existsOnGPU

R2026b

Determine if gpuArray or CUDAKernel is available on GPU

Syntax

tf = existsOnGPU(data)

Description

tf = existsOnGPU(data) returns 1 (true) if the gpuArray or CUDAKernel object data is present on the GPU and available from your MATLAB^® session. Otherwise, it returns 0 (false).

If data is not present on the GPU, data is no longer valid and cannot be used. Such arrays and kernels are invalidated when the GPU device has been reset with any of the following:

• reset(dev), where dev is the current gpuDevice.

• gpuDevice(ind), where ind is an index in the range 1 to gpuDeviceCount.

• gpuDevice([]), with an empty argument (as opposed to no argument).

Examples

Query Existence of gpuArray

Create a gpuArray, then query its existence.

M = gpuArray(magic(4));
existsOnGPU(M)

ans = logical
   1

Reset the GPU device, then query the existence of the gpuArray again.

dev = gpuDevice;
reset(dev)
existsOnGPU(M)

ans = logical
   0

Try to display the gpuArray.

disp(M)

    Data no longer exists on the GPU.

Clear the gpuArray from the workspace.

clear M

Input Arguments

data — GPU data

gpuArray | parallel.gpu.CUDAKernel

GPU data, specified as a gpuArray or a parallel.gpu.CUDAKernel object.

Extended Capabilities

Thread-Based Environment

Run code in the background using MATLAB® backgroundPool or accelerate code with Parallel Computing Toolbox™ ThreadPool.

The existsOnGPU function fully supports thread-based environments. For more information, see Run MATLAB Functions in Thread-Based Environment.

GPU Arrays

Accelerate code by running on a graphics processing unit (GPU) using Parallel Computing Toolbox™.

The existsOnGPU function fully supports GPU arrays. To run the function on a GPU, specify the input data as a gpuArray. For more information, see Run MATLAB Functions on a GPU.

Version History

Introduced in R2012a