PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Opportunities

  • 📰 hackernoon
  • ⏱ Reading Time:
  • 24 sec. here
  • 2 min. at publisher
  • 📊 Quality Score:
  • News: 13%
  • Publisher: 51%

Singapore Singapore Headlines News

Singapore Singapore Latest News,Singapore Singapore Headlines

This paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.

This paper is available on arxiv under CC BY-NC-ND 4.0 DEED license. Authors: Minghao Yan, University of Wisconsin-Madison; Hongyi Wang, Carnegie Mellon University; Shivaram Venkataraman, myan@cs.wisc.edu. Table of Links Abstract & Introduction Motivation Opportunities Architecture Overview Proble Formulation: Two-Phase Tuning Modeling Workload Interference Experiments Conclusion & References A. Hardware Details B. Experimental Results C. Arithmetic Intensity D.

This indicates that the Results default memory frequency is higher than optimal for modern Deep Learning workloads. For heavy workloads such as Bert, memory tuning can account for the majority of the energy consumption reduction. This can be partially attributed to the memory-bound nature of Transformer-based models . Our result demonstrates that systems that aim to optimize energy use in neural network inference need to take memory frequency into account.

 

Thank you for your comment. Your comment will be published after being reviewed.
Please try again later.
We have summarized this news so that you can read it quickly. If you are interested in the news, you can read the full text here. Read more:

 /  🏆 532. in SG

Singapore Singapore Latest News, Singapore Singapore Headlines

Similar News:You can also read news stories similar to this one that we have collected from other news sources.

PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices: Experimental ResultsThis paper investigates how the configuration of on-device hardware affects energy consumption for neural network inference with regular fine-tuning.
Source: hackernoon - 🏆 532. / 51 Read more »

Using Machine Learning & Neural Networks to Maximize Solar Energy GloballyOther ways to generate solar energy that just trying to make solar cells efficient potential of luminescent solar concentration
Source: cleantechnica - 🏆 565. / 51 Read more »

CPS Energy progressing towards cleaner energy goals; set to shut down older plantsSAN ANTONIO- Cleaner energy: that's the goal cps energy is working toward -- by closing down coal and older natural gas plants. CPS energy announced they will b
Source: News4SA - 🏆 251. / 63 Read more »

Yellen: Pushing Green Energy to Lower Energy Costs ‘Over Time’ Is Key Part of Fighting InflationSource of breaking news and analysis, insightful commentary and original reporting, curated and written specifically for the new generation of independent and conservative thinkers.
Source: BreitbartNews - 🏆 610. / 51 Read more »

$22 Million to Improve Siting & Permitting for Large-Scale Renewable Energy & Energy StorageInvests $22 Million to Improve Siting and Permitting for Large-Scale Renewable Energy and Energy Storage in NC
Source: cleantechnica - 🏆 565. / 51 Read more »