问英特尔x86与AMD x86 CPU的非对齐访问性能

EN

#include <atomic>
#include <chrono>
#include <cstdint>
#include <iostream>
#include <random>
#include <vector>

void ClobberMemory() { std::atomic_signal_fence(std::memory_order_acq_rel); }

template <typename T>
void doNotOptimize(T const& val) {
  asm volatile("" : : "r,m"(val) : "memory");
}

struct PaddedStruct {
  uint64_t key;
  uint64_t value;
  bool is_valid;

  PaddedStruct() { reset(); }

  void reset() {
    key = uint64_t{};
    value = uint64_t{};
    is_valid = 0;
  }
};

struct PackedStruct {
  uint64_t key;
  uint64_t value;
  uint8_t is_valid;

  PackedStruct() { reset(); }

  void reset() {
    key = uint64_t{};
    value = uint64_t{};
    is_valid = 0;
  }
} __attribute__((__packed__));

int main() {
  const uint64_t size = 134217728;
  uint16_t repetitions = 0;
  uint16_t advancement = 0;

  std::cin >> repetitions;
  std::cout << "Got " << repetitions << std::endl;
  std::cin >> advancement;
  std::cout << "Got " << advancement << std::endl;
  std::cout << "Initializing." << std::endl;

  std::vector<PaddedStruct> padded(size);
  std::vector<PackedStruct> unaligned(size);
  std::vector<uint64_t> queries(size);

  // Initialize the structs with random values + prefault
  std::random_device rd;
  std::mt19937 gen{rd()};
  std::uniform_int_distribution<uint64_t> dist{0, 0xDEADBEEF};
  std::uniform_int_distribution<uint64_t> dist2{0, size - advancement - 1};

  for (uint64_t i = 0; i < padded.size(); ++i) {
    padded[i].key = dist(gen);
    padded[i].value = dist(gen);
    padded[i].is_valid = 1;
  }

  for (uint64_t i = 0; i < unaligned.size(); ++i) {
    unaligned[i].key = padded[i].key;
    unaligned[i].value = padded[i].value;
    unaligned[i].is_valid = 1;
  }

  for (uint64_t i = 0; i < unaligned.size(); ++i) {
    queries[i] = dist2(gen);
  }

  std::cout << "Running benchmark." << std::endl;

  ClobberMemory();
  auto start_padded = std::chrono::high_resolution_clock::now();
  PaddedStruct* padded_ptr = nullptr;
  uint64_t sum = 0;
  for (uint16_t j = 0; j < repetitions; j++) {
    for (const uint64_t& query : queries) {
      for (uint16_t i = 0; i < advancement; i++) {
        padded_ptr = &padded[query + i];
        if (padded_ptr->is_valid) [[likely]] {
          sum += padded_ptr->value;
        }
      }
      doNotOptimize(sum);
    }
  }

  ClobberMemory();
  auto end_padded = std::chrono::high_resolution_clock::now();
  uint64_t padded_runtime = static_cast<uint64_t>(std::chrono::duration_cast<std::chrono::milliseconds>(end_padded - start_padded).count());
  std::cout << "Padded Runtime (ms): " << padded_runtime << " (sum = " << sum << ")" << std::endl;  // print sum to avoid that it gets optimized out

  ClobberMemory();
  auto start_unaligned = std::chrono::high_resolution_clock::now();
  uint64_t sum2 = 0;
  PackedStruct* packed_ptr = nullptr;
  for (uint16_t j = 0; j < repetitions; j++) {
    for (const uint64_t& query : queries) {
      for (uint16_t i = 0; i < advancement; i++) {
        packed_ptr = &unaligned[query + i];
        if (packed_ptr->is_valid) [[likely]] {
          sum2 += packed_ptr->value;
        }
      }
      doNotOptimize(sum2);
    }
  }
  ClobberMemory();
  auto end_unaligned = std::chrono::high_resolution_clock::now();
  uint64_t unaligned_runtime = static_cast<uint64_t>(std::chrono::duration_cast<std::chrono::milliseconds>(end_unaligned - start_unaligned).count());
  std::cout << "Unaligned Runtime (ms): " << unaligned_runtime << " (sum = " << sum2 << ")" << std::endl;
}