Search research articles

Search research articles

Related Experiment Videos

Inexactness and a future of computing.

Krishna V Palem¹

¹Department of Computer Science and ECE, Rice University, 6100 Main Street, Houston, TX 77005, USA palem@rice.edu.

Philosophical Transactions. Series A, Mathematical, Physical, and Engineering Sciences

|May 21, 2014

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Domain-driven models yield better predictions at lower cost than reservoir computers in Lorenz systems.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2021

Same author

On the use of inexact, pruned hardware in atmospheric modelling.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2014

Same author

High-performance and low-power rewritable SiOx 1 kbit one diode-one resistor crossbar memory array.

Advanced materials (Deerfield Beach, Fla.)·2013

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Computing systems face energy constraints, driving interest in approximate computing. This approach sacrifices exactness for significant efficiency gains, particularly in hardware design.

Area of Science:

Computer Engineering
Computational Science

Background:

Growing energy consumption and scaling limitations challenge traditional computing systems.
There is an increasing consideration of trading accuracy for improved performance and efficiency.

Purpose of the Study:

To provide a perspective on the progress and potential of inexact or approximate computing systems.
To highlight the opportunities for research and innovation in designing efficient, albeit inexact, computing architectures.

Main Methods:

Exploration of the philosophy and design principles of approximate computing.
Case study of co-designing floating-point arithmetic units for stochastic climate models.

Main Results:

Demonstrated potential for extreme efficiencies by embracing inexactness in computing.

Keywords:

approximation algorithms heuristics inexact computing information theory probabilistic CMOS randomized algorithms

Related Experiment Videos

Successful tailoring of hardware components (floating-point units) for specific application needs (climate modeling).

Conclusions:

Inexact computing presents a promising domain for future research and innovation.
System co-design, integrating application and technology features, is crucial for advancing approximate computing, requiring closer software and hardware collaboration.