Design of Energy Efficient Arithmetic VLSI Circuits

Design of Energy Efficient Arithmetic  VLSI Circuits

P. Sumalatha1, Dr. T. Ragavandra Vishnu2

1M. Tech student, Department of ECE, Priyadarshini Institute of  Technology and Science for Women, Guntur

2Associate Professor, Department of ECE, Priyadarshini Institute of  Technology and Science for Women, Guntur

Abstract: Advanced electronics have become an integral part of human lives, from Smartphones in our pockets to the modern vehicles on the road and to the satellites that orbit the earth. Power consumption has become a major constraint in these applications, often employing data- intensive digital signal processing systems and architectures. While enormous transistor density at the nanoscale has been increased in the Very Large-Scale Integration (VLSI) multicore era comparable to Moore's law, improving the performance of computing systems has become extremely difficult. Sustaining technological advancements for such energy-constrained devices has paved the way for new areas in research.

“Approximate Computing (AC)” has become one of the most promising paradigms, a field that has gained significant attention in the quest for energy efficiency in recent years. AC algorithms are numerically approximate rather than accurate. Inherent error resilience is the primary source of motivation behind AC. Recent research demonstrates that error resilience is pervasive in cyber search, deep learning, multimedia, recognition and data mining. Arithmetic units are the fundamental building blocks in most of the data dominated applications at the micro- architectural level of abstraction. AC is optimal for power and area efficient arithmetic circuits.