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

//! SHA-256 CPU reference implementation.

// compress.rs
pub fn compress(state: &mut [u32; 8], block: &[u8]) {
    let mut w = [0u32; 64];
    for (slot, bytes) in w[..16].iter_mut().zip(block.chunks_exact(4)) {
        *slot = u32::from_be_bytes([bytes[0], bytes[1], bytes[2], bytes[3]]);
    }
    for i in 16..64 {
        let s0 = w[i - 15].rotate_right(7) ^ w[i - 15].rotate_right(18) ^ (w[i - 15] >> 3);
        let s1 = w[i - 2].rotate_right(17) ^ w[i - 2].rotate_right(19) ^ (w[i - 2] >> 10);
        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..64 {
        let s1 = e.rotate_right(6) ^ e.rotate_right(11) ^ e.rotate_right(25);
        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(2) ^ a.rotate_right(13) ^ a.rotate_right(22);
        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);
    }
}

// h0.rs
pub const H0: [u32; 8] = [
    0x6a09_e667,
    0xbb67_ae85,
    0x3c6e_f372,
    0xa54f_f53a,
    0x510e_527f,
    0x9b05_688c,
    0x1f83_d9ab,
    0x5be0_cd19,
];

// k.rs
pub const K: [u32; 64] = [
    0x428a_2f98,
    0x7137_4491,
    0xb5c0_fbcf,
    0xe9b5_dba5,
    0x3956_c25b,
    0x59f1_11f1,
    0x923f_82a4,
    0xab1c_5ed5,
    0xd807_aa98,
    0x1283_5b01,
    0x2431_85be,
    0x550c_7dc3,
    0x72be_5d74,
    0x80de_b1fe,
    0x9bdc_06a7,
    0xc19b_f174,
    0xe49b_69c1,
    0xefbe_4786,
    0x0fc1_9dc6,
    0x240c_a1cc,
    0x2de9_2c6f,
    0x4a74_84aa,
    0x5cb0_a9dc,
    0x76f9_88da,
    0x983e_5152,
    0xa831_c66d,
    0xb003_27c8,
    0xbf59_7fc7,
    0xc6e0_0bf3,
    0xd5a7_9147,
    0x06ca_6351,
    0x1429_2967,
    0x27b7_0a85,
    0x2e1b_2138,
    0x4d2c_6dfc,
    0x5338_0d13,
    0x650a_7354,
    0x766a_0abb,
    0x81c2_c92e,
    0x9272_2c85,
    0xa2bf_e8a1,
    0xa81a_664b,
    0xc24b_8b70,
    0xc76c_51a3,
    0xd192_e819,
    0xd699_0624,
    0xf40e_3585,
    0x106a_a070,
    0x19a4_c116,
    0x1e37_6c08,
    0x2748_774c,
    0x34b0_bcb5,
    0x391c_0cb3,
    0x4ed8_aa4a,
    0x5b9c_ca4f,
    0x682e_6ff3,
    0x748f_82ee,
    0x78a5_636f,
    0x84c8_7814,
    0x8cc7_0208,
    0x90be_fffa,
    0xa450_6ceb,
    0xbef9_a3f7,
    0xc671_78f2,
];

// sha256_words.rs
/// Compute SHA-256 and return eight big-endian digest words.
#[must_use]
pub(crate) fn sha256_words(input: &[u8]) -> [u32; 8] {
    let mut state = H0;
    let mut blocks = input.chunks_exact(64);
    for block in &mut blocks {
        compress(&mut state, block);
    }
    let rem = blocks.remainder();
    let bit_len = (input.len() as u64).wrapping_mul(8);
    let mut tail = [0u8; 128];
    tail[..rem.len()].copy_from_slice(rem);
    tail[rem.len()] = 0x80;
    let total = if rem.len() < 56 { 64 } else { 128 };
    tail[total - 8..total].copy_from_slice(&bit_len.to_be_bytes());
    for block in tail[..total].chunks_exact(64) {
        compress(&mut state, block);
    }
    state
}