.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, 72
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	add $m11, $m12, -72
	mov	$m0, $m15
	{
		get $m2, 1
		setzi $a0, 2
	}
	ld32 $m1, $m13, $m15, 4
	sub $m1, 0, $m1
	ld32 $m4, $m13, $m15, 6
	and $m1, $m1, 255
	ld32 $m9, $m13, $m15, 0
	ld32 $m3, $m13, $m15, 1
	ld32 $m10, $m13, $m15, 2
	st32 $m1, $m11, $m15, 2
	ld32 $a1, $m11, $m15, 2
	ld32 $m1, $m13, $m15, 5
	#APP
	put	9, $a0
	put	10, $a1
	#NO_APP
	st32 $m4, $m11, $m15, 16                # 4-byte Folded Spill
	brz $m4, .LBB0_5
# %bb.1:                                # %entry
	brz $m10, .LBB0_5
# %bb.2:                                # %land.rhs.i
	ld32 $m0, $m11, $m15, 16                # 4-byte Folded Reload
	shl $m0, $m0, 1
	add $m0, $m9, $m0
	add $m0, $m0, -1
	shr $m0, $m0, 15
	shr $m4, $m3, 15
	cmpult $m0, $m0, $m4
	brz $m0, .LBB0_4
# %bb.3:
	setzi $m0, 1
.LBB0_5:                                # %land.end.i
	and $m4, $m2, 7
	brz $m1, .LBB0_18
.LBB0_6:                                # %if.then.i
	mul $m2, $m1, 192
	cmpult $m2, $m10, $m2
	cmpult $m5, $m1, 33
	cmpeq $m2, $m2, 0
	and $m2, $m5, $m2
	shl $m5, $m1, 5
	st32 $m5, $m11, $m15, 17                # 4-byte Folded Spill
	st32 $m9, $m11, $m15, 14                # 4-byte Folded Spill
	brz $m2, .LBB0_8
# %bb.7:
	setzi $m5, 1
	setzi $m6, 32
	st32 $m6, $m11, $m15, 9                 # 4-byte Folded Spill
	setzi $m6, 6
	st32 $m1, $m11, $m15, 15                # 4-byte Folded Spill
	bri .LBB0_9
.LBB0_8:                                # %cond.false28.i
	sub $m5, $m1, $m4
	add $m5, $m5, 5
	setzi $m6, 43691
	sort4x16lo $m7, $m5, $m15
	shr $m5, $m5, 16
	mul $m8, $m7, $m6
	mul $m6, $m5, $m6
	shr $m8, $m8, 16
	add $m6, $m6, $m8
	setzi $m8, 43690
	sort4x16lo $m9, $m6, $m15
	mul $m7, $m7, $m8
	shr $m6, $m6, 16
	mul $m5, $m5, $m8
	add $m7, $m7, $m9
	add $m5, $m5, $m6
	shr $m6, $m7, 16
	add $m5, $m5, $m6
	setzi $m6, 192
	st32 $m6, $m11, $m15, 9                 # 4-byte Folded Spill
	shr $m5, $m5, 2
	st32 $m5, $m11, $m15, 15                # 4-byte Folded Spill
	setzi $m5, 6
	setzi $m6, 1
.LBB0_9:                                # %cond.end31.i
	mov	$m9, $m15
	ld32 $m7, $m11, $m15, 17                # 4-byte Folded Reload
	mul $m7, $m7, $m4
	movnz	$m9, $m2, $m7
	cmpult $m7, $m9, $m10
	brz $m7, .LBB0_45
# %bb.10:                               # %cond.end31.i
	mov	$m7, $m4
	movnz	$m7, $m2, $m15
	cmpult $m8, $m7, $m1
	brz $m8, .LBB0_45
# %bb.11:                               # %for.body.lr.ph.i
	mov	$m8, $m15
	shl $m4, $m4, 5
	shl $m1, $m1, 4
	movnz	$m8, $m2, $m4
	ld32 $m4, $m13, $m15, 7
	mul $m5, $m4, $m5
	st32 $m3, $m11, $m15, 11                # 4-byte Folded Spill
	shl $m3, $m5, 1
	ld32 $m5, $m11, $m15, 17                # 4-byte Folded Reload
	mul $m5, $m6, $m5
	st32 $m5, $m11, $m15, 5                 # 4-byte Folded Spill
	mov	$m5, $m0
	cmpeq $m0, $m4, 0
	ld32 $m6, $m11, $m15, 9                 # 4-byte Folded Reload
	st32 $m6, $m11, $m15, 9                 # 4-byte Folded Spill
	movnz	$m3, $m0, $m6
	mul $m4, $m7, $m4
	add $m8, $m8, $m4
	setzi $m4, 1
	xor $m6, $m5, $m4
	st32 $m3, $m11, $m15, 8                 # 4-byte Folded Spill
	shr $m4, $m3, 3
	setzi $m5, 16
	st32 $m0, $m11, $m15, 13                # 4-byte Folded Spill
	movnz	$m5, $m0, $m1
	ld32 $m1, $m11, $m15, 15                # 4-byte Folded Reload
	cmpult $m1, $m1, 16
	or $m0, $m6, $m1
	add $m1, $m4, -514
	add $m3, $m4, -3
	st32 $m3, $m11, $m15, 4                 # 4-byte Folded Spill
	shl $m3, $m5, 1
	st32 $m3, $m11, $m15, 7                 # 4-byte Folded Spill
	add $m4, $m15, -512
	cmpult $m1, $m1, $m4
	or $m0, $m0, $m1
	st32 $m0, $m11, $m15, 6                 # 4-byte Folded Spill
	shl $m0, $m7, 5
	shl $m1, $m7, 4
	st32 $m1, $m11, $m15, 12                # 4-byte Folded Spill
	ld32 $m7, $m11, $m15, 5                 # 4-byte Folded Reload
	ld32 $m1, $m11, $m15, 11                # 4-byte Folded Reload
	add $m0, $m1, $m0
	st32 $m0, $m11, $m15, 11                # 4-byte Folded Spill
	ld32 $m0, $m11, $m15, 9                 # 4-byte Folded Reload
	shr $m0, $m0, 3
	add $m0, $m0, -3
	st32 $m0, $m11, $m15, 3                 # 4-byte Folded Spill
	setzi $m1, 32
	setzi $m0, 192
	movnz	$m1, $m2, $m0
	st32 $m1, $m11, $m15, 10                # 4-byte Folded Spill
	bri .LBB0_12
.LBB0_13:                               # %if.then83.i
                                        #   in Loop: Header=BB0_12 Depth=1
	mov	$m1, $m15
	mov	$m3, $m15
	ld32 $m4, $m11, $m15, 9                 # 4-byte Folded Reload
	ld32 $m5, $m11, $m15, 15                # 4-byte Folded Reload
	ld32 $m6, $m11, $m15, 8                 # 4-byte Folded Reload
	#APP
	{
		rpt $m5, 9
		fnop
	}

	{
		ld64 $ap0, $m0, $m1, 0
		fnop
	}

	{
		ld64 $ap1, $m0, $m1, 1
		fnop
	}

	{
		ld64 $ap0, $m0, $m1, 2
		f16v8tof8 $ap2, $aq0
	}

	{
		ld64 $ap1, $m0, $m1, 3
		fnop
	}

	{
		st64 $ap2, $m2, $m3, 0
		f16v8tof8 $ap3, $aq0
	}

	{
		st64 $ap3, $m2, $m3, 1
		zero	$ap2
	}

	{
		st64 $ap2, $m2, $m3, 2
		fnop
	}

	{
		st64 $ap2, $m2, $m3, 3
		fnop
	}

	{
		add $m1, $m1, $m6
		fnop
	}

	{
		add $m3, $m3, $m4
		fnop
	}


	#NO_APP
.LBB0_17:                               # %cleanup.i
                                        #   in Loop: Header=BB0_12 Depth=1
	add $m9, $m9, $m7
	cmpult $m0, $m9, $m10
	ld32 $m1, $m11, $m15, 10                # 4-byte Folded Reload
	add $m8, $m8, $m1
	brz $m0, .LBB0_45
.LBB0_12:                               # %for.body.i
                                        # =>This Inner Loop Header: Depth=1
	ld32 $m0, $m11, $m15, 12                # 4-byte Folded Reload
	add $m0, $m0, $m9
	mov	$m1, $m8
	ld32 $m2, $m11, $m15, 13                # 4-byte Folded Reload
	movnz	$m1, $m2, $m0
	ld32 $m0, $m11, $m15, 17                # 4-byte Folded Reload
	add $m0, $m0, $m9
	shl $m1, $m1, 1
	ld32 $m2, $m11, $m15, 16                # 4-byte Folded Reload
	cmpult $m3, $m2, $m0
	ld32 $m0, $m11, $m15, 14                # 4-byte Folded Reload
	add $m0, $m0, $m1
	ld32 $m1, $m11, $m15, 11                # 4-byte Folded Reload
	add $m2, $m1, $m9
	brnz $m3, .LBB0_13
# %bb.14:                               # %if.end.i
                                        #   in Loop: Header=BB0_12 Depth=1
	ld32 $m1, $m11, $m15, 7                 # 4-byte Folded Reload
	add $m1, $m0, $m1
	ld32 $m3, $m11, $m15, 6                 # 4-byte Folded Reload
	brz $m3, .LBB0_15
# %bb.16:                               # %if.end93.i
                                        #   in Loop: Header=BB0_12 Depth=1
	ld32 $m3, $m11, $m15, 15                # 4-byte Folded Reload
	ld32 $m4, $m11, $m15, 4                 # 4-byte Folded Reload
	ld32 $m5, $m11, $m15, 3                 # 4-byte Folded Reload
	#APP
	{
		rpt $m3, 11
		fnop
	}

	{
		ld64step $ap0, $m15, $m0+=, 1
		fnop
	}

	{
		ld64step $ap1, $m15, $m0+=, 1
		fnop
	}

	{
		ld64step $ap0, $m15, $m0+=, 1
		f16v8tof8 $ap2, $aq0
	}

	{
		ld64step $ap1, $m15, $m0+=, $m4
		fnop
	}

	{
		st64step $ap2, $m15, $m2+=, 1
		f16v8tof8 $ap3, $aq0
	}

	{
		ld64step $ap0, $m15, $m1+=, 1
		fnop
	}

	{
		ld64step $ap1, $m15, $m1+=, 1
		fnop
	}

	{
		st64step $ap3, $m15, $m2+=, 1
		f16v8tof8 $ap2, $aq0
	}

	{
		ld64step $ap0, $m15, $m1+=, 1
		fnop
	}

	{
		ld64step $ap1, $m15, $m1+=, $m4
		fnop
	}

	{
		st64step $ap2, $m15, $m2+=, 1
		f16v8tof8 $ap3, $aq0
	}

	{
		st64step $ap3, $m15, $m2+=, $m5
		fnop
	}


	#NO_APP
	bri .LBB0_17
.LBB0_15:                               # %if.then92.i
                                        #   in Loop: Header=BB0_12 Depth=1
	ld32 $m3, $m11, $m15, 8                 # 4-byte Folded Reload
	st32 $m3, $m11, $m15, 1
	ld32 $m3, $m11, $m15, 9                 # 4-byte Folded Reload
	st32 $m3, $m11, $m15, 0
	ld32 $m3, $m11, $m15, 15                # 4-byte Folded Reload
	mov	$m7, $m10
	call $m10, _ZL14castPackedRowsPKDhS0_Phjjj
	mov	$m10, $m7
	ld32 $m7, $m11, $m15, 5                 # 4-byte Folded Reload
	bri .LBB0_17
.LBB0_4:                                # %lor.rhs.i
	add $m0, $m3, $m10
	add $m0, $m0, -1
	shr $m0, $m0, 15
	shr $m4, $m9, 15
	cmpult $m0, $m0, $m4
	and $m4, $m2, 7
	brnz $m1, .LBB0_6
.LBB0_18:                               # %if.end118.i
	shr $m1, $m10, 3
	sub $m1, $m1, $m4
	add $m1, $m1, 5
	setzi $m2, 43691
	sort4x16lo $m5, $m1, $m15
	shr $m6, $m1, 16
	mul $m7, $m5, $m2
	mul $m2, $m6, $m2
	shr $m7, $m7, 16
	add $m2, $m2, $m7
	setzi $m7, 43690
	sort4x16lo $m8, $m2, $m15
	mul $m5, $m5, $m7
	shr $m2, $m2, 16
	mul $m6, $m6, $m7
	setzi $m7, 23
	add $m5, $m5, $m8
	cmpult $m1, $m7, $m1
	add $m2, $m6, $m2
	shr $m5, $m5, 16
	and $m0, $m0, $m1
	add $m1, $m2, $m5
	shl $m5, $m4, 3
	shl $m2, $m4, 4
	cmpeq $m0, $m0, 1
	shr $m4, $m1, 2
	add $m6, $m9, $m2
	add $m7, $m3, $m5
	brz $m0, .LBB0_20
# %bb.19:                               # %if.then130.i
	add $m8, $m4, -1
	#APP
	ld64step $ap0, $m15, $m6+=, 1
	ld64step $ap1, $m15, $m6+=, 11
	tapack $m0:1, $m6, $m15, $m7
	ld64step $apzero, $m15, $m6+=, 1
	mul $m2, $m8, 48
	add $m7, $m7, $m2
	setzi $m2, 12294
	{
		rpt $m8, 1
		fnop
	}

	{
		ld64step $ap1, $m15, $m6+=, 12
		f16v8tof8 $ap0, $aq0
	}

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

	f16v8tof8 $ap1, $aq0
	st64step $ap1, $m15, $m7+=, 6

	#NO_APP
	bri .LBB0_21
.LBB0_20:                               # %if.else.i
	#APP
	{
		rpt $m4, 3
		fnop
	}

	{
		ld64step $ap0, $m15, $m6+=, 1
		fnop
	}

	{
		ld64step $ap1, $m15, $m6+=, 11
		fnop
	}

	{
		nop
		f16v8tof8 $ap2, $aq0
	}

	{
		st64step $ap2, $m15, $m7+=, 6
		fnop
	}


	#NO_APP
.LBB0_21:                               # %if.end135.i
	mul $m0, $m4, 48
	add $m1, $m0, $m5
	cmpult $m0, $m1, $m10
	brz $m0, .LBB0_45
# %bb.22:                               # %if.end150.i
	mov	$m6, $m9
	ldb16 $a0, $m6, $m15, $m1
	sort4x16lo $a4, $a0, $azero
	{
		or $m0, $m1, 4
		mov	$a5, $azero
	}
	cmpult $m2, $m0, $m10
	brz $m2, .LBB0_23
# %bb.24:                               # %if.then154.i
	ldb16 $a0, $m6, $m15, $m0
	sort4x16lo $a6, $a0, $azero
	{
		bri .LBB0_25
		mov	$a7, $azero
	}
.LBB0_23:
	zero	$ap3
.LBB0_25:                               # %for.inc160.i
	or $m4, $m1, 1
	cmpult $m5, $m4, $m10
	brz $m5, .LBB0_27
# %bb.26:                               # %if.then147.1.i
	ldb16 $a0, $m6, $m15, $m4
	sort4x16lo $a4, $a4, $a0
.LBB0_27:                               # %if.end150.1.i
	or $m4, $m1, 5
	cmpult $m5, $m4, $m10
	brz $m5, .LBB0_29
# %bb.28:                               # %if.then154.1.i
	ldb16 $a0, $m6, $m15, $m4
	sort4x16lo $a6, $a6, $a0
.LBB0_29:                               # %for.inc160.1.i
	or $m4, $m1, 2
	cmpult $m5, $m4, $m10
	brz $m5, .LBB0_31
# %bb.30:                               # %if.then147.2.i
	ldb16 $a0, $m6, $m15, $m4
	roll16 $a0, $a5, $a0
	swap16	$a5, $a0
.LBB0_31:                               # %if.end150.2.i
	or $m4, $m1, 6
	cmpult $m5, $m4, $m10
	brz $m5, .LBB0_33
# %bb.32:                               # %if.then154.2.i
	ldb16 $a0, $m6, $m15, $m4
	roll16 $a0, $a7, $a0
	swap16	$a7, $a0
.LBB0_33:                               # %for.inc160.2.i
	or $m4, $m1, 3
	cmpult $m5, $m4, $m10
	brz $m5, .LBB0_35
# %bb.34:                               # %if.then147.3.i
	ldb16 $a0, $m6, $m15, $m4
	sort4x16lo $a5, $a5, $a0
.LBB0_35:                               # %if.end150.3.i
	or $m4, $m1, 7
	cmpult $m5, $m4, $m10
	brz $m5, .LBB0_37
# %bb.36:                               # %if.then154.3.i
	ldb16 $a0, $m6, $m15, $m4
	sort4x16lo $a7, $a7, $a0
.LBB0_37:                               # %for.body172.i
	sub $m4, $m10, $m1
	#APP
	mov	$ap0, $ap2
	mov	$ap1, $ap3
	f16v8tof8 $ap2, $aq0
	#NO_APP
	cmpult $m5, $m4, 4
	brnz $m5, .LBB0_39
# %bb.38:                               # %if.then181.i
	mov	$m4, $a4
	mov	$m5, $a5
	st32 $m4, $m3, $m1, 0
	brnz $m2, .LBB0_41
.LBB0_45:                               # %_ZN8Cast2To17computeEj.exit
	exitz $m15
.LBB0_39:                               # %if.else183.i
	shl $m4, $m4, 3
	add $m5, $m15, -1
	shl $m4, $m5, $m4
	ld32 $m5, $m3, $m1, 0
	and $m5, $m5, $m4
	mov	$m6, $a4
	mov	$m7, $a5
	andc $m4, $m6, $m4
	or $m4, $m5, $m4
	st32 $m4, $m3, $m1, 0
	brz $m2, .LBB0_45
.LBB0_41:                               # %for.body172.1.i
	sub $m1, $m10, $m0
	setzi $m2, 3
	cmpult $m2, $m2, $m1
	brz $m2, .LBB0_42
# %bb.43:                               # %if.then181.1.i
	mov	$m4, $a4
	mov	$m5, $a5
	st32 $m5, $m3, $m0, 0
	exitz $m15
.LBB0_42:                               # %if.else183.1.i
	shl $m1, $m1, 3
	add $m2, $m15, -1
	shl $m1, $m2, $m1
	ld32 $m2, $m3, $m0, 0
	and $m2, $m2, $m1
	mov	$m4, $a4
	mov	$m5, $a5
	andc $m1, $m5, $m1
	or $m5, $m2, $m1
	st32 $m5, $m3, $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	72
	.section	.text.__runCodelet_Cast2To1,"ax",@progbits
                                        # -- End function
	.section	.text._ZL14castPackedRowsPKDhS0_Phjjj,"ax",@progbits
	.p2align	2                               # -- Begin function _ZL14castPackedRowsPKDhS0_Phjjj
	.type	_ZL14castPackedRowsPKDhS0_Phjjj,@function
_ZL14castPackedRowsPKDhS0_Phjjj:        # @_ZL14castPackedRowsPKDhS0_Phjjj
	.worker
.Lfunc_begin1:
# %bb.0:                                # %entry
	add $m11, $m11, -32
	sub $m6, $m12, $m11
	cmpult $m6, $m6, __worker_stack_max_growth_plus_one
	brz $m6, _stackoverflow
	st32 $m8, $m11, $m15, 7                 # 4-byte Folded Spill
	st32 $m9, $m11, $m15, 6                 # 4-byte Folded Spill
	st32 $m10, $m11, $m15, 5                # 4-byte Folded Spill
	st64 $ap3, $m11, $m15, 1                # 8-byte Folded Spill
	st32 $m7, $m11, $m15, 1                 # 4-byte Folded Spill
	mov	$m4, $m2
	mov	$m5, $m1
	mov	$m6, $m0
	ld32 $m0, $m11, $m15, 8
	ld32 $m1, $m11, $m15, 9
	shl $m2, $m0, 17
	setzi $m7, 1048575
	shr $m1, $m1, 3
	andc $m2, $m2, $m7
	or $m7, $m15, 4293918720
	add $m8, $m1, -2
	add $m1, $m2, $m7
	add $m7, $m3, -1
	or $m1, $m1, $m8
	mul $m0, $m7, $m0
	or $m9, $m1, 2048
	add $m10, $m4, $m0
	#APP
	ld64step $ap0, $m15, $m6+=, 1
	ld64step $ap1, $m15, $m6+=, 2
	ld64step $ap2, $m15, $m5+=, 1
	ld64step $ap3, $m15, $m5+=, 2
	add $m0, $m6, -8
	tapack $m0:1, $m0, $m15, $m4
	add $m2, $m5, -8
	add $m3, $m4, 16
	tapack $m2:3, $m2, $m15, $m3
	{
		rpt $m7, 7
		fnop
	}

	{
		ld64step $ap1, $m15, $m6+=, $m8
		f16v8tof8 $ap0, $aq0
	}

	{
		ldst64pace $ap0, $ap0, $m0:1+=, $m9, 1
		fnop
	}

	{
		ld64step $ap1, $m15, $m6+=, 2
		f16v8tof8 $ap0, $aq0
	}

	{
		ldst64pace $ap0, $ap0, $m0:1+=, $m9, 14
		fnop
	}

	{
		ld64step $ap3, $m15, $m5+=, $m8
		f16v8tof8 $ap2, $aq1
	}

	{
		ldst64pace $ap2, $ap2, $m2:3+=, $m9, 1
		fnop
	}

	{
		ld64step $ap3, $m15, $m5+=, 2
		f16v8tof8 $ap2, $aq1
	}

	{
		ldst64pace $ap2, $ap2, $m2:3+=, $m9, 14
		fnop
	}

	{
		ld64 $ap1, $m6, $m15, 0
		f16v8tof8 $ap0, $aq0
	}

	{
		ldst64pace $ap0, $ap0, $m0:1+=, $m9, 1
		fnop
	}

	{
		nop
		f16v8tof8 $ap1, $aq0
	}

	{
		ld64 $ap3, $m5, $m15, 0
		f16v8tof8 $ap2, $aq1
	}

	{
		ldst64pace $ap2, $ap2, $m2:3+=, $m9, 1
		fnop
	}

	{
		st64 $ap1, $m10, $m15, 1
		f16v8tof8 $ap3, $aq1
	}

	{
		st64 $ap3, $m10, $m15, 3
		fnop
	}


	#NO_APP
	ld32 $m7, $m11, $m15, 1                 # 4-byte Folded Reload
	ld64 $ap3, $m11, $m15, 1                # 8-byte Folded Reload
	ld32 $m10, $m11, $m15, 5                # 4-byte Folded Reload
	ld32 $m9, $m11, $m15, 6                 # 4-byte Folded Reload
	ld32 $m8, $m11, $m15, 7                 # 4-byte Folded Reload
	add $m11, $m11, 32
	br $m10
.Lfunc_end1:
	.size	_ZL14castPackedRowsPKDhS0_Phjjj, .Lfunc_end1-_ZL14castPackedRowsPKDhS0_Phjjj
	.section	.stack_sizes,"o",@progbits,.text._ZL14castPackedRowsPKDhS0_Phjjj
	.long	.Lfunc_begin1
	.byte	32
	.section	.text._ZL14castPackedRowsPKDhS0_Phjjj,"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