git clone https://github.com/LaurieWired/tailslayer.git
cp -r tailslayer/include/tailslayer /your/project/include/

#include <tailslayer/hedged_reader.hpp>

git clone https://github.com/LaurieWired/tailslayer.git
cd tailslayer
make
./tailslayer_example

HedgedReader(
    uint64_t channel_offset = DEFAULT_OFFSET,  // undocumented channel scrambling offset
    uint64_t channel_bit    = DEFAULT_BIT,     // bit used for channel selection
    std::size_t n_replicas  = 2                // number of DRAM channel replicas
)

reader.insert(T value);       // Insert value, replicated across all channels
reader.start_workers();       // Launch per-channel worker threads (blocking)

tailslayer::pin_to_core(core_id);        // Pin calling thread to a specific core
tailslayer::CORE_MAIN                    // Constant: recommended core for main thread

#include <tailslayer/hedged_reader.hpp>
#include <cstdint>
#include <cstdio>

// 1. Define your signal function — waits for your event, returns index to read
[[gnu::always_inline]] inline std::size_t my_signal() {
    // Example: busy-wait for an external flag, then return the index
    extern volatile std::size_t g_index;
    extern volatile bool g_trigger;
    while (!g_trigger) {}
    g_trigger = false;
    return g_index;
}

// 2. Define your work function — receives the read value immediately
template <typename T>
[[gnu::always_inline]] inline void my_work(T val) {
    // Process val as fast as possible
    printf("Read value: %u\n", (unsigned)val);
}

int main() {
    using T = uint8_t;

    // Pin main thread to recommended core
    tailslayer::pin_to_core(tailslayer::CORE_MAIN);

    // Construct reader with 2 replicas (default)
    tailslayer::HedgedReader<T, my_signal, my_work<T>> reader{};

    // Insert data — replicated across both DRAM channels automatically
    reader.insert(0x43);
    reader.insert(0x44);

    // Launch workers — blocks; workers spin until signal fires
    reader.start_workers();

    return 0;
}

#include <tailslayer/hedged_reader.hpp>

// Signal function with args
[[gnu::always_inline]] inline std::size_t my_signal(int threshold, int channel) {
    // use threshold and channel...
    return 0;
}

// Work function with args
template <typename T>
[[gnu::always_inline]] inline void my_work(T val, int multiplier) {
    volatile int result = (int)val * multiplier;
    (void)result;
}

int main() {
    using T = uint8_t;
    tailslayer::pin_to_core(tailslayer::CORE_MAIN);

    tailslayer::HedgedReader<
        T,
        my_signal,
        my_work<T>,
        tailslayer::ArgList<10, 1>,   // args forwarded to my_signal: threshold=10, channel=1
        tailslayer::ArgList<2>        // args forwarded to my_work:   multiplier=2
    > reader{};

    reader.insert(0xAB);
    reader.start_workers();
}

// Example: 4 replicas, custom channel bit 8 (common for AMD/Intel)
tailslayer::HedgedReader<T, my_signal, my_work<T>> reader{
    /* channel_offset */ 0,
    /* channel_bit    */ 8,
    /* n_replicas     */ 4
};

cd discovery/benchmark
make
sudo chrt -f 99 ./hedged_read_cpp --all --channel-bit 8

cd discovery
gcc -O2 -o trefi_probe trefi_probe.c
sudo ./trefi_probe

// Pre-load order book prices into hedged reader
// Signal on market data arrival, process immediately

[[gnu::always_inline]] inline std::size_t await_market_signal() {
    extern volatile std::size_t g_book_idx;
    extern volatile bool g_tick;
    while (!g_tick) { __builtin_ia32_pause(); }
    g_tick = false;
    return g_book_idx;
}

template <typename T>
[[gnu::always_inline]] inline void process_price(T price) {
    // Submit order using price with minimal latency
    extern void submit_order(T);
    submit_order(price);
}

int main() {
    tailslayer::pin_to_core(tailslayer::CORE_MAIN);
    tailslayer::HedgedReader<uint64_t, await_market_signal, process_price<uint64_t>> reader{};
    for (uint64_t price : preloaded_prices) {
        reader.insert(price);
    }
    reader.start_workers();
}

// Each insert automatically maps to correct DRAM channel via address calculation
// Access is via logical index — tailslayer manages physical placement

tailslayer::HedgedReader<uint32_t, my_signal, my_work<uint32_t>> reader{};

std::vector<uint32_t> lut = {100, 200, 300, 400};
for (auto v : lut) {
    reader.insert(v);
}
reader.start_workers();

tailslayer/
├── include/tailslayer/
│   └── hedged_reader.hpp       # Main library header (copy this)
├── tailslayer_example.cpp      # Usage example
├── discovery/
│   ├── trefi_probe.c           # DRAM refresh spike timing tool
│   └── benchmark/              # N-way channel hedging benchmark
└── Makefile