Floating-Point CORDIC for Matrix Computations

Abstract

The CORDIC algorithms provide a VLSI hardware technique for computing the inverse tangents and vector rotations needed by many matrix decomposition algorithms. Although normally stated for fixed-point arithmetic, the CORDIC algorithms may be performed in floating-point arithmetic. A novel simplified CORDIC processor composed of floating-point data paths with a fixed-point angle calculation is proposed. This hybrid processor allows sufficient accuracy for matrix computations.