A Synthesis of Green Architectural Tactics for ML-Enabled Systems

Author:

Järvenpää Heli1ORCID,Lago Patricia1ORCID,Bogner Justus1ORCID,Lewis Grace2ORCID,Muccini Henry3ORCID,Ozkaya Ipek2ORCID

Affiliation:

1. Vrije Universiteit Amsterdam, Amsterdam, Netherlands

2. Carnegie Mellon Software Engineering Institute, Pittsburgh, PA, United States of America

3. University of L'Aquila, L'Aquila, Italy

Funder

US Department of Defense

PNRR ICSC National Research Centre for High Performance Computing, Big Data and Quantum Computing

Publisher

ACM

Reference71 articles.

1. A framework for designing power-efficient inference accelerators in tree-based learning applications

2. VLSI Design of Tree-Based Inference for Low-Power Learning Applications

3. Software Engineering for Machine Learning: A Case Study

4. Phyllis Ang, Bhuwan Dhingra, and Lisa Wu Wills. 2022. Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models. In 1st Workshop on Efficient Benchmarking in Nlp. Association for Computational Linguistics, Dublin, Ireland, 113--121.

5. Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Measuring the Effectiveness of Carbon-Aware AI Training Strategies in Cloud Instances: A Confirmation Study;Future Internet;2024-09-13

2. Towards Green AI: Current Status and Future Research;2024 Electronics Goes Green 2024+ (EGG);2024-06-18

3. EcoMLS: A Self-Adaptation Approach for Architecting Green ML-Enabled Systems;2024 IEEE 21st International Conference on Software Architecture Companion (ICSA-C);2024-06-04

4. Balancing Progress and Responsibility: A Synthesis of Sustainability Trade-Offs of AI-Based Systems;2024 IEEE 21st International Conference on Software Architecture Companion (ICSA-C);2024-06-04

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3