Hundreds of functions in MATLAB® and other toolboxes run automatically on a GPU if you supply a
A = gpuArray([1 0 1; -1 -2 0; 0 1 -1]); e = eig(A);
Whenever you call any of these functions with at least one gpuArray as a data
input argument, the function executes on the GPU. The function generates a gpuArray
as the result, unless returning MATLAB data is more appropriate (for example,
can mix inputs using both gpuArray and MATLAB arrays in the same function call. To learn more about when a function
runs on GPU or CPU, see Special Conditions for gpuArray Inputs. GPU-enabled
functions include the discrete Fourier transform (
mtimes), left matrix division
mldivide), and hundreds of others. For more information, see
Check GPU-Supported Functions.
If a MATLAB function has support for gpuArrays, you can consult additional GPU usage information on its function page. See GPU Arrays in the Extended Capabilities section at the end of the function page.
For a filtered list of MATLAB that support GPU arrays, see Function List (GPU-arrays).
Several MATLAB toolboxes include functions with built-in GPU support. To view lists of all functions in these toolboxes that support gpuArrays, use the links in the following table. Functions in the lists with warning indicators have limitations or usage notes specific to running the function on a GPU. You can check the usage notes and limitations in the Extended Capabilities section of the function reference page. For information about updates to individual GPU-enabled functions, see the release notes.
|Toolbox name||List of functions with gpuArray support|
|MATLAB||Functions with gpuArray support|
|Statistics and Machine Learning Toolbox™||Functions with gpuArray support|
|Image Processing Toolbox™||Functions with gpuArray support|
|Deep Learning Toolbox™||
*(see also Deep Learning with GPUs)
|Computer Vision Toolbox™||Functions with gpuArray support|
|Communications Toolbox™||Functions with gpuArray support|
|Signal Processing Toolbox™||Functions with gpuArray support|
|Audio Toolbox™||Functions with gpuArray support|
|Wavelet Toolbox™||Functions with gpuArray support|
|Curve Fitting Toolbox™||Functions with gpuArray support|
You can browse GPU-supported functions from all MathWorks® products at the following link: GPU-supported functions. Alternatively, you can filter by product. On the Help bar, click Functions. In the function list, browse the left pane to select a product, for example, MATLAB. At the bottom of the left pane, select GPU Arrays. If you select a product that does not have GPU-enabled functions, then the GPU Arrays filter is not available.
For many functions in Deep Learning Toolbox, GPU support is automatic if you have a suitable GPU and Parallel Computing Toolbox™. You do not need to convert your data to gpuArray. The following is a non-exhaustive list of functions that, by default, run on the GPU if available.
For more information about automatic GPU-support in Deep Learning Toolbox, see Deep Learning with Big Data on GPUs and in Parallel (Deep Learning Toolbox).
For advanced networks and workflows that use networks defined as
dlnetwork objects or model
functions, convert your data to gpuArray. Use functions with gpuArray support to
run custom training loops or prediction on the GPU.
If you have a GPU, then MATLAB automatically uses it for GPU computations. You can check your GPU
gpuDevice function. If you have
multiple GPUs, then you can use
gpuDevice to select one of them,
or use multiple GPUs with a parallel pool. For an example, see Identify and Select a GPU and Use Multiple GPUs in a Parallel Pool. To check if
your GPU is supported, see GPU Support by Release.
For deep learning, MATLAB provides automatic parallel support for multiple GPUs. See Deep Learning with MATLAB on Multiple GPUs (Deep Learning Toolbox).
This example shows how to use GPU-enabled MATLAB functions to operate with gpuArrays. You can check the properties of your GPU using the
ans = CUDADevice with properties: Name: 'GeForce GTX 1080' Index: 1 ComputeCapability: '6.1' SupportsDouble: 1 DriverVersion: 10.1000 ToolkitVersion: 10.1000 MaxThreadsPerBlock: 1024 MaxShmemPerBlock: 49152 MaxThreadBlockSize: [1024 1024 64] MaxGridSize: [2.1475e+09 65535 65535] SIMDWidth: 32 TotalMemory: 8.5899e+09 AvailableMemory: 6.9012e+09 MultiprocessorCount: 20 ClockRateKHz: 1733500 ComputeMode: 'Default' GPUOverlapsTransfers: 1 KernelExecutionTimeout: 1 CanMapHostMemory: 1 DeviceSupported: 1 DeviceSelected: 1
Create a row vector that repeats values from -15 to 15. To transfer it to the GPU and create a gpuArray, use the
X = [-15:15 0 -15:15 0 -15:15]; gpuX = gpuArray(X); whos gpuX
Name Size Bytes Class Attributes gpuX 1x95 4 gpuArray
To operate with gpuArrays, use any GPU-enabled MATLAB function. MATLAB automatically runs calculations on the GPU. For more information, see Run MATLAB Functions on a GPU. For example, use a combination of
gpuE = expm(diag(gpuX,-1)) * expm(diag(gpuX,1)); gpuM = mod(round(abs(gpuE)),2); gpuF = gpuM + fliplr(gpuM);
Plot the results.
If you need to transfer the data back from the GPU, use
gather. Gathering back to the CPU can be costly, and is generally not necessary unless you need to use your result with functions that do not support gpuArray.
result = gather(gpuF); whos result
Name Size Bytes Class Attributes result 96x96 73728 double
In general there can be differences in the results if you run the code on the CPU, due to numerical precision and algorithmic differences between GPU and CPU. Answers on CPU and GPU are both equally valid floating point approximations to the true analytical result, having been subjected to different roundoff during computation. In this example, the results are integers and
round eliminates the roundoff errors.
This example shows how to sharpen an image using gpuArrays and GPU-enabled functions.
Read the image, and send it to the GPU using the
image = gpuArray(imread('peppers.png'));
Convert the image to doubles, and apply convolutions to obtain the gradient image. Then, using the gradient image, sharpen the image by a factor of
dimage = im2double(image); gradient = convn(dimage,ones(3)./9,'same') - convn(dimage,ones(5)./25,'same'); amount = 5; sharpened = dimage + amount.*gradient;
Resize, plot and compare the original and sharpened images.
imshow(imresize([dimage, sharpened],0.7)); title('Original image (left) vs sharpened image (right)');
This example shows how to use GPU-enabled MATLAB functions to compute a well-known mathematical construction: the Mandelbrot set. Check your GPU using the
Define the parameters. The Mandelbrot algorithm iterates over a grid of real and imaginary parts. The following code defines the number of iterations, grid size, and grid limits.
maxIterations = 500; gridSize = 1000; xlim = [-0.748766713922161, -0.748766707771757]; ylim = [ 0.123640844894862, 0.123640851045266];
You can use the
gpuArray function to transfer data to the GPU and create a
gpuArray, or you can create an array directly on the GPU.
gpuArray provides GPU versions of many functions that you can use to create data arrays, such as
linspace. For more information, see Create GPU Arrays Directly.
x = gpuArray.linspace(xlim(1),xlim(2),gridSize); y = gpuArray.linspace(ylim(1),ylim(2),gridSize); whos x y
Name Size Bytes Class Attributes x 1x1000 4 gpuArray y 1x1000 4 gpuArray
Many MATLAB functions support gpuArrays. When you supply a gpuArray argument to any GPU-enabled function, the function runs automatically on the GPU. For more information, see Run MATLAB Functions on a GPU. Create a complex grid for the algorithm, and create the array
count for the results. To create this array directly on the GPU, use the
ones function, and specify
[xGrid,yGrid] = meshgrid(x,y); z0 = complex(xGrid,yGrid); count = ones(size(z0),'gpuArray');
The following code implements the Mandelbrot algorithm using GPU-enabled functions. Because the code uses gpuArrays, the calculations happen on the GPU.
z = z0; for n = 0:maxIterations z = z.*z + z0; inside = abs(z) <= 2; count = count + inside; end count = log(count);
When computations are done, plot the results.
imagesc(x,y,count) colormap([jet();flipud(jet());0 0 0]); axis off
The following functions support sparse gpuArrays.
abs angle bicg bicgstab ceil cgs classUnderlying conj ctranspose deg2rad diag end expm1 find fix floor full gmres gpuArray.speye imag isaUnderlying isdiag isempty
isequal isequaln isfloat isinteger islogical isnumeric isreal issparse istril istriu length log1p lsqr minus mtimes ndims nextpow2 nnz nonzeros norm numel nzmax pcg
plus qmr rad2deg real realsqrt round sign size sparse spfun spones sprandsym sqrt sum tfqmr times (.*) trace transpose tril triu uminus uplus
x = [0 1 0 0 0; 0 0 0 0 1]
0 1 0 0 0 0 0 0 0 1
s = sparse(x)
(1,2) 1 (2,5) 1
g = gpuArray(s); % g is a sparse gpuArray gt = transpose(g); % gt is a sparse gpuArray f = full(gt) % f is a full gpuArray
0 0 1 0 0 0 0 0 0 1
Sparse gpuArrays do not support indexing. Instead, use
find to locate nonzero elements of the array and their row and
column indices. Then, replace the values you want and construct a new sparse
If the output of a function running on the GPU could potentially be complex, you
must explicitly specify its input arguments as complex. This applies to
gpuArray or to functions called in code run by
For example, if creating a gpuArray that might have negative elements, use
G = gpuArray(complex(p)), then you can successfully execute
Or, within a function passed to
x is a vector of real numbers, and some elements have
sqrt(x) generates an error; instead you should
If the result is a gpuArray of complex data and all the imaginary parts are zero,
these parts are retained and the data remains complex. This could have an impact
isreal, and so on.
The following table lists the functions that might return complex data, along with the input range over which the output remains real.
|Function||Input Range for Real Output|
GPU-enabled functions run on the GPU only when the data is on the GPU. For example, the following code runs on GPU because the data, the first input, is on the GPU:
MAGMA is a library of linear algebra routines that take advantage of GPU acceleration. Linear algebra functions implemented for gpuArrays in Parallel Computing Toolbox leverage MAGMA to achieve high performance and accuracy.