m15, 3
	or $m6, $m7, 28
	st32 $m4, $m2, $m6, 0
	ld32 $m6, $m9, $m15, 4
	bri .Lpack1_7_BB0_6
.Lpack1_7_BB0_4:                                # %cond.end.7.i
                                        #   in Loop: Header=BB0_3 Depth=2
	mov	$m6, $m15
	st32 $azero, $m2, $m15, $m4
	or $m4, $m7, 4
	st32 $azero, $m2, $m4, 0
	or $m4, $m7, 8
	st32 $azero, $m2, $m4, 0
	or $m4, $m7, 12
	st32 $azero, $m2, $m4, 0
	or $m4, $m7, 16
	st32 $azero, $m2, $m4, 0
	or $m4, $m7, 20
	st32 $azero, $m2, $m4, 0
	or $m4, $m7, 24
	st32 $azero, $m2, $m4, 0
	or $m4, $m7, 28
	st32 $azero, $m2, $m4, 0
.Lpack1_7_BB0_6:                                # %cond.end.7.1.i
                                        #   in Loop: Header=BB0_3 Depth=2
	or $m4, $m7, 512
	st32 $m6, $m2, $m4, 0
	or $m4, $m7, 516
	or $m6, $m7, 520
	st32 $azero, $m2, $m4, 0
	or $m4, $m7, 524
	st32 $azero, $m2, $m6, 0
	or $m6, $m7, 528
	st32 $azero, $m2, $m4, 0
	or $m4, $m7, 532
	st32 $azero, $m2, $m6, 0
	or $m6, $m7, 536
	or $m7, $m7, 540
	st32 $azero, $m2, $m4, 0
	st32 $azero, $m2, $m6, 0
	st32 $azero, $m2, $m7, 0
	add $m1, $m1, 6
	add $m3, $m3, 192
	add $m10, $m10, 96
	add $m9, $m9, 216
	brnzdec $m8, .Lpack1_7_BB0_3
# %bb.7:                                # %for.cond.cleanup5.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m1, $m11, $m15, 1                 # 4-byte Folded Reload
	ld32 $m1, $m1, $m15, 0
	add $m0, $m0, 1
	cmpult $m1, $m0, $m1
	add $m2, $m2, 5120
	add $m5, $m5, 2628
	brnz $m1, .Lpack1_7_BB0_2
.Lpack1_7_BB0_8:                                # %_ZN14Vertex_pack1_77computeEj.exit
	exitz $m15
.Lpack1_7_func_end0:
	.size	__runCodelet_Vertex_pack1_7, .Lpack1_7_func_end0-__runCodelet_Vertex_pack1_7
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack1_7
	.long	.Lpack1_7_func_begin0
	.byte	24
	.section	.text.__runCodelet_Vertex_pack1_7,"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