Characterizing the Energy Requirement of
Computer Vision
Name
edelman-danieled-meng-eecs-2023-thesis.pdf
Description
Thesis PDF
Size
2.69 MB
Format
Adobe PDF
Checksum (MD5)
a05044741b3b9084cfae50155bc7597c
Author(s)
Edelman, Daniel
Advisor(s)
Gadepally, Vijay N.
Leiserson, Charles E.
Date Issued
June 2023
Publisher
Massachusetts Institute of Technology
Abstract
The energy requirements of neural network learning are growing at a rapid rate. Increased energy demands have caused a global need to seek ways to improve energy efficiency of neural network learning. This thesis aims to establish a baseline on how adjusting basic parameters can affect energy consumption in neural network learning on Computer Vision tasks. I catalogued the effects of various adjust adjustment from simple batch size adjustment to more complicated hardware configuration (such as power capping). Findings include that adjusting from single precision model to a mixed precision model can result in energy reductions of nearly 40%. Additionally power capping the GPU can reduce energy cost by an additional 10%.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
