Solving x = A\b for large sparse matrices

Hi,

I am currently attempting to solve the problem x = A\b for large sparse matrices A. I am able to obtain a solution and my matrices are well conditioned. The problem I am having is that the matrices are of sizes up to 1 000 000 * 1 000 000. Solving this equation for different A matrices several times is very time consuming.

I was therefore wondering if there was a way to parallellize this operation in order to reduce the computation time? Currently matlab only uses 1 out of my 12 processers to solve the problem.

Any improvement would be helpful

thanks in advance!