// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only

#pragma once

#include <cstddef>
#include <cstdint>

// FNV-1a over a block of bytes. Not a cryptographic hash and does not need to be - it exists to
// notice that the bytes behind a reused address changed, not to resist anyone. Its user is the
// shared device-table cache (image_analysis/indexing/CudaSharedTables.h), which keys on it; it lives
// here so the classes that own those tables can compute their own checksum once and hand it in.
//
// Run over eight interleaved lanes and fold them at the end. FNV's multiply is a loop-carried
// dependency, so one lane retires a byte every few cycles however much memory bandwidth is going
// spare; eight independent chains fill that latency.
inline uint64_t TableChecksum(const void *data, size_t bytes) {
    constexpr uint64_t PRIME = 1099511628211ULL;
    constexpr size_t LANES = 8;
    const auto *p = static_cast<const unsigned char *>(data);
    uint64_t h[LANES];
    for (size_t l = 0; l < LANES; l++)
        h[l] = 1469598103934665603ULL + l;
    const size_t n = bytes / LANES * LANES;
    for (size_t i = 0; i < n; i += LANES)
        for (size_t l = 0; l < LANES; l++) {
            h[l] ^= p[i + l];
            h[l] *= PRIME;
        }
    uint64_t out = 1469598103934665603ULL;
    for (size_t l = 0; l < LANES; l++) {
        out ^= h[l];
        out *= PRIME;
    }
    for (size_t i = n; i < bytes; i++) {
        out ^= p[i];
        out *= PRIME;
    }
    return out;
}