.text
	.allow_optimizations
	.file	"3"
	.section	.text.__runCodelet_Cast2To1,"ax",@progbits
	.globl	__runCodelet_Cast2To1           # -- Begin function __runCodelet_Cast2To1
	.p2align	2
	.type	__runCodelet_Cast2To1,@function
__runCodelet_Cast2To1:                  # @__runCodelet_Cast2To1
	.worker
.Lfunc_begin0:
# %bb.0:                                # %entry
	setzi $m6, 56
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -56
	{
		get $m0, 1
		setzi $a0, 2
	}
	ld32 $m1, $m13, $m15, 4
	sub $m1, 0, $m1
	ld32 $m10, $m13, $m15, 5
	and $m1, $m1, 255
	and $m7, $m0, 7
	ld32 $m8, $m13, $m15, 0
	ld32 $m6, $m13, $m15, 1
	ld32 $m9, $m13, $m15, 2
	ld32 $m0, $m13, $m15, 6
	st32 $m0, $m11, $m15, 12                # 4-byte Folded Spill
	st32 $m1, $m11, $m15, 1
	ld32 $a1, $m11, $m15, 1
	#APP
	put	9, $a0
	put	10, $a1
	#NO_APP
	brz $m10, .LBB0_11
# %bb.1:                                # %if.then.i
	st32 $m8, $m11, $m15, 9                 # 4-byte Folded Spill
	mul $m0, $m10, 192
	cmpult $m0, $m9, $m0
	cmpult $m1, $m10, 33
	cmpeq $m0, $m0, 0
	and $m5, $m1, $m0
	shl $m0, $m10, 5
	st32 $m0, $m11, $m15, 13                # 4-byte Folded Spill
	brz $m5, .LBB0_3
# %bb.2:
	setzi $m0, 32
	st32 $m0, $m11, $m15, 11                # 4-byte Folded Spill
	setzi $m0, 1
	setzi $m3, 6
	st32 $m10, $m11, $m15, 8                # 4-byte Folded Spill
	bri .LBB0_4
.LBB0_11:                               # %if.end89.i
	shr $m0, $m9, 3
	sub $m0, $m0, $m7
	add $m0, $m0, 5
	setzi $m1, 43691
	sort4x16lo $m2, $m0, $m15
	shr $m3, $m0, 16
	mul $m4, $m2, $m1
	mul $m1, $m3, $m1
	shr $m4, $m4, 16
	add $m1, $m1, $m4
	setzi $m4, 43690
	sort4x16lo $m5, $m1, $m15
	mul $m2, $m2, $m4
	shr $m1, $m1, 16
	mul $m3, $m3, $m4
	add $m2, $m2, $m5
	add $m1, $m3, $m1
	shr $m2, $m2, 16
	add $m1, $m1, $m2
	shl $m3, $m7, 3
	shl $m2, $m7, 4
	cmpult $m0, $m0, 24
	shr $m4, $m1, 2
	add $m5, $m8, $m2
	mov	$m10, $m6
	add $m6, $m6, $m3
	brnz $m0, .LBB0_17
# %bb.12:                               # %if.end89.i
	ld32 $m0, $m11, $m15, 12                # 4-byte Folded Reload
	brz $m0, .LBB0_17
# %bb.13:                               # %if.end89.i
	brz $m9, .LBB0_17
# %bb.14:                               # %land.rhs104.i
	ld32 $m0, $m11, $m15, 12                # 4-byte Folded Reload
	shl $m0, $m0, 1
	add $m0, $m8, $m0
	add $m0, $m0, -1
	shr $m0, $m0, 15
	shr $m1, $m10, 15
	cmpult $m0, $m0, $m1
	brnz $m0, .LBB0_16
# %bb.15:                               # %lor.rhs.i
	add $m0, $m10, $m9
	add $m0, $m0, -1
	shr $m0, $m0, 15
	shr $m1, $m8, 15
	cmpult $m0, $m0, $m1
	brz $m0, .LBB0_17
.LBB0_16:                               # %if.then118.i
	add $m7, $m4, -1
	#APP
	ld64step $ap0, $m15, $m5+=, 1
	ld64step $ap1, $m15, $m5+=, 11
	tapack $m0:1, $m5, $m15, $m6
	ld64step $apzero, $m15, $m5+=, 1
	mul $m2, $m7, 48
	add $m6, $m6, $m2
	setzi $m2, 12294
	{
		rpt $m7, 1
		fnop
	}

	{
		ld64step $ap1, $m15, $m5+=, 12
		f16v8tof8 $ap0, $aq0
	}

	{
		ldst64pace $ap0, $ap0, $m0:1+=, $m2, 6
		fnop
	}

	f16v8tof8 $ap1, $aq0
	st64step $ap1, $m15, $m6+=, 6

	#NO_APP
	bri .LBB0_18
.LBB0_3:                                # %cond.false14.i
	sub $m0, $m10, $m7
	add $m0, $m0, 5
	setzi $m1, 43691
	sort4x16lo $m2, $m0, $m15
	shr $m0, $m0, 16
	mul $m3, $m2, $m1
	mul $m1, $m0, $m1
	shr $m3, $m3, 16
	add $m1, $m1, $m3
	setzi $m3, 43690
	sort4x16lo $m4, $m1, $m15
	mul $m2, $m2, $m3
	shr $m1, $m1, 16
	mul $m0, $m0, $m3
	add $m2, $m2, $m4
	add $m0, $m0, $m1
	shr $m1, $m2, 16
	add $m0, $m0, $m1
	setzi $m1, 192
	st32 $m1, $m11, $m15, 11                # 4-byte Folded Spill
	shr $m0, $m0, 2
	st32 $m0, $m11, $m15, 8                 # 4-byte Folded Spill
	setzi $m0, 6
	setzi $m3, 1
.LBB0_4:                                # %cond.end16.i
	mov	$m8, $m15
	ld32 $m1, $m11, $m15, 13                # 4-byte Folded Reload
	mul $m1, $m1, $m7
	movnz	$m8, $m5, $m1
	st32 $m9, $m11, $m15, 10                # 4-byte Folded Spill
	cmpult $m1, $m8, $m9
	brz $m1, .LBB0_42
# %bb.5:                                # %cond.end16.i
	mov	$m1, $m7
	movnz	$m1, $m5, $m15
	cmpult $m2, $m1, $m10
	brz $m2, .LBB0_42
# %bb.6:                                # %for.body.lr.ph.i
	mov	$m2, $m15
	shl $m4, $m7, 5
	mov	$m7, $m5
	shl $m5, $m10, 4
	movnz	$m2, $m7, $m4
	ld32 $m9, $m13, $m15, 7
	mul $m0, $m9, $m0
	shl $m4, $m0, 1
	ld32 $m0, $m11, $m15, 13                # 4-byte Folded Reload
	mul $m0, $m3, $m0
	st32 $m0, $m11, $m15, 6                 # 4-byte Folded Spill
	cmpeq $m10, $m9, 0
	mul $m0, $m1, $m9
	ld32 $m3, $m11, $m15, 11                # 4-byte Folded Reload
	movnz	$m4, $m10, $m3
	st32 $m4, $m11, $m15, 7                 # 4-byte Folded Spill
	add $m9, $m2, $m0
	setzi $m2, 16
	st32 $m10, $m11, $m15, 5                # 4-byte Folded Spill
	movnz	$m2, $m10, $m5
	shl $m0, $m1, 5
	shl $m1, $m1, 4
	st32 $m1, $m11, $m15, 4                 # 4-byte Folded Spill
	add $m0, $m6, $m0
	st32 $m0, $m11, $m15, 3                 # 4-byte Folded Spill
	setzi $m0, 32
	shl $m1, $m2, 1
	st32 $m1, $m11, $m15, 2                 # 4-byte Folded Spill
	setzi $m1, 192
	movnz	$m0, $m7, $m1
	bri .LBB0_7
.LBB0_9:                                # %if.end.i
                                        #   in Loop: Header=BB0_7 Depth=1
	mov	$m6, $m15
	mov	$m10, $m15
	ld32 $m3, $m11, $m15, 2                 # 4-byte Folded Reload
	add $m7, $m1, $m3
	ld32 $m4, $m11, $m15, 11                # 4-byte Folded Reload
	ld32 $m5, $m11, $m15, 8                 # 4-byte Folded Reload
	ld32 $m3, $m11, $m15, 7                 # 4-byte Folded Reload
	#APP
	{
		rpt $m5, 13
		fnop
	}

	{
		ld64 $ap0, $m1, $m6, 0
		fnop
	}

	{
		ld64 $ap1, $m1, $m6, 1
		fnop
	}

	{
		ld64 $ap0, $m1, $m6, 2
		f16v8tof8 $ap2, $aq0
	}

	{
		ld64 $ap1, $m1, $m6, 3
		fnop
	}

	{
		st64 $ap2, $m2, $m10, 0
		f16v8tof8 $ap3, $aq0
	}

	{
		ld64 $ap0, $m7, $m6, 0
		fnop
	}

	{
		ld64 $ap1, $m7, $m6, 1
		fnop
	}

	{
		st64 $ap3, $m2, $m10, 1
		f16v8tof8 $ap2, $aq0
	}

	{
		ld64 $ap0, $m7, $m6, 2
		fnop
	}

	{
		ld64 $ap1, $m7, $m6, 3
		fnop
	}

	{
		st64 $ap2, $m2, $m10, 2
		f16v8tof8 $ap3, $aq0
	}

	{
		st64 $ap3, $m2, $m10, 3
		fnop
	}

	{
		add $m6, $m6, $m3
		fnop
	}

	{
		add $m10, $m10, $m4
		fnop
	}


	#NO_APP
.LBB0_10:                               # %cleanup.i
                                        #   in Loop: Header=BB0_7 Depth=1
	ld32 $m1, $m11, $m15, 6                 # 4-byte Folded Reload
	add $m8, $m8, $m1
	ld32 $m1, $m11, $m15, 10                # 4-byte Folded Reload
	cmpult $m1, $m8, $m1
	add $m9, $m9, $m0
	brz $m1, .LBB0_42
.LBB0_7:                                # %for.body.i
                                        # =>This Inner Loop Header: Depth=1
	ld32 $m1, $m11, $m15, 4                 # 4-byte Folded Reload
	add $m1, $m1, $m8
	mov	$m2, $m9
	ld32 $m3, $m11, $m15, 5                 # 4-byte Folded Reload
	movnz	$m2, $m3, $m1
	ld32 $m1, $m11, $m15, 13                # 4-byte Folded Reload
	add $m1, $m1, $m8
	shl $m2, $m2, 1
	ld32 $m6, $m11, $m15, 12                # 4-byte Folded Reload
	cmpult $m6, $m6, $m1
	ld32 $m1, $m11, $m15, 9                 # 4-byte Folded Reload
	add $m1, $m1, $m2
	ld32 $m2, $m11, $m15, 3                 # 4-byte Folded Reload
	add $m2, $m2, $m8
	brz $m6, .LBB0_9
# %bb.8:                                # %if.then68.i
                                        #   in Loop: Header=BB0_7 Depth=1
	mov	$m6, $m15
	mov	$m10, $m15
	ld32 $m4, $m11, $m15, 11                # 4-byte Folded Reload
	ld32 $m5, $m11, $m15, 8                 # 4-byte Folded Reload
	ld32 $m3, $m11, $m15, 7                 # 4-byte Folded Reload
	#APP
	{
		rpt $m5, 9
		fnop
	}

	{
		ld64 $ap0, $m1, $m6, 0
		fnop
	}

	{
		ld64 $ap1, $m1, $m6, 1
		fnop
	}

	{
		ld64 $ap0, $m1, $m6, 2
		f16v8tof8 $ap2, $aq0
	}

	{
		ld64 $ap1, $m1, $m6, 3
		fnop
	}

	{
		st64 $ap2, $m2, $m10, 0
		f16v8tof8 $ap3, $aq0
	}

	{
		st64 $ap3, $m2, $m10, 1
		zero	$ap2
	}

	{
		st64 $ap2, $m2, $m10, 2
		fnop
	}

	{
		st64 $ap2, $m2, $m10, 3
		fnop
	}

	{
		add $m6, $m6, $m3
		fnop
	}

	{
		add $m10, $m10, $m4
		fnop
	}


	#NO_APP
	bri .LBB0_10
.LBB0_17:                               # %if.else.i
	#APP
	{
		rpt $m4, 3
		fnop
	}

	{
		ld64step $ap0, $m15, $m5+=, 1
		fnop
	}

	{
		ld64step $ap1, $m15, $m5+=, 11
		fnop
	}

	{
		nop
		f16v8tof8 $ap2, $aq0
	}

	{
		st64step $ap2, $m15, $m6+=, 6
		fnop
	}


	#NO_APP
.LBB0_18:                               # %if.end123.i
	mul $m0, $m4, 48
	add $m1, $m0, $m3
	mov	$m2, $m9
	cmpult $m0, $m1, $m9
	mov	$m6, $m10
	brz $m0, .LBB0_42
# %bb.19:                               # %if.end138.i
	mov	$m7, $m8
	ldb16 $a0, $m7, $m15, $m1
	sort4x16lo $a4, $a0, $azero
	{
		or $m0, $m1, 4
		mov	$a5, $azero
	}
	mov	$m5, $m2
	cmpult $m8, $m0, $m5
	brz $m8, .LBB0_20
# %bb.21:                               # %if.then142.i
	ldb16 $a0, $m7, $m15, $m0
	sort4x16lo $a6, $a0, $azero
	{
		bri .LBB0_22
		mov	$a7, $azero
	}
.LBB0_20:
	zero	$ap3
.LBB0_22:                               # %for.inc148.i
	or $m3, $m1, 1
	cmpult $m4, $m3, $m5
	brz $m4, .LBB0_24
# %bb.23:                               # %if.then135.1.i
	ldb16 $a0, $m7, $m15, $m3
	sort4x16lo $a4, $a4, $a0
.LBB0_24:                               # %if.end138.1.i
	or $m3, $m1, 5
	cmpult $m4, $m3, $m5
	brz $m4, .LBB0_26
# %bb.25:                               # %if.then142.1.i
	ldb16 $a0, $m7, $m15, $m3
	sort4x16lo $a6, $a6, $a0
.LBB0_26:                               # %for.inc148.1.i
	or $m3, $m1, 2
	cmpult $m4, $m3, $m5
	brz $m4, .LBB0_28
# %bb.27:                               # %if.then135.2.i
	ldb16 $a0, $m7, $m15, $m3
	roll16 $a0, $a5, $a0
	swap16	$a5, $a0
.LBB0_28:                               # %if.end138.2.i
	or $m3, $m1, 6
	cmpult $m4, $m3, $m5
	brz $m4, .LBB0_30
# %bb.29:                               # %if.then142.2.i
	ldb16 $a0, $m7, $m15, $m3
	roll16 $a0, $a7, $a0
	swap16	$a7, $a0
.LBB0_30:                               # %for.inc148.2.i
	or $m3, $m1, 3
	cmpult $m4, $m3, $m5
	brz $m4, .LBB0_32
# %bb.31:                               # %if.then135.3.i
	ldb16 $a0, $m7, $m15, $m3
	sort4x16lo $a5, $a5, $a0
.LBB0_32:                               # %if.end138.3.i
	or $m3, $m1, 7
	cmpult $m4, $m3, $m5
	brz $m4, .LBB0_34
# %bb.33:                               # %if.then142.3.i
	ldb16 $a0, $m7, $m15, $m3
	sort4x16lo $a7, $a7, $a0
.LBB0_34:                               # %for.body160.i
	sub $m3, $m5, $m1
	#APP
	mov	$ap0, $ap2
	mov	$ap1, $ap3
	f16v8tof8 $ap2, $aq0
	#NO_APP
	cmpult $m4, $m3, 4
	brnz $m4, .LBB0_36
# %bb.35:                               # %if.then169.i
	mov	$m4, $a4
	mov	$m5, $a5
	st32 $m4, $m6, $m1, 0
	brnz $m8, .LBB0_38
.LBB0_42:                               # %_ZN8Cast2To17computeEj.exit
	exitz $m15
.LBB0_36:                               # %if.else171.i
	shl $m3, $m3, 3
	add $m4, $m15, -1
	shl $m3, $m4, $m3
	ld32 $m4, $m6, $m1, 0
	and $m4, $m4, $m3
	mov	$m6, $a4
	mov	$m7, $a5
	andc $m3, $m6, $m3
	mov	$m6, $m10
	or $m4, $m4, $m3
	st32 $m4, $m6, $m1, 0
	brz $m8, .LBB0_42
.LBB0_38:                               # %for.body160.1.i
	sub $m1, $m2, $m0
	setzi $m2, 3
	cmpult $m2, $m2, $m1
	brz $m2, .LBB0_39
# %bb.40:                               # %if.then169.1.i
	mov	$m2, $a4
	mov	$m3, $a5
	st32 $m3, $m6, $m0, 0
	exitz $m15
.LBB0_39:                               # %if.else171.1.i
	shl $m1, $m1, 3
	add $m2, $m15, -1
	shl $m1, $m2, $m1
	ld32 $m2, $m6, $m0, 0
	and $m2, $m2, $m1
	mov	$m4, $a4
	mov	$m5, $a5
	andc $m1, $m5, $m1
	or $m3, $m2, $m1
	st32 $m3, $m6, $m0, 0
	exitz $m15
.Lfunc_end0:
	.size	__runCodelet_Cast2To1, .Lfunc_end0-__runCodelet_Cast2To1
	.section	.stack_sizes,"o",@progbits,.text.__runCodelet_Cast2To1
	.long	.Lfunc_begin0
	.byte	56
	.section	.text.__runCodelet_Cast2To1,"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