NVIDIA interview question

How to solve a matrix multiplication high efficiently without shared memory in GPU.

Interview Answer

Anonymous

8 Sept 2016

// y = Ax // A : m by n matrix, x : n elements vector // y : m elements vector void my(float *y, float *A, float *x, int m , int n) { for ( int i = 0; i < m; i++) { y[i] = 0; for ( int j = 0; j < n ; j++) y[i] += A[i * n +j] * x[j] } }

1