Run MATLAB Functions on a GPU
You can speed up your code by running MATLAB® functions a GPU. GPU computing in MATLAB requires Parallel Computing Toolbox™.
MATLAB Functions with
Many functions in MATLAB and other toolboxes run automatically on a GPU if you supply a
gpuArray data argument. A
gpuArray in MATLAB represents an array that is stored on the
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 numeric data to the local workspace is more appropriate (for example,
size). You can mix inputs using both
gpuArray data and arrays stored in host memory in the same
gpuArray-enabled functions include the discrete
Fourier transform (
fft), matrix multiplication
mtimes), left matrix division (
and hundreds of others.
GPU-enabled functions run on the GPU only when the input data is on the GPU.
The data type of parameter arguments such as dimensions or indices do not affect
where the function is run. For example, the
sum function in
this code runs on the GPU because the data, the first input, is on the
A = rand(10); d = 2; sum(gpuArray(A),d);
sumfunction in this code does not run on GPU because the data, the first input, is not on the GPU.
A = rand(10); d = 2; sum(A,gpuArray(d));
Work with Complex Numbers on a GPU
If the output of a function running on a GPU could potentially be complex, you must explicitly specify its input arguments as complex. For more information, see Work with Complex Numbers on a GPU.
Work with Sparse Arrays on a GPU
sparse function can be used to
gpuArray objects. Many MATLAB functions support sparse
gpuArray objects. For
more information, see Work with Sparse Arrays on a GPU.
Several MATLAB toolboxes include functions with
gpuArray support. To view
lists of all functions in these toolboxes that support
gpuArray objects, use
the links in the following table. Functions in the lists with information 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
gpuArray-enabled functions, see the
|Toolbox Name||List of Functions with ||GPU-Specific Documentation|
|Statistics and Machine Learning Toolbox™||Functions with
||Analyze and Model Data on GPU (Statistics and Machine Learning Toolbox)|
|Image Processing Toolbox™||Functions with
||GPU Computing (Image Processing Toolbox)|
|Deep Learning Toolbox™|
*(see also Deep Learning with GPUs)
Scale Up Deep Learning in Parallel, on GPUs, and in the Cloud (Deep Learning Toolbox)
Deep Learning with MATLAB on Multiple GPUs (Deep Learning Toolbox)
|Computer Vision Toolbox™||Functions with
||GPU Code Generation and Acceleration (Computer Vision Toolbox)|
|Communications Toolbox™||Functions with
||Code Generation and Acceleration Support (Communications Toolbox)|
|Signal Processing Toolbox™||Functions with
||Code Generation and GPU Support (Signal Processing Toolbox)|
|Audio Toolbox™||Functions with
||Code Generation and GPU Support (Audio Toolbox)|
|Wavelet Toolbox™||Functions with
||Code Generation and GPU Support (Wavelet Toolbox)|
|Curve Fitting Toolbox™||Functions with
For a list of functions with
gpuArray support in all
MathWorks® products, see
gpuArray-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
gpuArray-enabled functions, then the
GPU Arrays filter is not available.
Deep Learning with GPUs
For many functions in Deep Learning Toolbox, GPU support is automatic if you have a supported GPU and Parallel Computing Toolbox. You do not need to convert your data to
The following is a non-exhaustive list of functions that, by default, run on the GPU
trainNetwork(Deep Learning Toolbox)
predict(Deep Learning Toolbox)
predictAndUpdateState(Deep Learning Toolbox)
classify(Deep Learning Toolbox)
classifyAndUpdateState(Deep Learning Toolbox)
activations(Deep Learning Toolbox)
For more information about automatic GPU support in Deep Learning Toolbox, see Scale Up Deep Learning in Parallel, on GPUs, and in the Cloud (Deep Learning Toolbox).
For networks and workflows that use networks defined as
dlnetwork (Deep Learning Toolbox) objects or model
functions, convert your data to
gpuArray. Use functions with
support (Deep Learning Toolbox) to run custom training loops or inference on the GPU.
Check or Select a GPU
If you have a supported GPU, then MATLAB automatically uses it for GPU computation. If you have multiple GPUs,
then you can use
gpuDeviceTable to examine the properties of all GPUs detected in
your system. You can use
gpuDevice to select one of them,
or use multiple GPUs with a parallel pool. For more information, see Identify and Select a GPU Device and Run MATLAB Functions on Multiple GPUs. To check if
your GPU is supported, see GPU Computing Requirements.
Index Name ComputeCapability DeviceAvailable DeviceSelected _____ __________________ _________________ _______________ ______________ 1 "NVIDIA RTX A5000" "8.6" true true 2 "Quadro P620" "6.1" true false
Alternatively, you can determine how many GPU devices are available, inspect some of their properties, and select a device to use from the MATLAB® desktop. On the Home tab, in the Environment area, select Parallel > Select GPU Environment.
Use MATLAB Functions with the GPU
This example shows how to use
gpuArray-enabled MATLAB functions to operate with
gpuArray objects. You can check the properties of your GPU using the
ans = CUDADevice with properties: Name: 'Quadro P620' Index: 2 ComputeCapability: '6.1' SupportsDouble: 1 GraphicsDriverVersion: '511.79' DriverModel: 'WDDM' ToolkitVersion: 11.2000 MaxThreadsPerBlock: 1024 MaxShmemPerBlock: 49152 (49.15 KB) MaxThreadBlockSize: [1024 1024 64] MaxGridSize: [2.1475e+09 65535 65535] SIMDWidth: 32 TotalMemory: 2147287040 (2.15 GB) AvailableMemory: 1615209678 (1.62 GB) CachePolicy: 'balanced' MultiprocessorCount: 4 ClockRateKHz: 1354000 ComputeMode: 'Default' GPUOverlapsTransfers: 1 KernelExecutionTimeout: 1 CanMapHostMemory: 1 DeviceSupported: 1 DeviceAvailable: 1 DeviceSelected: 1
Create a row vector that repeats values from -15 to 15. To transfer it to the GPU and create a
gpuArray object, use the
X = [-15:15 0 -15:15 0 -15:15]; gpuX = gpuArray(X); whos gpuX
Name Size Bytes Class Attributes gpuX 1x95 760 gpuArray
To operate with
gpuArray objects, use any
gpuArray-enabled MATLAB function. MATLAB automatically runs calculations on the GPU. For more information, see Run MATLAB Functions on a GPU. For example, use
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. Transferring data 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
result = gather(gpuF); whos result
Name Size Bytes Class Attributes result 96x96 73728 double
In general, running code on the CPU and the GPU can produce different results due to numerical precision and algorithmic differences between the GPU and CPU. Answers from the CPU and GPU are both equally valid floating point approximations to the true analytical result, having been subjected to different roundoff behavior during computation. In this example, the results are integers and
round eliminates the roundoff errors.
Examples Using GPUs
Examples Running MATLAB Functions on GPUs
The following examples pass
gpuArray objects to supported
MATLAB functions, causing those functions to run on the GPU.
|Image Processing Toolbox||
|Deep Learning Toolbox||
|Signal Processing Toolbox||
Other Examples Using GPUs
The following examples make use of other automatic GPU support.
|Deep Learning Toolbox||
MAGMA is a library of linear
algebra routines that take advantage of GPU acceleration. Linear algebra functions
gpuArray objects in Parallel Computing Toolbox leverage MAGMA to achieve high performance and accuracy.
- Identify and Select a GPU Device
- Establish Arrays on a GPU
- Measure and Improve GPU Performance
- Sharpen an Image Using the GPU
- Compute the Mandelbrot Set using GPU-Enabled Functions