rind 0.1.4

Pure-Rust cryptography for MoQ, forked from graviola
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93

// Copyright (c) 2020, CloudFlare Ltd.
// SPDX-License-Identifier: ISC
//
// Generated by admin/import-aws-lc from aws-lc 91c93a8eb860e51482a871a8772cb9b1b310baea:
// generated-src/ios-aarch64/crypto/cipher_extra/chacha20_poly1305_armv8.S, which aws-lc generates from crypto/cipher_extra/asm/chacha20_poly1305_armv8.pl.
// Do not edit by hand.
.cfi_startproc
	cbnz	x4, Lchacha_poly_poly_hash_intro
	ret

Lchacha_poly_poly_hash_intro:
	cmp	x4, #16
	b.lt	Lchacha_poly_poly_hash_ad_tail
	ldp	x11, x12, [x3], 16
	adds	x8, x8, x11
	adcs	x9, x9, x12
	adc	x10, x10, x15
	mul	x11, x8, x16     // [t2:t1:t0] = [acc2:acc1:acc0] * r0
	umulh	x12, x8, x16
	mul	x13, x9, x16
	umulh	x14, x9, x16
	adds	x12, x12, x13
	mul	x13, x10, x16
	adc	x13, x13, x14
	mul	x14, x8, x17       // [t3:t2:t1:t0] = [acc2:acc1:acc0] * [r1:r0]
	umulh	x8, x8, x17
	adds	x12, x12, x14
	mul	x14, x9, x17
	umulh	x9, x9, x17
	adcs	x14, x14, x8
	mul	x10, x10, x17
	adc	x10, x10, x9
	adds	x13, x13, x14
	adc	x14, x10, xzr
	and	x10, x13, #3         // At this point acc2 is 2 bits at most (value of 3)
	and	x8, x13, #-4
	extr	x13, x14, x13, #2
	adds	x8, x8, x11
	lsr	x11, x14, #2
	adc	x9, x14, x11        // No carry out since t0 is 61 bits and t3 is 63 bits
	adds	x8, x8, x13
	adcs	x9, x9, x12
	adc	x10, x10, xzr      // At this point acc2 has the value of 4 at most
	sub	x4, x4, #16
	b	{poly_hash_ad_internal}

Lchacha_poly_poly_hash_ad_tail:
	cbz	x4, Lchacha_poly_poly_hash_ad_ret

	eor	v20.16b, v20.16b, v20.16b // Use T0 to load the AAD
	sub	x4, x4, #1

Lchacha_poly_poly_hash_tail_16_compose:
	ext	v20.16b, v20.16b, v20.16b, #15
	ldrb	w11, [x3, x4]
	mov	v20.b[0], w11
	subs	x4, x4, #1
	b.ge	Lchacha_poly_poly_hash_tail_16_compose
	mov	x11, v20.d[0]
	mov	x12, v20.d[1]
	adds	x8, x8, x11
	adcs	x9, x9, x12
	adc	x10, x10, x15
	mul	x11, x8, x16     // [t2:t1:t0] = [acc2:acc1:acc0] * r0
	umulh	x12, x8, x16
	mul	x13, x9, x16
	umulh	x14, x9, x16
	adds	x12, x12, x13
	mul	x13, x10, x16
	adc	x13, x13, x14
	mul	x14, x8, x17       // [t3:t2:t1:t0] = [acc2:acc1:acc0] * [r1:r0]
	umulh	x8, x8, x17
	adds	x12, x12, x14
	mul	x14, x9, x17
	umulh	x9, x9, x17
	adcs	x14, x14, x8
	mul	x10, x10, x17
	adc	x10, x10, x9
	adds	x13, x13, x14
	adc	x14, x10, xzr
	and	x10, x13, #3         // At this point acc2 is 2 bits at most (value of 3)
	and	x8, x13, #-4
	extr	x13, x14, x13, #2
	adds	x8, x8, x11
	lsr	x11, x14, #2
	adc	x9, x14, x11        // No carry out since t0 is 61 bits and t3 is 63 bits
	adds	x8, x8, x13
	adcs	x9, x9, x12
	adc	x10, x10, xzr      // At this point acc2 has the value of 4 at most

Lchacha_poly_poly_hash_ad_ret:
	ret
.cfi_endproc