.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack2_0,"ax",@progbits
	.globl	__runCodelet_Vertex_pack2_0     # -- Begin function __runCodelet_Vertex_pack2_0
	.p2align	2
	.type	__runCodelet_Vertex_pack2_0,@function
__runCodelet_Vertex_pack2_0:            # @__runCodelet_Vertex_pack2_0
	.worker
.Lpack2_0_func_begin0:
# %bb.0:                                # %entry
	setzi $m6, 48
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -48
	get $m0, 1
	ld32 $m1, $m13, $m15, 7
	brz $m1, .Lpack2_0_BB0_7
# %bb.1:                                # %for.cond3.preheader.i.preheader
	mov	$m4, $m15
	and $m3, $m0, 7
	sub $m0, 137, $m3
	setzi $m1, 43691
	setzi $m2, 43690
	mul $m1, $m0, $m1
	mul $m0, $m0, $m2
	shr $m1, $m1, 16
	add $m0, $m0, $m1
	ld32 $m1, $m13, $m15, 0
	st32 $m3, $m11, $m15, 2                 # 4-byte Folded Spill
	mul $m3, $m3, 448
	shr $m0, $m0, 18
	ld32 $m2, $m13, $m15, 1
	add $m10, $m1, $m3
	add $m0, $m0, 2
	st32 $m0, $m11, $m15, 1                 # 4-byte Folded Spill
	add $m0, $m13, 28
	st32 $m0, $m11, $m15, 0                 # 4-byte Folded Spill
	setzi $m0, 65534
	st32 $m0, $m11, $m15, 7                 # 4-byte Folded Spill
	setzi $m0, 58255
	st32 $m0, $m11, $m15, 6                 # 4-byte Folded Spill
	setzi $m0, 56
	st32 $m0, $m11, $m15, 5                 # 4-byte Folded Spill
.Lpack2_0_BB0_2:                                # %for.cond3.preheader.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
                                        #       Child Loop BB0_4 Depth 3
	st32 $m4, $m11, $m15, 4                 # 4-byte Folded Spill
	ld32 $m0, $m11, $m15, 1                 # 4-byte Folded Reload
	st32 $m10, $m11, $m15, 3                # 4-byte Folded Spill
	ld32 $m1, $m11, $m15, 2                 # 4-byte Folded Reload
	add $m0, $m0, -1
.Lpack2_0_BB0_3:                                # %for.body6.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Loop Header: Depth=2
                                        #       Child Loop BB0_4 Depth 3
	st32 $m0, $m11, $m15, 10                # 4-byte Folded Spill
	mov	$m5, $m15
	mov	$m4, $m15
	st32 $m1, $m11, $m15, 8                 # 4-byte Folded Spill
	shl $m7, $m1, 1
	ld32 $m0, $m11, $m15, 7                 # 4-byte Folded Reload
	and $m3, $m7, $m0
	ld32 $m1, $m11, $m15, 6                 # 4-byte Folded Reload
	mul $m3, $m3, $m1
	shr $m3, $m3, 24
	mul $m3, $m3, 288
	ld32 $m8, $m11, $m15, 5                 # 4-byte Folded Reload
	sub $m3, $m7, $m3
	add $m8, $m8, -1
	and $m0, $m3, $m0
	st32 $m0, $m11, $m15, 11                # 4-byte Folded Spill
	and $m7, $m7, 14
	st32 $m10, $m11, $m15, 9                # 4-byte Folded Spill
.Lpack2_0_BB0_4:                                # %if.then.i
                                        #   Parent Loop BB0_2 Depth=1
                                        #     Parent Loop BB0_3 Depth=2
                                        # =>    This Inner Loop Header: Depth=3
	shr $m6, $m4, 4
	mul $m6, $m6, 288
	ld32 $m0, $m11, $m15, 11                # 4-byte Folded Reload
	add $m6, $m6, $m0
	setzi $m0, 1048320
	shl $m6, $m6, 4
	or $m0, $m0, 2146435072
	and $m1, $m5, 224
	ld32 $m9, $m10, $m15, 56
	ld32step $m3, $m15, $m10+=, 1
	and $m0, $m6, $m0
	setzi $m6, 65535
	or $m1, $m1, $m7
	andc $m6, $m9, $m6
	shl $m9, $m9, 16
	or $m0, $m1, $m0
	sort4x16lo $m1, $m3, $m15
	shr $m3, $m3, 16
	or $m1, $m9, $m1
	or $m3, $m6, $m3
	shl $m0, $m0, 1
	st32 $m1, $m2, $m0, 0
	st32 $m3, $m2, $m0, 8
	add $m4, $m4, 2
	add $m5, $m5, 32
	brnzdec $m8, .Lpack2_0_BB0_4
# %bb.5:                                # %for.cond.cleanup9.i
                                        #   in Loop: Header=BB0_3 Depth=2
	ld32 $m0, $m11, $m15, 10                # 4-byte Folded Reload
	ld32 $m1, $m11, $m15, 8                 # 4-byte Folded Reload
	add $m1, $m1, 6
	ld32 $m10, $m11, $m15, 9                # 4-byte Folded Reload
	add $m10, $m10, 2688
	brnzdec $m0, .Lpack2_0_BB0_3
# %bb.6:                                # %for.cond.cleanup5.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m0, $m11, $m15, 0                 # 4-byte Folded Reload
	ld32 $m0, $m0, $m15, 0
	ld32 $m4, $m11, $m15, 4                 # 4-byte Folded Reload
	add $m4, $m4, 1
	cmpult $m0, $m4, $m0
	add $m2, $m2, 64512
	ld32 $m10, $m11, $m15, 3                # 4-byte Folded Reload
	add $m10, $m10, 64512
	brnz $m0, .Lpack2_0_BB0_2
.Lpack2_0_BB0_7:                                # %_ZN14Vertex_pack2_07computeEj.exit
	exitz $m15
.Lpack2_0_func_end0:
	.size	__runCodelet_Vertex_pack2_0, .Lpack2_0_func_end0-__runCodelet_Vertex_pack2_0
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack2_0
	.long	.Lpack2_0_func_begin0
	.byte	48
	.section	.text.__runCodelet_Vertex_pack2_0,"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