changed the order in which nested loops are traversed. It now goes over all nsigmas for a single data point.
Done.

Now unrolling the loop in this one.
Unrolled 4 times. Working. Time consumed = 0.44ms average

Created threads for computing MSE and inner products. Both run in parallel now.
Software check Done. Working

Hardware Check -> done. Timing improvement from 0.57ms to 0.44ms. Expected better results. Find out the bottleneck. 

Adding Paper contents Kartik wrote, to the git repo.

Reference fixed, figure for statemachine added to paper.

Working on Filter and QRS detector.
Filter function file prepared.

Detector H/W implementation finished; tested and verified.