ryzen-5-vs-core-i5.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "dominant-temperature",
   "metadata": {},
   "source": [
    "# Сравнение Ryzen 5 3600x vs Core i5-8600K на сборке ядра Linux\n",
    "\n",
    "Ядро взято из репозитория Raspberry Pi, сборка производилась с помощью кросс-компиляции, тулчейн GCC 7.2. \n",
    "\n",
    "Конфигурации компьютеров приблизительно одинаковы: DDR4 32 GB, 1 HDD, 1 SSD/NVMe накопитель. Оба процессора являются 6-ядерными, но у Ryzen 5 3600x есть гипертрединг - по два потока на ядро, а у Core i5-8600K по одному потоку на ядро. Тактовые частоты тоже примерно одинаковы. Базовая у AMD: 3800 МГц, у Intel: 3600 МГц, в турбо режиме у обоих 4200 МГц, а при полной нагрузке именно на этой  частоте оба и работают.\n",
    "\n",
    "Данные собраны следующим образом. Выкачаны исходные коды ядра Linux для платформы Raspberry Py, настройки все по умолчанию, и на каждом процессоре производилась сборка с указанием следующего количества используемых потоков:\n",
    "\n",
    "1, 2, 4, 6, 8, 10, 12\n",
    "\n",
    "Замерялось время каждого прогона.\n",
    "\n",
    "****************************************************************\n",
    "Ryzen 5 3600x (HDD)\n",
    "\n",
    "<pre>\n",
    "make       1932.01s user 171.88s system  107% cpu 32:32.58 total\n",
    "make -j2   1978.12s user 174.67s system  215% cpu 16:41.06 total\n",
    "make -j4   2154.34s user 189.45s system  427% cpu  9:08.67 total\n",
    "make -j6   2343.60s user 204.65s system  635% cpu  6:41.06 total\n",
    "make -j8   2596.57s user 220.37s system  831% cpu  5:38.79 total\n",
    "make -j10  2781.01s user 226.84s system 1014% cpu  4:56.50 total\n",
    "make -j12  2918.06s user 247.39s system 1116% cpu  4:43.43 total\n",
    "\n",
    "----------------------------------------------------------------\n",
    "Ryzen 5 3600x (NVMe)\n",
    "\n",
    "make       1939.71s user 174.10s system  107% cpu 32:42.32 total\n",
    "make -j2   1984.44s user 175.03s system  215% cpu 16:44.13 total\n",
    "make -j4   2134.97s user 187.52s system  427% cpu  9:03.24 total\n",
    "make -j6   2338.44s user 200.66s system  634% cpu  6:40.19 total\n",
    "make -j8   2575.02s user 217.51s system  836% cpu  5:33.73 total\n",
    "make -j10  2778.57s user 230.84s system 1016% cpu  4:56.18 total\n",
    "make -j12  2914.25s user 244.50s system 1126% cpu  4:40.49 total\n",
    "****************************************************************\n",
    "\n",
    "****************************************************************\n",
    "Core i5-8600K (HDD)\n",
    "\n",
    "make       1721.10s user 170.71s system 107% cpu 29:21.81 total\n",
    "make -j2   1766.46s user 175.17s system 213% cpu 15:08.25 total\n",
    "make -j3   1818.99s user 182.00s system 318% cpu 10:28.60 total\n",
    "make -j4   1853.33s user 184.01s system 411% cpu  8:14.82 total\n",
    "make -j5   1877.61s user 187.18s system 503% cpu  6:49.99 total\n",
    "make -j6   1899.50s user 189.94s system 556% cpu  6:15.73 total\n",
    "make -j8   1916.64s user 188.26s system 563% cpu  6:13.42 total\n",
    "make -j10  1930.85s user 189.35s system 569% cpu  6:12.48 total\n",
    "make -j12  1942.89s user 189.54s system 570% cpu  6:13.74 total\n",
    "\n",
    "----------------------------------------------------------------\n",
    "Core i5-8600K (SSD)\n",
    "make       1721.69s user 169.55s system 107% cpu 29:18.83 total\n",
    "make -j2   1766.96s user 174.09s system 214% cpu 15:04.80 total\n",
    "make -j4   1850.97s user 182.10s system 419% cpu  8:04.73 total\n",
    "make -j6   1899.09s user 187.62s system 559% cpu  6:13.19 total\n",
    "make -j8   1917.02s user 186.46s system 565% cpu  6:11.82 total\n",
    "make -j10  1930.72s user 188.86s system 567% cpu  6:13.59 total\n",
    "make -j12  1941.11s user 189.79s system 570% cpu  6:13.23 total\n",
    "****************************************************************\n",
    "</pre>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "dangerous-advantage",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "from matplotlib.pylab import plt\n",
    "import matplotlib.patches as mpatches\n",
    "import numpy as np\n",
    "\n",
    "#-------------------------------------------------\n",
    "#\n",
    "#  Origins \n",
    "#\n",
    "\n",
    "# core count array\n",
    "cores    = np.array([1, 2, 4, 6, 8, 10, 12])\n",
    "\n",
    "# runs execution time corresponding to core count\n",
    "r5_3600x = ['32:32.58', '16:41.06', '9:08.67', '6:41.06', '5:38.79', '4:56.50', '4:43.43']\n",
    "i5_8600k = ['29:21.81', '15:08.25', '8:14.82', '6:15.73', '6:13.42', '6:12.48', '6:13.74']\n",
    "\n",
    "#-------------------------------------------------\n",
    "#\n",
    "#   Converting min:sec time format to seconds\n",
    "#\n",
    "def tsec(t):\n",
    "    ts = t.split(':')\n",
    "    return int(ts[0])*60 + float(ts[1])\n",
    "\n",
    "r5_3600x_s = []\n",
    "i5_8600k_s = []\n",
    "\n",
    "for i in r5_3600x:\n",
    "    r5_3600x_s.append(tsec(i))\n",
    "    \n",
    "for i in i5_8600k:\n",
    "    i5_8600k_s.append(tsec(i))\n",
    "\n",
    "#-------------------------------------------------\n",
    "#\n",
    "#   Plot diagrams\n",
    "#\n",
    "fig, ax = plt.subplots()\n",
    "ax.bar(cores-0.2, r5_3600x_s, width=0.3);\n",
    "ax.bar(cores+0.2, i5_8600k_s, width=0.3);\n",
    "\n",
    "fig.set_figwidth(12)    #  ширина Figure\n",
    "fig.set_figheight(8)    #  высота Figure\n",
    "fig.set_facecolor('floralwhite')\n",
    "\n",
    "i5_patch = mpatches.Patch(color='orange', label='Intel Core i5-8600K')\n",
    "r5_patch = mpatches.Patch(color='cornflowerblue', label='AMD Ryzen 5 3600x')\n",
    "plt.legend(handles=[i5_patch, r5_patch]);\n",
    "\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "increasing-affiliation",
   "metadata": {},
   "source": [
    "Здесь графики показывают время сборки в секундах в зависимости от количества потоков. Отчётливо видно два обстоятельства:\n",
    "\n",
    "1. До 6 потоков Intel выигрывает у AMD приблизительно на 10%. Это можно объяснить тем, что полноценное ядро всё-таки быстрее одного потока многопоточного ядра.\n",
    "2. Производительность Intel не растёт при увеличении количества потоков более 6. Это объясняется тем, что у этого процессора всего 6 ядер и 6 потоков.\n",
    "\n",
    "Предварительный вывод: сравнивать аппаратный поток и полноценное ядро не совсем корректно, более адекватное сравнение - это противопоставлять одно ядро AMD одному ядру Intel, хотя очевидно, что здесь результат будет не в пользу Intel, т.к. два более медленных потока AMD (примерно на 10% медленнее) всё же будут быстрее одного у Intel."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "equivalent-killer",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#-------------------------------------------------\n",
    "#\n",
    "#  Origins \n",
    "#\n",
    "\n",
    "# core count array\n",
    "cores    = np.array([1, 2, 3, 4, 5, 6])\n",
    "r5_3600x = ['16:41.06',  '9:08.67', '6:41.06',  '5:38.79', '4:56.50', '4:43.43']\n",
    "i5_8600k = ['29:21.81', '15:08.25', '10:28.60', '8:14.82', '6:49.99', '6:15.73']\n",
    "\n",
    "#-------------------------------------------------\n",
    "#\n",
    "#   Converting min:sec time format to seconds\n",
    "#\n",
    "r5_3600x_s = []\n",
    "i5_8600k_s = []\n",
    "\n",
    "for i in r5_3600x:\n",
    "    r5_3600x_s.append(tsec(i))\n",
    "    \n",
    "for i in i5_8600k:\n",
    "    i5_8600k_s.append(tsec(i))\n",
    "\n",
    "#-------------------------------------------------\n",
    "#\n",
    "#   Plot diagrams\n",
    "#\n",
    "fig, ax = plt.subplots()\n",
    "ax.bar(cores-0.1, r5_3600x_s, width=0.15);\n",
    "ax.bar(cores+0.1, i5_8600k_s, width=0.15);\n",
    "\n",
    "fig.set_figwidth(12) \n",
    "fig.set_figheight(8) \n",
    "fig.set_facecolor('floralwhite')\n",
    "\n",
    "i5_patch = mpatches.Patch(color='orange', label='Intel Core i5-8600K')\n",
    "r5_patch = mpatches.Patch(color='cornflowerblue', label='AMD Ryzen 5 3600x')\n",
    "plt.legend(handles=[i5_patch, r5_patch]);\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "liberal-recycling",
   "metadata": {},
   "source": [
    "Здесь картина уже совсем иная: очевидно, что гипертрединг даёт значительное преимущество. Интересный момент: по мере увеличения количества ядер, относительная разница в производительности уменьшается - например, на одном ядре разница 1.76 раза, а для шести - всего 1.33."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "threaded-england",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "r5_s = np.array(r5_3600x_s)\n",
    "i5_s = np.array(i5_8600k_s)\n",
    "\n",
    "ratio =i5_s/r5_s\n",
    "\n",
    "plt.plot(cores, ratio);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "classical-tours",
   "metadata": {},
   "source": [
    "Одно из объяснений заключается в том, что помере роста количества ядер, возрастает нагрузка на процессорное окружение - в первую очередь доступ в память, где ядрам при интенсивной работе приходится конкурировать за канал доступа. Этот момент наглядно иллюстрирует ограниченность перспективы наращивания производительности путём увеличения колечества ядер."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}