Not able to achieve linear speedup using threadpool

I want to calculate number of even numbers among all pairwise sums till 100000. And I want to do it using threadpools. Previously I did it in a static way, i.e., I allocated work to all the threads in the beginning itself. I was able to achieve linear speedup in that case. But the bottleneck is that the threads which started early, finished early (because there were less pairs to compute). So instead of that I want to allocate work to the threads dynamically, i.e., I will initially assign some work to the threads and as soon as they complete the work, they come back to take more work from the queue. Below is my threadpool code, main.cpp :

#include <iostream>
#include <random>
#include<chrono>
#include<iomanip>
#include<future>
#include<vector>

#include "../include/ThreadPool.h"

std::random_device rd;
std::mt19937 mt(rd());
std::uniform_int_distribution<int> dist(-10, 10);
auto rnd = std::bind(dist, mt);
int thread_work;

long long pairwise(const int start) {
  long long sum = 0;
  long long counter = 0;
  for(int i = start+1; i <= start+thread_work; i++)
  {
      for(int j = i-1; j >= 0; j--)
      {
          sum = i + j;
          if(sum%2 == 0)
            counter++;
      }
  }
  //std::cout<<counter<<std::endl;
  return counter;
}

int main(int argc, char *argv[])
{
  // Create pool with x threads
  int x;
  std::cout<<"Enter num of threads : ";
  std::cin>>x;
  std::cout<<"Enter thread_work : ";
  std::cin>>thread_work;
  ThreadPool pool(x);
  // Initialize pool
  pool.init();
  int N = 100000;
  long long res = 0;
  auto start = std::chrono::high_resolution_clock::now();
  for(int i = 0; i < N; i = i + thread_work)
  {
      std::future<long long int> fut = pool.submit(pairwise,i);
      res += fut.get();
  }
  std::cout<<"total is "<<res<<std::endl;
  pool.shutdown();
  auto end = std::chrono::high_resolution_clock::now();
  double time_taken = std::chrono::duration_cast<std::chrono::nanoseconds>(end - start).count();
  time_taken *= 1e-9;
  std::cout << "Time taken by program is : " << std::fixed << time_taken << std::setprecision(9)<<" secs"<<std::endl;
  return 0;
}

my SafeQueue.h :

#pragma once
#include <mutex>
#include <queue>

// Thread safe implementation of a Queue using an std::queue
template <typename T>
class SafeQueue {
private:
  std::queue<T> m_queue;
  std::mutex m_mutex;
public:
  SafeQueue() {

  }

  SafeQueue(SafeQueue& other) {
    //TODO:
  }

  ~SafeQueue() {

  }


  bool empty() {
    std::unique_lock<std::mutex> lock(m_mutex);
    return m_queue.empty();
  }

  int size() {
    std::unique_lock<std::mutex> lock(m_mutex);
    return m_queue.size();
  }

  void enqueue(T& t) {
    std::unique_lock<std::mutex> lock(m_mutex);
    m_queue.push(t);
  }

  bool dequeue(T& t) {
    std::unique_lock<std::mutex> lock(m_mutex);

    if (m_queue.empty()) {
      return false;
    }
    t = std::move(m_queue.front());

    m_queue.pop();
    return true;
  }
};

and my ThreadPool.h :

#pragma once

#include <functional>
#include <future>
#include <mutex>
#include <queue>
#include <thread>
#include <utility>
#include <vector>

#include "SafeQueue.h"

class ThreadPool {
private:
  class ThreadWorker {
  private:
    int m_id;
    ThreadPool * m_pool;
  public:
    ThreadWorker(ThreadPool * pool, const int id)
      : m_pool(pool), m_id(id) {
    }

    void operator()() {
      std::function<void()> func;
      bool dequeued;
      while (!m_pool->m_shutdown) {
        {
          std::unique_lock<std::mutex> lock(m_pool->m_conditional_mutex);
          if (m_pool->m_queue.empty()) {
            m_pool->m_conditional_lock.wait(lock);
          }
          dequeued = m_pool->m_queue.dequeue(func);
        }
        if (dequeued) {
          func();
        }
      }
    }
  };

  bool m_shutdown;
  SafeQueue<std::function<void()>> m_queue;
  std::vector<std::thread> m_threads;
  std::mutex m_conditional_mutex;
  std::condition_variable m_conditional_lock;
public:
  ThreadPool(const int n_threads)
    : m_threads(std::vector<std::thread>(n_threads)), m_shutdown(false) {
  }

  ThreadPool(const ThreadPool &) = delete;
  ThreadPool(ThreadPool &&) = delete;

  ThreadPool & operator=(const ThreadPool &) = delete;
  ThreadPool & operator=(ThreadPool &&) = delete;

  // Inits thread pool
  void init() {
    for (int i = 0; i < m_threads.size(); ++i) {
      m_threads[i] = std::thread(ThreadWorker(this, i));
    }
  }

  // Waits until threads finish their current task and shutdowns the pool
  void shutdown() {
    m_shutdown = true;
    m_conditional_lock.notify_all();

    for (int i = 0; i < m_threads.size(); ++i) {
      if(m_threads[i].joinable()) {
        m_threads[i].join();
      }
    }
  }

  // Submit a function to be executed asynchronously by the pool
  template<typename F, typename...Args>
  auto submit(F&& f, Args&&... args) -> std::future<decltype(f(args...))> {
    // Create a function with bounded parameters ready to execute
    std::function<decltype(f(args...))()> func = std::bind(std::forward<F>(f), std::forward<Args>(args)...);
    // Encapsulate it into a shared ptr in order to be able to copy construct / assign
    auto task_ptr = std::make_shared<std::packaged_task<decltype(f(args...))()>>(func);

    // Wrap packaged task into void function
    std::function<void()> wrapper_func = [task_ptr]() {
      (*task_ptr)();
    };

    // Enqueue generic wrapper function
    m_queue.enqueue(wrapper_func);

    // Wake up one thread if its waiting
    m_conditional_lock.notify_one();

    // Return future from promise
    return task_ptr->get_future();
  }
};