Versatile Direct and Transpose Matrix Multiplication with Chained Operations: An Optimized Architecture Using Circulant Matrices

With growing demands in real-time control, classification or prediction, algorithms become more complex while low power and small size devices are required. Matrix multiplication (direct or transpose) is common for such computation algorithms. In numerous algorithms, it is also required to perform matrix multiplication repeatedly, where the result of a multiplication is further multiplied again. This work describes a versatile computation procedure and architecture: one of the matrices is stored in internal memory in its circulant form, then, a sequence of direct or transpose multiplications can be performed without timing penalty. The architecture proposes a RAM-ALU block for each matrix c…