{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Extending to multiple GPUs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A simple way to extend this example to multiple GPUs is to use a single host process that manages multiple GPUs. If we have *M* GPUs and *N* sample points to evaluate, we can distribute *N/M* to each GPU, and in principle calculate the result up to *M* times more quickly.\n",
    "\n",
    "Look at [exercises/monte_carlo_mgpu_cuda.cpp](exercises/monte_carlo_mgpu_cuda.cpp) for an example of this. We've given you a few simple tasks to do in the code -- look for locations denoted by `FIXME`. Note that in this example we're giving each GPU a different seed for the random number generator so that they're each doing different work. As a result our answer will change a little.\n",
    "\n",
    "If you get stuck, you can consult [the solution](solutions/monte_carlo_mgpu_cuda.cpp)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "!nvcc -x cu -arch=sm_70 -rdc=true -o monte_carlo_mgpu_cuda solutions/monte_carlo_mgpu_cuda.cpp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using 4 GPUs\n",
      "Estimated value of pi = 3.14072\n",
      "Error = 0.000277734\n",
      "CPU times: user 18.4 ms, sys: 11.1 ms, total: 29.5 ms\n",
      "Wall time: 2.04 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "!./monte_carlo_mgpu_cuda"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}