CORDIC-based Architecture for Powering Computation in Fixed-Point\n Arithmetic

2016/05/10 by Nia Simmonds, Joshua Mack, Simmonds, Nia +5
Computer Science · Engineering · Physics and Astronomy · #Digital Filter Design and Implementation #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Low-power high-performance VLSI design #Model Reduction and Neural Networks #Numerical Methods and Algorithms

paper · pdf · doi:10.48550/arxiv.1605.03229

openalex publication_date 2016/05/10 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28

Abstract

We present a fixed point architecture (source VHDL code is provided) for\npowering computation. The fully customized architecture, based on the expanded\nhyperbolic CORDIC algorithm, allows for design space exploration to establish\ntrade-offs among design parameters (numerical format, number of iterations),\nexecution time, resource usage and accuracy. We also generate Pareto-optimal\nrealizations in the resource-accuracy space: this approach can produce optimal\nhardware realizations that simultaneously satisfy resource and accuracy\nrequirements.\n

Related

• CORDIC Is All You Need
• FPGA implementation of short critical path CORDIC-based approximation of the eight-point DCT
• Error Analysis of CORDIC Processor with FPGA Implementation
• A study and comparison of COordinate Rotation DIgital Computer (CORDIC) architectures
• Generalized Hyperbolic CORDIC and Its Logarithmic and Exponential Computation With Arbitrary Fixed Base