vyre 0.4.0

GPU compute intermediate representation with a standard operation library
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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187

//! SHA-384 and SHA-512 CPU reference implementations.

// compress.rs
pub fn compress(state: &mut [u64; 8], block: &[u8]) {
    let mut w = [0u64; 80];
    for (slot, bytes) in w[..16].iter_mut().zip(block.chunks_exact(8)) {
        *slot = u64::from_be_bytes([
            bytes[0], bytes[1], bytes[2], bytes[3], bytes[4], bytes[5], bytes[6], bytes[7],
        ]);
    }
    for i in 16..80 {
        let s0 = w[i - 15].rotate_right(1) ^ w[i - 15].rotate_right(8) ^ (w[i - 15] >> 7);
        let s1 = w[i - 2].rotate_right(19) ^ w[i - 2].rotate_right(61) ^ (w[i - 2] >> 6);
        w[i] = w[i - 16]
            .wrapping_add(s0)
            .wrapping_add(w[i - 7])
            .wrapping_add(s1);
    }

    let [mut a, mut b, mut c, mut d, mut e, mut f, mut g, mut h] = *state;
    for i in 0..80 {
        let s1 = e.rotate_right(14) ^ e.rotate_right(18) ^ e.rotate_right(41);
        let ch = (e & f) ^ ((!e) & g);
        let t1 = h
            .wrapping_add(s1)
            .wrapping_add(ch)
            .wrapping_add(K[i])
            .wrapping_add(w[i]);
        let s0 = a.rotate_right(28) ^ a.rotate_right(34) ^ a.rotate_right(39);
        let maj = (a & b) ^ (a & c) ^ (b & c);
        let t2 = s0.wrapping_add(maj);
        h = g;
        g = f;
        f = e;
        e = d.wrapping_add(t1);
        d = c;
        c = b;
        b = a;
        a = t1.wrapping_add(t2);
    }

    for (slot, value) in state.iter_mut().zip([a, b, c, d, e, f, g, h]) {
        *slot = slot.wrapping_add(value);
    }
}

// digest.rs
pub fn digest(input: &[u8], mut state: [u64; 8]) -> [u64; 8] {
    let mut blocks = input.chunks_exact(128);
    for block in &mut blocks {
        compress(&mut state, block);
    }
    let rem = blocks.remainder();
    let bit_len = (input.len() as u128).wrapping_mul(8);
    let mut tail = [0u8; 256];
    tail[..rem.len()].copy_from_slice(rem);
    tail[rem.len()] = 0x80;
    let total = if rem.len() < 112 { 128 } else { 256 };
    tail[total - 16..total].copy_from_slice(&bit_len.to_be_bytes());
    for block in tail[..total].chunks_exact(128) {
        compress(&mut state, block);
    }
    state
}

// h384.rs
pub const H384: [u64; 8] = [
    0xcbbb9d5dc1059ed8,
    0x629a292a367cd507,
    0x9159015a3070dd17,
    0x152fecd8f70e5939,
    0x67332667ffc00b31,
    0x8eb44a8768581511,
    0xdb0c2e0d64f98fa7,
    0x47b5481dbefa4fa4,
];

// h512.rs
pub const H512: [u64; 8] = [
    0x6a09e667f3bcc908,
    0xbb67ae8584caa73b,
    0x3c6ef372fe94f82b,
    0xa54ff53a5f1d36f1,
    0x510e527fade682d1,
    0x9b05688c2b3e6c1f,
    0x1f83d9abfb41bd6b,
    0x5be0cd19137e2179,
];

// k.rs
pub const K: [u64; 80] = [
    0x428a2f98d728ae22,
    0x7137449123ef65cd,
    0xb5c0fbcfec4d3b2f,
    0xe9b5dba58189dbbc,
    0x3956c25bf348b538,
    0x59f111f1b605d019,
    0x923f82a4af194f9b,
    0xab1c5ed5da6d8118,
    0xd807aa98a3030242,
    0x12835b0145706fbe,
    0x243185be4ee4b28c,
    0x550c7dc3d5ffb4e2,
    0x72be5d74f27b896f,
    0x80deb1fe3b1696b1,
    0x9bdc06a725c71235,
    0xc19bf174cf692694,
    0xe49b69c19ef14ad2,
    0xefbe4786384f25e3,
    0x0fc19dc68b8cd5b5,
    0x240ca1cc77ac9c65,
    0x2de92c6f592b0275,
    0x4a7484aa6ea6e483,
    0x5cb0a9dcbd41fbd4,
    0x76f988da831153b5,
    0x983e5152ee66dfab,
    0xa831c66d2db43210,
    0xb00327c898fb213f,
    0xbf597fc7beef0ee4,
    0xc6e00bf33da88fc2,
    0xd5a79147930aa725,
    0x06ca6351e003826f,
    0x142929670a0e6e70,
    0x27b70a8546d22ffc,
    0x2e1b21385c26c926,
    0x4d2c6dfc5ac42aed,
    0x53380d139d95b3df,
    0x650a73548baf63de,
    0x766a0abb3c77b2a8,
    0x81c2c92e47edaee6,
    0x92722c851482353b,
    0xa2bfe8a14cf10364,
    0xa81a664bbc423001,
    0xc24b8b70d0f89791,
    0xc76c51a30654be30,
    0xd192e819d6ef5218,
    0xd69906245565a910,
    0xf40e35855771202a,
    0x106aa07032bbd1b8,
    0x19a4c116b8d2d0c8,
    0x1e376c085141ab53,
    0x2748774cdf8eeb99,
    0x34b0bcb5e19b48a8,
    0x391c0cb3c5c95a63,
    0x4ed8aa4ae3418acb,
    0x5b9cca4f7763e373,
    0x682e6ff3d6b2b8a3,
    0x748f82ee5defb2fc,
    0x78a5636f43172f60,
    0x84c87814a1f0ab72,
    0x8cc702081a6439ec,
    0x90befffa23631e28,
    0xa4506cebde82bde9,
    0xbef9a3f7b2c67915,
    0xc67178f2e372532b,
    0xca273eceea26619c,
    0xd186b8c721c0c207,
    0xeada7dd6cde0eb1e,
    0xf57d4f7fee6ed178,
    0x06f067aa72176fba,
    0x0a637dc5a2c898a6,
    0x113f9804bef90dae,
    0x1b710b35131c471b,
    0x28db77f523047d84,
    0x32caab7b40c72493,
    0x3c9ebe0a15c9bebc,
    0x431d67c49c100d4c,
    0x4cc5d4becb3e42b6,
    0x597f299cfc657e2a,
    0x5fcb6fab3ad6faec,
    0x6c44198c4a475817,
];

// sha384_words.rs
/// Compute SHA-384 and return six big-endian digest words.
#[must_use]
pub(crate) fn sha384_words(input: &[u8]) -> [u64; 6] {
    let full = digest(input, H384);
    [full[0], full[1], full[2], full[3], full[4], full[5]]
}

// sha512_words.rs
/// Compute SHA-512 and return eight big-endian digest words.
#[must_use]
pub(crate) fn sha512_words(input: &[u8]) -> [u64; 8] {
    digest(input, H512)
}