First, load the CUDALink application:

This performs the dot product:

This performs matrix-vector multiplication:

Contents of CUDAVector:

Multiply a CUDA matrix and a CUDA sparse vector

Contents of CUDAVector:

Multiply two CUDA matrices, result is a CUDA matrix:

Contents of CUDAMatrix:

Multiply two CUDA sparse matrices, result is a CUDA sparse matrix:

Contents of CUDASparseMatrix:

Multiply CUDA sparse matrix with CUDA matrix, result is a CUDA matrix:

Contents of CUDAMatrix:

For large vectors, performing operations on the GPU can be quicker.

This creates a large CUDA vector of type "Real64":

This performs dot product on the GPU and measures timing:

This performs dot product on the CPU and measures timing:

Performing dot product on the GPU is faster:

Performance can be improved by using CUDA vector of type "Real32":

Performing dot product of CUDA vector of "Real32" on GPU is even faster:

CUDADot works with vectors in list form:

CUDADot supports CUDAMemory:

This multiplies the two input memories together :

Memory is retrieved using CUDAMemoryGet:

Memory must be freed with CUDAMemoryUnload :