ACME: An Energy-Efficient Approximate Bus Encoding for I<sup>2</sup>C

Xie, Chen; Pagliari, Daniele Jahier; Calimera, Andrea; Macii, Enrico; Poncino, Massimo

doi:10.1109/islped52811.2021.9502495

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cross-coupling between interconnects contributes to power dissipation and to compute the interconnect power it is required to consider several factors. Xie et al [25] presented a technique for power reducing in network on chip switching activity is reduced by examining the handover transition and coupling between the links to reduce the power consumption and cross coupling. using.…”

Section: Introductionmentioning

confidence: 99%

Reconfigurable data encoding schemes for on-chip interconnect power reduction in deep submicron technology

Shavali

Maripareddy

Reddy

2022

IJEECS

View full text Add to dashboard Cite

With technology scaling, size of both transistor and interconnects are reduced. Power dissipation due to dynamic switching is high in the interconnects. Suitable encoding schemes that reduces transition between data bits are used to minimize interconnect power dissipation. In this paper transition between data bits is minimized based on three novel data encoding schemes identifying the novel methods estimates bit transitions in a pair of data bits and performs half inversion or full inversion on one byte of data thus reducing the switching activity by 50%. The encoder and decoder for the three encoding schemes are modelled in verilog hardware description language (HDL) and implemented using application specefic integrates circuit (ASIC) flow targeting 32 nm. Technology over all power dissipation of encoding scheme is 1.04 μW in addition over head area of 210 cells with encoding delay of 340 ps. Encoder decoder register transfer logic (RTL) code is implemented and the total area required is 34980 units. The data encoding and decoding schemes are suitable for low power applications.

show abstract

Section: Introductionmentioning

confidence: 99%