Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions
Energy-efficient software helps improve mobile device experiences and reduce the carbon footprint of data centers. However, energy goals are often de-prioritized in order to meet other requirements. We take inspiration from recent work exploring the use of large language models (LLMs) for different...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-10 |
---|---|
Hauptverfasser: | , , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Peng, Huiyun Gupte, Arjun Eliopoulos, Nicholas John Chien Chou Ho Mantri, Rishi Deng, Leo Jiang, Wenxin Lu, Yung-Hsiang Läufer, Konstantin Thiruvathukal, George K Davis, James C |
description | Energy-efficient software helps improve mobile device experiences and reduce the carbon footprint of data centers. However, energy goals are often de-prioritized in order to meet other requirements. We take inspiration from recent work exploring the use of large language models (LLMs) for different software engineering activities. We propose a novel application of LLMs: as code optimizers for energy efficiency. We describe and evaluate a prototype, finding that over 6 small programs our system can improve energy efficiency in 3 of them, up to 2x better than compiler optimizations alone. From our experience, we identify some of the challenges of energy-efficient LLM code optimization and propose a research agenda. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3116750062</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3116750062</sourcerecordid><originalsourceid>FETCH-proquest_journals_31167500623</originalsourceid><addsrcrecordid>eNqNir0KwjAURoMgWLTvcMG5kCa2Fdea4lAXERxLaG9LSk00P4NvbwYfwOk7nPOtSMI4z7PjgbENSZ2bKaWsrFhR8IQ8WmknhFbqKcgIVzPg4mA0FoRGO30yMY6qV6g91LGdQDyjVnqCG7qweAdSD9AEHyzCWVnsvTLa7ch6lIvD9Ldbsm_Evb5kL2veAZ3vZhOsjqnjeV5WBaUl4_-9vuR3QM8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3116750062</pqid></control><display><type>article</type><title>Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions</title><source>Free E- Journals</source><creator>Peng, Huiyun ; Gupte, Arjun ; Eliopoulos, Nicholas John ; Chien Chou Ho ; Mantri, Rishi ; Deng, Leo ; Jiang, Wenxin ; Lu, Yung-Hsiang ; Läufer, Konstantin ; Thiruvathukal, George K ; Davis, James C</creator><creatorcontrib>Peng, Huiyun ; Gupte, Arjun ; Eliopoulos, Nicholas John ; Chien Chou Ho ; Mantri, Rishi ; Deng, Leo ; Jiang, Wenxin ; Lu, Yung-Hsiang ; Läufer, Konstantin ; Thiruvathukal, George K ; Davis, James C</creatorcontrib><description>Energy-efficient software helps improve mobile device experiences and reduce the carbon footprint of data centers. However, energy goals are often de-prioritized in order to meet other requirements. We take inspiration from recent work exploring the use of large language models (LLMs) for different software engineering activities. We propose a novel application of LLMs: as code optimizers for energy efficiency. We describe and evaluate a prototype, finding that over 6 small programs our system can improve energy efficiency in 3 of them, up to 2x better than compiler optimizations alone. From our experience, we identify some of the challenges of energy-efficient LLM code optimization and propose a research agenda.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Large language models ; Software engineering</subject><ispartof>arXiv.org, 2024-10</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Peng, Huiyun</creatorcontrib><creatorcontrib>Gupte, Arjun</creatorcontrib><creatorcontrib>Eliopoulos, Nicholas John</creatorcontrib><creatorcontrib>Chien Chou Ho</creatorcontrib><creatorcontrib>Mantri, Rishi</creatorcontrib><creatorcontrib>Deng, Leo</creatorcontrib><creatorcontrib>Jiang, Wenxin</creatorcontrib><creatorcontrib>Lu, Yung-Hsiang</creatorcontrib><creatorcontrib>Läufer, Konstantin</creatorcontrib><creatorcontrib>Thiruvathukal, George K</creatorcontrib><creatorcontrib>Davis, James C</creatorcontrib><title>Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions</title><title>arXiv.org</title><description>Energy-efficient software helps improve mobile device experiences and reduce the carbon footprint of data centers. However, energy goals are often de-prioritized in order to meet other requirements. We take inspiration from recent work exploring the use of large language models (LLMs) for different software engineering activities. We propose a novel application of LLMs: as code optimizers for energy efficiency. We describe and evaluate a prototype, finding that over 6 small programs our system can improve energy efficiency in 3 of them, up to 2x better than compiler optimizations alone. From our experience, we identify some of the challenges of energy-efficient LLM code optimization and propose a research agenda.</description><subject>Large language models</subject><subject>Software engineering</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNir0KwjAURoMgWLTvcMG5kCa2Fdea4lAXERxLaG9LSk00P4NvbwYfwOk7nPOtSMI4z7PjgbENSZ2bKaWsrFhR8IQ8WmknhFbqKcgIVzPg4mA0FoRGO30yMY6qV6g91LGdQDyjVnqCG7qweAdSD9AEHyzCWVnsvTLa7ch6lIvD9Ldbsm_Evb5kL2veAZ3vZhOsjqnjeV5WBaUl4_-9vuR3QM8</recordid><startdate>20241011</startdate><enddate>20241011</enddate><creator>Peng, Huiyun</creator><creator>Gupte, Arjun</creator><creator>Eliopoulos, Nicholas John</creator><creator>Chien Chou Ho</creator><creator>Mantri, Rishi</creator><creator>Deng, Leo</creator><creator>Jiang, Wenxin</creator><creator>Lu, Yung-Hsiang</creator><creator>Läufer, Konstantin</creator><creator>Thiruvathukal, George K</creator><creator>Davis, James C</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241011</creationdate><title>Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions</title><author>Peng, Huiyun ; Gupte, Arjun ; Eliopoulos, Nicholas John ; Chien Chou Ho ; Mantri, Rishi ; Deng, Leo ; Jiang, Wenxin ; Lu, Yung-Hsiang ; Läufer, Konstantin ; Thiruvathukal, George K ; Davis, James C</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31167500623</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Large language models</topic><topic>Software engineering</topic><toplevel>online_resources</toplevel><creatorcontrib>Peng, Huiyun</creatorcontrib><creatorcontrib>Gupte, Arjun</creatorcontrib><creatorcontrib>Eliopoulos, Nicholas John</creatorcontrib><creatorcontrib>Chien Chou Ho</creatorcontrib><creatorcontrib>Mantri, Rishi</creatorcontrib><creatorcontrib>Deng, Leo</creatorcontrib><creatorcontrib>Jiang, Wenxin</creatorcontrib><creatorcontrib>Lu, Yung-Hsiang</creatorcontrib><creatorcontrib>Läufer, Konstantin</creatorcontrib><creatorcontrib>Thiruvathukal, George K</creatorcontrib><creatorcontrib>Davis, James C</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Peng, Huiyun</au><au>Gupte, Arjun</au><au>Eliopoulos, Nicholas John</au><au>Chien Chou Ho</au><au>Mantri, Rishi</au><au>Deng, Leo</au><au>Jiang, Wenxin</au><au>Lu, Yung-Hsiang</au><au>Läufer, Konstantin</au><au>Thiruvathukal, George K</au><au>Davis, James C</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions</atitle><jtitle>arXiv.org</jtitle><date>2024-10-11</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Energy-efficient software helps improve mobile device experiences and reduce the carbon footprint of data centers. However, energy goals are often de-prioritized in order to meet other requirements. We take inspiration from recent work exploring the use of large language models (LLMs) for different software engineering activities. We propose a novel application of LLMs: as code optimizers for energy efficiency. We describe and evaluate a prototype, finding that over 6 small programs our system can improve energy efficiency in 3 of them, up to 2x better than compiler optimizations alone. From our experience, we identify some of the challenges of energy-efficient LLM code optimization and propose a research agenda.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-10 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3116750062 |
source | Free E- Journals |
subjects | Large language models Software engineering |
title | Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T20%3A39%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Large%20Language%20Models%20for%20Energy-Efficient%20Code:%20Emerging%20Results%20and%20Future%20Directions&rft.jtitle=arXiv.org&rft.au=Peng,%20Huiyun&rft.date=2024-10-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3116750062%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3116750062&rft_id=info:pmid/&rfr_iscdi=true |