Which is a quick way to parallelize element-wise m

问题:

I use a NumPy function einsum to perform element-wise multiplication of two 2D NumPy arrays and sum.

np.einsum('ij,ij',A,B)

Each of these array A, B are sized around 10000 x 10000. I notice this operation is the bottleneck in my code taking up ~85 % of the processing time. How do I quickly parallelize this operation?