Germany
Opinion
Highly-Flexible and Optimized, Area: and Energy-Efficient Matrix Decomposition Accelerators based on Givens Algorithms and CORDIC Rotations
Author(s): Upasna Vishnoi and Tobias G NollUpasna Vishnoi and Tobias G Noll
Matrix decomposition accelerators are attractive SoC components for many applications with a wide range of specifications. In this work, a new family of highly area- and energy-efficient modular matrix decomposition architectures based on the givens-algorithms and CORDIC rotations are elaborated. Accurate algebraic cost models enable for early cost estimation as well as for cross-level optimization over architecture, micro-architecture and circuit-level using a rich set of parameters. Quantitative results for an exemplary QRD application, implemented in 40-nm CMOS technology, are presented... Read More»
DOI:
10.4172/2332-0796.1000231
Journal of Electrical & Electronic Systems received 733 citations as per Google Scholar report