Area efficient architecture of Hyperbolic functions for high frequency applications

Saha, Anurup; Kumar, K Gaurav; Ghosh, Archisman; Naskar, Mrinal Kanti

doi:10.1109/ccube.2017.8394139

Cited by 3 publications

(26 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The methods developed by [3,32] and the proposed architecture in this study are three variants of the CORDIC algorithm. For an equal comparison, set N to 128 in [3,32].…”

Section: Fpga Implementation Analysismentioning

confidence: 99%

“…The methods developed by [3,32] and the proposed architecture in this study are three variants of the CORDIC algorithm. For an equal comparison, set N to 128 in [3,32]. Meanwhile, the study by [3] only focuses on hyperbolic functions with fixed-point inputs that are convergent to ROC of basic CORDIC.…”

Section: Fpga Implementation Analysismentioning

confidence: 99%

“…For an equal comparison, set N to 128 in [3,32]. Meanwhile, the study by [3] only focuses on hyperbolic functions with fixed-point inputs that are convergent to ROC of basic CORDIC. Hence, for equal comparison, only Module Cordic_core (without states PRE_B and PRE_A) of the proposed architecture is synthesized.…”

Section: Fpga Implementation Analysismentioning

confidence: 99%

“…Extensive literature exists describing hardware implementation of functions sinhx and coshx. Look-up table (LUT) approach, polynomial approximation technique, and coordinate rotation digital computer (CORDIC) algorithm are three typical computational implementation methods of sinhx and coshx functions [3]. In recent years, the stochastic computing method has also attracted much attention.…”

Section: Introductionmentioning

confidence: 99%

“…Only shift and addition operations are applied in this algorithm to compute functions sinhx and coshx. It takes much fewer registers and fewer clock cycles to calculate functions sinhx and coshx, making CORDIC the most suited algorithm for the realization of hardware [3,9,10]. However, the CORDIC algorithm calculates vector rotations in one of two modes: rotation and vectoring [11]; as such, it is well characterized as having the latency of a serial multiplication.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Low-Latency Hardware Implementation of High-Precision Hyperbolic Functions Sinhx and Coshx Based on Improved CORDIC Algorithm

Xia

Lin

et al. 2021

Electronics

View full text Add to dashboard Cite

CORDIC algorithm is used for low-cost hardware implementation to calculate transcendental functions. This paper proposes a low-latency high-precision architecture for the computation of hyperbolic functions sinhx and coshx based on an improved CORDIC algorithm, that is, the QH-CORDIC. The principle, structure, and range of convergence of the QH-CORDIC are discussed, and the hardware circuit architecture of functions sinhx and coshx using the QH-CORDIC is plotted in this paper. The proposed architecture is implemented using an FPGA device, showing that it has 75% and 50% latency overhead over the two latest prior works. In the synthesis using TSMC 65 nm standard cell library, ASIC implementation results show that the proposed architecture is also superior to the two latest prior works in terms of total time (latency × period), ATP (area × total time), total energy (power × total time), energy efficiency (total energy/efficient bits), and area efficiency (efficient bits/area/total time). Comparison of related works indicates that it is much more favorable for the proposed architecture to perform high-precision floating-point computations on functions sinhx and coshx than the LUT method, stochastic computing, and other CORDIC algorithms.

show abstract

“…The methods developed by [3,32] and the proposed architecture in this study are three variants of the CORDIC algorithm. For an equal comparison, set N to 128 in [3,32].…”

Section: Fpga Implementation Analysismentioning

confidence: 99%