{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python2.7/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.\n",
      "  from ._conv import register_converters as _register_converters\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[22. 28.]\n",
      " [49. 64.]]\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')\n",
    "b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3, 2], name='b')\n",
    "c = tf.matmul(a, b)\n",
    "# Creates a session with log_device_placement set to True.\n",
    "sess = tf.Session(config=tf.ConfigProto(log_device_placement=True))\n",
    "# Runs the op.\n",
    "print(sess.run(c))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[22. 28.]\n",
      " [49. 64.]]\n"
     ]
    }
   ],
   "source": [
    "with tf.device('/cpu:0'):\n",
    "  a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')\n",
    "  b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3, 2], name='b')\n",
    "c = tf.matmul(a, b)\n",
    "# Creates a session with log_device_placement set to True.\n",
    "sess = tf.Session(config=tf.ConfigProto(log_device_placement=True))\n",
    "# Runs the op.\n",
    "print(sess.run(c))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[22. 28.]\n",
      " [49. 64.]]\n"
     ]
    }
   ],
   "source": [
    "with tf.device('/gpu:0'):\n",
    "  a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')\n",
    "  b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3, 2], name='b')\n",
    "c = tf.matmul(a, b)\n",
    "# Creates a session with log_device_placement set to True.\n",
    "sess = tf.Session(config=tf.ConfigProto(log_device_placement=True))\n",
    "# Runs the op.\n",
    "print(sess.run(c))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "import numpy as np\n",
    "import tensorflow as tf\n",
    "from datetime import datetime\n",
    "\n",
    "def matmul(device_name=\"gpu\", shape=(10,10)):\n",
    "#device_name = sys.argv[1]  # Choose device from cmd line. Options: gpu or cpu\n",
    "#shape = (int(sys.argv[2]), int(sys.argv[2]))\n",
    "    if device_name == \"gpu0\":\n",
    "        device_name = \"/gpu:0\"\n",
    "    elif device_name == \"gpu1\":\n",
    "        device_name = \"/gpu:1\"\n",
    "    else:\n",
    "        device_name = \"/cpu:0\"\n",
    "\n",
    "    with tf.device(device_name):\n",
    "        random_matrix = tf.random_uniform(shape=shape, minval=0, maxval=1)\n",
    "        dot_operation = tf.matmul(random_matrix, tf.transpose(random_matrix))\n",
    "        sum_operation = tf.reduce_sum(dot_operation)\n",
    "\n",
    "\n",
    "    startTime = datetime.now()\n",
    "    with tf.Session(config=tf.ConfigProto(log_device_placement=True)) as session:\n",
    "            result = session.run(sum_operation)\n",
    "            print(result)\n",
    "\n",
    "    # It can be hard to see the results on the terminal with lots of output -- add some newlines to improve readability.\n",
    "    print(\"\\n\" * 5)\n",
    "    print(\"Shape:\", shape, \"Device:\", device_name)\n",
    "    print(\"Time taken:\", datetime.now() - startTime)\n",
    "\n",
    "    print(\"\\n\" * 5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "254401050000.0\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "('Shape:', (10000, 10000), 'Device:', '/cpu:0')\n",
      "('Time taken:', datetime.timedelta(0, 20, 334651))\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "matmul(device_name=\"cpu\",shape=(10000,10000))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "250021800000.0\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "('Shape:', (10000, 10000), 'Device:', '/gpu:0')\n",
      "('Time taken:', datetime.timedelta(0, 0, 419122))\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "matmul(device_name=\"gpu0\",shape=(10000,10000))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "250002110000.0\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "('Shape:', (10000, 10000), 'Device:', '/gpu:1')\n",
      "('Time taken:', datetime.timedelta(0, 0, 907009))\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "matmul(device_name=\"gpu1\",shape=(10000,10000))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tue Feb 20 13:38:53 2018       \n",
      "+-----------------------------------------------------------------------------+\n",
      "| NVIDIA-SMI 387.26                 Driver Version: 387.26                    |\n",
      "|-------------------------------+----------------------+----------------------+\n",
      "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
      "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
      "|===============================+======================+======================|\n",
      "|   0  GeForce GTX TIT...  Off  | 00000000:02:00.0 Off |                  N/A |\n",
      "| 31%   48C    P8    29W / 250W |   5801MiB /  6080MiB |      0%      Default |\n",
      "+-------------------------------+----------------------+----------------------+\n",
      "|   1  GeForce GTX TIT...  Off  | 00000000:03:00.0 Off |                  N/A |\n",
      "| 22%   51C    P2    76W / 250W |  11633MiB / 12207MiB |      0%      Default |\n",
      "+-------------------------------+----------------------+----------------------+\n",
      "                                                                               \n",
      "+-----------------------------------------------------------------------------+\n",
      "| Processes:                                                       GPU Memory |\n",
      "|  GPU       PID   Type   Process name                             Usage      |\n",
      "|=============================================================================|\n",
      "+-----------------------------------------------------------------------------+\n"
     ]
    }
   ],
   "source": [
    "%%bash\n",
    "nvidia-smi"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}