.build_version macos, 27, 0	sdk_version 27, 0
	.section	__TEXT,__text,regular,pure_instructions
	.globl	_main                           ; -- Begin function main
	.p2align	2
_main:                                  ; @main
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #288
	stp	d9, d8, [sp, #176]              ; 16-byte Folded Spill
	stp	x28, x27, [sp, #192]            ; 16-byte Folded Spill
	stp	x26, x25, [sp, #208]            ; 16-byte Folded Spill
	stp	x24, x23, [sp, #224]            ; 16-byte Folded Spill
	stp	x22, x21, [sp, #240]            ; 16-byte Folded Spill
	stp	x20, x19, [sp, #256]            ; 16-byte Folded Spill
	stp	x29, x30, [sp, #272]            ; 16-byte Folded Spill
	add	x29, sp, #272
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
	.cfi_offset w19, -24
	.cfi_offset w20, -32
	.cfi_offset w21, -40
	.cfi_offset w22, -48
	.cfi_offset w23, -56
	.cfi_offset w24, -64
	.cfi_offset w25, -72
	.cfi_offset w26, -80
	.cfi_offset w27, -88
	.cfi_offset w28, -96
	.cfi_offset b8, -104
	.cfi_offset b9, -112
	mov	w8, #1048576                    ; =0x100000
	stur	x8, [x29, #-120]
	mov	w8, #192                        ; =0xc0
	stur	x8, [x29, #-128]
	mov	w8, #32                         ; =0x20
	str	x8, [sp, #136]
	mov	w8, #5                          ; =0x5
	str	x8, [sp, #128]
	cmp	w0, #2
	b.lt	LBB0_12
; %bb.1:
	mov	x19, x1
	mov	x20, x0
	ldr	x21, [x1, #8]
Lloh0:
	adrp	x1, l_.str@PAGE
Lloh1:
	add	x1, x1, l_.str@PAGEOFF
	mov	x0, x21
	bl	_strcmp
	cbz	w0, LBB0_4
; %bb.2:
	cmp	w20, #6
	b.lo	LBB0_5
; %bb.3:
	ldr	x8, [x19]
Lloh2:
	adrp	x9, ___stderrp@GOTPAGE
Lloh3:
	ldr	x9, [x9, ___stderrp@GOTPAGEOFF]
Lloh4:
	ldr	x0, [x9]
	mov	w9, #1000                       ; =0x3e8
	mov	w10, #2048                      ; =0x800
	stp	x10, x9, [sp, #16]
	mov	w9, #16777216                   ; =0x1000000
	stp	x8, x9, [sp]
Lloh5:
	adrp	x1, l_.str.6@PAGE
Lloh6:
	add	x1, x1, l_.str.6@PAGEOFF
	bl	_fprintf
	mov	w0, #2                          ; =0x2
	b	LBB0_117
LBB0_4:
	ldr	x8, [x19]
Lloh7:
	adrp	x9, ___stderrp@GOTPAGE
Lloh8:
	ldr	x9, [x9, ___stderrp@GOTPAGEOFF]
Lloh9:
	ldr	x0, [x9]
	mov	w9, #1000                       ; =0x3e8
	mov	w10, #2048                      ; =0x800
	stp	x10, x9, [sp, #16]
	mov	w9, #16777216                   ; =0x1000000
	stp	x8, x9, [sp]
Lloh10:
	adrp	x1, l_.str.6@PAGE
Lloh11:
	add	x1, x1, l_.str.6@PAGEOFF
	bl	_fprintf
	b	LBB0_116
LBB0_5:
Lloh12:
	adrp	x1, l_.str.1@PAGE
Lloh13:
	add	x1, x1, l_.str.1@PAGEOFF
	sub	x3, x29, #120
	mov	x0, x21
	mov	w2, #16777216                   ; =0x1000000
	bl	_parse_size_arg
	cbz	w0, LBB0_34
; %bb.6:
	cmp	w20, #2
	b.eq	LBB0_12
; %bb.7:
	ldr	x0, [x19, #16]
Lloh14:
	adrp	x1, l_.str.2@PAGE
Lloh15:
	add	x1, x1, l_.str.2@PAGEOFF
	sub	x3, x29, #128
	mov	w2, #2048                       ; =0x800
	bl	_parse_size_arg
	cbz	w0, LBB0_34
; %bb.8:
	cmp	w20, #4
	b.lo	LBB0_12
; %bb.9:
	ldr	x0, [x19, #24]
Lloh16:
	adrp	x1, l_.str.3@PAGE
Lloh17:
	add	x1, x1, l_.str.3@PAGEOFF
	add	x3, sp, #136
	mov	w2, #2048                       ; =0x800
	bl	_parse_size_arg
	cbz	w0, LBB0_34
; %bb.10:
	cmp	w20, #5
	b.ne	LBB0_12
; %bb.11:
	ldr	x0, [x19, #32]
Lloh18:
	adrp	x1, l_.str.4@PAGE
Lloh19:
	add	x1, x1, l_.str.4@PAGEOFF
	add	x3, sp, #128
	mov	w2, #1000                       ; =0x3e8
	bl	_parse_size_arg
	cbz	w0, LBB0_34
LBB0_12:
	ldr	x8, [sp, #136]
	ldur	x20, [x29, #-128]
	str	x8, [sp, #80]                   ; 8-byte Folded Spill
	cmp	x8, x20
	b.ls	LBB0_14
; %bb.13:
Lloh20:
	adrp	x8, ___stderrp@GOTPAGE
Lloh21:
	ldr	x8, [x8, ___stderrp@GOTPAGEOFF]
Lloh22:
	ldr	x3, [x8]
Lloh23:
	adrp	x0, l_.str.5@PAGE
Lloh24:
	add	x0, x0, l_.str.5@PAGEOFF
	mov	w1, #26                         ; =0x1a
	mov	w2, #1                          ; =0x1
	bl	_fwrite
	mov	w0, #2                          ; =0x2
	b	LBB0_117
LBB0_14:
	ldur	x26, [x29, #-120]
	ldr	x8, [sp, #128]
	str	x8, [sp, #112]                  ; 8-byte Folded Spill
	cbz	x26, LBB0_17
; %bb.15:
	lsr	x8, x26, #60
	cbnz	x8, LBB0_125
; %bb.16:
	lsl	x22, x26, #4
	b	LBB0_18
LBB0_17:
	mov	x22, #0                         ; =0x0
LBB0_18:
	mov	x0, x22
	bl	_malloc
	cbz	x0, LBB0_119
; %bb.19:
	mov	x21, x0
	lsl	x23, x26, #2
	mov	x0, x23
	bl	_malloc
	cbz	x0, LBB0_120
; %bb.20:
	mov	x22, x0
	cbz	x26, LBB0_45
; %bb.21:
	mov	x8, #0                          ; =0x0
	add	x9, x21, #8
LBB0_22:                                ; =>This Inner Loop Header: Depth=1
	and	x10, x8, #0x3ff
	add	x11, x10, #1
	ucvtf	s0, x11
	add	x11, x10, #2
	ucvtf	s1, x11
	add	x11, x10, #3
	ucvtf	s2, x11
	add	x10, x10, #4
	ucvtf	s3, x10
	stp	s0, s1, [x9, #-8]
	stp	s2, s3, [x9], #16
	str	s0, [x22, x8, lsl #2]
	add	x8, x8, #1
	cmp	x26, x8
	b.ne	LBB0_22
; %bb.23:
	cmp	x26, #4
	b.hs	LBB0_25
; %bb.24:
	mov	x8, #0                          ; =0x0
	movi.2d	v0, #0000000000000000
	b	LBB0_28
LBB0_25:
	and	x8, x26, #0xfffffffffffffffc
	add	x9, x21, #32
	movi.2d	v0, #0000000000000000
	mov	x10, x8
LBB0_26:                                ; =>This Inner Loop Header: Depth=1
	ldur	s1, [x9, #-32]
	ldur	s2, [x9, #-16]
	ldr	s3, [x9]
	ldr	s4, [x9, #16]
	fadd	s0, s0, s1
	fadd	s0, s0, s2
	fadd	s0, s0, s3
	fadd	s0, s0, s4
	add	x9, x9, #64
	subs	x10, x10, #4
	b.ne	LBB0_26
; %bb.27:
	cmp	x26, x8
	b.eq	LBB0_30
LBB0_28:
	sub	x9, x26, x8
	add	x8, x21, x8, lsl #4
LBB0_29:                                ; =>This Inner Loop Header: Depth=1
	ldr	s1, [x8], #16
	fadd	s0, s0, s1
	subs	x9, x9, #1
	b.ne	LBB0_29
LBB0_30:
	cmp	x26, #4
	b.hs	LBB0_32
; %bb.31:
	mov	x8, #0                          ; =0x0
	movi.2d	v1, #0000000000000000
	b	LBB0_42
LBB0_32:
	cmp	x26, #16
	b.hs	LBB0_35
; %bb.33:
	mov	x8, #0                          ; =0x0
	movi.2d	v1, #0000000000000000
	b	LBB0_39
LBB0_34:
	mov	w0, #2                          ; =0x2
	b	LBB0_117
LBB0_35:
	and	x8, x26, #0xfffffffffffffff0
	add	x9, x22, #32
	movi.2d	v1, #0000000000000000
	mov	x10, x8
LBB0_36:                                ; =>This Inner Loop Header: Depth=1
	ldp	q2, q3, [x9, #-32]
	mov	s4, v2[3]
	mov	s5, v2[2]
	mov	s6, v2[1]
	mov	s7, v3[3]
	mov	s16, v3[2]
	mov	s17, v3[1]
	ldp	q18, q19, [x9], #64
	mov	s20, v18[3]
	mov	s21, v18[2]
	mov	s22, v18[1]
	mov	s23, v19[3]
	mov	s24, v19[2]
	mov	s25, v19[1]
	fadd	s1, s1, s2
	fadd	s1, s1, s6
	fadd	s1, s1, s5
	fadd	s1, s1, s4
	fadd	s1, s1, s3
	fadd	s1, s1, s17
	fadd	s1, s1, s16
	fadd	s1, s1, s7
	fadd	s1, s1, s18
	fadd	s1, s1, s22
	fadd	s1, s1, s21
	fadd	s1, s1, s20
	fadd	s1, s1, s19
	fadd	s1, s1, s25
	fadd	s1, s1, s24
	fadd	s1, s1, s23
	subs	x10, x10, #16
	b.ne	LBB0_36
; %bb.37:
	cmp	x26, x8
	b.eq	LBB0_44
; %bb.38:
	tst	x26, #0xc
	b.eq	LBB0_42
LBB0_39:
	mov	x10, x8
	and	x8, x26, #0xfffffffffffffffc
	sub	x9, x10, x8
	add	x10, x22, x10, lsl #2
LBB0_40:                                ; =>This Inner Loop Header: Depth=1
	ldr	q2, [x10], #16
	mov	s3, v2[3]
	mov	s4, v2[2]
	mov	s5, v2[1]
	fadd	s1, s1, s2
	fadd	s1, s1, s5
	fadd	s1, s1, s4
	fadd	s1, s1, s3
	adds	x9, x9, #4
	b.ne	LBB0_40
; %bb.41:
	cmp	x26, x8
	b.eq	LBB0_44
LBB0_42:
	sub	x9, x26, x8
	add	x8, x22, x8, lsl #2
LBB0_43:                                ; =>This Inner Loop Header: Depth=1
	ldr	s2, [x8], #4
	fadd	s1, s1, s2
	subs	x9, x9, #1
	b.ne	LBB0_43
LBB0_44:
	fcmp	s0, s1
	b.ne	LBB0_126
LBB0_45:
	ldr	x8, [sp, #112]                  ; 8-byte Folded Reload
	cbz	x8, LBB0_65
; %bb.46:
	mov	x19, #0                         ; =0x0
	and	x27, x26, #0xfffffffffffffff0
	and	x9, x26, #0xc
	and	x28, x26, #0xfffffffffffffffc
	add	x8, x22, #32
	stp	x9, x8, [sp, #96]               ; 16-byte Folded Spill
	neg	x8, x28
	str	x8, [sp, #120]                  ; 8-byte Folded Spill
Lloh25:
	adrp	x23, l_.str.10@PAGE
Lloh26:
	add	x23, x23, l_.str.10@PAGEOFF
	b	LBB0_49
LBB0_47:                                ;   in Loop: Header=BB0_49 Depth=1
	stur	wzr, [x29, #-108]
	mov	w0, #8                          ; =0x8
	bl	_clock_gettime_nsec_np
	mov	x25, x0
	movi.2d	v0, #0000000000000000
LBB0_48:                                ;   in Loop: Header=BB0_49 Depth=1
	stur	s0, [x29, #-112]
	mov	w0, #8                          ; =0x8
	bl	_clock_gettime_nsec_np
	sub	x8, x25, x24
	sub	x9, x0, x25
	ldur	s0, [x29, #-108]
	ldur	s1, [x29, #-112]
	fadd	s0, s0, s1
	fcvt	d0, s0
	str	d0, [sp, #32]
	stp	x8, x9, [sp, #16]
	stp	x19, x26, [sp]
	mov	x0, x23
	bl	_printf
	add	x19, x19, #1
	ldr	x8, [sp, #112]                  ; 8-byte Folded Reload
	cmp	x19, x8
	b.eq	LBB0_65
LBB0_49:                                ; =>This Loop Header: Depth=1
                                        ;     Child Loop BB0_51 Depth 2
                                        ;     Child Loop BB0_57 Depth 2
                                        ;     Child Loop BB0_61 Depth 2
                                        ;     Child Loop BB0_64 Depth 2
	mov	w0, #8                          ; =0x8
	bl	_clock_gettime_nsec_np
	mov	x24, x0
	cbz	x26, LBB0_47
; %bb.50:                               ;   in Loop: Header=BB0_49 Depth=1
	movi.2d	v0, #0000000000000000
	mov	x8, x21
	mov	x9, x26
LBB0_51:                                ;   Parent Loop BB0_49 Depth=1
                                        ; =>  This Inner Loop Header: Depth=2
	ldr	s1, [x8], #16
	fadd	s0, s0, s1
	subs	x9, x9, #1
	b.ne	LBB0_51
; %bb.52:                               ;   in Loop: Header=BB0_49 Depth=1
	stur	s0, [x29, #-108]
	mov	w0, #8                          ; =0x8
	bl	_clock_gettime_nsec_np
	mov	x25, x0
	cmp	x26, #4
	b.hs	LBB0_54
; %bb.53:                               ;   in Loop: Header=BB0_49 Depth=1
	mov	x9, #0                          ; =0x0
	movi.2d	v0, #0000000000000000
	b	LBB0_63
LBB0_54:                                ;   in Loop: Header=BB0_49 Depth=1
	cmp	x26, #16
	b.hs	LBB0_56
; %bb.55:                               ;   in Loop: Header=BB0_49 Depth=1
	mov	x10, #0                         ; =0x0
	movi.2d	v0, #0000000000000000
	b	LBB0_60
LBB0_56:                                ;   in Loop: Header=BB0_49 Depth=1
	movi.2d	v0, #0000000000000000
	ldr	x8, [sp, #104]                  ; 8-byte Folded Reload
	mov	x9, x27
LBB0_57:                                ;   Parent Loop BB0_49 Depth=1
                                        ; =>  This Inner Loop Header: Depth=2
	ldp	q1, q2, [x8, #-32]
	mov	s3, v1[3]
	mov	s4, v1[2]
	mov	s5, v1[1]
	mov	s6, v2[3]
	mov	s7, v2[2]
	mov	s16, v2[1]
	ldp	q17, q18, [x8], #64
	mov	s19, v17[3]
	mov	s20, v17[2]
	mov	s21, v17[1]
	mov	s22, v18[3]
	mov	s23, v18[2]
	mov	s24, v18[1]
	fadd	s0, s0, s1
	fadd	s0, s0, s5
	fadd	s0, s0, s4
	fadd	s0, s0, s3
	fadd	s0, s0, s2
	fadd	s0, s0, s16
	fadd	s0, s0, s7
	fadd	s0, s0, s6
	fadd	s0, s0, s17
	fadd	s0, s0, s21
	fadd	s0, s0, s20
	fadd	s0, s0, s19
	fadd	s0, s0, s18
	fadd	s0, s0, s24
	fadd	s0, s0, s23
	fadd	s0, s0, s22
	subs	x9, x9, #16
	b.ne	LBB0_57
; %bb.58:                               ;   in Loop: Header=BB0_49 Depth=1
	cmp	x26, x27
	b.eq	LBB0_48
; %bb.59:                               ;   in Loop: Header=BB0_49 Depth=1
	mov	x10, x27
	mov	x9, x27
	ldr	x8, [sp, #96]                   ; 8-byte Folded Reload
	cbz	x8, LBB0_63
LBB0_60:                                ;   in Loop: Header=BB0_49 Depth=1
	ldr	x8, [sp, #120]                  ; 8-byte Folded Reload
	add	x8, x8, x10
	add	x9, x22, x10, lsl #2
LBB0_61:                                ;   Parent Loop BB0_49 Depth=1
                                        ; =>  This Inner Loop Header: Depth=2
	ldr	q1, [x9], #16
	mov	s2, v1[3]
	mov	s3, v1[2]
	mov	s4, v1[1]
	fadd	s0, s0, s1
	fadd	s0, s0, s4
	fadd	s0, s0, s3
	fadd	s0, s0, s2
	adds	x8, x8, #4
	b.ne	LBB0_61
; %bb.62:                               ;   in Loop: Header=BB0_49 Depth=1
	mov	x9, x28
	cmp	x26, x28
	b.eq	LBB0_48
LBB0_63:                                ;   in Loop: Header=BB0_49 Depth=1
	sub	x8, x26, x9
	add	x9, x22, x9, lsl #2
LBB0_64:                                ;   Parent Loop BB0_49 Depth=1
                                        ; =>  This Inner Loop Header: Depth=2
	ldr	s1, [x9], #4
	fadd	s0, s0, s1
	subs	x8, x8, #1
	b.ne	LBB0_64
	b	LBB0_48
LBB0_65:
	mov	x0, x21
	bl	_free
	mov	x0, x22
	bl	_free
	lsr	x8, x20, #32
	cbnz	x8, LBB0_118
; %bb.66:
	mul	x26, x20, x20
	lsr	x8, x26, #62
	cbnz	x8, LBB0_118
; %bb.67:
	lsl	x25, x26, #2
	mov	x0, x25
	bl	_malloc
	str	x0, [sp, #120]                  ; 8-byte Folded Spill
	cbz	x0, LBB0_121
; %bb.68:
	mov	x0, x25
	bl	_malloc
	cbz	x0, LBB0_122
; %bb.69:
	mov	x21, x0
	mov	x0, x25
	bl	_malloc
	cbz	x0, LBB0_123
; %bb.70:
	mov	x28, x0
	mov	x0, x25
	bl	_malloc
	str	x0, [sp, #88]                   ; 8-byte Folded Spill
	cbz	x0, LBB0_124
; %bb.71:
	lsl	x19, x20, #2
	cbz	x20, LBB0_90
; %bb.72:
	mov	x8, #0                          ; =0x0
	mov	w9, #-6                         ; =0xfffffffa
	mov	w10, #-8                        ; =0xfffffff8
	mov	x11, #20165                     ; =0x4ec5
	movk	x11, #50412, lsl #16
	movk	x11, #60494, lsl #32
	movk	x11, #20164, lsl #48
	mov	w12, #13                        ; =0xd
	mov	x13, #-1085102592571150096      ; =0xf0f0f0f0f0f0f0f0
	movk	x13, #61681
	fmov	s0, #17.00000000
	fmov	s1, #13.00000000
	ldr	x14, [sp, #120]                 ; 8-byte Folded Reload
	mov	x15, x21
	mov	x16, x26
LBB0_73:                                ; =>This Inner Loop Header: Depth=1
	umulh	x17, x8, x11
	lsr	x17, x17, #2
	msub	w17, w17, w12, w9
	umulh	x0, x8, x13
	lsr	x0, x0, #4
	add	w0, w0, w0, lsl #4
	sub	w0, w10, w0
	scvtf	s2, w0
	fdiv	s2, s2, s0
	scvtf	s3, w17
	fdiv	s3, s3, s1
	str	s2, [x14], #4
	str	s3, [x15], #4
	add	x8, x8, #1
	add	w9, w9, #1
	add	w10, w10, #1
	subs	x16, x16, #1
	b.ne	LBB0_73
; %bb.74:
	mul	x1, x19, x20
	mov	x0, x28
	str	x1, [sp, #72]                   ; 8-byte Folded Spill
	bl	_bzero
	mov	x8, #0                          ; =0x0
	and	x9, x20, #0xfffffff0
	and	x10, x20, #0xc
	and	x11, x20, #0xfffffffc
	add	x12, x21, #32
	add	x13, x28, #32
	neg	x14, x11
	mov	x15, x28
	b	LBB0_76
LBB0_75:                                ;   in Loop: Header=BB0_76 Depth=1
	add	x8, x8, #1
	add	x13, x13, x19
	add	x15, x15, x19
	cmp	x8, x20
	b.eq	LBB0_91
LBB0_76:                                ; =>This Loop Header: Depth=1
                                        ;     Child Loop BB0_78 Depth 2
                                        ;       Child Loop BB0_83 Depth 3
                                        ;       Child Loop BB0_87 Depth 3
                                        ;       Child Loop BB0_89 Depth 3
	mov	x16, #0                         ; =0x0
	mul	x17, x8, x20
	ldr	x0, [sp, #120]                  ; 8-byte Folded Reload
	add	x17, x0, x17, lsl #2
	mov	x0, x21
	mov	x1, x12
	b	LBB0_78
LBB0_77:                                ;   in Loop: Header=BB0_78 Depth=2
	add	x16, x16, #1
	add	x1, x1, x19
	add	x0, x0, x19
	cmp	x16, x20
	b.eq	LBB0_75
LBB0_78:                                ;   Parent Loop BB0_76 Depth=1
                                        ; =>  This Loop Header: Depth=2
                                        ;       Child Loop BB0_83 Depth 3
                                        ;       Child Loop BB0_87 Depth 3
                                        ;       Child Loop BB0_89 Depth 3
	ldr	s0, [x17, x16, lsl #2]
	cmp	x20, #3
	b.hi	LBB0_80
; %bb.79:                               ;   in Loop: Header=BB0_78 Depth=2
	mov	x2, #0                          ; =0x0
	b	LBB0_89
LBB0_80:                                ;   in Loop: Header=BB0_78 Depth=2
	cmp	x20, #16
	b.hs	LBB0_82
; %bb.81:                               ;   in Loop: Header=BB0_78 Depth=2
	mov	x3, #0                          ; =0x0
	b	LBB0_86
LBB0_82:                                ;   in Loop: Header=BB0_78 Depth=2
	mov	x2, x13
	mov	x3, x1
	mov	x4, x9
LBB0_83:                                ;   Parent Loop BB0_76 Depth=1
                                        ;     Parent Loop BB0_78 Depth=2
                                        ; =>    This Inner Loop Header: Depth=3
	ldp	q1, q2, [x3, #-32]
	ldp	q3, q4, [x3], #64
	ldp	q5, q6, [x2, #-32]
	ldp	q7, q16, [x2]
	fmla.4s	v5, v1, v0[0]
	fmla.4s	v6, v2, v0[0]
	fmla.4s	v7, v3, v0[0]
	fmla.4s	v16, v4, v0[0]
	stp	q5, q6, [x2, #-32]
	stp	q7, q16, [x2], #64
	subs	x4, x4, #16
	b.ne	LBB0_83
; %bb.84:                               ;   in Loop: Header=BB0_78 Depth=2
	cmp	x20, x9
	b.eq	LBB0_77
; %bb.85:                               ;   in Loop: Header=BB0_78 Depth=2
	mov	x2, x9
	mov	x3, x9
	cbz	x10, LBB0_89
LBB0_86:                                ;   in Loop: Header=BB0_78 Depth=2
	add	x2, x14, x3
	lsl	x4, x3, #2
	add	x3, x15, x4
	add	x4, x0, x4
LBB0_87:                                ;   Parent Loop BB0_76 Depth=1
                                        ;     Parent Loop BB0_78 Depth=2
                                        ; =>    This Inner Loop Header: Depth=3
	ldr	q1, [x4], #16
	ldr	q2, [x3]
	fmla.4s	v2, v1, v0[0]
	str	q2, [x3], #16
	adds	x2, x2, #4
	b.ne	LBB0_87
; %bb.88:                               ;   in Loop: Header=BB0_78 Depth=2
	mov	x2, x11
	cmp	x20, x11
	b.eq	LBB0_77
LBB0_89:                                ;   Parent Loop BB0_76 Depth=1
                                        ;     Parent Loop BB0_78 Depth=2
                                        ; =>    This Inner Loop Header: Depth=3
	ldr	s1, [x0, x2, lsl #2]
	ldr	s2, [x15, x2, lsl #2]
	fmadd	s1, s0, s1, s2
	str	s1, [x15, x2, lsl #2]
	add	x2, x2, #1
	cmp	x20, x2
	b.ne	LBB0_89
	b	LBB0_77
LBB0_90:
	str	xzr, [sp, #72]                  ; 8-byte Folded Spill
LBB0_91:
	lsr	x8, x20, #1
	madd	x8, x8, x20, x8
	str	x8, [sp, #64]                   ; 8-byte Folded Spill
	ldr	s8, [x28, x8, lsl #2]
	ldr	x0, [sp, #120]                  ; 8-byte Folded Reload
	mov	x1, x21
	ldp	x4, x2, [sp, #80]               ; 16-byte Folded Reload
	mov	x3, x20
	bl	_matmul_blocked
	cbz	x20, LBB0_95
; %bb.92:
	mov.16b	v1, v0
	movi.2d	v2, #0000000000000000
	mov	x8, x28
	ldr	x9, [sp, #88]                   ; 8-byte Folded Reload
LBB0_93:                                ; =>This Inner Loop Header: Depth=1
	ldr	s0, [x8], #4
	ldr	s3, [x9], #4
	fsub	s4, s0, s3
	fsub	s5, s3, s0
	fcmp	s0, s3
	fcsel	s0, s4, s5, gt
	fcvt	d0, s0
	fcmp	d2, d0
	fcsel	d2, d0, d2, mi
	subs	x26, x26, #1
	b.ne	LBB0_93
; %bb.94:
	mov	x8, #43516                      ; =0xa9fc
	movk	x8, #54001, lsl #16
	movk	x8, #25165, lsl #32
	movk	x8, #16208, lsl #48
	fmov	d0, x8
	fcmp	d2, d0
	b.gt	LBB0_127
LBB0_95:
	ldr	x8, [sp, #112]                  ; 8-byte Folded Reload
	cbz	x8, LBB0_115
; %bb.96:
	mov	x22, #0                         ; =0x0
	and	x25, x20, #0xfffffff0
	and	x24, x20, #0xc
	and	x23, x20, #0xfffffffc
	add	x27, x21, #32
	add	x8, x28, #32
	stp	x8, x21, [sp, #48]              ; 16-byte Folded Spill
	neg	x26, x23
	b	LBB0_98
LBB0_97:                                ;   in Loop: Header=BB0_98 Depth=1
	ldr	x8, [sp, #64]                   ; 8-byte Folded Reload
	ldr	s0, [x28, x8, lsl #2]
	stur	s0, [x29, #-108]
	mov	w0, #8                          ; =0x8
	bl	_clock_gettime_nsec_np
	mov	x22, x28
	mov	x28, x0
	ldr	x0, [sp, #120]                  ; 8-byte Folded Reload
	mov	x1, x21
	ldp	x21, x2, [sp, #80]              ; 16-byte Folded Reload
	mov	x3, x20
	mov	x4, x21
	bl	_matmul_blocked
	stur	s0, [x29, #-112]
	mov	w0, #8                          ; =0x8
	bl	_clock_gettime_nsec_np
	ldr	x8, [sp, #96]                   ; 8-byte Folded Reload
	sub	x8, x28, x8
	sub	x9, x0, x28
	mov	x28, x22
	ldur	s0, [x29, #-108]
	ldur	s1, [x29, #-112]
	fadd	s0, s0, s1
	fcvt	d0, s0
	str	d0, [sp, #40]
	stp	x8, x9, [sp, #24]
	stp	x20, x21, [sp, #8]
	ldr	x21, [sp, #56]                  ; 8-byte Folded Reload
	ldr	x22, [sp, #104]                 ; 8-byte Folded Reload
	str	x22, [sp]
Lloh27:
	adrp	x0, l_.str.14@PAGE
Lloh28:
	add	x0, x0, l_.str.14@PAGEOFF
	bl	_printf
	add	x22, x22, #1
	ldr	x8, [sp, #112]                  ; 8-byte Folded Reload
	cmp	x22, x8
	b.eq	LBB0_115
LBB0_98:                                ; =>This Loop Header: Depth=1
                                        ;     Child Loop BB0_101 Depth 2
                                        ;       Child Loop BB0_103 Depth 3
                                        ;         Child Loop BB0_108 Depth 4
                                        ;         Child Loop BB0_112 Depth 4
                                        ;         Child Loop BB0_114 Depth 4
	str	x22, [sp, #104]                 ; 8-byte Folded Spill
	mov	w0, #8                          ; =0x8
	bl	_clock_gettime_nsec_np
	str	x0, [sp, #96]                   ; 8-byte Folded Spill
	mov	x0, x28
	ldr	x1, [sp, #72]                   ; 8-byte Folded Reload
	bl	_bzero
	cbz	x20, LBB0_97
; %bb.99:                               ;   in Loop: Header=BB0_98 Depth=1
	mov	x8, #0                          ; =0x0
	mov	x9, x28
	ldr	x10, [sp, #48]                  ; 8-byte Folded Reload
	b	LBB0_101
LBB0_100:                               ;   in Loop: Header=BB0_101 Depth=2
	add	x8, x8, #1
	add	x10, x10, x19
	add	x9, x9, x19
	cmp	x8, x20
	b.eq	LBB0_97
LBB0_101:                               ;   Parent Loop BB0_98 Depth=1
                                        ; =>  This Loop Header: Depth=2
                                        ;       Child Loop BB0_103 Depth 3
                                        ;         Child Loop BB0_108 Depth 4
                                        ;         Child Loop BB0_112 Depth 4
                                        ;         Child Loop BB0_114 Depth 4
	mov	x11, #0                         ; =0x0
	mul	x12, x8, x20
	ldr	x13, [sp, #120]                 ; 8-byte Folded Reload
	add	x12, x13, x12, lsl #2
	mov	x13, x21
	mov	x14, x27
	b	LBB0_103
LBB0_102:                               ;   in Loop: Header=BB0_103 Depth=3
	add	x11, x11, #1
	add	x14, x14, x19
	add	x13, x13, x19
	cmp	x11, x20
	b.eq	LBB0_100
LBB0_103:                               ;   Parent Loop BB0_98 Depth=1
                                        ;     Parent Loop BB0_101 Depth=2
                                        ; =>    This Loop Header: Depth=3
                                        ;         Child Loop BB0_108 Depth 4
                                        ;         Child Loop BB0_112 Depth 4
                                        ;         Child Loop BB0_114 Depth 4
	ldr	s0, [x12, x11, lsl #2]
	cmp	x20, #3
	b.hi	LBB0_105
; %bb.104:                              ;   in Loop: Header=BB0_103 Depth=3
	mov	x15, #0                         ; =0x0
	b	LBB0_114
LBB0_105:                               ;   in Loop: Header=BB0_103 Depth=3
	cmp	x20, #16
	b.hs	LBB0_107
; %bb.106:                              ;   in Loop: Header=BB0_103 Depth=3
	mov	x16, #0                         ; =0x0
	b	LBB0_111
LBB0_107:                               ;   in Loop: Header=BB0_103 Depth=3
	mov	x15, x10
	mov	x16, x14
	mov	x17, x25
LBB0_108:                               ;   Parent Loop BB0_98 Depth=1
                                        ;     Parent Loop BB0_101 Depth=2
                                        ;       Parent Loop BB0_103 Depth=3
                                        ; =>      This Inner Loop Header: Depth=4
	ldp	q1, q2, [x16, #-32]
	ldp	q3, q4, [x16], #64
	ldp	q5, q6, [x15, #-32]
	ldp	q7, q16, [x15]
	fmla.4s	v5, v1, v0[0]
	fmla.4s	v6, v2, v0[0]
	fmla.4s	v7, v3, v0[0]
	fmla.4s	v16, v4, v0[0]
	stp	q5, q6, [x15, #-32]
	stp	q7, q16, [x15], #64
	subs	x17, x17, #16
	b.ne	LBB0_108
; %bb.109:                              ;   in Loop: Header=BB0_103 Depth=3
	cmp	x20, x25
	b.eq	LBB0_102
; %bb.110:                              ;   in Loop: Header=BB0_103 Depth=3
	mov	x15, x25
	mov	x16, x25
	cbz	x24, LBB0_114
LBB0_111:                               ;   in Loop: Header=BB0_103 Depth=3
	add	x15, x26, x16
	lsl	x17, x16, #2
	add	x16, x9, x17
	add	x17, x13, x17
LBB0_112:                               ;   Parent Loop BB0_98 Depth=1
                                        ;     Parent Loop BB0_101 Depth=2
                                        ;       Parent Loop BB0_103 Depth=3
                                        ; =>      This Inner Loop Header: Depth=4
	ldr	q1, [x17], #16
	ldr	q2, [x16]
	fmla.4s	v2, v1, v0[0]
	str	q2, [x16], #16
	adds	x15, x15, #4
	b.ne	LBB0_112
; %bb.113:                              ;   in Loop: Header=BB0_103 Depth=3
	mov	x15, x23
	cmp	x20, x23
	b.eq	LBB0_102
LBB0_114:                               ;   Parent Loop BB0_98 Depth=1
                                        ;     Parent Loop BB0_101 Depth=2
                                        ;       Parent Loop BB0_103 Depth=3
                                        ; =>      This Inner Loop Header: Depth=4
	ldr	s1, [x13, x15, lsl #2]
	ldr	s2, [x9, x15, lsl #2]
	fmadd	s1, s0, s1, s2
	str	s1, [x9, x15, lsl #2]
	add	x15, x15, #1
	cmp	x20, x15
	b.ne	LBB0_114
	b	LBB0_102
LBB0_115:
	ldr	x0, [sp, #120]                  ; 8-byte Folded Reload
	bl	_free
	mov	x0, x21
	bl	_free
	mov	x0, x28
	bl	_free
	ldr	x0, [sp, #88]                   ; 8-byte Folded Reload
	bl	_free
LBB0_116:
	mov	w0, #0                          ; =0x0
LBB0_117:
	ldp	x29, x30, [sp, #272]            ; 16-byte Folded Reload
	ldp	x20, x19, [sp, #256]            ; 16-byte Folded Reload
	ldp	x22, x21, [sp, #240]            ; 16-byte Folded Reload
	ldp	x24, x23, [sp, #224]            ; 16-byte Folded Reload
	ldp	x26, x25, [sp, #208]            ; 16-byte Folded Reload
	ldp	x28, x27, [sp, #192]            ; 16-byte Folded Reload
	ldp	d9, d8, [sp, #176]              ; 16-byte Folded Reload
	add	sp, sp, #288
	ret
LBB0_118:
	bl	_main.cold.8
LBB0_119:
	mov	x0, x22
	bl	_main.cold.10
LBB0_120:
	mov	x0, x23
	bl	_main.cold.9
LBB0_121:
	mov	x0, x25
	bl	_main.cold.7
LBB0_122:
	mov	x0, x25
	bl	_main.cold.6
LBB0_123:
	mov	x0, x25
	bl	_main.cold.5
LBB0_124:
	mov	x0, x25
	bl	_main.cold.4
LBB0_125:
	bl	_main.cold.1
LBB0_126:
	bl	_main.cold.2
LBB0_127:
	mov.16b	v0, v8
	bl	_main.cold.3
	.loh AdrpAdd	Lloh0, Lloh1
	.loh AdrpAdd	Lloh5, Lloh6
	.loh AdrpLdrGotLdr	Lloh2, Lloh3, Lloh4
	.loh AdrpAdd	Lloh10, Lloh11
	.loh AdrpLdrGotLdr	Lloh7, Lloh8, Lloh9
	.loh AdrpAdd	Lloh12, Lloh13
	.loh AdrpAdd	Lloh14, Lloh15
	.loh AdrpAdd	Lloh16, Lloh17
	.loh AdrpAdd	Lloh18, Lloh19
	.loh AdrpAdd	Lloh23, Lloh24
	.loh AdrpLdrGotLdr	Lloh20, Lloh21, Lloh22
	.loh AdrpAdd	Lloh25, Lloh26
	.loh AdrpAdd	Lloh27, Lloh28
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function parse_size_arg
_parse_size_arg:                        ; @parse_size_arg
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #80
	stp	x22, x21, [sp, #32]             ; 16-byte Folded Spill
	stp	x20, x19, [sp, #48]             ; 16-byte Folded Spill
	stp	x29, x30, [sp, #64]             ; 16-byte Folded Spill
	add	x29, sp, #64
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
	.cfi_offset w19, -24
	.cfi_offset w20, -32
	.cfi_offset w21, -40
	.cfi_offset w22, -48
	str	xzr, [sp, #24]
	ldrb	w8, [x0]
	cmp	w8, #45
	ccmp	w8, #0, #4, ne
	b.ne	LBB1_2
; %bb.1:
Lloh29:
	adrp	x8, ___stderrp@GOTPAGE
Lloh30:
	ldr	x8, [x8, ___stderrp@GOTPAGEOFF]
Lloh31:
	ldr	x0, [x8]
	mov	w8, #1                          ; =0x1
	stp	x8, x2, [sp, #8]
	str	x1, [sp]
	b	LBB1_5
LBB1_2:
	mov	x21, x3
	mov	x20, x1
	mov	x22, x2
	mov	x19, x0
	bl	___error
	str	wzr, [x0]
	add	x1, sp, #24
	mov	x0, x19
	mov	w2, #10                         ; =0xa
	bl	_strtoull
	mov	x19, x0
	bl	___error
	mov	x8, x22
	ldr	w9, [x0]
	cbnz	w9, LBB1_4
; %bb.3:
	ldr	x9, [sp, #24]
	ldrb	w9, [x9]
	sub	x10, x19, #1
	cmp	w9, #0
	ccmp	x10, x8, #2, eq
	b.lo	LBB1_7
LBB1_4:
Lloh32:
	adrp	x9, ___stderrp@GOTPAGE
Lloh33:
	ldr	x9, [x9, ___stderrp@GOTPAGEOFF]
Lloh34:
	ldr	x0, [x9]
	str	x8, [sp, #16]
	mov	w8, #1                          ; =0x1
	stp	x20, x8, [sp]
LBB1_5:
Lloh35:
	adrp	x1, l_.str.7@PAGE
Lloh36:
	add	x1, x1, l_.str.7@PAGEOFF
	bl	_fprintf
	mov	w0, #0                          ; =0x0
LBB1_6:
	ldp	x29, x30, [sp, #64]             ; 16-byte Folded Reload
	ldp	x20, x19, [sp, #48]             ; 16-byte Folded Reload
	ldp	x22, x21, [sp, #32]             ; 16-byte Folded Reload
	add	sp, sp, #80
	ret
LBB1_7:
	str	x19, [x21]
	mov	w0, #1                          ; =0x1
	b	LBB1_6
	.loh AdrpLdrGotLdr	Lloh29, Lloh30, Lloh31
	.loh AdrpLdrGotLdr	Lloh32, Lloh33, Lloh34
	.loh AdrpAdd	Lloh35, Lloh36
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function matmul_blocked
_matmul_blocked:                        ; @matmul_blocked
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #384
	stp	x28, x27, [sp, #288]            ; 16-byte Folded Spill
	stp	x26, x25, [sp, #304]            ; 16-byte Folded Spill
	stp	x24, x23, [sp, #320]            ; 16-byte Folded Spill
	stp	x22, x21, [sp, #336]            ; 16-byte Folded Spill
	stp	x20, x19, [sp, #352]            ; 16-byte Folded Spill
	stp	x29, x30, [sp, #368]            ; 16-byte Folded Spill
	add	x29, sp, #368
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
	.cfi_offset w19, -24
	.cfi_offset w20, -32
	.cfi_offset w21, -40
	.cfi_offset w22, -48
	.cfi_offset w23, -56
	.cfi_offset w24, -64
	.cfi_offset w25, -72
	.cfi_offset w26, -80
	.cfi_offset w27, -88
	.cfi_offset w28, -96
	mov	x21, x4
	mov	x20, x3
	str	x1, [sp, #64]                   ; 8-byte Folded Spill
	stur	x0, [x29, #-144]                ; 8-byte Folded Spill
	mul	x8, x3, x3
	lsl	x1, x8, #2
	str	x2, [sp, #16]                   ; 8-byte Folded Spill
	mov	x0, x2
	bl	_bzero
	cbz	x20, LBB2_25
; %bb.1:
	mov	x10, #0                         ; =0x0
	mov	x15, #0                         ; =0x0
	mul	x8, x21, x20
	lsl	x12, x8, #2
	lsl	x8, x21, #2
	str	x8, [sp, #160]                  ; 8-byte Folded Spill
	lsl	x11, x20, #2
	ldr	x9, [sp, #64]                   ; 8-byte Folded Reload
	add	x8, x9, #4
	str	x8, [sp, #48]                   ; 8-byte Folded Spill
	ldr	x8, [sp, #16]                   ; 8-byte Folded Reload
	add	x13, x8, #4
	add	x9, x9, #32
	stp	x9, x13, [sp]                   ; 16-byte Folded Spill
	add	x9, x8, #32
	str	x9, [sp, #72]                   ; 8-byte Folded Spill
	str	x8, [sp, #128]                  ; 8-byte Folded Spill
	mov	x9, x21
	stur	x20, [x29, #-96]                ; 8-byte Folded Spill
	str	x21, [sp, #168]                 ; 8-byte Folded Spill
	str	x12, [sp, #56]                  ; 8-byte Folded Spill
	b	LBB2_3
LBB2_2:                                 ;   in Loop: Header=BB2_3 Depth=1
	ldp	x9, x10, [sp, #32]              ; 16-byte Folded Reload
	add	x9, x9, x21
	add	x10, x10, #1
	ldr	x8, [sp, #72]                   ; 8-byte Folded Reload
	add	x8, x8, x12
	str	x8, [sp, #72]                   ; 8-byte Folded Spill
	ldr	x8, [sp, #128]                  ; 8-byte Folded Reload
	add	x8, x8, x12
	str	x8, [sp, #128]                  ; 8-byte Folded Spill
	ldr	x8, [sp, #24]                   ; 8-byte Folded Reload
	mov	x15, x8
	cmp	x8, x20
	b.hs	LBB2_25
LBB2_3:                                 ; =>This Loop Header: Depth=1
                                        ;     Child Loop BB2_5 Depth 2
                                        ;       Child Loop BB2_7 Depth 3
                                        ;         Child Loop BB2_10 Depth 4
                                        ;           Child Loop BB2_13 Depth 5
                                        ;             Child Loop BB2_18 Depth 6
                                        ;             Child Loop BB2_22 Depth 6
                                        ;             Child Loop BB2_24 Depth 6
	mov	x14, #0                         ; =0x0
	mov	x16, #0                         ; =0x0
	stp	x9, x10, [sp, #32]              ; 16-byte Folded Spill
	mul	x8, x12, x10
	cmp	x20, x9
	csel	x3, x20, x9, lo
	add	x9, x15, x21
	cmp	x9, x20
	str	x9, [sp, #24]                   ; 8-byte Folded Spill
	csel	x9, x9, x20, lo
	str	x9, [sp, #152]                  ; 8-byte Folded Spill
	ldr	x9, [sp, #16]                   ; 8-byte Folded Reload
	add	x9, x9, x8
	str	x9, [sp, #120]                  ; 8-byte Folded Spill
	ldr	x9, [sp, #8]                    ; 8-byte Folded Reload
	add	x8, x9, x8
	str	x8, [sp, #112]                  ; 8-byte Folded Spill
	ldr	x8, [sp, #64]                   ; 8-byte Folded Reload
	stur	x8, [x29, #-136]                ; 8-byte Folded Spill
	ldr	x19, [sp]                       ; 8-byte Folded Reload
	mov	x10, x21
	str	x15, [sp, #176]                 ; 8-byte Folded Spill
	b	LBB2_5
LBB2_4:                                 ;   in Loop: Header=BB2_5 Depth=2
	ldp	x10, x19, [sp, #88]             ; 16-byte Folded Reload
	add	x10, x10, x21
	ldr	x14, [sp, #104]                 ; 8-byte Folded Reload
	add	x14, x14, #1
	ldr	x12, [sp, #56]                  ; 8-byte Folded Reload
	add	x19, x19, x12
	ldur	x8, [x29, #-136]                ; 8-byte Folded Reload
	add	x8, x8, x12
	stur	x8, [x29, #-136]                ; 8-byte Folded Spill
	ldr	x8, [sp, #80]                   ; 8-byte Folded Reload
	mov	x16, x8
	cmp	x8, x20
	b.hs	LBB2_2
LBB2_5:                                 ;   Parent Loop BB2_3 Depth=1
                                        ; =>  This Loop Header: Depth=2
                                        ;       Child Loop BB2_7 Depth 3
                                        ;         Child Loop BB2_10 Depth 4
                                        ;           Child Loop BB2_13 Depth 5
                                        ;             Child Loop BB2_18 Depth 6
                                        ;             Child Loop BB2_22 Depth 6
                                        ;             Child Loop BB2_24 Depth 6
	stp	xzr, xzr, [x29, #-160]          ; 16-byte Folded Spill
	mov	x8, #0                          ; =0x0
	mul	x9, x12, x14
	cmp	x20, x10
	str	x10, [sp, #88]                  ; 8-byte Folded Spill
	csel	x13, x20, x10, lo
	str	x14, [sp, #104]                 ; 8-byte Folded Spill
	mul	x10, x21, x14
	mvn	x10, x10
	add	x10, x13, x10
	add	x12, x16, x21
	cmp	x12, x20
	str	x12, [sp, #80]                  ; 8-byte Folded Spill
	csel	x14, x12, x20, lo
	ldr	x12, [sp, #64]                  ; 8-byte Folded Reload
	add	x12, x12, x9
	str	x12, [sp, #144]                 ; 8-byte Folded Spill
	ldr	x12, [sp, #48]                  ; 8-byte Folded Reload
	add	x9, x12, x9
	madd	x9, x11, x10, x9
	str	x9, [sp, #136]                  ; 8-byte Folded Spill
	ldr	x9, [sp, #72]                   ; 8-byte Folded Reload
	stur	x9, [x29, #-168]                ; 8-byte Folded Spill
	str	x19, [sp, #96]                  ; 8-byte Folded Spill
	mov	x10, x21
	b	LBB2_7
LBB2_6:                                 ;   in Loop: Header=BB2_7 Depth=3
	ldr	x21, [sp, #168]                 ; 8-byte Folded Reload
	ldr	x10, [sp, #184]                 ; 8-byte Folded Reload
	add	x10, x10, x21
	ldp	x9, x8, [x29, #-168]            ; 16-byte Folded Reload
	add	x8, x8, #1
	stur	x8, [x29, #-160]                ; 8-byte Folded Spill
	ldur	x8, [x29, #-152]                ; 8-byte Folded Reload
	sub	x8, x8, x21
	stur	x8, [x29, #-152]                ; 8-byte Folded Spill
	ldr	x8, [sp, #160]                  ; 8-byte Folded Reload
	add	x19, x19, x8
	add	x9, x9, x8
	stur	x9, [x29, #-168]                ; 8-byte Folded Spill
	ldur	x9, [x29, #-176]                ; 8-byte Folded Reload
	mov	x8, x9
	ldur	x20, [x29, #-96]                ; 8-byte Folded Reload
	cmp	x9, x20
	ldr	x15, [sp, #176]                 ; 8-byte Folded Reload
	b.hs	LBB2_4
LBB2_7:                                 ;   Parent Loop BB2_3 Depth=1
                                        ;     Parent Loop BB2_5 Depth=2
                                        ; =>    This Loop Header: Depth=3
                                        ;         Child Loop BB2_10 Depth 4
                                        ;           Child Loop BB2_13 Depth 5
                                        ;             Child Loop BB2_18 Depth 6
                                        ;             Child Loop BB2_22 Depth 6
                                        ;             Child Loop BB2_24 Depth 6
	cmp	x20, x10
	str	x10, [sp, #184]                 ; 8-byte Folded Spill
	csel	x9, x20, x10, lo
	add	x10, x8, x21
	stur	x10, [x29, #-176]               ; 8-byte Folded Spill
	ldr	x10, [sp, #152]                 ; 8-byte Folded Reload
	cmp	x15, x10
	b.hs	LBB2_6
; %bb.8:                                ;   in Loop: Header=BB2_7 Depth=3
	mov	x27, #0                         ; =0x0
	ldp	x17, x10, [x29, #-160]          ; 16-byte Folded Reload
	add	x10, x9, x10
	and	x12, x10, #0xfffffffffffffffc
	neg	x22, x12
	and	x1, x10, #0xfffffffffffffff0
	ldp	x15, x10, [sp, #160]            ; 16-byte Folded Reload
	mul	x10, x10, x17
	sub	x12, x9, x10
	mul	x15, x15, x17
	mvn	x10, x10
	add	x10, x9, x10
	lsl	x10, x10, #2
	ldr	x17, [sp, #144]                 ; 8-byte Folded Reload
	add	x17, x17, x15
	stur	x17, [x29, #-104]               ; 8-byte Folded Spill
	ldr	x17, [sp, #136]                 ; 8-byte Folded Reload
	add	x17, x17, x15
	add	x17, x17, x10
	stur	x17, [x29, #-112]               ; 8-byte Folded Spill
	ldur	x17, [x29, #-96]                ; 8-byte Folded Reload
	ldp	x0, x5, [x29, #-176]            ; 16-byte Folded Reload
	cmp	x0, x17
	csel	x6, x0, x17, lo
	ldr	x17, [sp, #120]                 ; 8-byte Folded Reload
	add	x17, x17, x15
	stur	x17, [x29, #-120]               ; 8-byte Folded Spill
	ldr	x17, [sp, #112]                 ; 8-byte Folded Reload
	add	x15, x17, x15
	add	x10, x15, x10
	stur	x10, [x29, #-128]               ; 8-byte Folded Spill
	and	x4, x12, #0xfffffffffffffff0
	add	x17, x8, x4
	and	x10, x12, #0xc
	and	x26, x12, #0xfffffffffffffffc
	add	x0, x8, x26
	ldr	x23, [sp, #128]                 ; 8-byte Folded Reload
	ldr	x30, [sp, #176]                 ; 8-byte Folded Reload
	b	LBB2_10
LBB2_9:                                 ;   in Loop: Header=BB2_10 Depth=4
	add	x30, x30, #1
	add	x27, x27, #1
	add	x5, x5, x11
	add	x23, x23, x11
	cmp	x30, x3
	b.eq	LBB2_6
LBB2_10:                                ;   Parent Loop BB2_3 Depth=1
                                        ;     Parent Loop BB2_5 Depth=2
                                        ;       Parent Loop BB2_7 Depth=3
                                        ; =>      This Loop Header: Depth=4
                                        ;           Child Loop BB2_13 Depth 5
                                        ;             Child Loop BB2_18 Depth 6
                                        ;             Child Loop BB2_22 Depth 6
                                        ;             Child Loop BB2_24 Depth 6
	cmp	x16, x14
	b.hs	LBB2_9
; %bb.11:                               ;   in Loop: Header=BB2_10 Depth=4
	mul	x15, x11, x27
	ldp	x21, x2, [x29, #-136]           ; 16-byte Folded Reload
	add	x2, x2, x15
	ldur	x7, [x29, #-96]                 ; 8-byte Folded Reload
	mul	x7, x30, x7
	ldur	x20, [x29, #-144]               ; 8-byte Folded Reload
	add	x28, x20, x7, lsl #2
	ldur	x7, [x29, #-120]                ; 8-byte Folded Reload
	add	x15, x7, x15
	ldur	x7, [x29, #-112]                ; 8-byte Folded Reload
	cmp	x15, x7
	ldur	x15, [x29, #-104]               ; 8-byte Folded Reload
	ccmp	x15, x2, #2, lo
	ccmp	x11, #0, #8, hs
	cset	w24, lt
	mov	x20, x19
	mov	x7, x16
	b	LBB2_13
LBB2_12:                                ;   in Loop: Header=BB2_13 Depth=5
	add	x7, x7, #1
	add	x20, x20, x11
	add	x21, x21, x11
	cmp	x7, x13
	b.eq	LBB2_9
LBB2_13:                                ;   Parent Loop BB2_3 Depth=1
                                        ;     Parent Loop BB2_5 Depth=2
                                        ;       Parent Loop BB2_7 Depth=3
                                        ;         Parent Loop BB2_10 Depth=4
                                        ; =>        This Loop Header: Depth=5
                                        ;             Child Loop BB2_18 Depth 6
                                        ;             Child Loop BB2_22 Depth 6
                                        ;             Child Loop BB2_24 Depth 6
	cmp	x8, x6
	b.hs	LBB2_12
; %bb.14:                               ;   in Loop: Header=BB2_13 Depth=5
	ldr	s0, [x28, x7, lsl #2]
	cmp	x12, #4
	cset	w15, lo
	orr	w2, w15, w24
	mov	x15, x8
	tbnz	w2, #0, LBB2_24
; %bb.15:                               ;   in Loop: Header=BB2_13 Depth=5
	cmp	x12, #16
	b.hs	LBB2_17
; %bb.16:                               ;   in Loop: Header=BB2_13 Depth=5
	mov	x2, #0                          ; =0x0
	b	LBB2_21
LBB2_17:                                ;   in Loop: Header=BB2_13 Depth=5
	mov	x15, x5
	mov	x25, x20
	mov	x2, x1
LBB2_18:                                ;   Parent Loop BB2_3 Depth=1
                                        ;     Parent Loop BB2_5 Depth=2
                                        ;       Parent Loop BB2_7 Depth=3
                                        ;         Parent Loop BB2_10 Depth=4
                                        ;           Parent Loop BB2_13 Depth=5
                                        ; =>          This Inner Loop Header: Depth=6
	ldp	q1, q2, [x25, #-32]
	ldp	q3, q4, [x25], #64
	ldp	q5, q6, [x15, #-32]
	ldp	q7, q16, [x15]
	fmla.4s	v5, v1, v0[0]
	fmla.4s	v6, v2, v0[0]
	fmla.4s	v7, v3, v0[0]
	fmla.4s	v16, v4, v0[0]
	stp	q5, q6, [x15, #-32]
	stp	q7, q16, [x15], #64
	subs	x2, x2, #16
	b.ne	LBB2_18
; %bb.19:                               ;   in Loop: Header=BB2_13 Depth=5
	cmp	x12, x4
	b.eq	LBB2_12
; %bb.20:                               ;   in Loop: Header=BB2_13 Depth=5
	mov	x2, x4
	mov	x15, x17
	cbz	x10, LBB2_24
LBB2_21:                                ;   in Loop: Header=BB2_13 Depth=5
	add	x15, x22, x2
	add	x2, x8, x2
	lsl	x25, x2, #2
	add	x2, x23, x25
	add	x25, x21, x25
LBB2_22:                                ;   Parent Loop BB2_3 Depth=1
                                        ;     Parent Loop BB2_5 Depth=2
                                        ;       Parent Loop BB2_7 Depth=3
                                        ;         Parent Loop BB2_10 Depth=4
                                        ;           Parent Loop BB2_13 Depth=5
                                        ; =>          This Inner Loop Header: Depth=6
	ldr	q1, [x25], #16
	ldr	q2, [x2]
	fmla.4s	v2, v1, v0[0]
	str	q2, [x2], #16
	adds	x15, x15, #4
	b.ne	LBB2_22
; %bb.23:                               ;   in Loop: Header=BB2_13 Depth=5
	mov	x15, x0
	cmp	x12, x26
	b.eq	LBB2_12
LBB2_24:                                ;   Parent Loop BB2_3 Depth=1
                                        ;     Parent Loop BB2_5 Depth=2
                                        ;       Parent Loop BB2_7 Depth=3
                                        ;         Parent Loop BB2_10 Depth=4
                                        ;           Parent Loop BB2_13 Depth=5
                                        ; =>          This Inner Loop Header: Depth=6
	ldr	s1, [x21, x15, lsl #2]
	ldr	s2, [x23, x15, lsl #2]
	fmadd	s1, s0, s1, s2
	str	s1, [x23, x15, lsl #2]
	add	x15, x15, #1
	cmp	x9, x15
	b.ne	LBB2_24
	b	LBB2_12
LBB2_25:
	lsr	x8, x20, #1
	madd	x8, x8, x20, x8
	ldr	x9, [sp, #16]                   ; 8-byte Folded Reload
	ldr	s0, [x9, x8, lsl #2]
	ldp	x29, x30, [sp, #368]            ; 16-byte Folded Reload
	ldp	x20, x19, [sp, #352]            ; 16-byte Folded Reload
	ldp	x22, x21, [sp, #336]            ; 16-byte Folded Reload
	ldp	x24, x23, [sp, #320]            ; 16-byte Folded Reload
	ldp	x26, x25, [sp, #304]            ; 16-byte Folded Reload
	ldp	x28, x27, [sp, #288]            ; 16-byte Folded Reload
	add	sp, sp, #384
	ret
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.1
_main.cold.1:                           ; @main.cold.1
	.cfi_startproc
; %bb.0:
	stp	x29, x30, [sp, #-16]!           ; 16-byte Folded Spill
	mov	x29, sp
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
Lloh37:
	adrp	x8, ___stderrp@GOTPAGE
Lloh38:
	ldr	x8, [x8, ___stderrp@GOTPAGEOFF]
Lloh39:
	ldr	x3, [x8]
Lloh40:
	adrp	x0, l_.str.8@PAGE
Lloh41:
	add	x0, x0, l_.str.8@PAGEOFF
	mov	w1, #33                         ; =0x21
	mov	w2, #1                          ; =0x1
	bl	_fwrite
	bl	_OUTLINED_FUNCTION_1
	.loh AdrpAdd	Lloh40, Lloh41
	.loh AdrpLdrGotLdr	Lloh37, Lloh38, Lloh39
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.2
_main.cold.2:                           ; @main.cold.2
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #32
	stp	x29, x30, [sp, #16]             ; 16-byte Folded Spill
	add	x29, sp, #16
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
Lloh42:
	adrp	x8, ___stderrp@GOTPAGE
Lloh43:
	ldr	x8, [x8, ___stderrp@GOTPAGEOFF]
Lloh44:
	ldr	x0, [x8]
	fcvt	d0, s0
	fcvt	d1, s1
	stp	d0, d1, [sp]
Lloh45:
	adrp	x1, l_.str.9@PAGE
Lloh46:
	add	x1, x1, l_.str.9@PAGEOFF
	bl	_fprintf
	mov	w0, #1                          ; =0x1
	bl	_exit
	.loh AdrpAdd	Lloh45, Lloh46
	.loh AdrpLdrGotLdr	Lloh42, Lloh43, Lloh44
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.3
_main.cold.3:                           ; @main.cold.3
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #48
	stp	x29, x30, [sp, #32]             ; 16-byte Folded Spill
	add	x29, sp, #32
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
Lloh47:
	adrp	x8, ___stderrp@GOTPAGE
Lloh48:
	ldr	x8, [x8, ___stderrp@GOTPAGEOFF]
Lloh49:
	ldr	x0, [x8]
	fcvt	d0, s0
	fcvt	d1, s1
	stp	d1, d2, [sp, #8]
	str	d0, [sp]
Lloh50:
	adrp	x1, l_.str.13@PAGE
Lloh51:
	add	x1, x1, l_.str.13@PAGEOFF
	bl	_fprintf
	mov	w0, #1                          ; =0x1
	bl	_exit
	.loh AdrpAdd	Lloh50, Lloh51
	.loh AdrpLdrGotLdr	Lloh47, Lloh48, Lloh49
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.4
_main.cold.4:                           ; @main.cold.4
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #32
	stp	x29, x30, [sp, #16]             ; 16-byte Folded Spill
	add	x29, sp, #16
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
	bl	_OUTLINED_FUNCTION_0
	bl	_OUTLINED_FUNCTION_1
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.5
_main.cold.5:                           ; @main.cold.5
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #32
	stp	x29, x30, [sp, #16]             ; 16-byte Folded Spill
	add	x29, sp, #16
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
	bl	_OUTLINED_FUNCTION_0
	bl	_OUTLINED_FUNCTION_1
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.6
_main.cold.6:                           ; @main.cold.6
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #32
	stp	x29, x30, [sp, #16]             ; 16-byte Folded Spill
	add	x29, sp, #16
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
	bl	_OUTLINED_FUNCTION_0
	bl	_OUTLINED_FUNCTION_1
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.7
_main.cold.7:                           ; @main.cold.7
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #32
	stp	x29, x30, [sp, #16]             ; 16-byte Folded Spill
	add	x29, sp, #16
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
	bl	_OUTLINED_FUNCTION_0
	bl	_OUTLINED_FUNCTION_1
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.8
_main.cold.8:                           ; @main.cold.8
	.cfi_startproc
; %bb.0:
	stp	x29, x30, [sp, #-16]!           ; 16-byte Folded Spill
	mov	x29, sp
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
Lloh52:
	adrp	x8, ___stderrp@GOTPAGE
Lloh53:
	ldr	x8, [x8, ___stderrp@GOTPAGEOFF]
Lloh54:
	ldr	x3, [x8]
Lloh55:
	adrp	x0, l_.str.12@PAGE
Lloh56:
	add	x0, x0, l_.str.12@PAGEOFF
	mov	w1, #32                         ; =0x20
	mov	w2, #1                          ; =0x1
	bl	_fwrite
	bl	_OUTLINED_FUNCTION_1
	.loh AdrpAdd	Lloh55, Lloh56
	.loh AdrpLdrGotLdr	Lloh52, Lloh53, Lloh54
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.9
_main.cold.9:                           ; @main.cold.9
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #32
	stp	x29, x30, [sp, #16]             ; 16-byte Folded Spill
	add	x29, sp, #16
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
	bl	_OUTLINED_FUNCTION_0
	bl	_OUTLINED_FUNCTION_1
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function main.cold.10
_main.cold.10:                          ; @main.cold.10
	.cfi_startproc
; %bb.0:
	sub	sp, sp, #32
	stp	x29, x30, [sp, #16]             ; 16-byte Folded Spill
	add	x29, sp, #16
	.cfi_def_cfa w29, 16
	.cfi_offset w30, -8
	.cfi_offset w29, -16
	bl	_OUTLINED_FUNCTION_0
	bl	_OUTLINED_FUNCTION_1
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function OUTLINED_FUNCTION_0
_OUTLINED_FUNCTION_0:                   ; @OUTLINED_FUNCTION_0 Thunk
	.cfi_startproc
; %bb.0:
	adrp	x8, ___stderrp@GOTPAGE
	ldr	x8, [x8, ___stderrp@GOTPAGEOFF]
	ldr	x8, [x8]
	str	x0, [sp]
	adrp	x1, l_.str.11@PAGE
	add	x1, x1, l_.str.11@PAGEOFF
	mov	x0, x8
	b	_fprintf
	.cfi_endproc
                                        ; -- End function
	.p2align	2                               ; -- Begin function OUTLINED_FUNCTION_1
_OUTLINED_FUNCTION_1:                   ; @OUTLINED_FUNCTION_1 Thunk
	.cfi_startproc
; %bb.0:
	mov	w0, #2                          ; =0x2
	b	_exit
	.cfi_endproc
                                        ; -- End function
	.section	__TEXT,__cstring,cstring_literals
l_.str:                                 ; @.str
	.asciz	"--help"

l_.str.1:                               ; @.str.1
	.asciz	"aos_soa_n"

l_.str.2:                               ; @.str.2
	.asciz	"matmul_n"

l_.str.3:                               ; @.str.3
	.asciz	"block"

l_.str.4:                               ; @.str.4
	.asciz	"reps"

l_.str.5:                               ; @.str.5
	.asciz	"block must be <= matmul_n\n"

l_.str.6:                               ; @.str.6
	.asciz	"usage: %s [aos_soa_n<=%u] [matmul_n<=%u] [block<=matmul_n] [reps<=%u]\n"

l_.str.7:                               ; @.str.7
	.asciz	"%s must be an integer in [%zu, %zu]\n"

l_.str.8:                               ; @.str.8
	.asciz	"aos/soa allocation size overflow\n"

l_.str.9:                               ; @.str.9
	.asciz	"aos/soa mismatch: %.8g %.8g\n"

l_.str.10:                              ; @.str.10
	.asciz	"{\"case\":\"aos_soa\",\"rep\":%zu,\"n\":%zu,\"aos_ns\":%llu,\"soa_ns\":%llu,\"checksum\":%.8g}\n"

l_.str.11:                              ; @.str.11
	.asciz	"allocation failed: %zu bytes\n"

l_.str.12:                              ; @.str.12
	.asciz	"matmul allocation size overflow\n"

l_.str.13:                              ; @.str.13
	.asciz	"matmul mismatch: center %.8g %.8g max_diff %.8g\n"

l_.str.14:                              ; @.str.14
	.asciz	"{\"case\":\"matmul\",\"rep\":%zu,\"n\":%zu,\"block\":%zu,\"plain_ns\":%llu,\"blocked_ns\":%llu,\"checksum\":%.8g}\n"

.subsections_via_symbols