Designing energy-efficient approximate adders using parallel genetic algorithms

Approximate computing involves selectively reducing the number of transistors in a circuit to improve energy savings. Energy savings may be achieved at the cost of reduced accuracy for signal processing applications whereby constituent adder and multiplier circuits need not generate a precise output...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:SoutheastCon 2015 s. 1 - 7
Hlavní autoři: Naseer, Adnan Aquib, Ashraf, Rizwan A., Dechev, Damian, DeMara, Ronald F.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.04.2015
Témata:
adder
Adders
approximate computing
Approximation methods
delay
error distance
Genetic algorithms
inexact arithmetic units
low power
Mathematical model
Mirrors
parallel genetic algorithm
parallelism
power consumption
power reduction
process variation
Sociology
Statistics
variable accuracy
ISSN:1091-0050
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Approximate computing involves selectively reducing the number of transistors in a circuit to improve energy savings. Energy savings may be achieved at the cost of reduced accuracy for signal processing applications whereby constituent adder and multiplier circuits need not generate a precise output. Since the performance versus energy savings landscape is complex, we investigate the acceleration of the design of approximate adders using parallelized Genetic Algorithms (GAs). The fitness evaluation of each approximate adder is explored by the GA in a non-sequential fashion to automatically generate novel approximate designs within specified performance thresholds. This paper advances methods of parallelizing GAs and implements a new parallel GA approach for approximate multi-bit adder design. A speedup of approximately 1.6-fold is achieved using a quad-core Intel processor and results indicate that the proposed GA is able to find adders which consume 63:8% less energy than accurate adders.
ISSN:1091-0050
DOI:10.1109/SECON.2015.7132970