Work with Sparse Arrays on a GPU

Create Sparse GPU Arrays

You can create a sparse gpuArray either by calling sparse with a gpuArray input, or by calling gpuArray with a sparse input.

Create a sparse gpuArray, G.

X = [0 1 0 0 0; 0 0 0 0 1]

X = 2×5
     0     1     0     0     0
     0     0     0     0     1

S = sparse(X)

S = 2×5 sparse double matrix (2 nonzeros)
   (1,2)        1
   (2,5)        1

G = gpuArray(S);

You can also create a sparse gpuArray directly using the following functions. For more information, see the Extended Capabilities section of the function reference page.

Indexing Sparse GPU Arrays

Sparse GPU arrays support referencing contiguous submatrices only, that is, rectangular blocks of adjacent elements. (since R2026b)

To access submatrix of a sparse gpuArray, index into the array using consecutive row and column indices. For example, access the central 3-by-3 submatrix of a 10-by-10 sparse gpuArray.

A = gpuArray.speye(10);
A(4:6,4:6)

  3×3 sparse gpuArray double matrix (3 nonzeros)

   (1,1)        1
   (2,2)        1
   (3,3)        1

full(A(4:6,4:6))

     1     0     0
     0     1     0
     0     0     1

Before R2026b: Sparse GPU arrays only support referencing whole rows or columns by index. For example, to access the fifth row of sparse matrix A, call A(5,:) or A(5,1:end).

To locate nonzero elements of a sparse GPU array, use the find function.

[row,col,val] = find(A);
[row,col,val]

     1     1     1
     2     2     1
     3     3     1
     4     4     1
     5     5     1
     6     6     1
     7     7     1
     8     8     1
     9     9     1
    10    10     1

To replace values or add new nonzero elements, you must construct a new sparse gpuArray, as assigning values to sparse GPU arrays by index is not supported. For example, use the outputs of the find function replace the fifth nonzero element, add a new nonzero element at position (1,7), and construct a new sparse gpuArray.

val(5) = 0;

val(end+1) = 1;
row(end+1) = 1;
col(end+1) = 7;

A = sparse(row,col,val);

Adding or removing elements from a sparse array affects the sparsity pattern, which changes the size of the array in memory. To plot the new sparsity pattern, use the spy function.

spy(A)

To see the size of the array in memory, use the whos function.

whos A

  Name       Size            Bytes  Class       Attributes

  A         10x10              176  gpuArray    sparse    

Functions That Support Sparse GPU Arrays

These tables lists functions that support sparse gpuArray input. For limitations and usage notes for specific functions, see the Extended Capabilities section of the function reference page.