#include "common.hpp"
#include <atomic>
#include <thread>

// Original seed -> x -> z -> cells nesting, counting every matching anchor.
std::vector<show::Hit> scan(const show::Args& a) {
    std::atomic<uint64_t> next{0}, count{0};
    std::atomic<bool> overflow{false};
    std::vector<std::vector<show::Hit>> local(a.cpuThreads);
    std::vector<std::thread> workers;
    for(int t=0;t<a.cpuThreads;++t) workers.emplace_back([&,t] {
        for (;;) {
            const uint64_t s=next.fetch_add(1,std::memory_order_relaxed);
            if(s>=a.seeds) break;
            for(uint64_t xi=0;xi<a.width;++xi) for(uint64_t zi=0;zi<a.height;++zi) {
                const int32_t x=int32_t(int64_t(a.x0)+xi), z=int32_t(int64_t(a.z0)+zi);
                if(show::solid<1>(a.seed+s,x,z,a.n)) {
                    if(count.fetch_add(1,std::memory_order_relaxed)<a.capacity)
                        local[t].push_back({a.seed+s,x,z});
                    else overflow.store(true,std::memory_order_relaxed);
                }
            }
        }
    });
    for(auto& w:workers) w.join();
    if(overflow.load()) throw std::runtime_error("hit buffer overflow; raise --capacity");
    std::vector<show::Hit> result;
    for(const auto& v:local) result.insert(result.end(),v.begin(),v.end());
    return result;
}

int main(int argc,char** argv) {
    try {
        const auto a=show::parse(argc,argv);
        std::cout.precision(10);
        auto expected=scan(a); // full-workload warmup
        std::sort(expected.begin(),expected.end());
        std::vector<double> times;
        for(int r=0;r<a.repeats;++r) {
            const auto begin=std::chrono::steady_clock::now();
            auto hits=scan(a);
            times.push_back(show::ms(begin)); // thread creation + scan + collection, excludes sort
            std::sort(hits.begin(),hits.end());
            if(hits!=expected) throw std::runtime_error("CPU repeats disagree");
        }
        std::cout << '{'; show::workload(a);
        std::cout << ",\"mode\":\"01_cpu\",\"cpu_threads\":" << a.cpuThreads
                  << ",\"samples_ms\":"; show::array(times);
        std::cout << ",\"median_ms\":" << show::median(times) << ",\"hits\":";
        show::results(expected); std::cout << "}\n";
    } catch(const std::exception& e) { std::cerr << e.what() << '\n'; return 1; }
}