Hands-On GPU-Accelerated Computer Vision with OpenCV and CUDA

Matrix multiplication

The second most important mathematical operation performed on a GPU using CUDA is matrix multiplication. It is a very complicated mathematical operation when the sizes of the matrices are very large. It should be kept in mind that for matrix multiplication, the number of columns in the first matrix should be equal to the number of rows in the second matrix. Matrix multiplication is not a cumulative operation. To avoid complexity, in this example, we are taking a square matrix of the same size. If you are familiar with the mathematics of matrix multiplication, then you may recall that a row in the first matrix will be multiplied with all the columns in the second matrix. This is repeated for all rows in the first matrix. ...