I'm working on Parallel Programming and as part of a project (this is not homework) I'm trying to implement an iterative form of Strassens Algorithm using loops.
I understand how the recursive formulation works (credit to this and this), however I haven't found any resources (blogs or scientific literature) about an iterative formulation of the algorithm. I wanted to know if there's anyone here willing to share resources or implemented their own iterative version of the algorithm.
Thank you.
Try to parallelize the following $8\times8\times8$ algorithm which is equivalent to a three-layer recursion of Strassen's $2\times2\times2$ algorithm: