AND	$7, X10, X9
	AND	$7, X11, X19
	BNE	X9, X19, loop4_check
	BEQZ	X9, loop32_check

	// Check one byte at a time until we reach 8 byte alignment.
	SUB	X9, X0, X9
	ADD	$8, X9, X9
	SUB	X9, X12, X12
align:
	SUB	$1, X9
	MOVBU	0(X10), X19
	MOVBU	0(X11), X20
	BNE	X19, X20, not_eq
	ADD	$1, X10
	ADD	$1, X11
	BNEZ	X9, align

loop32_check:
	MOV	$32, X9

	VGF2P8AFFINEINVQB $64, X0, X16, K3, X19            // 62e3fd03cfd840
	VGF2P8AFFINEINVQB $64, -17(BP), X16, K3, X19       // 62e3fd03cf9defffffff40
	VGF2P8AFFINEINVQB $64, -15(R14)(R15*8), X16, K3, X19 // 6283fd03cf9cfef1ffffff40
	VGF2P8AFFINEINVQB $64, X8, X7, K3, X19             // 62c3c50bcfd840
	VGF2P8AFFINEINVQB $64, X1, X7, K3, X19             // 62e3c50bcfd940

	VPCLMULQDQ $127, X19, X21, X15                     // 6233550044fb7f or 6233d50044fb7f
	VPCLMULQDQ $127, -17(BP)(SI*8), X21, X15           // 6273550044bcf5efffffff7f or 6273d50044bcf5efffffff7f
	VPCLMULQDQ $127, (R15), X21, X15                   // 62535500443f7f or 6253d500443f7f
	VPCLMULQDQ $127, X22, X0, X15                      // 62337d0844fe7f or 6233fd0844fe7f

cmp8b:
	MOV	$0xff, X19
cmp8_loop:
	AND	X17, X19, X8
	AND	X18, X19, X9
	BNE	X8, X9, cmp
	SLLI	$8, X19
	JMP	cmp8_loop

cmp1a:
	SLTU	X9, X8, X5
	SLTU	X8, X9, X6
	JMP	cmp_ret
cmp1b:
	SLTU	X16, X15, X5
	SLTU	X15, X16, X6
	JMP	cmp_ret
cmp1c:
	SLTU	X18, X17, X5
	SLTU	X17, X18, X6
	JMP	cmp_ret
cmp1d:
	SLTU	X20, X19, X5
	SLTU	X19, X20, X6
	JMP	cmp_ret

	MUL	X17, X6, X17	// z_lo[3] = x[3] * y
	ADD	X17, X19, X21	// z_lo[3] = x[3] * y + z[3]
	SLTU	X17, X21, X22
	ADD	X18, X22, X18	// z_hi[3] = x[3] * y + z[3]
	ADD	X21, X29, X19	// z_lo[3] = x[3] * y + z[3] + c
	SLTU	X21, X19, X22
	ADD	X18, X22, X29	// next c

	MOV	X10, 0*8(X5)	// z[0]
	MOV	X13, 1*8(X5)	// z[1]
	MOV	X16, 2*8(X5)	// z[2]
	MOV	X19, 3*8(X5)	// z[3]

	ADD	$32, X5
	ADD	$32, X7

	SUB	$4, X30

	.cfi_offset 27, -80
	.cfi_offset 28, -72

	mov x19, x0
	mov x20, x1
	mov x0, x2

	blr x20
	blr x19

	ldp x27, x28, [sp, #16]
	.cfi_restore 27
	.cfi_restore 28
	ldp x25, x26, [sp, #32]
	.cfi_restore 25
	.cfi_restore 26
	ldp x23, x24, [sp, #48]
	.cfi_restore 23
	.cfi_restore 24
	ldp x21, x22, [sp, #64]
	.cfi_restore 21
	.cfi_restore 22
	ldp x19, x20, [sp, #80]
	.cfi_restore 19
	.cfi_restore 20

	VRCP28SD X25, X14, K4, X19                         // 62828d0ccbd9
	VRCP28SD X11, X14, K4, X19                         // 62c28d0ccbdb
	VRCP28SD X17, X14, K4, X19                         // 62a28d0ccbd9
	VRCP28SD X25, X0, K4, X19                          // 6282fd0ccbd9
	VRCP28SD X11, X0, K4, X19                          // 62c2fd0ccbdb
	VRCP28SD X17, X0, K4, X19                          // 62a2fd0ccbd9

f_loop64:
	MOV	0(X11), X14
	MOV	8(X11), X15
	MOV	16(X11), X16
	MOV	24(X11), X17
	MOV	32(X11), X18
	MOV	40(X11), X19
	MOV	48(X11), X20
	MOV	56(X11), X21
	MOV	X14, 0(X10)
	MOV	X15, 8(X10)
	MOV	X16, 16(X10)
	MOV	X17, 24(X10)
	MOV	X18, 32(X10)
	MOV	X19, 40(X10)
	MOV	X20, 48(X10)
	MOV	X21, 56(X10)
	ADD	$64, X10
	ADD	$64, X11
	SUB	$64, X12
	BGE	X12, X9, f_loop64
	BEQZ	X12, done

	var x10, x11, x12, x13, x14, x15, x16, x17, x18, x19 int
	var x20, x21, x22, x23, x24, x25, x26, x27, x28, x29 int
	var x30, x31, x32 int

	_ = x00
	_ = x01
	_ = x02
	_ = x03
	_ = x04
	_ = x05
	_ = x06
	_ = x07
	_ = x08
	_ = x09

	_ = x10
	_ = x11
	_ = x12
	_ = x13
	_ = x14
	_ = x15
	_ = x16
	_ = x17
	_ = x18
	_ = x19

	_ = x20
	_ = x21
	_ = x22
	_ = x23

//line x19.go:4
package main