Changes

To optimize our code, we used shared memory inside the kernel. This reduced On average, the run time for each all 7 different problem sizesizes was reduced by approximately 216 milliseconds. Below is a picture of the optimized kernel: [[File:QuickerKernel.PNG]]  Below is a graph that illustrates the time saved on all 7 different problem sizes with the optimized kernel: [[File:OptimizationGraph.PNG]]