DESIGN OF A PIPELINED CORDIC ARCHITECTURE WITH HIGH ACCURACY AND LOW LATENCY USING OPTIMISED ITERATION SCHEDULING
DOI:
https://doi.org/10.62643/Abstract
Trigonometric functions like sine and cosine are frequently calculated using the Coordinate Rotation Digital Computer (CORDIC) technique, which uses iterative shift-and-add operations. Because it may avoid general-purpose multipliers, it is appealing for digital signal processing. While simple pipelining can increase register and routing cost, conventional iterative CORDIC systems may need several sequential iterations, leading to excessive latency. In this paper, an optimised iteration scheduling pipelined CORDIC architecture with excellent accuracy and low latency is shown. The suggested approach initialises coordinate and angle variables, translates the input angle, determines its quadrant, and goes through several pipeline phases to perform rotation iterations. Iterations are grouped, assigned to stages, and critical-path balance is taken into account by an optimised scheduler. Using predetermined arctangent constants, each stage executes shift, addition/subtraction, and angle accumulation. Sine and cosine outputs are obtained by final coordinate adjustment. The architecture is designed for Xilinx Vivado 2026 functional verification and synthesis evaluation, and it is specified in Verilog HDL.1. Evaluation metrics include area, power, timing, latency, and numerical correctness. Prior to publishing, actual tool reports must be substituted with numerical comparison values, which are illustrative approximations rather than measured Vivado outcomes.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.













