This is machine translation

Translated by Microsoft
Mouseover text to see original. Click the button below to return to the English version of the page.

Note: This page has been translated by MathWorks. Click here to see
To view all translated materials including this page, select Country from the country navigator on the bottom of this page.

Run MATLAB Functions on Multiple GPUs

This example shows how to run MATLAB code on multiple GPUs in parallel, first on your local machine, then scaling up to a cluster. The example uses the logistic map, an equation that models the growth of a population, as a sample problem.

A growing number of features in MATLAB offer automatic parallel support, including multi-gpu support, without requiring any extra coding. For details, see Parallel Computing Support in MathWorks Products. For example, the trainNetwork function offers multi-gpu support for training of neural networks and inference. For more information, see Deep Learning with Big Data on GPUs and in Parallel (Deep Learning Toolbox).

Follow the next steps to learn how to write your own parallel code that runs on multiple GPUs.

Use a Single GPU

To run computations on a single GPU, use gpuArray objects as inputs to GPU-enabled MATLAB functions. To learn more about GPU-enabled functions, see Run MATLAB Functions on a GPU.

Create gpuArrays for the growth rate, r, and the population, x. For more information on creating gpuArrays, see Establish Arrays on a GPU.

N = 1000;
r = gpuArray.linspace(0,4,N);
x = rand(1,N,'gpuArray');

Use a simple algorithm to iterate the logistic map. Because the algorithm uses GPU-enabled operators on gpuArrays, the computations run on the GPU.

numIterations = 1000;
for n=1:numIterations
    x = r.*x.*(1-x);

When the computations are done, plot the growth rate against the population.


If you need more performance, gpuArrays supports several options. For a list, see the gpuArray function page. For example, the algorithm in this example only performs element-wise operations on gpuArrays, and so you can use the arrayfun function to precompile them for GPU. For more information, see Run Element-wise MATLAB Code on GPU.

Use Multiple GPUs with parfor

You can use parfor loops to distribute for-loop iterations among parallel workers. If your computations use GPU-enabled functions, then the computations run on the GPU of the worker. As an example, you use the Monte Carlo method to randomly simulate the evolution of populations. The simulations are computed with multiple GPUs in parallel using a parfor loop.

Create a parallel pool with as many workers as GPUs available. To determine the number of GPUs available, use the gpuDeviceCount function. By default, MATLAB assigns a different GPU to each worker for best performance. For more information on selecting GPUs in a parallel pool, see Use Multiple GPUs in a Parallel Pool.

Starting parallel pool (parpool) using the 'local' profile ...
connected to 2 workers.

Define the number of simulations, and create an array in the GPU to store the population vector for each simulation.

numSimulations = 100;
X = zeros(numSimulations,N,'gpuArray');

Use a parfor loop to distribute simulations to workers in the pool. The code inside the loop creates a random gpuArray for the initial population, and iterates the logistic map on it. Because the code uses GPU-enabled operators on gpuArrays, the computations automatically run on the GPU of the worker.

parfor i = 1:numSimulations
    X(i,:) = rand(1,N,'gpuArray');
    for n=1:numIterations
        X(i,:) = r.*X(i,:).*(1-X(i,:));

When the computations are done, plot the results of all simulations. Each color represents a different simulation.


If you need greater control over your calculations, you can use more advanced parallel functionality. For example, you can use a DataQueue to send data from the workers during computations. For an example, see Plot During Parameter Sweep with parfor.

If you want to generate a reproducible set of random numbers, then you can control the random number generation on the worker GPU. For more information, see Control Random Number Streams.

Use Multiple GPUs Asynchronously with parfeval

You can use parfeval to run computations asynchronously on parallel pool workers. If your computations use GPU-enabled functions, then the computations run on the GPU of the worker. As an example, you run Monte Carlo simulations on multiple GPUs asynchronously.

To hold the results of computations after the workers complete them, use future objects. Preallocate an array of future objects for the result of each simulation.

f(numSimulations) = parallel.FevalFuture;

To run computations with parfeval, you must place them inside a function. For example, myParallelFcn contains the code of a single simulation.

type myParallelFcn
function x = myParallelFcn(r)
    N = 1000;
    x = gpuArray.rand(1,N);
    numIterations = 1000;
    for n=1:numIterations
        x = r.*x.*(1-x);

Use a for loop to loop over simulations, and use parfeval to run them asynchronously on a worker in the parallel pool. myParallelFcn uses GPU-enabled functions on gpuArrays, so they run on the GPU of the worker. Because parfeval performs the computations asynchronously, it does not block MATLAB and you can continue working while computations happen.

for i=1:numSimulations
    f(i) = parfeval(@myParallelFcn,1,r);

To collect the results from parfeval when they are ready, you can use fetchOutputs (FevalFuture) or fetchNext on the future objects. Also, you can use afterEach or afterAll to invoke functions on the results automatically when they are ready. For example, to plot the result of each simulation immediately after it completes, use afterEach on the future objects. Each color represents a different simulation.

hold on
afterEach(f,@(x) plot(r,x,'.'),0);

Use Multiple GPUs in a Cluster

If you have access to a cluster with multiple GPUs, then you can scale up your computations. Use the parpool function to start a parallel pool on the cluster. When you do so, parallel features, such as parfor loops or parfeval, run on the cluster workers. If your computations use GPU-enabled functions on gpuArrays, then those functions run on the GPU of the cluster worker. To learn more about running parallel features on a cluster, see Scale up from Desktop to Cluster.

See Also

| | | | | |

Related Examples

More About

External Websites