建立数组GPU
AgpuArray
in MATLAB®represents an array that is stored on the GPU. For a complete list of functions that support arrays on the GPU, seeRun MATLAB Functions on a GPU.
Create GPU Arrays from Existing Data
Send Arrays to the GPU
GPU arrays can be created by transferring existing arrays from the workspace to the GPU. Use thegpuArray
function to transfer an array from MATLAB to the GPU:
N = 6; M = magic(N); G = gpuArray(M);
You can accomplish this in a single line of code:
G = gpuArray(magic(N));
G
is now a MATLAB gpuArray object that represents the magic square stored on the GPU. The input provided togpuArray
must be numeric (for example:single
,double
,int8
, etc.) or logical. (See alsoWork with Complex Numbers on a GPU.)
Retrieve Arrays from the GPU
Use thegather
function to retrieve arrays from the GPU to the MATLAB workspace. This takes an array that is on the GPU represented by a gpuArray object, and transfers it to the MATLAB workspace as a regular MATLAB array. You can useisequal
to verify that you get the correct values back:
G = gpuArray(ones(100,'uint32')); D = gather(G); OK = isequal(D,ones(100,'uint32'))
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 supportgpuArray
.
Example: Transfer Array to the GPU
Create a 1000-by-1000 random matrix in MATLAB, and then transfer it to the GPU:
X = rand(1000); G = gpuArray(X);
Example: Transfer Array of a Specified Precision
Create a matrix of double-precision random values in MATLAB, and then transfer the matrix as single-precision from MATLAB to the GPU:
X = rand(1000); G = gpuArray(single(X));
Create GPU Arrays Directly
A number of functions allow you to directly construct arrays on the GPU by specifying the'gpuArray'
type as an input argument. These functions require only array size and data class information, so they can construct an array without having to transfer any elements from the MATLAB workspace. For more information, seegpuArray
.
Example: Construct an Identity Matrix on the GPU
To create a 1024-by-1024 identity matrix of typeint32
on the GPU, type
II = eye(1024,'int32','gpuArray'); size(II)
1024 1024
With one numerical argument, you create a 2-dimensional matrix.
Example: Construct a Multidimensional Array on the GPU
To create a 3-dimensional array of ones with data classdouble
on the GPU, type
G = ones(100,100,50,'gpuArray'); size(G)
100 100 50
classUnderlying(G)
double
The default class of the data isdouble
, so you do not have to specify it.
Example: Construct a Vector on the GPU
To create a 8192-element column vector of zeros on the GPU, type
Z = zeros(8192,1,'gpuArray'); size(Z)
8192 1
For a column vector, the size of the second dimension is 1.
Examine gpuArray Characteristics
There are several functions available for examining the characteristics of a gpuArray object:
Function | Description |
---|---|
classUnderlying |
Class of the underlying data in the array |
existsOnGPU |
Indication if array exists on the GPU and is accessible |
isreal |
Indication if array data is real |
isaUnderlying |
Determine if tall array data is of specified class, such as |
isequal |
Determine if two or more arrays are equal |
isnumeric |
Determine if an array is of a numeric data type |
issparse |
Determine if an array is sparse |
length |
Length of vector or largest array dimension |
ndims |
Number of dimensions in the array |
size |
Size of array dimensions |
For example, to examine the size of the gpuArray objectG
, type:
G = rand(100,'gpuArray'); s = size(G)
100 100
Save and Load gpuArrays
You can save gpuArray variables as MAT files for later use. When you save a gpuArray from the MATLAB workspace, the data is saved as a gpuArray variable in a MAT file. When you load a MAT file containing a gpuArray variable, the data is loaded onto the GPU as a gpuArray.
Note
你可以加载MAT files containing gpuArray data as in-memory arrays when a GPU is not available. A gpuArray loaded without a GPU is limited and you cannot use it for computations. To use a gpuArray loaded without a GPU, retrieve the contents usinggather
.
For more information about how to save and load variables in the MATLAB workspace, seeSave and Load Workspace Variables(MATLAB).