TCSE logo 
 Sigsoft logo
Sustainability badge

The increasing electricity demands of personal computers, communication networks, and data centers contribute to higher atmospheric greenhouse gas emissions, which in turn lead to global warming and climate change. Therefore the energy consumption of code must be minimized. Code can be generated by large language models. We look at the influence of prompt modification on the energy consumption of the code generated. We use three different Python code problems of varying difficulty levels. Prompt modification is done by adding the sentence ``Give me an energy-optimized solution for this problem'' or by using two Python coding best practices. The large language models used are CodeLlama-70b, CodeLlama-70b-Instruct, CodeLlama-70b-Python, DeepSeek-Coder-33b-base, and DeepSeek-Coder-33b-instruct. We find a decrease in energy consumption for a specific combination of prompt optimization, LLM, and Python code problem. However, no single optimization prompt consistently decreases energy consumption for the same LLM across the different Python code problems.

Tue 29 Apr

Displayed time zone: Eastern Time (US & Canada) change

11:00 - 12:30
Session 2: Pitch Session 2 (7-minute pitch of each paper and 3-minute question/comment)GREENS at 203
Chair(s): Elisa Yumi Nakagawa University of São Paulo
11:00
10m
Talk
Generating Energy-efficient code with LLMs
GREENS
Tom Cappendijk University of Amsterdam, Pepijn de Reus University of Amsterdam, Ana Oprescu University of Amsterdam
11:10
10m
Talk
Prompt engineering and its implications on the energy consumption of Large Language Models
GREENS
Riccardo Rubei University of L'Aquila, Aicha Moussaid University of L'Aquila (Italy), Claudio Di Sipio University of l'Aquila, Davide Di Ruscio University of L'Aquila
11:20
10m
Talk
Breaking the ICE: Exploring promises and challenges of benchmarks for Inference Carbon & Energy estimation for LLMs
GREENS
Samarth Sikand Accenture Labs, Rohit Mehra Accenture Labs, Priyavanshi Pathania Accenture Labs, Nikhil Bamby Accenture Labs, Vibhu Saujanya Sharma Accenture Labs, Vikrant Kaulgud Accenture Labs, India, Sanjay Podder Accenture, Adam P. Burden Accenture
11:30
10m
Talk
Calculating Software’s Energy Use and Carbon Emissions: A Survey of the State of Art, Challenges, and the Way Ahead
GREENS
Priyavanshi Pathania Accenture Labs, Nikhil Bamby Accenture Labs, Rohit Mehra Accenture Labs, Samarth Sikand Accenture Labs, Vibhu Saujanya Sharma Accenture Labs, Vikrant Kaulgud Accenture Labs, India, Sanjay Podder Accenture, Adam P. Burden Accenture
11:40
10m
Talk
Responsible and Sustainable AI: Considering Energy Consumption in Automated Text Classification Evaluation Tasks
GREENS
Angelika Kaplan Karlsruhe Institute of Technology (KIT), Jan Keim Karlsruhe Institute of Technology (KIT), Lukas Greiner Karlsruhe Institute of Technology (KIT), Ralf Sieger FZI Research Center for Information Technology, Raffaela Mirandola Karlsruhe Institute of Technology (KIT), Ralf Reussner Karlsruhe Institute of Technology (KIT) and FZI - Research Center for Information Technology (FZI)
DOI Pre-print
11:50
10m
Talk
Mapping of the system of software-related emissions and shared responsibilities
GREENS
Laura Partanen LUT University, Antti Sipilä LUT University, Sanaul Haque LUT University, Jari Porras LUT University
12:00
10m
Talk
PowerLetrics: An Open-Source Framework for Power and Energy Metrics for Linux
GREENS
Geerd-Dietger Hoffmann Employed by Green Coding Solutions, Verena Majuntke HTW Berlin
12:10
10m
Talk
Echoes of the Future: Designing a Game for Green Software Engineering
GREENS
Georgia Samaritaki University of Amsterdam, Humeyra Tugce Yavuz University of Amsterdam, Daphnee Chabal University of Amsterdam, Ana Oprescu University of Amsterdam
12:20
10m
Other
Final question/comment filling and posting (via Miro)
GREENS

:
:
:
: