Relative Performance Speedup.

<p>Figure shows the relative performance improvement of our GPU model with respect to a similar Python implementation using numpy's BLAS implementation. Relative performance refers to the percentage increase in performance by considering the absolute timings of the two implementations over an entire simulation. The horizontal axis indicates <b>Ind_total</b>, that is the total number of independent trials which in this case represents independent animats (rather than animats in different configurations). A: Represents the case for our model without lateral connections. B: Represents a case with lateral connections which is the same however it includes an additional code execution to perform simulation of the lateral spike propagation.