.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Vertex_pack0_0,"ax",@progbits
	.globl	__runCodelet_Vertex_pack0_0     # -- Begin function __runCodelet_Vertex_pack0_0
	.p2align	2
	.type	__runCodelet_Vertex_pack0_0,@function
__runCodelet_Vertex_pack0_0:            # @__runCodelet_Vertex_pack0_0
	.worker
.Lpack0_0_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 $m0, 1
	ld32 $m1, $m13, $m15, 7
	brz $m1, .Lpack0_0_BB0_8
# %bb.1:                                # %for.body.lr.ph.i
	mov	$m4, $m13
	mov	$m1, $m15
	and $m5, $m0, 7
	sub $m0, 281, $m5
	setzi $m2, 43691
	setzi $m3, 43690
	mul $m2, $m0, $m2
	mul $m0, $m0, $m3
	shr $m2, $m2, 16
	add $m0, $m0, $m2
	ld32step $m2, $m15, $m4+=, 7
	st32 $m4, $m11, $m15, 3                 # 4-byte Folded Spill
	st32 $m5, $m11, $m15, 2                 # 4-byte Folded Spill
	mul $m4, $m5, 240
	shr $m0, $m0, 18
	ld32 $m3, $m13, $m15, 1
	add $m8, $m2, $m4
	add $m0, $m0, 2
	st32 $m0, $m11, $m15, 1                 # 4-byte Folded Spill
	setzi $m0, 64
	st32 $m0, $m11, $m15, 5                 # 4-byte Folded Spill
.Lpack0_0_BB0_2:                                # %for.body.i
                                        # =>This Loop Header: Depth=1
                                        #     Child Loop BB0_3 Depth 2
                                        #       Child Loop BB0_4 Depth 3
	ld32 $m7, $m11, $m15, 1                 # 4-byte Folded Reload
	st32 $m8, $m11, $m15, 4                 # 4-byte Folded Spill
	ld32 $m9, $m11, $m15, 2                 # 4-byte Folded Reload
	add $m7, $m7, -1
.Lpack0_0_BB0_3:                                # %for.cond8.preheader.i
                                        #   Parent Loop BB0_2 Depth=1
                                        # =>  This Loop Header: Depth=2
                                        #       Child Loop BB0_4 Depth 3
	mov	$m10, $m15
	ld32 $m6, $m11, $m15, 5                 # 4-byte Folded Reload
	shl $m2, $m9, 5
	add $m6, $m6, -1
.Lpack0_0_BB0_4:                                # %for.body11.i
                                        #   Parent Loop BB0_2 Depth=1
                                        #     Parent Loop BB0_3 Depth=2
                                        # =>    This Inner Loop Header: Depth=3
	setzi $m5, 239
	cmpult $m5, $m5, $m10
	brz $m5, .Lpack0_0_BB0_9
# %bb.5:                                #   in Loop: Header=BB0_4 Depth=3
	mov	$m5, $m15
	bri .Lpack0_0_BB0_12
.Lpack0_0_BB0_9:                                # %if.end.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	cmpult $m5, $m10, 237
	brz $m5, .Lpack0_0_BB0_10
# %bb.11:                               # %if.then9.i.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ld32 $m5, $m8, $m10, 0
	bri .Lpack0_0_BB0_12
.Lpack0_0_BB0_10:                               # %for.body.i.preheader.i
                                        #   in Loop: Header=BB0_4 Depth=3
	ldz8 $m5, $m8, $m10, 1
	ldz8 $m4, $m8, $m15, $m10
	shl $m5, $m5, 8
	or $m4, $m5, $m4
	ldz8 $m5, $m8, $m10, 2
	shl $m5, $m5, 16
	or $m4, $m4, $m5
	ldz8 $m5, $m8, $m10, 3
	shl $m5, $m5, 24
	or $m5, $m4, $m5
.Lpack0_0_BB0_12:                               # %_ZZN14Vertex_pack0_07computeEjENKUljjE_clEjj.exit.i
                                        #   in Loop: Header=BB0_4 Depth=3
	shr $m4, $m10, 5
	ld32 $m0, $m13, $m15, 7
	mul $m0, $m0, $m4
	add $m0, $m0, $m1
	and $m4, $m10, 28
	mul $m0, $m0, 9216
	or $m4, $m4, $m2
	add $m0, $m4, $m0
	st32 $m5, $m3, $m0, 0
	add $m10, $m10, 4
	brnzdec $m6, .Lpack0_0_BB0_4
# %bb.6:                                # %for.cond.cleanup10.i
                                        #   in Loop: Header=BB0_3 Depth=2
	add $m9, $m9, 6
	add $m8, $m8, 1440
	brnzdec $m7, .Lpack0_0_BB0_3
# %bb.7:                                # %for.cond.cleanup6.loopexit.i
                                        #   in Loop: Header=BB0_2 Depth=1
	ld32 $m0, $m11, $m15, 3                 # 4-byte Folded Reload
	ld32 $m2, $m0, $m15, 0
	add $m1, $m1, 1
	setzi $m5, 69120
	cmpult $m2, $m1, $m2
	ld32 $m8, $m11, $m15, 4                 # 4-byte Folded Reload
	add $m8, $m8, $m5
	brnz $m2, .Lpack0_0_BB0_2
.Lpack0_0_BB0_8:                                # %_ZN14Vertex_pack0_07computeEj.exit
	exitz $m15
.Lpack0_0_func_end0:
	.size	__runCodelet_Vertex_pack0_0, .Lpack0_0_func_end0-__runCodelet_Vertex_pack0_0
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Vertex_pack0_0
	.long	.Lpack0_0_func_begin0
	.byte	24
	.section	.text.__runCodelet_Vertex_pack0_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