#include <metal_stdlib>
using namespace metal;

#define MASK 0x0fffffffu
constant uint SEEDW[8] = { 0x667d0fbdu, 0x7b8e5963u, 0x31c67e5eu, 0x4529ddc6u, 0xef19d6d8u, 0xaccf6211u, 0xda0aed32u, 0xabc6df31u };

inline uint splitmix32(uint x) {
    x ^= x >> 16; x *= 0x7feb352du;
    x ^= x >> 15; x *= 0x846ca68bu;
    x ^= x >> 16;
    return x;
}
inline uint rotl_imm(uint x, uint n) { return (x << n) | (x >> (32u - n)); }          // n in 1..31
inline uint rotr_var(uint x, uint n) { n &= 31u; return (x >> n) | (x << ((32u - n) & 31u)); }
inline uint ds_elem(uint i, uint d0, uint d1) {
    uint x = i ^ d0;
    x *= 0x9E3779B1u; x ^= x >> 15;
    x += d1;
    x *= 0x85EBCA77u; x ^= x >> 13;
    x *= 0xC2B2AE3Du; x ^= x >> 16;
    return x;
}

// Header-bound variant: the init words come from buffer 3 (bind.rs), not from SEEDW.
kernel void igneum_hash_bound(device const uint* dataset [[buffer(0)]],
                        device ulong* out [[buffer(1)]],
                        constant uint& baseNonce [[buffer(2)]],
                        constant uint* initw [[buffer(3)]],
                        uint gid [[thread_position_in_grid]]) {
    uint nonce = baseNonce + gid;
    uint r0, r1, r2, r3, r4, r5, r6, r7;
    { uint x = nonce ^ initw[0]; x += 0x9e3779b9u * 1u; x = splitmix32(x); r0 = x ^ initw[1]; }
    { uint x = nonce ^ initw[1]; x += 0x9e3779b9u * 2u; x = splitmix32(x); r1 = x ^ initw[2]; }
    { uint x = nonce ^ initw[2]; x += 0x9e3779b9u * 3u; x = splitmix32(x); r2 = x ^ initw[3]; }
    { uint x = nonce ^ initw[3]; x += 0x9e3779b9u * 4u; x = splitmix32(x); r3 = x ^ initw[4]; }
    { uint x = nonce ^ initw[4]; x += 0x9e3779b9u * 5u; x = splitmix32(x); r4 = x ^ initw[5]; }
    { uint x = nonce ^ initw[5]; x += 0x9e3779b9u * 6u; x = splitmix32(x); r5 = x ^ initw[6]; }
    { uint x = nonce ^ initw[6]; x += 0x9e3779b9u * 7u; x = splitmix32(x); r6 = x ^ initw[7]; }
    { uint x = nonce ^ initw[7]; x += 0x9e3779b9u * 8u; x = splitmix32(x); r7 = x ^ initw[0]; }

    for (uint it = 0u; it < 8u; ++it) {
        uint sel = r0;
        r4 = r4 + r5 + select(0xea86e152u, 0x5810667au, ((sel >> 13u) & 1u) != 0u);  // 0
        r2 = r2 ^ simd_shuffle_xor(r0, (ushort)4);  // 1
        r3 = r3 + r2 + select(0x2cccb6cau, 0x642e66dbu, ((sel >> 10u) & 1u) != 0u);  // 2
        r0 = rotl_imm(r0, 19u);  // 3
        r7 = rotr_var(r7, r6);  // 4
        r7 = r7 + r4 + select(0xee02465fu, 0xc1535555u, ((sel >> 21u) & 1u) != 0u);  // 5
        r1 = mulhi(r1, r7);  // 6
        r4 = r4 ^ dataset[r2 & MASK];  // 7
        r7 = r7 ^ dataset[r4 & MASK];  // 8
        r0 = r0 ^ dataset[r3 & MASK];  // 9
        r5 = r5 ^ dataset[r1 & MASK];  // 10
        r1 = r1 ^ dataset[r5 & MASK];  // 11
        r3 = mulhi(r3, r5);  // 12
        r1 = r1 ^ dataset[r3 & MASK];  // 13
        r0 = r0 - r3;  // 14
        r5 = r1 * r3 + r5;  // 15
        r6 = mulhi(r6, r1);  // 16
        r5 = r5 + r2 + select(0x697b3d00u, 0x8b965b57u, ((sel >> 28u) & 1u) != 0u);  // 17
        r0 = mulhi(r0, r6);  // 18
        r5 = rotr_var(r5, r3);  // 19
        r5 = mulhi(r5, r2);  // 20
        r1 = r1 + r0 + select(0xebcf247au, 0x6d7e8d05u, ((sel >> 1u) & 1u) != 0u);  // 21
        r7 = r7 + r5 + select(0xf66e7017u, 0xb9e3577eu, ((sel >> 12u) & 1u) != 0u);  // 22
        r1 = mulhi(r1, r5);  // 23
        r2 = r2 - r5;  // 24
        r7 = r7 + r4 + select(0x08ffa6c7u, 0x699ef1bbu, ((sel >> 2u) & 1u) != 0u);  // 25
        r3 = r3 ^ simd_shuffle_xor(r4, (ushort)2);  // 26
        r7 = r7 + r1 + select(0xe60fea84u, 0xb4ead2fbu, ((sel >> 14u) & 1u) != 0u);  // 27
        r3 = r3 + r1 + select(0x65c76dabu, 0x8f30d21du, ((sel >> 6u) & 1u) != 0u);  // 28
        r2 = r2 ^ dataset[r1 & MASK];  // 29
        r5 = r5 ^ dataset[r7 & MASK];  // 30
        r2 = r2 ^ dataset[r5 & MASK];  // 31
        r1 = r1 ^ simd_shuffle_xor(r7, (ushort)4);  // 32
        r4 = r5 * r7 + r4;  // 33
        r4 = r4 + r2 + select(0x0480debeu, 0xc7ce690cu, ((sel >> 21u) & 1u) != 0u);  // 34
        r3 = r3 ^ simd_shuffle_xor(r7, (ushort)8);  // 35
        r7 = r7 + r1 + select(0xc53b542eu, 0xe10c2c95u, ((sel >> 2u) & 1u) != 0u);  // 36
        r5 = r5 ^ r7;  // 37
        r2 = r2 | r1;  // 38
        r1 = mulhi(r1, r0);  // 39
        r6 = rotl_imm(r6, 19u);  // 40
        r4 = mulhi(r4, r6);  // 41
        r6 = r6 - r0;  // 42
        r6 = r6 ^ simd_shuffle_xor(r3, (ushort)4);  // 43
        r4 = r4 ^ dataset[r2 & MASK];  // 44
        r1 = r1 ^ r3;  // 45
        r7 = r7 ^ dataset[r0 & MASK];  // 46
        r3 = r3 ^ dataset[r1 & MASK];  // 47
        r5 = r5 * r3;  // 48
        r1 = r1 - r5;  // 49
        r2 = rotl_imm(r2, 8u);  // 50
        r1 = r1 + r5 + select(0xa900fec4u, 0x77b9bd43u, ((sel >> 23u) & 1u) != 0u);  // 51
        r4 = r4 ^ dataset[r7 & MASK];  // 52
        r2 = r2 - r7;  // 53
        r4 = r4 ^ r0;  // 54
        r1 = r1 + r6 + select(0xe09f54e9u, 0x83e825bfu, ((sel >> 14u) & 1u) != 0u);  // 55
        r2 = r2 ^ dataset[r4 & MASK];  // 56
        r0 = r1 * r4 + r0;  // 57
        r3 = r3 ^ dataset[r5 & MASK];  // 58
        r5 = r5 | r6;  // 59
        r6 = r5 * r7 + r6;  // 60
        r4 = rotl_imm(r4, 28u);  // 61
        r5 = mulhi(r5, r0);  // 62
        r3 = r3 ^ dataset[r6 & MASK];  // 63
    }
    uint lo = r0 ^ rotl_imm(r1, 7u) ^ rotl_imm(r2, 14u) ^ rotl_imm(r3, 21u);
    uint hi = r4 ^ rotl_imm(r5, 9u) ^ rotl_imm(r6, 18u) ^ rotl_imm(r7, 27u);
    out[gid] = ((ulong)hi << 32) | (ulong)lo;
}