Search research 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

Search research articles

Related Experiment Videos

Changing computing paradigms towards power efficiency.

Pavel Klavík¹, A Cristiano I Malossi², Costas Bekas³

¹Faculty of Mathematics and Physics, Computer Science Institute, Charles University in Prague, Malostranské nám. 25, 118 00 Prague, Czech Republic.

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

Advancing biomolecular simulation through exascale HPC, AI and quantum computing.

Current opinion in structural biology·2024

Same author

Predicting retrosynthetic pathways using transformer-based models and a hyper-graph exploration strategy.

Chemical science·2021

Same author

Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction.

ACS central science·2019

Same author

"Found in Translation": predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models.

Chemical science·2018

Same author

Reaction Dynamics of ATP Hydrolysis in Actin Determined by ab Initio Molecular Dynamics Simulations.

Journal of chemical theory and computation·2015

Same author

Characterizing and Understanding Divalent Adsorbates on Carbon Nanotubes with Ab Initio and Classical Approaches: Size, Chirality, and Coverage Effects.

Journal of chemical theory and computation·2015

Same journal

Inverse FIP effect plasma in the solar atmosphere: a synthesis of current understanding and new insights from AR 11967.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026

Same journal

Signs of sulfur fractionation under high magnetic field strength.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026

Same journal

First ionization potential fractionation of sulfur observed with spectral imaging of the coronal environment.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026

Same journal

Chromospheric dynamics and turbulence regulate the solar FIP effect.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026

Same journal

Exploring the link between wave activity in the photospheric velocity driver and the FIP bias in the solar corona.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026

Same journal

Radiative hydrodynamic simulations of first ionization potential fractionation in solar flares.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026

See all related articles

This study introduces a power-efficient computing approach using mixed-precision arithmetic for solving linear equations. Tools for fine-grain power profiling and analysis of post-FLOPS/W metrics are developed to optimize energy consumption in data-centric workloads.

Area of Science:

Computer Science
Computational Science

Background:

Growing importance of power awareness in computing, from high-performance computing to data-centric workloads.
Need for energy-efficient solutions in scientific and engineering applications, data analytics, statistics, and machine learning.

Purpose of the Study:

To develop a power-efficient computing paradigm combining low- and high-precision arithmetic.
To showcase these ideas using the kernel for solving systems of linear equations.
To introduce tools for fine-grain power profiling of applications.

Main Methods:

Development of tools for seamless, fine-grain power profiling of applications.
Implementation of a mixed-precision arithmetic approach for solving systems of linear equations.
Verification and analysis of post-FLOPS/W metrics for power/energy profiling.

Keywords:

Cholesky method conjugate gradient method energy-aware computing performance metrics power consumption

Related Experiment Videos

Main Results:

Demonstration of a power-efficient computing paradigm through mixed-precision arithmetic.
Successful application to the widely used kernel for solving systems of linear equations.
Validation of post-FLOPS/W metrics for enhanced power/energy insights.

Conclusions:

Mixed-precision arithmetic offers a viable path towards power-efficient computing.
Fine-grain power profiling tools are crucial for optimizing energy consumption.
Post-FLOPS/W metrics provide valuable insights into application power/energy profiles.